DETAILED ACTION
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 09/24/2025 has been entered.
Status of Claims
Claims 1-11, 13, and 15-22 submitted on 09/24/2025 are pending and have been examined. Claims 1, 3, 6, 8-11, 13, 16, 18-22 have been amended. Claims 12 and 14 been canceled.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
No foreign priority or domestic benefit was claimed by the applicant and the application has been examined with respect to its filing date of 01/30/2023.
Claim Objections
Claim 21 is objected to because of the following informalities:
Claim 21 recites, “non-transitory computer-readable…” on page 9 of the claims submitted on 09/24/2025. For purposes of compact prosecution and clarity on the record, Examiner will interpret the limitation as, “A non-transitory computer-readable…”
Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-11, 13, and 15-22 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception without significantly more. The claims recite an abstract idea. This judicial exception is not integrated into a practical application. The claim(s) do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Step 1
Claims 1-10 are directed to a machine, claims 11, 13, 15-20 are directed to a process and claims 21-22 are directed to an article of manufacture (see MPEP 2106.03).
Step 2A, Prong 1
Claim 1, taken as representative, recites at least the following limitations that recite an abstract idea:
a system comprising:
identifying, using a proactive low discoverability identification model, first products having discoverabilities within a marketplace that are low relative to discoverabilities of other products published on the marketplace by:
receiving historical engagement information for products in the marketplace;
clustering the products of a product type into clusters according to a set of attributes;
identifying a cluster of the products with a highest quantity of the products as a first subset of the products;
identifying a second subset of the products, from one or more clusters other than the identified cluster, that are similar to the first subset of the products based on at least one similarity criterion; and
determining a third subset of the products by filtering the second subset of the products based on comparing the historical engagement information for the second subset of the products to the historical engagement information for the first subset of the products and identifying the third subset of the products as a portion of the second subset of the products that are less than an engagement threshold of an engagement for the first subset of the products;
displaying the third subset of the products with increased frequency on the marketplace based on one or more searches in the marketplace; and
determining, using an impact assessment model, an impact on the discoverabilities of the first products based on displaying the third subset of the products with increased frequency by:
determining at least one benchmark for the first subset of the products based on the historical engagement information for the first subset of the products; and
determining a lift score for the third subset of the products based on the at least one benchmark and engagement information for the third subset of the products, as displayed with the increased frequency.
The above limitation, under its broadest reasonable interpretation, falls within the “Mental Processes” grouping of abstract ideas, enumerated in MPEP 2106.04(a)(2)(III), in that it recites concepts performed in the human mind (including an observation, evaluation, judgement, opinion). Further, the broadest reasonable interpretation of the limitations also encompasses “Certain Methods of Organizing Human Activity” grouping of abstract ideas, enumerated in MPEP 2106.04(a)(2)(II), in that it recites a commercial interaction (see at least ¶0002 of the specification). Claims 11 and 21 recites similar limitations as claim 1.
Thus, under Prong 1 of Step 2A, claims 1, 11, and 21 recite an abstract idea.
Step 2A, Prong 2
Claim 1 includes the following additional elements that are bolded:
a system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform:
identifying, using a proactive low discoverability identification model, first products having discoverabilities within a web-based marketplace that are low relative to discoverabilities of other products published on the web-based marketplace by:
receiving historical engagement information for products in the web- based marketplace;
clustering the products of a product type into clusters according to a set of attributes;
identifying a cluster of the products with a highest quantity of the products as a first subset of the products;
identifying a second subset of the products, from one or more clusters other than the identified cluster, that are similar to the first subset of the products based on at least one similarity criterion; and
determining a third subset of the products by filtering the second subset of the products based on comparing the historical engagement information for the second subset of the products to the historical engagement information for the first subset of the products and identifying the third subset of the products as a portion of the second subset of the products that are less than an engagement threshold of an engagement for the first subset of the products;
displaying the third subset of the products on one or more graphical user interface (GUIs) with increased frequency on the web-based marketplace based on one or more web-based searches in the web-based marketplace; and
determining, using an impact assessment model, an impact on the discoverabilities of the first products based on displaying the third subset of the products with increased frequency by:
determining at least one benchmark for the first subset of the products based on the historical engagement information for the first subset of the products; and
determining a lift score for the third subset of the products based on the at least one benchmark and engagement information for the third subset of the products, as displayed with the increased frequency.
Claims 11 and 21 include the same additional elements as claim 1.
The additional elements recited in claims 1, 11, and 21 merely invoke such elements as a tool to perform the abstract idea and generally link the use of the abstract idea to a particular technological environment of GUIs and web-based marketplaces (see MPEP 2106.05(f) and MPEP 2106.05(h). These additional elements are described at a high level in Applicant’s specification without any meaningful detail about their structure or configuration (see Fig. 2; ¶¶0022-0024).
As such, under Prong 2 of Step 2A, when considered both individually and as a whole, the additional elements do not integrate the judicial exception into a practical application and, thus, claims 1, 11, and 21 are directed to an abstract idea.
Step 2B
As noted above, while the recitation of the additional elements in independent claims 1, 11, and 21 are acknowledged, claims 1, 11, and 21 merely invoke such additional elements as a tool to perform the abstract idea and generally link the use of the abstract idea to a particular technological environment (see MPEP 2106.05(f) and MPEP 2106.05(h)).
Even when considered as an ordered combination, the additional elements of claim 1, 11, and 21 do not add anything that is not already present when they are considered individually. Therefore, under Step 2B, there are no meaningful limitations in claims 1, 11, and 21 that transform the judicial exception into a patent eligible application such that the claims amount to significantly more than the judicial exception itself (see MPEP 2106.05).
As such, independent claims 1, 11, and 21 are ineligible.
Dependent claims 2, 4, 6-10, 16-20, and 22 when analyzed as a whole, are held to be patent ineligible under 35 U.S.C. 101 because they do not add “significantly more” to the abstract idea. More specifically, dependent claims 2, 4, 6-10, 16-20, and 22 merely further define the abstract limitations of claims 1, 11, and 21 or provide further embellishments of the limitations recited in independent claim 1, 11, and 21. Claims 2, 4, 6-10, 16-20, and 22 do not introduce any further additional elements. Thus, dependent claims 2, 4, 6-10, 16-20, and 22 are ineligible.
Furthermore, it is noted that certain dependent claims recite additional elements supplemental to those recited in independent claims 1, 11, and 21: using k-means clustering (claims 3 and 13) and an output of an audio similarity algorithm (claims 5 and 15). However, these elements do not integrate the abstract idea into a practical application because they merely amount to using a computer to apply the abstract idea to a particular technological environment or field of use and thus do not act to integrate the abstract idea into a practical application of the abstract idea. Additionally, the additional elements do not amount to significantly more because they merely amount to using a computer to apply the abstract idea and amount to no more than a general link of the use of the abstract idea to a particular technological environment.
Thus, dependent claims 3, 5, 13, and 15 are ineligible.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-4, 6, 11, 13, 16, and 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chan et al. (US 7,689,457 B2 [previously cited]) in view of Byrne et al. (US 2013/0041779 A1 [previously cited]) in view of Kumar et al. (US 2020/0311108 A1) in view of Decker et al. (US 2024/0152512 A1 [previously cited]).
Regarding Claim 1, Chan discloses a system comprising:
one or more processors (Fig. 9; Col 22, lines 31-42); and
one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform (Fig. 9; Col 22, lines 31-42[The services and other application components… may be implemented in software code modules executed by any number of general purpose computers or processors, with different services optionally… The various data repositories 104, 108, 120 may similarly be implemented using any type of computer storage, and may be implemented using databases, flat files, or any other type of computer storage architecture]):
using a proactive low discoverability identification model, published on the web-based marketplace by (Figs. 1-2; Col. 7, lines 29-32[In block 40, the selected source items are used to generate recommendations for the target user]; Examiner notes that the computer system performing the steps in Fig. 2 is comparable to a proactive low discoverability identification model and that the steps are comparable to identifying product recommendations):
receiving historical engagement information for products in the web- based marketplace (Figs. 7 and 9; Col. 20, line 50 to Col. 21, line 23[a web-based system that provides functionality for users to browse and purchase items from an electronic catalog…web servers 100 provide user access to a catalog of items represented in a database 108 or collection of databases. The items preferably include or consist of items that may be purchased via the web site… The system also includes a data repository 116 (e.g., one or more databases) that stores various types of user data… For example, the data repository 116 may store users’ purchase histories, item viewing histories, item ratings, and item tags. The purchase histories and item viewing histories may be stored as lists of item identifiers together with associated event timestamps. The various types of user data may be accessible to other components of the system via a data service (not shown), which may be implemented as a web service]; Examiner notes storing users’ purchase histories, item viewing histories, item ratings, and item tags is comparable to receiving historical engagement information in view of ¶0051 of the applicant’s specification);
clustering the products of a product type into clusters according to a set of attributes (Figs. 1-2; Col. 4, lines 20-60[in FIG. 1, the collection consists of items purchased by the user, and each point rep resents a purchased item… the collection may additionally or alternatively be based on other types of item “selection' actions (e.g., rentals, views, downloads, shopping cart adds, wish list adds, Subscription purchases, etc.). The distance between each pair of items (points) in FIG. 1 represents the calculated degree to which the items are similar, with relatively small distances representing relatively high degrees of similarity. Any appropriate distance metric(s) can be used for item clustering. For example, if the items are represented in a hierarchical browse structure such as a directed acyclic graph, each item may be represented as a vector of the browse nodes or categories in which it falls… The respective vectors of two items can then be compared to compute the distance between the items… The distances between the items may additionally or alter natively be calculated based on other criteria. For example, the distance between two items, A and B, may be calculated based on any one or more of the following: (a) the relative frequency with which A and B co-occur within purchase histories of users, (b) the relative frequency with which A and B co-occur within item viewing histories of users, (c) the relative frequency with which users tag A and B with the same textual tag, (d) the relative frequency with which A and B co-occur within results of keyword searches, (e) the degree to which A and B contain or are characterized by common keywords. The foregoing are merely examples; numerous other criteria may be used to calculate the item distances] in view of Col. 6, lines 42-52[As depicted by block 30, the relevant item collection for the target user is initially retrieved. This collection may, for example, include or consist of items the target user has purchased, rented, viewed, downloaded, rated, added to a shopping cart, or added to a wish list. The items may be products represented in an electronic catalog, or may be some other type of item (e.g., web sites) that is amenable to clustering]);
identifying a cluster of the products with a highest quantity of the products as a first subset of the products (Col. 7, lines 4-14[The cluster scores may be based on a variety of factors, such as some or all of the following: (1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster, (6) if applicable, the extent to which the items that the cluster contains are close to items that represent known gift purchases. The Sources may, for example, be selected from the highest scored clusters only.]; examiner notes that scoring clustered based on the number of items then selecting the highest scored cluster is comparable to identifying a cluster with a highest quantity of the products);
identifying a second subset of the products, that are similar to the first subset of the products based on at least one similarity criterion (Col. 7, lines 1-18[As one example, a score may be generated for each cluster, and these scores may be used to select the clusters from which the source items are obtained. The cluster scores may be based on a variety of factors, such as some or all of the following: (1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster, (6) if applicable, the extent to which the items that the cluster contains are close to items that represent known gift purchases. The Sources may, for example, be selected from the highest scored clusters only, with addition ally item-specific criteria optionally used to select specific items from these clusters]; Examiner notes that scoring clusters based on distance from one cluster to another (similarity) and selecting the highest scored cluster is comparable to identifying a second subset of products similar to the first subset); and
determining a third subset of the products by filtering the second subset of the products based on comparing the historical engagement information for the second subset of the products to the historical engagement information for the first subset of the products and identifying the third subset of the products as a portion of the second subset of the products (Col. 7, lines 1-18[As one example, a score may be generated for each cluster, and these scores may be used to select the clusters from which the source items are obtained. The cluster scores may be based on a variety of factors, such as some or all of the following: (1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster… The Sources may, for example, be selected from the highest scored clusters only, with addition ally item-specific criteria optionally used to select specific items from these clusters] in view of Col. 7, lines 29-44[The ranked list of recommended items, or an appropriately filtered version of this list (e.g., with items already purchased by the user removed), is then presented to the target user (examiner notes that according to the reference, the ranked list of items is the second group and the filtered version of that list is the third group]; Examiner notes that scoring clusters based on purchase dates of items in the cluster (comparable to historical engagement information according to ¶0051 of the applicant’s specification) and selecting the highest scored cluster is comparable to comparing clusters);
displaying the third subset of the products on one or more graphical user interface (GUIs) on the web-based marketplace based on one or more web-based searches in the web-based marketplace (Figs. 6 and 7[shows the displaying on the user GUI]; Col 11, lines 32-41[In the context of a system that Supports item sales, this item collection may, for example, include or consist of items purchased and/or rated by the target user. In the context of a news web site, the item collection may, for example, include or consist of news articles viewed (or viewed for some threshold amount of time) by the target user] in view of Col. 7, lines 29-32[In block 40, the selected source items are used to generate recommendations for the target user]); and
determining, using an impact assessment model, of the first products by (Figs. 2 and 7[shows the displaying on the user GUI]; Col. 7, lines 29-32[In block 40, the selected source items are used to generate recommendations for the target user]; Examiner notes that the generated recommendations are comparable to the first products with increased visibility on the marketplace and that the computer system performing the steps in Fig. 2 is comparable to an impact assessment model):
determining at least one benchmark for the first subset of the products based on the historical engagement information for the first subset of the products (Fig. 6; Col 11, lines 32-41[FIG. 6 illustrates a second embodiment of a process of arranging the recommended items into mutually exclusive categories or clusters. In step 80, a clustering algorithm is applied to an appropriate item collection of the target user. In the context of a system that Supports item sales, this item collection may, for example, include or consist of items purchased and/or rated by the target user. In the context of a news web site, the item collection may, for example, include or consist of news articles viewed (or viewed for some threshold amount of time) by the target user.] in view of Col. 8, lines 7-9[The clusters may be generated by applying an appropriate clustering algorithm to the user's purchase history or other collection] further in view of Col. 22, lines 56-60[The various features and processes described above may be used independently of one another, or may be combined in various ways. All possible combinations are intended to fall within the scope of this disclosure]; examiner notes that a threshold amount of time is comparable to a benchmark and according to ¶0051 of the applicant’s specification, historical engagement information is comparable to item viewing histories and purchase histories); and
determining a score for the third subset of the products at least one benchmark and the third subset of the products, as displayed (Col. 6, lines 21-33 [each cluster or item (or each outlier cluster or item) can be scored based on multiple criteria], col. 7, lines 1-28 [a score may be generated for each cluster, and these scores may be used to select the clusters from which the source items are obtained. The cluster scores may be based on a variety of factors, such as some or all of the following: (1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster, (6) if applicable, the extent to which the items that the cluster contains are close to items that represent known gift purchases]) and at least one benchmark and the third subset of the products, as displayed with the increased visibility (Figs. 6 and 7[shows the displaying on the user GUI]; Col 11, lines 32-41[In the context of a system that Supports item sales, this item collection may, for example, include or consist of items purchased and/or rated by the target user. In the context of a news web site, the item collection may, for example, include or consist of news articles viewed (or viewed for some threshold amount of time) by the target user] in view of Col. 7, lines 29-32[In block 40, the selected source items are used to generate recommendations for the target user]; Examiner notes that the generated recommendations are comparable to the products with increased visibility on the marketplace; Examiner notes that a threshold amount is comparable to a benchmark).
Although Chan discloses identifying product recommendations published on a web-based marketplace, Chan does not explicitly disclose identifying first products having discoverabilities within a web-based marketplace that are low relative to discoverabilities of other products.
However, Byrne et al., hereinafter, Byrne, teaches identifying products having discoverabilities that are low relative to other products (Fig. 2; Claim 1[identifying, by the processor, a first SKU of a relatively low performing product and a second SKU of a relatively high performing product based at least in part on analysis of the sales data] in view of ¶0029[The index or performance score 206 may represent, for example, the performance of a given SKU 202 relative to other SKUs in a given category or it may provide a formulaic representation of the SKUs performance in the view of the retailer (i.e., according the analysis performed by the retailer)]; Examiner notes that performance is comparable to discoverability of a product).
Although Chan discloses displaying a subset of products on GUIs on the web-based marketplace based on web-based searches, Chan does not explicitly disclose displaying products with increased frequency.
However, Byrne teaches displaying products with increased frequency (¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that ranking higher within search results is comparable to displaying the result with increased frequency).
Although Chan discloses displaying a subset of products on GUIs on the web-based marketplace based on web-based searches, Chan does not explicitly disclose determining an impact on the discoverabilities of products based on displaying the third subset of the products with increased frequency.
However, Byrne teaches an impact on the discoverabilities of the products based on display (Fig. 2; ¶0044[As previously noted, after making modifications to one or more parameters associated with the offering and presentation of a particular SKU 202, the supplier may return to the interface 200 to monitor the SKU 202 and determine whether there has been any change in its performance by reviewing the various categories of information 204, 208, 210 and 212. The supplier may continue to do this as indicated previously with regard to FIG. 1, until they are satisfied with the sales performance of the SKU 202.] in view of ¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that ranking higher within search results is comparable to displaying the result with increased frequency).
Although Chan discloses displaying a subset of products on GUIs on the web-based marketplace based on web-based searches, Chan does not explicitly disclose determining a lift score for the third subset of the products based on the benchmark and engagement information for products as displayed with the increased frequency.
However, Byrne teaches determining a lift score for products based on engagement information (Fig. 2; ¶0029[The information may be provided to the supplier in any of a number of forms. For example, the information may be provided as raw data, such as in a table or in a trending graph (see, e.g., FIG. 6). The data and information may also be presented as analytical data such as by comparing it to other SKUs in a common category of goods, or it may be provided in the form of an index or performance score 206. The index or performance score 206 may represent, for example, the performance of a given SKU 202 relative to other SKUs in a given category or it may provide a formulaic representation of the SKUs performance in the view of the retailer (i.e., according the analysis performed by the retailer). In one particular embodiment, the index or performance score 206 may be represented as a percentage of average performance for a defined category of goods. In other words, a score of 100% indicates that the SKU is performing at least as well as the average SKU within the defined category. A score of less than 100% would indicate that the SKU is performing sub optimally, or less than average, relative to other SKUs within the goods category for the specified parameter (e.g., Impressions)] in view of ¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that a performance score is comparable to a lift score and impressions are comparable to engagement information).
The system of Byrne is applicable to the system of Chan as they share characteristics and capabilities, namely, they are both targeted to generating product recommendations online. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chan to include products having lower discoverability than other products, lift scores, and displaying products with increased frequency as taught by Byrne. One of ordinary skill in the art would have been motivated to expand the system of Chan in order to improve the e-commerce experience including efforts to provide systems and methods that make the experience more effective and more profitable for those offering goods and services for sale (¶0006).
Although Chan discloses identifying a second subset of products that are similar to the first subset of the products based on a similarity criterion, Chan in view of Byrne does not explicitly teach identifying a subset of products from one or more cluster other than the identified cluster.
However, Kumar et al., hereinafter, Kumar, teaches identifying a subset of products from clusters other than an identified cluster (Fig. 28; ¶0120[Determining the one or more product clusters may comprise receiving (e.g., from a database stored on the server 102) a first plurality of product identifiers each sharing a common attribute. The common attribute may be based on clinical equivalence, intended use, size, quantity, a combination thereof, and the like.]).
The system of Kumar is applicable to the system of Chan in view of Byrne as they share characteristics and capabilities, namely, they are all targeted to improving search. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chan in view of Byrne to include identifying a subset of products from one or more cluster other than the identified cluster as taught by Kumar. One of ordinary skill in the art would have been motivated to expand the system of Chan in view of Byrne in order to operate quickly and efficiently (¶0043).
Although Chan discloses determining a third subset of products by filtering the second subset of products based on comparing historical engagement information, Chan in view of Byrne in view of Kumar does not explicitly teach products that are less than an engagement threshold of an engagement for the first subset of the products.
However, Decker et al., hereinafter, Decker, teaches determining products that are less than an engagement threshold of an engagement threshold of products (Fig. 1; ¶0033[The cold start search system 102 may adjust the position of the newly added item within the search results. The cold start search system 102 may adjust the position of the newly added item within the plurality of search results based on the engagement score assigned by the system to the newly added item. For example, the cold start search system 102 may adjust the position of the newly added item so that it appears earlier (e.g., one or more positions closer to the beginning) in the search results, based on the relative value of the engagement score assigned to the newly added item compared to the engagement scores of other (e.g., historical) items in the search result.]).
The system of Decker is applicable to the system of Chan in view of Byrne in view of Kumar as they share characteristics and capabilities, namely, they are all directed to improving search. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the filtering of products as taught by Chan in view of Byrne in view of Kumar to include determining products that are within an engagement threshold as taught by Decker. One of ordinary skill in the art before the effective filing would have been motivated to expand the system of Chan in view of Byrne in view of Kumar in order to enable improved search results because the position of items that lack engagement data (e.g., newly added items) may be adjusted based on engagement data associated with similar items (abstract).
Regarding Claim 2, Chan in view of Byrne in view of Kumar in view of Decker teaches the system of claim 1, Chan further discloses wherein the historical engagement information comprises at least one of: an impression, a product view, an add-to-cart, or an order (Col. 21, lines 13-23[The system also includes a data repository 116 (e.g., one or more databases) that stores various types of user data, including identifiers of the items in each user's collection. For example, the data repository 116 may store users’ purchase histories, item viewing histories, item ratings, and item tags. The purchase histories and item viewing histories may be stored as lists of item identifiers together with associated event timestamps. The various types of user data may be accessible to other components of the system via a data service (not shown), which may be implemented as a web service]).
Regarding Claim 3, Chan in view of Byrne in view of Kumar in view of Decker teaches the system of claim 1, Chan further discloses wherein clustering of the product type into clusters according to the set of attributes further comprises:
using k-means clustering according to the set of attributes (Fig. 2; Col. 6, lines 42-52[This collection may, for example, include or consist of items the target user has purchased, rented, viewed, downloaded, rated, added to a shopping cart, or added to a wish list. The items may be products represented in an electronic catalog, or may be some other type of item (e.g., web sites) that is amenable to clustering (according to ¶0052 of the applicant’s specification, attributes are comparable to a number of reviews, an average rating, a quality score, a number of orders in a season, or a number of impressions in a season)] in view of Col. 4, lines 62-65[The clusters may be generated using any appropriate type of clustering algorithm that uses item distances to cluster items. Examples include K-means] in further in view of Col. 22, lines 56-60[The various features and processes described above may be used independently of one another, or may be combined in various ways. All possible combinations are intended to fall within the scope of this disclosure]; also refer to Col. 10 which discloses that each category corresponds uniquely to a cluster).
Regarding Claim 4, Chan in view of Byrne in view of Kumar in view of Decker teaches the system of claim 3, Chan further discloses wherein the set of attributes includes at least one of: a number of reviews, an average rating, a quality score, a number of orders in a season, or a number of impressions in the season (Fig. 2; Col. 6, lines 42-52[As depicted by block 30, the relevant item collection for the target user is initially retrieved. This collection may, for example, include or consist of items the target user has purchased, rented, viewed, downloaded, rated, added to a shopping cart, or added to a wish list. The items may be products represented in an electronic catalog, or may be some other type of item (e.g., web sites) that is amenable to clustering.] in view of Col. 5, lines 43-53 which disclose the consideration of the purchase dates (or seasons) when clustering, further in view of Col. 22, lines 56-60[The various features and processes described above may be used independently of one another, or may be combined in various ways. All possible combinations are intended to fall within the scope of this disclosure]).
Regarding Claim 6, Chan in view of Byrne in view of Kumar in view of Decker teaches the system of claim 1, Chan further discloses wherein determining the third subset of the products by filtering the second subset of the products based on the historical engagement information for the second subset of the products further comprises:
identifying the historical engagement information for the second subset of the products (Col. 21, lines 13-23[The system also includes a data repository 116 (e.g., one or more databases) that stores various types of user data, including identifiers of the items in each user's collection. For example, the data repository 116 may store users’ purchase histories, item viewing histories, item ratings, and item tags. The purchase histories and item viewing histories may be stored as lists of item identifiers together with associated event timestamps. The various types of user data may be accessible to other components of the system via a data service (not shown), which may be implemented as a web service] in view of Col. 22, lines 56-60[The various features and processes described above may be used independently of one another, or may be combined in various ways. All possible combinations are intended to fall within the scope of this disclosure]; according to ¶0051 of the applicant’s specification, historical engagement information is comparable to item viewing histories and purchase histories).
Regarding Claim 11, Chan discloses a method implemented via execution of computing instructions configured to run at one or more processors and configured to be stored at non-transitory computer-readable media, the method comprising (Fig. 9; Col 22, lines 31-42[The services and other application components… may be implemented in software code modules executed by any number of general purpose computers or processors, with different services optionally but not necessarily implemented on different machines interconnected by a network. The code modules may be stored in any type or types of computer storage, such as hard disk drives and solid state memory devices. The various data repositories 104, 108, 120 may similarly be implemented using any type of computer storage, and may be implemented using databases, flat files, or any other type of computer storage architecture]):
using a proactive low discoverability identification model, published on the web-based marketplace by (Figs. 1-2; Col. 7, lines 29-32[In block 40, the selected source items are used to generate recommendations for the target user]; Examiner notes that the computer system performing the steps in Fig. 2 is comparable to a proactive low discoverability identification model and that the steps are comparable to identifying product recommendations):
receiving historical engagement information for products in the web-based marketplace, wherein the historical engagement information comprises at least one of: an impression, a product view, an add-to-cart, or an order (Col. 21, lines 13-23[The system also includes a data repository 116 (e.g., one or more databases) that stores various types of user data, including identifiers of the items in each user's collection. For example, the data repository 116 may store users’ purchase histories, item viewing histories, item ratings, and item tags. The purchase histories and item viewing histories may be stored as lists of item identifiers together with associated event timestamps. The various types of user data may be accessible to other components of the system via a data service (not shown), which may be implemented as a web service]);
clustering the products of a product type into clusters according to a set of attributes, wherein the set of attributes includes at least one of: a number of reviews, an average rating, a quality score, a number of orders in a season, or a number of impressions in the season (Fig. 2; Col. 6, lines 42-52[As depicted by block 30, the relevant item collection for the target user is initially retrieved. This collection may, for example, include or consist of items the target user has purchased, rented, viewed, downloaded, rated, added to a shopping cart, or added to a wish list. The items may be products represented in an electronic catalog, or may be some other type of item (e.g., web sites) that is amenable to clustering.] in view of Col. 5, lines 43-53 which disclose the consideration of the purchase dates (or seasons) when clustering, further in view of Col. 22, lines 56-60[The various features and processes described above may be used independently of one another, or may be combined in various ways. All possible combinations are intended to fall within the scope of this disclosure]);
identifying a cluster of the products with a highest quantity of the products as a first subset of the products (Col. 7, lines 4-14[The cluster scores may be based on a variety of factors, such as some or all of the following: (1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster, (6) if applicable, the extent to which the items that the cluster contains are close to items that represent known gift purchases. The Sources may, for example, be selected from the highest scored clusters only.]; examiner notes that scoring clustered based on the number of items then selecting the highest scored cluster is comparable to identifying a cluster with a highest quantity of the products);
identifying a second subset of the products, that are similar to the first subset of the products based on at least one similarity criterion (Col. 7, lines 1-18[As one example, a score may be generated for each cluster, and these scores may be used to select the clusters from which the source items are obtained. The cluster scores may be based on a variety of factors, such as some or all of the following: (1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster, (6) if applicable, the extent to which the items that the cluster contains are close to items that represent known gift purchases. The Sources may, for example, be selected from the highest scored clusters only, with addition ally item-specific criteria optionally used to select specific items from these clusters]; Examiner notes that scoring clusters based on distance from one cluster to another (similarity) and selecting the highest scored cluster is comparable to identifying a second subset of products similar to the first subset); and
determining a third subset of the products by filtering the second subset of the products based on comparing the historical engagement information for the second subset of the products to the historical engagement information for the first subset of the products and identifying the third subset of the products as a portion of the second subset of the products (Col. 7, lines 1-18[As one example, a score may be generated for each cluster, and these scores may be used to select the clusters from which the source items are obtained. The cluster scores may be based on a variety of factors, such as some or all of the following: (1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster… The Sources may, for example, be selected from the highest scored clusters only, with addition ally item-specific criteria optionally used to select specific items from these clusters] in view of Col. 7, lines 29-44[The ranked list of recommended items, or an appropriately filtered version of this list (e.g., with items already purchased by the user removed), is then presented to the target user (examiner notes that according to the reference, the ranked list of items is the second group and the filtered version of that list is the third group]; Examiner notes that scoring clusters based on purchase dates of items in the cluster (comparable to historical engagement information according to ¶0051 of the applicant’s specification) and selecting the highest scored cluster is comparable to comparing clusters);
displaying the third subset of the products on one or more graphical user interface (GUIs) on the web-based marketplace based on one or more web- based searches in the web-based marketplace (Figs. 6 and 7[shows the displaying on the user GUI]; Col 11, lines 32-41[In the context of a system that Supports item sales, this item collection may, for example, include or consist of items purchased and/or rated by the target user. In the context of a news web site, the item collection may, for example, include or consist of news articles viewed (or viewed for some threshold amount of time) by the target user] in view of Col. 7, lines 29-32[In block 40, the selected source items are used to generate recommendations for the target user]); and
determining, using an impact assessment model, of the first products by (Figs. 2 and 7[shows the displaying on the user GUI]; Col. 7, lines 29-32[In block 40, the selected source items are used to generate recommendations for the target user]; Examiner notes that the generated recommendations are comparable to the first products with increased visibility on the marketplace and that the computer system performing the steps in Fig. 2 is comparable to an impact assessment model):
determining at least one benchmark for the first subset of the products based on the historical engagement information for the first subset of the products (Fig. 6; Col 11, lines 32-41[FIG. 6 illustrates a second embodiment of a process of arranging the recommended items into mutually exclusive categories or clusters. In step 80, a clustering algorithm is applied to an appropriate item collection of the target user. In the context of a system that Supports item sales, this item collection may, for example, include or consist of items purchased and/or rated by the target user. In the context of a news web site, the item collection may, for example, include or consist of news articles viewed (or viewed for some threshold amount of time) by the target user.] in view of Col. 8, lines 7-9[The clusters may be generated by applying an appropriate clustering algorithm to the user's purchase history or other collection] further in view of Col. 22, lines 56-60[The various features and processes described above may be used independently of one another, or may be combined in various ways. All possible combinations are intended to fall within the scope of this disclosure]; examiner notes that a threshold amount of time is comparable to a benchmark and according to ¶0051 of the applicant’s specification, historical engagement information is comparable to item viewing histories and purchase histories); and
determining a score for the third subset of the products at least one benchmark and the third subset of the products, as displayed (Col. 6, lines 21-33 [each cluster or item (or each outlier cluster or item) can be scored based on multiple criteria], col. 7, lines 1-28 [a score may be generated for each cluster, and these scores may be used to select the clusters from which the source items are obtained. The cluster scores may be based on a variety of factors, such as some or all of the following: (1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster, (6) if applicable, the extent to which the items that the cluster contains are close to items that represent known gift purchases]) and at least one benchmark and the third subset of the products, as displayed with the increased visibility (Figs. 6 and 7[shows the displaying on the user GUI]; Col 11, lines 32-41[In the context of a system that Supports item sales, this item collection may, for example, include or consist of items purchased and/or rated by the target user. In the context of a news web site, the item collection may, for example, include or consist of news articles viewed (or viewed for some threshold amount of time) by the target user] in view of Col. 7, lines 29-32[In block 40, the selected source items are used to generate recommendations for the target user]; Examiner notes that the generated recommendations are comparable to the products with increased visibility on the marketplace; Examiner notes that a threshold amount is comparable to a benchmark).
Although Chan discloses identifying product recommendations published on a web-based marketplace, Chan does not explicitly disclose identifying first products having discoverabilities within a web-based marketplace that are low relative to discoverabilities of other products.
However, Byrne teaches identifying products having discoverabilities that are low relative to other products (Fig. 2; Claim 1[identifying, by the processor, a first SKU of a relatively low performing product and a second SKU of a relatively high performing product based at least in part on analysis of the sales data] in view of ¶0029[The index or performance score 206 may represent, for example, the performance of a given SKU 202 relative to other SKUs in a given category or it may provide a formulaic representation of the SKUs performance in the view of the retailer (i.e., according the analysis performed by the retailer)]; Examiner notes that performance is comparable to discoverability of a product).
Although Chan discloses displaying a subset of products on GUIs on the web-based marketplace based on web-based searches, Chan does not explicitly disclose displaying products with increased frequency.
However, Byrne teaches displaying products with increased frequency (¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that ranking higher within search results is comparable to displaying the result with increased frequency).
Although Chan discloses displaying a subset of products on GUIs on the web-based marketplace based on web-based searches, Chan does not explicitly disclose determining an impact on the discoverabilities of products based on displaying the third subset of the products with increased frequency.
However, Byrne teaches an impact on the discoverabilities of the products based on display (Fig. 2; ¶0044[As previously noted, after making modifications to one or more parameters associated with the offering and presentation of a particular SKU 202, the supplier may return to the interface 200 to monitor the SKU 202 and determine whether there has been any change in its performance by reviewing the various categories of information 204, 208, 210 and 212. The supplier may continue to do this as indicated previously with regard to FIG. 1, until they are satisfied with the sales performance of the SKU 202.] in view of ¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that ranking higher within search results is comparable to displaying the result with increased frequency).
Although Chan discloses displaying a subset of products on GUIs on the web-based marketplace based on web-based searches, Chan does not explicitly disclose determining a lift score for the third subset of the products based on the benchmark and engagement information for products as displayed with the increased frequency.
However, Byrne teaches determining a lift score for products based on engagement information (Fig. 2; ¶0029[The information may be provided to the supplier in any of a number of forms. For example, the information may be provided as raw data, such as in a table or in a trending graph (see, e.g., FIG. 6). The data and information may also be presented as analytical data such as by comparing it to other SKUs in a common category of goods, or it may be provided in the form of an index or performance score 206. The index or performance score 206 may represent, for example, the performance of a given SKU 202 relative to other SKUs in a given category or it may provide a formulaic representation of the SKUs performance in the view of the retailer (i.e., according the analysis performed by the retailer). In one particular embodiment, the index or performance score 206 may be represented as a percentage of average performance for a defined category of goods. In other words, a score of 100% indicates that the SKU is performing at least as well as the average SKU within the defined category. A score of less than 100% would indicate that the SKU is performing sub optimally, or less than average, relative to other SKUs within the goods category for the specified parameter (e.g., Impressions)] in view of ¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that a performance score is comparable to a lift score and impressions are comparable to engagement information).
The method of Byrne is applicable to the method of Chan as they share characteristics and capabilities, namely, they are both targeted to generating product recommendations online. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chan to include products having lower discoverability than other products, lift scores, and displaying products with increased frequency as taught by Byrne. One of ordinary skill in the art would have been motivated to expand the method of Chan in order to improve the e-commerce experience including efforts to provide systems and methods that make the experience more effective and more profitable for those offering goods and services for sale (¶0006).
Although Chan discloses identifying a second subset of products that are similar to the first subset of the products based on a similarity criterion, Chan in view of Byrne does not explicitly teach identifying a subset of products from one or more clusters other than the identified cluster.
However, Kumar teaches identifying a subset of products from clusters other than an identified cluster (Fig. 28; ¶0120[Determining the one or more product clusters may comprise receiving (e.g., from a database stored on the server 102) a first plurality of product identifiers each sharing a common attribute. The common attribute may be based on clinical equivalence, intended use, size, quantity, a combination thereof, and the like.]).
The method of Kumar is applicable to the method of Chan in view of Byrne as they share characteristics and capabilities, namely, they are all targeted to improving search. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chan in view of Byrne to include identifying a subset of products from one or more cluster other than the identified cluster as taught by Kumar. One of ordinary skill in the art would have been motivated to expand the method of Chan in view of Byrne in order to operate quickly and efficiently (¶0043).
Although Chan discloses determining a third subset of products by filtering the second subset of products based on comparing historical engagement information, Chan in view of Byrne in view of Kumar does not explicitly teach products that are less than an engagement threshold of an engagement for the first subset of the products.
However, Decker teaches determining products that are less than an engagement threshold of an engagement threshold of products (Fig. 1; ¶0033[The cold start search system 102 may adjust the position of the newly added item within the search results. The cold start search system 102 may adjust the position of the newly added item within the plurality of search results based on the engagement score assigned by the system to the newly added item. For example, the cold start search system 102 may adjust the position of the newly added item so that it appears earlier (e.g., one or more positions closer to the beginning) in the search results, based on the relative value of the engagement score assigned to the newly added item compared to the engagement scores of other (e.g., historical) items in the search result.]).
The method of Decker is applicable to the method of Chan in view of Byrne in view of Kumar as they share characteristics and capabilities, namely, they are all directed to improving search. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the filtering of products as taught by Chan in view of Byrne in view of Kumar to include determining products that are within an engagement threshold as taught by Decker. One of ordinary skill in the art before the effective filing would have been motivated to expand the method of Chan in view of Byrne in view of Kumar in order to enable improved search results because the position of items that lack engagement data (e.g., newly added items) may be adjusted based on engagement data associated with similar items (abstract).
Regarding Claim 13, Chan in view of Byrne in view of Kumar in view of Decker teaches the method of claim 11, Chan further discloses wherein clustering the products of the product type into clusters according to the set of attributes further comprises:
using k-means clustering according to the set of attributes (Fig. 2; Col. 6, lines 42-52[This collection may, for example, include or consist of items the target user has purchased, rented, viewed, downloaded, rated, added to a shopping cart, or added to a wish list. The items may be products represented in an electronic catalog, or may be some other type of item (e.g., web sites) that is amenable to clustering (according to ¶0052 of the applicant’s specification, attributes are comparable to a number of reviews, an average rating, a quality score, a number of orders in a season, or a number of impressions in a season)] in view of Col. 4, lines 62-65[The clusters may be generated using any appropriate type of clustering algorithm that uses item distances to cluster items. Examples include K-means] in further in view of Col. 22, lines 56-60[The various features and processes described above may be used independently of one another, or may be combined in various ways. All possible combinations are intended to fall within the scope of this disclosure]; also refer to Col. 10 which discloses that each category corresponds uniquely to a cluster).
Regarding Claim 16, Chan in view of Byrne in view of Kumar in view of Decker teaches the method of claim 11, Chan further discloses wherein determining the third subset of the products by filtering the second subset of the products based on the historical engagement information for the second subset of the products further comprises:
identifying the historical engagement information for the second subset of the products (Col. 21, lines 13-23[The system also includes a data repository 116 (e.g., one or more databases) that stores various types of user data, including identifiers of the items in each user's collection. For example, the data repository 116 may store users’ purchase histories, item viewing histories, item ratings, and item tags. The purchase histories and item viewing histories may be stored as lists of item identifiers together with associated event timestamps. The various types of user data may be accessible to other components of the system via a data service (not shown), which may be implemented as a web service] in view of Col. 22, lines 56-60[The various features and processes described above may be used independently of one another, or may be combined in various ways. All possible combinations are intended to fall within the scope of this disclosure]; according to ¶0051 of the applicant’s specification, historical engagement information is comparable to item viewing histories and purchase histories).
Regarding Claim 21, Chan discloses a non-transitory computer-readable medium storing instructions, the instructions, upon execution by a processor, cause the processor to perform operations comprising a method, the method comprising (Fig. 9; Col 22, lines 31-42[The services and other application components… may be implemented in software code modules executed by any number of general purpose computers or processors, with different services optionally but not necessarily implemented on different machines interconnected by a network. The code modules may be stored in any type or types of computer storage, such as hard disk drives and solid state memory devices. The various data repositories 104, 108, 120 may similarly be implemented using any type of computer storage, and may be implemented using databases, flat files, or any other type of computer storage architecture]):
using a proactive low discoverability identification model, published on a web-based marketplace by (Figs. 1-2; Col. 7, lines 29-32[In block 40, the selected source items are used to generate recommendations for the target user]; Examiner notes that the computer system performing the steps in Fig. 2 is comparable to a proactive low discoverability identification model and that the steps are comparable to identifying product recommendations):
receiving historical engagement information for products in the web-based marketplace, wherein the historical engagement information comprises at least one of: an impression, a product view, an add-to-cart, or an order (Figs. 7 and 9; Col. 21, lines 13-23[The system also includes a data repository 116 (e.g., one or more databases) that stores various types of user data, including identifiers of the items in each user's collection. For example, the data repository 116 may store users’ purchase histories, item viewing histories, item ratings, and item tags. The purchase histories and item viewing histories may be stored as lists of item identifiers together with associated event timestamps. The various types of user data may be accessible to other components of the system via a data service (not shown), which may be implemented as a web service]);
clustering the products of a product type into clusters according to a set of attributes, wherein the set of attributes includes at least one: a number of reviews, an average rating, a quality score, a number of orders in a season, or a number of impressions in the season (Fig. 2; Col. 6, lines 42-52[As depicted by block 30, the relevant item collection for the target user is initially retrieved. This collection may, for example, include or consist of items the target user has purchased, rented, viewed, downloaded, rated, added to a shopping cart, or added to a wish list. The items may be products represented in an electronic catalog, or may be some other type of item (e.g., web sites) that is amenable to clustering.] in view of Col. 5, lines 43-53 which disclose the consideration of the purchase dates (or seasons) when clustering, further in view of Col. 22, lines 56-60[The various features and processes described above may be used independently of one another, or may be combined in various ways. All possible combinations are intended to fall within the scope of this disclosure]);
identifying a cluster of the products with a highest quantity of the products as a first subset of the products (Col. 7, lines 4-14[The cluster scores may be based on a variety of factors, such as some or all of the following: (1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster, (6) if applicable, the extent to which the items that the cluster contains are close to items that represent known gift purchases. The Sources may, for example, be selected from the highest scored clusters only.]; examiner notes that scoring clustered based on the number of items then selecting the highest scored cluster is comparable to identifying a cluster with a highest quantity of the products);
identifying a second subset of the products, that are similar to the first subset of the products based on at least one similarity criterion (Col. 7, lines 1-18[As one example, a score may be generated for each cluster, and these scores may be used to select the clusters from which the source items are obtained. The cluster scores may be based on a variety of factors, such as some or all of the following: (1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster, (6) if applicable, the extent to which the items that the cluster contains are close to items that represent known gift purchases. The Sources may, for example, be selected from the highest scored clusters only, with addition ally item-specific criteria optionally used to select specific items from these clusters]; Examiner notes that scoring clusters based on distance from one cluster to another (similarity) and selecting the highest scored cluster is comparable to identifying a second subset of products similar to the first subset); and
determining a third subset of the products by filtering the second subset of the products based on comparing the historical engagement information for the second subset of the products to the historical engagement information for the first subset of the products and identifying the third subset of the products as a portion of the second subset of the products (Col. 7, lines 1-18[As one example, a score may be generated for each cluster, and these scores may be used to select the clusters from which the source items are obtained. The cluster scores may be based on a variety of factors, such as some or all of the following: (1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster… The Sources may, for example, be selected from the highest scored clusters only, with addition ally item-specific criteria optionally used to select specific items from these clusters] in view of Col. 7, lines 29-44[The ranked list of recommended items, or an appropriately filtered version of this list (e.g., with items already purchased by the user removed), is then presented to the target user (examiner notes that according to the reference, the ranked list of items is the second group and the filtered version of that list is the third group]; Examiner notes that scoring clusters based on purchase dates of items in the cluster (comparable to historical engagement information according to ¶0051 of the applicant’s specification) and selecting the highest scored cluster is comparable to comparing clusters);
displaying the third subset of the products on one or more graphical user interface (GUIs) on the web-based marketplace based on one or more web- based searches in the web-based marketplace (Figs. 6 and 7[shows the displaying on the user GUI]; Col 11, lines 32-41[In the context of a system that Supports item sales, this item collection may, for example, include or consist of items purchased and/or rated by the target user. In the context of a news web site, the item collection may, for example, include or consist of news articles viewed (or viewed for some threshold amount of time) by the target user] in view of Col. 7, lines 29-32[In block 40, the selected source items are used to generate recommendations for the target user]); and
determining, using an impact assessment model, of the first products by (Figs. 2 and 7[shows the displaying on the user GUI]; Col. 7, lines 29-32[In block 40, the selected source items are used to generate recommendations for the target user]; Examiner notes that the generated recommendations are comparable to the first products with increased visibility on the marketplace and that the computer system performing the steps in Fig. 2 is comparable to an impact assessment model):
determining at least one benchmark for the first subset of the products based on the historical engagement information for the first subset of the products (Fig. 6; Col 11, lines 32-41[FIG. 6 illustrates a second embodiment of a process of arranging the recommended items into mutually exclusive categories or clusters. In step 80, a clustering algorithm is applied to an appropriate item collection of the target user. In the context of a system that Supports item sales, this item collection may, for example, include or consist of items purchased and/or rated by the target user. In the context of a news web site, the item collection may, for example, include or consist of news articles viewed (or viewed for some threshold amount of time) by the target user.] in view of Col. 8, lines 7-9[The clusters may be generated by applying an appropriate clustering algorithm to the user's purchase history or other collection] further in view of Col. 22, lines 56-60[The various features and processes described above may be used independently of one another, or may be combined in various ways. All possible combinations are intended to fall within the scope of this disclosure]; examiner notes that a threshold amount of time is comparable to a benchmark and according to ¶0051 of the applicant’s specification, historical engagement information is comparable to item viewing histories and purchase histories); and
determining a score for the third subset of the products at least one benchmark and the third subset of the products, as displayed (Col. 6, lines 21-33 [each cluster or item (or each outlier cluster or item) can be scored based on multiple criteria], col. 7, lines 1-28 [a score may be generated for each cluster, and these scores may be used to select the clusters from which the source items are obtained. The cluster scores may be based on a variety of factors, such as some or all of the following: (1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster, (6) if applicable, the extent to which the items that the cluster contains are close to items that represent known gift purchases]) and at least one benchmark and the third subset of the products, as displayed with the increased visibility (Figs. 6 and 7[shows the displaying on the user GUI]; Col 11, lines 32-41[In the context of a system that Supports item sales, this item collection may, for example, include or consist of items purchased and/or rated by the target user. In the context of a news web site, the item collection may, for example, include or consist of news articles viewed (or viewed for some threshold amount of time) by the target user] in view of Col. 7, lines 29-32[In block 40, the selected source items are used to generate recommendations for the target user]; Examiner notes that the generated recommendations are comparable to the products with increased visibility on the marketplace; Examiner notes that a threshold amount is comparable to a benchmark).
Although Chan discloses identifying product recommendations published on a web-based marketplace, Chan does not explicitly disclose identifying first products having discoverabilities within a web-based marketplace that are low relative to discoverabilities of other products.
However, Byrne teaches identifying products having discoverabilities that are low relative to other products (Fig. 2; Claim 1[identifying, by the processor, a first SKU of a relatively low performing product and a second SKU of a relatively high performing product based at least in part on analysis of the sales data] in view of ¶0029[The index or performance score 206 may represent, for example, the performance of a given SKU 202 relative to other SKUs in a given category or it may provide a formulaic representation of the SKUs performance in the view of the retailer (i.e., according the analysis performed by the retailer)]; Examiner notes that performance is comparable to discoverability of a product).
Although Chan discloses displaying a subset of products on GUIs on the web-based marketplace based on web-based searches, Chan does not explicitly disclose displaying products with increased frequency.
However, Byrne teaches displaying products with increased frequency (¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that ranking higher within search results is comparable to displaying the result with increased frequency).
Although Chan discloses displaying a subset of products on GUIs on the web-based marketplace based on web-based searches, Chan does not explicitly disclose determining an impact on the discoverabilities of products based on displaying the third subset of the products with increased frequency.
However, Byrne teaches an impact on the discoverabilities of the products based on display (Fig. 2; ¶0044[As previously noted, after making modifications to one or more parameters associated with the offering and presentation of a particular SKU 202, the supplier may return to the interface 200 to monitor the SKU 202 and determine whether there has been any change in its performance by reviewing the various categories of information 204, 208, 210 and 212. The supplier may continue to do this as indicated previously with regard to FIG. 1, until they are satisfied with the sales performance of the SKU 202.] in view of ¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that ranking higher within search results is comparable to displaying the result with increased frequency).
Although Chan discloses displaying a subset of products on GUIs on the web-based marketplace based on web-based searches, Chan does not explicitly disclose determining a lift score for the third subset of the products based on the benchmark and engagement information for products as displayed with the increased frequency.
However, Byrne teaches determining a lift score for products based on engagement information (Fig. 2; ¶0029[The information may be provided to the supplier in any of a number of forms. For example, the information may be provided as raw data, such as in a table or in a trending graph (see, e.g., FIG. 6). The data and information may also be presented as analytical data such as by comparing it to other SKUs in a common category of goods, or it may be provided in the form of an index or performance score 206. The index or performance score 206 may represent, for example, the performance of a given SKU 202 relative to other SKUs in a given category or it may provide a formulaic representation of the SKUs performance in the view of the retailer (i.e., according the analysis performed by the retailer). In one particular embodiment, the index or performance score 206 may be represented as a percentage of average performance for a defined category of goods. In other words, a score of 100% indicates that the SKU is performing at least as well as the average SKU within the defined category. A score of less than 100% would indicate that the SKU is performing sub optimally, or less than average, relative to other SKUs within the goods category for the specified parameter (e.g., Impressions)] in view of ¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that a performance score is comparable to a lift score and impressions are comparable to engagement information).
The system of Byrne is applicable to the system of Chan as they share characteristics and capabilities, namely, they are both targeted to generating product recommendations online. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chan to include products having lower discoverability than other products, lift scores, and displaying products with increased frequency as taught by Byrne. One of ordinary skill in the art would have been motivated to expand the system of Chan in order to improve the e-commerce experience including efforts to provide systems and methods that make the experience more effective and more profitable for those offering goods and services for sale (¶0006).
Although Chan discloses identifying a second subset of products that are similar to the first subset of the products based on a similarity criterion, Chan in view of Byrne does not explicitly teach identifying a subset of products from one or more clusters other than the identified cluster.
However, Kumar teaches identifying a subset of products from clusters other than an identified cluster (Fig. 28; ¶0120[Determining the one or more product clusters may comprise receiving (e.g., from a database stored on the server 102) a first plurality of product identifiers each sharing a common attribute. The common attribute may be based on clinical equivalence, intended use, size, quantity, a combination thereof, and the like.]).
The system of Kumar is applicable to the system of Chan in view of Byrne as they share characteristics and capabilities, namely, they are all targeted to improving search. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chan in view of Byrne to include identifying a subset of products from one or more cluster other than the identified cluster as taught by Kumar. One of ordinary skill in the art would have been motivated to expand the system of Chan in view of Byrne in order to operate quickly and efficiently (¶0043).
Although Chan discloses determining a third subset of products by filtering the second subset of products based on comparing historical engagement information, Chan in view of Byrne in view of Kumar does not explicitly teach products that are less than an engagement threshold of an engagement for the first subset of the products.
However, Decker teaches determining products that are less than an engagement threshold of an engagement threshold of products (Fig. 1; ¶0033[The cold start search system 102 may adjust the position of the newly added item within the search results. The cold start search system 102 may adjust the position of the newly added item within the plurality of search results based on the engagement score assigned by the system to the newly added item. For example, the cold start search system 102 may adjust the position of the newly added item so that it appears earlier (e.g., one or more positions closer to the beginning) in the search results, based on the relative value of the engagement score assigned to the newly added item compared to the engagement scores of other (e.g., historical) items in the search result.]).
The system of Decker is applicable to the system of Chan in view of Byrne in view of Kumar as they share characteristics and capabilities, namely, they are all directed to improving search. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the filtering of products as taught by Chan in view of Byrne in view of Kumar to include determining products that are within an engagement threshold as taught by Decker. One of ordinary skill in the art before the effective filing would have been motivated to expand the system of Chan in view of Byrne in view of Kumar in order to enable improved search results because the position of items that lack engagement data (e.g., newly added items) may be adjusted based on engagement data associated with similar items (abstract).
Claim(s) 5 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chan in view of Byrne in view of Kumar in view of Decker in further of view Zhao et al. (US 2023/0004989 A1 [previously cited]).
Regarding Claim 5, Chan in view of Byrne in view of Kumar in view of Decker teaches the system of claim 1, Chan further discloses wherein identifying the second subset of the products that are similar to the first subset of the products based on the at least one similarity criterion further comprises:
identifying a group of the products that are similar to the first subset of the products (Col. 7, lines 1-18[As one example, a score may be generated for each cluster, and these scores may be used to select the clusters from which the source items are obtained. The cluster scores may be based on a variety of factors, such as some or all of the following: (1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster, (6) if applicable, the extent to which the items that the cluster contains are close to items that represent known gift purchases. The Sources may, for example, be selected from the highest scored clusters only, with addition ally item-specific criteria optionally used to select specific items from these clusters]; examiner notes that scoring clusters based on distance from one cluster to another (similarity) and selecting the highest scored cluster is comparable to identifying a second subset of products similar to the first subset);
determining a distance between the group of the products and the first subset of the products (Col. 7, lines 1-18 in view of Col 10 lines 16-30[The distances between these items and the centers of the user’s “interest clusters' (i.e., clusters designated as representing the target user's interests) may also be considered. With this approach, the decision whether to filter out a recommended item may be based on both (1) the distance between that item and the center of the closest not-interested cluster, and (2) the distance between that item and the center of the nearest interest cluster. For instance, the recommended item may be filtered out if its distance to the center of the closest not-interested cluster is both (a) less than a selected threshold, and (b) less than its distance to the center of the nearest interest cluster. Various other factors, such as the sizes of these clusters, may also be considered]); and
identifying the second subset of the products as being a portion of the group of the products that are within a threshold distance of the distance for the first subset of the products (Col 12, lines 1-15[assigning each recommended item to the interest cluster whose distance is shortest… The effect of this step 88 is to subdivide all or a portion of the set of recommended items into multiple clusters, each of which corresponds to a previously-identified interest of the user. Recommended items that are more than a threshold distance from the closest interest cluster may be filtered out (not displayed), or may be displayed under a category name (e.g., “more recommended items' or “all categories') that does not correspond to any particular interest cluster]).
Although Chan discloses identifying a group of items similar to another, determining a distance between the group of products and identifying a subset of products as being within a threshold distance of another subset of products, Chan in view of Byrne in view of Kumar in view of Decker does not explicitly teach identifying a group of products similar to another based on an output of an audio similarity algorithm, determining a Levenshtein distance and identifying a subset of products as being within a threshold Levenshtein distance of the Levenshtein distance for another subset.
However, Zhao et al., hereinafter, Zhao, teaches using audio similarity algorithms and Levenshtein distances when identifying similarities between identifiers (¶¶0043-0044[Multiple phonetic algorithms (Soundex, NYSIIS (New York State Information and Intelligence Systems), double metaphone, etc.) may be used to calculate the distances. The phonetic representation of a string replaces the original groups of characters from the original string with phonetic groups of characters that identify the sound made when pronouncing the original groups of characters. The phonetic representations use the same group of characters for different groups of characters with the same sound. For example, “to”, “two”, and “too”, which each sound the same, may be represented by “to” in a phonetic string… The distances may be calculated using the Levenshtein distance algorithm, which identifies the minimum number of single-character edits required to change one string into the other. As applied here, for the name of a user, the Levenshtein distance may be calculated for the original string data, for the Soundex representation, for the NYSIIS representation, and the double metaphone representation]).
The system of Zhao is applicable to the system of Chan in view of Byrne in view of Kumar in view of Decker as they share characteristics and capabilities, namely, they are all directed to online shopping and costumer shopping convenience. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the process of identifying groups of items based on similarities as taught by Chan in view of Byrne in view of Kumar in view of Decker to include determining similarities using audio similarity algorithms and Levenshtein distances as taught by Zhao. One of ordinary skill in the art before the effective filing would have been motivated to expand the System of Chan in view of Byrne in view of Kumar in view of Decker in order to implement improvements to machine learning and user identification technology and computing systems (¶0016).
Regarding Claim 15, Chan in view of Byrne in view of Kumar in view of Decker teaches the method of claim 11, Chan further discloses wherein identifying the second subset of the products that are similar to the first subset of the products based on the at least one similarity criterion further comprises:
identifying a group of the products that are similar to the first subset of the products (Col. 7, lines 1-18[As one example, a score may be generated for each cluster, and these scores may be used to select the clusters from which the source items are obtained. The cluster scores may be based on a variety of factors, such as some or all of the following: (1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster, (6) if applicable, the extent to which the items that the cluster contains are close to items that represent known gift purchases. The Sources may, for example, be selected from the highest scored clusters only, with addition ally item-specific criteria optionally used to select specific items from these clusters]; examiner notes that scoring clusters based on distance from one cluster to another (similarity) and selecting the highest scored cluster is comparable to identifying a second subset of products similar to the first subset);
determining a distance between the group of the products and the first subset of the products (Col. 7, lines 1-18 in view of Col 10 lines 16-30[The distances between these items and the centers of the user’s “interest clusters' (i.e., clusters designated as representing the target user's interests) may also be considered. With this approach, the decision whether to filter out a recommended item may be based on both (1) the distance between that item and the center of the closest not-interested cluster, and (2) the distance between that item and the center of the nearest interest cluster. For instance, the recommended item may be filtered out if its distance to the center of the closest not-interested cluster is both (a) less than a selected threshold, and (b) less than its distance to the center of the nearest interest cluster. Various other factors, such as the sizes of these clusters, may also be considered]); and
identifying the second subset of the products as being a portion of the group of the products that are within a threshold distance of the distance for the first subset of the products (Col 12, lines 1-15[assigning each recommended item to the interest cluster whose distance is shortest… The effect of this step 88 is to subdivide all or a portion of the set of recommended items into multiple clusters, each of which corresponds to a previously-identified interest of the user. Recommended items that are more than a threshold distance from the closest interest cluster may be filtered out (not displayed), or may be displayed under a category name (e.g., “more recommended items' or “all categories') that does not correspond to any particular interest cluster]).
Although Chan discloses identifying a group of items similar to another, determining a distance between the group of products and identifying a subset of products as being within a threshold distance of another subset of products, Chan in view of Byrne in view of Kumar in view of Decker does not explicitly teach identifying a group of products similar to another based on an output of an audio similarity algorithm, determining a Levenshtein distance and identifying a subset of products as being within a threshold Levenshtein distance of the Levenshtein distance for another subset.
However, Zhao teaches using audio similarity algorithms and Levenshtein distances when identifying similarities between identifiers (¶¶0043-0044[Multiple phonetic algorithms (Soundex, NYSIIS (New York State Information and Intelligence Systems), double metaphone, etc.) may be used to calculate the distances. The phonetic representation of a string replaces the original groups of characters from the original string with phonetic groups of characters that identify the sound made when pronouncing the original groups of characters. The phonetic representations use the same group of characters for different groups of characters with the same sound. For example, “to”, “two”, and “too”, which each sound the same, may be represented by “to” in a phonetic string… The distances may be calculated using the Levenshtein distance algorithm, which identifies the minimum number of single-character edits required to change one string into the other. As applied here, for the name of a user, the Levenshtein distance may be calculated for the original string data, for the Soundex representation, for the NYSIIS representation, and the double metaphone representation]).
The method of Zhao is applicable to the method of Chan in view of Byrne in view of Kumar in view of Decker as they share characteristics and capabilities, namely, they are all directed to online shopping and costumer shopping convenience. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the process of identifying groups of items based on similarities as taught by Chan in view of Byrne in view of Kumar in view of Decker to include determining similarities using audio similarity algorithms and Levenshtein distances as taught by Zhao. One of ordinary skill in the art before the effective filing would have been motivated to expand the method of Chan in view of Byrne in view of Kumar in view of Decker in order to implement improvements to machine learning and user identification technology and computing systems (¶0016).
Claim(s) 7 and 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson et al. (US 10,475,092 B1 [previously cited]) in further view of Ollikainen et al. (US 11,695,838 B2 [previously cited]).
Regarding Claim 7, Chan in view of Byrne in view of Kumar in view of Decker teaches the system of claim 1, Chan further discloses wherein determining the at least one benchmark for the first subset of the products based on the historical engagement information for the first subset of the products further comprises:
clustering the first subset of the products into age buckets based on lifecycle information for the first subset of the products, wherein the age buckets correspond to a plurality of time intervals (Col. 5, lines 43-53[Purchase date analysis. The purchase dates of the items may be taken into consideration in various ways. As one example, if most or all of the items in a given outlier cluster were purchased a relatively long time ago, an inference may be drawn that the outlier cluster represents a past interest of the user, or represents an interest of a past acquaintance of the user. As another example, if most or all of the items in an outlier cluster were purchased during a holiday season, or were purchased on approximately the same date over two or more years]; Examiner notes that clustering items with a similar purchase date is comparable to clustering a subset of products into an age group based on lifecycle information, also refer to applicant’s specification ¶0056 where they recite lifecycle information to correspond to product age/seasonality);
the age buckets (Col. 5, lines 43-53);
for each of the age buckets (Col. 5, lines 43-53);
determining an upper threshold for the benchmark (Col. 12, lines 7-12[Recommended items that are more than a threshold distance from the closest interest cluster may be filtered out (not displayed), or may be displayed under a category name (e.g., “more recommended items' or “all categories') that does not correspond to any particular interest cluster]; Examiner notes filtering items above a threshold is comparable to determining an upper threshold),
determining a lower threshold for the benchmark (Fig. 6; Col 11, lines 32-41[FIG. 6 illustrates a second embodiment of a process of arranging the recommended items into mutually exclusive categories or clusters. In step 80, a clustering algorithm is applied to an appropriate item collection of the target user. In the context of a system that Supports item sales, this item collection may, for example, include or consist of items purchased and/or rated by the target user. In the context of a news web site, the item collection may, for example, include or consist of news articles viewed (or viewed for some threshold amount of time) by the target user] in view of Col. 22, lines 56-60[The various features and processes described above may be used independently of one another, or may be combined in various ways. All possible combinations are intended to fall within the scope of this disclosure]; Examiner notes that a threshold amount is comparable to a benchmark and “viewed for some threshold amount of time” is comparable to determining a lower threshold).
Although Chan discloses clustering products into age buckets, Chan in view of Byrne in view of Kumar in view of Decker does not explicitly teach time intervals from publication on the web-based marketplace.
However, Patterson et al., hereinafter, Patterson, teaches intervals from publication on a web-based marketplace (Col. 9, lines 60-65[The listing server is configured to track the first period of time by computing an elapsed time from the first time of the listing of the product to a subsequent time associated with termination of the listing]; Examiner notes that a listing is comparable to a publication).
The system of Patterson is applicable to the system of Chan in view of Byrne in view of Kumar in view of Decker as they share characteristics and capabilities, namely, they are all directed to managing online environments. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the clustering of products as taught by Chan in view of Byrne in view of Kumar in view of Decker to include intervals of time from a time of listing as taught by Patterson. One of ordinary skill in the art before the effective filing would have been motivated to expand the system of Chan in view of Byrne in view of Kumar in view of Decker in order to take into account the possibility of automatically adjusting the price so that the price will fall into a preferable price range or will rise and thus creating an urgency to buy (Col. 1, lines 20-35).
Although Chan discloses determining age buckets and thresholds, Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson does not explicitly teach determining a mean for each of the age buckets, determining a standard deviation based on the mean for each of the age buckets, determining an upper threshold for the benchmark based on: mean + SD, wherein SD is the standard deviation and determining a lower threshold for the benchmark based on: mean – SD.
However, Ollikainen et al., hereinafter, Ollikainen, teaches determining a mean, determining a standard deviation based on the mean and the equations, mean plus or minus standard deviation (Col. 12, lines 23-35[the seed centroids may be chosen by calculating a linear regression, and mean value and standard deviation with respect to the tokens. The first seed centroid for clustering is then chosen such that the token which is closest to mean value plus standard deviation will become one of the centroids. The second seed centroid for clustering will then be chosen such that the token which is closest to mean value minus standard deviation will become another of the centroids]).
The system of Ollikainen is applicable to the system of Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson as they share characteristics and capabilities, namely, they are all directed to managing online environments. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the age buckets and thresholds as taught by Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson to include determining mean, standard deviations and equations using those variables as taught by Ollikainen. One of ordinary skill in the art before the effective filing would have been motivated to expand the System of Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson because mathematical methods need also to be used for understanding the context of a user and thus making better and better recommendations thereof (Col. 1, lines 60-62).
Regarding Claim 17, Chan in view of Byrne in view of Kumar in view of Decker teaches the method of claim 11, Chan further discloses wherein determining the at least one benchmark for the first subset of the products based on the historical engagement information for the first subset of the products further comprises:
clustering the first subset of the products into age buckets based on lifecycle information for the first subset of the products, wherein the age buckets correspond to a plurality of time intervals (Col. 5, lines 43-53[Purchase date analysis. The purchase dates of the items may be taken into consideration in various ways. As one example, if most or all of the items in a given outlier cluster were purchased a relatively long time ago, an inference may be drawn that the outlier cluster represents a past interest of the user, or represents an interest of a past acquaintance of the user. As another example, if most or all of the items in an outlier cluster were purchased during a holiday season, or were purchased on approximately the same date over two or more years]; Examiner notes that clustering items with a similar purchase date is comparable to clustering a subset of products into an age group based on lifecycle information, also refer to applicant’s specification ¶0056 where they recite lifecycle information to correspond to product age/seasonality);
the age buckets (Col. 5, lines 43-53);
for each of the age buckets (Col. 5, lines 43-53);
determining an upper threshold for the benchmark (Col. 12, lines 7-12[Recommended items that are more than a threshold distance from the closest interest cluster may be filtered out (not displayed), or may be displayed under a category name (e.g., “more recommended items' or “all categories') that does not correspond to any particular interest cluster]; Examiner notes filtering items above a threshold is comparable to determining an upper threshold),
determining a lower threshold for the benchmark (Fig. 6; Col 11, lines 32-41[FIG. 6 illustrates a second embodiment of a process of arranging the recommended items into mutually exclusive categories or clusters. In step 80, a clustering algorithm is applied to an appropriate item collection of the target user. In the context of a system that Supports item sales, this item collection may, for example, include or consist of items purchased and/or rated by the target user. In the context of a news web site, the item collection may, for example, include or consist of news articles viewed (or viewed for some threshold amount of time) by the target user] in view of Col. 22, lines 56-60[The various features and processes described above may be used independently of one another, or may be combined in various ways. All possible combinations are intended to fall within the scope of this disclosure]; Examiner notes that a threshold amount is comparable to a benchmark and “viewed for some threshold amount of time” is comparable to determining a lower threshold).
Although Chan discloses clustering products into age buckets, Chan in view of Byrne in view of Kumar in view of Decker does not explicitly teach time intervals from publication on the web-based marketplace.
However, Patterson teaches intervals from publication on a web-based marketplace (Col. 9, lines 60-65[The listing server is configured to track the first period of time by computing an elapsed time from the first time of the listing of the product to a subsequent time associated with termination of the listing]; Examiner notes that a listing is comparable to a publication).
The method of Patterson is applicable to the method of Chan in view of Byrne in view of Kumar in view of Decker as they share characteristics and capabilities, namely, they are all directed to managing online environments. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the clustering of products as taught by Chan in view of Byrne in view of Kumar in view of Decker to include intervals of time from a time of listing as taught by Patterson. One of ordinary skill in the art before the effective filing would have been motivated to expand the method of Chan in view of Byrne in view of Kumar in view of Decker in order to take into account the possibility of automatically adjusting the price so that the price will fall into a preferable price range or will rise and thus creating an urgency to buy (Col. 1, lines 20-35).
Although Chan discloses determining age buckets and thresholds, Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson does not explicitly teach determining a mean for each of the age buckets, determining a standard deviation based on the mean for each of the age buckets, determining an upper threshold for the benchmark based on: mean + SD, wherein SD is the standard deviation and determining a lower threshold for the benchmark based on: mean – SD.
However, Ollikainen teaches determining a mean, determining a standard deviation based on the mean and the equations, mean plus or minus standard deviation (Col. 12, lines 23-35[the seed centroids may be chosen by calculating a linear regression, and mean value and standard deviation with respect to the tokens. The first seed centroid for clustering is then chosen such that the token which is closest to mean value plus standard deviation will become one of the centroids. The second seed centroid for clustering will then be chosen such that the token which is closest to mean value minus standard deviation will become another of the centroids]).
The method of Ollikainen is applicable to the method of Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson as they share characteristics and capabilities, namely, they are all directed to managing online environments. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the age buckets and thresholds as taught by Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson to include determining mean, standard deviations and equations using those variables as taught by Ollikainen. One of ordinary skill in the art before the effective filing would have been motivated to expand the method of Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson because mathematical methods need also to be used for understanding the context of a user and thus making better and better recommendations thereof (Col. 1, lines 60-62).
Claim(s) 8, 9, 18, and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chan in view of Byrne in view of Kumar in view of Decker and in further view of Zhang et al. (US 8,301,518 B1 [previously cited]).
Regarding Claim 8, Chan in view of Byrne in view of Kumar in view of Decker teaches the system of claim 1, Chan further discloses wherein determining the lift score for the third subset of the products based on the at least one benchmark and the engagement information for the third subset of the products, as displayed with the increased frequency, further comprises determining a par score for each product in the third subset of the products, as displayed, based on an equation comprising (Fig. 7; Col. 7, lines 1-25 [a score may be generated for each cluster, and these scores may be used to select the clusters from which the source items are obtained. The cluster scores may be based on a variety of factors… a score may be assigned to each item in the collection] in view of Col. 13 and 14 which depict the equations used for scoring and Col. 11 and 12 which disclose being above or below upper and lower thresholds). Examiner notes that determining a score for each product is comparable to determining a par score for each product.
Although Chan discloses displaying a subset of products on GUIs on the web-based marketplace based on web-based searches, Chan does not explicitly disclose displaying products with the increased frequency.
However, Byrne teaches displaying products with increased frequency (¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that ranking higher within search results is comparable to displaying the result with increased frequency).
The system of Byrne is applicable to the system of Chan as they share characteristics and capabilities, namely, they are all targeted to improving search. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chan to include products having lower discoverability than other products, displaying products with increased frequency, and determining a lift score based on engagement information as taught by Byrne. One of ordinary skill in the art would have been motivated to expand the system of Chan in order to improve the e-commerce experience including efforts to provide systems and methods that make the experience more effective and more profitable for those offering goods and services for sale (¶0006).
Although Chan discloses upper and lower thresholds and determining a score for each product in a subset based on an equation, Chan in view of Byrne in view of Kumar in view of Decker does not explicitly teach determining whether a value is at, above or below thresholds or equaling zero/null (i.e.,
PNG
media_image1.png
24
163
media_image1.png
Greyscale
;
PNG
media_image2.png
22
158
media_image2.png
Greyscale
;
PNG
media_image3.png
26
230
media_image3.png
Greyscale
;
PNG
media_image4.png
22
279
media_image4.png
Greyscale
).
However, Zhang et al., hereinafter, Zhang, teaches values that are at, above or below thresholds or equaling zero (Col. 9, line 30 to Col 10, line 62[If the number of observations is less than a particular threshold, then the method proceeds to step 710. If the number of observations exceed the threshold, then the current values contained in the record can be used in the risk calculation… the obs count value was greater than or equal to the threshold value] in view of Col. 10, lines 36-47[if there is no mean values for the part at a line station or the obs count value is null, then the TBR cannot be calculated, but the removal date and time of removal are stored in a new record with a null TBR value and an obs count=0]).
The system of Zhang is applicable to the system of Chan in view of Byrne in view of Kumar in view of Decker as they share characteristics and capabilities, namely, they are all directed item inventory. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the determination of a score for products and the variables taught by Chan in view of Byrne in view of Kumar in view of Decker to include a determination of a value being above, below, equal to a threshold or equal to zero/null as taught by Zhang. One of ordinary skill in the art before the effective filing would have been motivated to expand the System of Chan in view of Byrne in view of Kumar in view of Decker so that a particular facility might have a faster rate of usage (Col. 1, lines 15-20).
Regarding Claim 9, Chan in view of Byrne in view of Kumar in view of Decker in further view of Zhang teaches the system of claim 8, Chan further discloses wherein determining the lift score for the third subset of the products based on the at least one benchmark and the engagement information for the third subset of the products, as displayed with the increased frequency, further comprises identifying a group of the third subset of the products, as displayed, that have a par score that satisfies a threshold (Fig. 7; Col. 5, lines 20-35[an item may be treated as an outlier and excluded if some or all of the following conditions are met: (a) the item falls in a cluster having less than some threshold number of items, such as 5; (b) this cluster is significantly smaller than the largest cluster (e.g., less than 10% of its size); (c) the item is some threshold distance from the nearest non-outlier cluster, (d) the item falls in a cluster that consists primarily of items rated below a selected threshold by the target user; (e) the item falls within a cluster having a cluster score that falls below some threshold, where the score generally represents the likelihood that the cluster represents an interest of the user]; Examiner notes that excluding items that fall under a threshold is comparable to identifying a group of the subset that have a par score that satisfy a threshold, and a cluster score is comparable to a par score).
Although Chan discloses displaying a subset of products on GUIs on the web-based marketplace based on web-based searches, Chan does not explicitly disclose displaying products with the increased frequency.
However, Byrne teaches displaying products with increased frequency (¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that ranking higher within search results is comparable to displaying the result with increased frequency).
The system of Byrne is applicable to the system of Chan as they share characteristics and capabilities, namely, they are all targeted to improving search. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chan to include products having lower discoverability than other products, displaying products with increased frequency, and determining a lift score based on engagement information as taught by Byrne. One of ordinary skill in the art would have been motivated to expand the system of Chan in order to improve the e-commerce experience including efforts to provide systems and methods that make the experience more effective and more profitable for those offering goods and services for sale (¶0006).
Regarding Claim 18, Chan in view of Byrne in view of Kumar in view of Decker teaches the method of claim 11, Chan further discloses wherein determining the lift score for the third subset of the products, based on the at least one benchmark and the engagement information for the third subset of the products, as displayed with the increaseddetermining a par score for each product in the third subset of the products, as displayed, based on an equation comprising (Fig. 7; Col. 7, lines 1-25 [a score may be generated for each cluster, and these scores may be used to select the clusters from which the source items are obtained. The cluster scores may be based on a variety of factors… a score may be assigned to each item in the collection] in view of Col. 13 and 14 which depict the equations used for scoring and Col. 11 and 12 which disclose being above or below upper and lower thresholds). Examiner notes that determining a score for each product is comparable to determining a par score for each product.
Although Chan discloses displaying a subset of products on GUIs on the web-based marketplace based on web-based searches, Chan does not explicitly disclose displaying products with the increased frequency.
However, Byrne teaches displaying products with increased frequency (¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that ranking higher within search results is comparable to displaying the result with increased frequency).
The method of Byrne is applicable to the method of Chan as they share characteristics and capabilities, namely, they are all targeted to improving search. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chan to include products having lower discoverability than other products, displaying products with increased frequency, and determining a lift score based on engagement information as taught by Byrne. One of ordinary skill in the art would have been motivated to expand the method of Chan in order to improve the e-commerce experience including efforts to provide systems and methods that make the experience more effective and more profitable for those offering goods and services for sale (¶0006).
Although Chan discloses upper and lower thresholds and determining a score for each product in a subset based on an equation, Chan in view of Byrne in view of Kumar in view of Decker does not explicitly teach determining whether a value is at, above or below thresholds or equaling zero/null (i.e.,
PNG
media_image1.png
24
163
media_image1.png
Greyscale
;
PNG
media_image2.png
22
158
media_image2.png
Greyscale
;
PNG
media_image3.png
26
230
media_image3.png
Greyscale
;
PNG
media_image4.png
22
279
media_image4.png
Greyscale
).
However, Zhang teaches values that are at, above or below thresholds or equaling zero (Col. 9, line 30 to Col 10, line 62[If the number of observations is less than a particular threshold, then the method proceeds to step 710. If the number of observations exceed the threshold, then the current values contained in the record can be used in the risk calculation… the obs count value was greater than or equal to the threshold value] in view of Col. 10, lines 36-47[if there is no mean values for the part at a line station or the obs count value is null, then the TBR cannot be calculated, but the removal date and time of removal are stored in a new record with a null TBR value and an obs count=0]).
The method of Zhang is applicable to the method of Chan in view of Byrne in view of Kumar in view of Decker as they share characteristics and capabilities, namely, they are all directed item inventory. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the determination of a score for products and the variables taught by Chan in view of Byrne in view of Kumar in view of Decker to include a determination of a value being above, below, equal to a threshold or equal to zero/null as taught by Zhang. One of ordinary skill in the art before the effective filing would have been motivated to expand the method of Chan in view of Byrne in view of Kumar in view of Decker so that a particular facility might have a faster rate of usage (Col. 1, lines 15-20).
Regarding Claim 19, Chan in view of Byrne in view of Kumar in view of Decker in view of Zhang teaches the method of claim 18, Chan further discloses wherein determining the lift score for the third subset of the products based on the at least one benchmark and the engagement information for the third subset of the products, as displayed with the increased frequency, further comprises identifying a group of the third subset of the products, as displayed, that have a par score that satisfies a threshold (Fig. 7; Col. 5, lines 20-35[an item may be treated as an outlier and excluded if some or all of the following conditions are met: (a) the item falls in a cluster having less than some threshold number of items, such as 5; (b) this cluster is significantly smaller than the largest cluster (e.g., less than 10% of its size); (c) the item is some threshold distance from the nearest non-outlier cluster, (d) the item falls in a cluster that consists primarily of items rated below a selected threshold by the target user; (e) the item falls within a cluster having a cluster score that falls below some threshold, where the score generally represents the likelihood that the cluster represents an interest of the user]; Examiner notes that excluding items that fall under a threshold is comparable to identifying a group of the subset that have a par score that satisfy a threshold, and a cluster score is comparable to a par score).
Although Chan discloses displaying a subset of products on GUIs on the web-based marketplace based on web-based searches, Chan does not explicitly disclose displaying products with the increased frequency.
However, Byrne teaches displaying products with increased frequency (¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that ranking higher within search results is comparable to displaying the result with increased frequency).
The system of Byrne is applicable to the system of Chan as they share characteristics and capabilities, namely, they are all targeted to improving search. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chan to include products having lower discoverability than other products, displaying products with increased frequency, and determining a lift score based on engagement information as taught by Byrne. One of ordinary skill in the art would have been motivated to expand the system of Chan in order to improve the e-commerce experience including efforts to provide systems and methods that make the experience more effective and more profitable for those offering goods and services for sale (¶0006).
Claim(s) 10 and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chan in view of Byrne in view of Kumar in view of Decker in view of Zhang and in further view of ExpertVillage Leaf Group (NPL [previously cited]).
Regarding Claim 10, Chan in view of Byrne in view of Kumar in view of Decker in view of Zhang teaches the system of claim 9, Chan further discloses wherein determining the lift score for the third subset of the products based on the at least one benchmark and the engagement information for the third subset of the products, as displayed with the increased frequency, further comprises:
determining the score for the group of the third subset of the products, as displayed, that has a par score that satisfies the threshold based on an equation comprising (Fig. 7; Col. 5, lines 20-35[an item may be treated as an outlier and excluded if some or all of the following conditions are met: (a) the item falls in a cluster having less than some threshold number of items, such as 5; (b) this cluster is significantly smaller than the largest cluster (e.g., less than 10% of its size); (c) the item is some threshold distance from the nearest non-outlier cluster, (d) the item falls in a cluster that consists primarily of items rated below a selected threshold by the target user; (e) the item falls within a cluster having a cluster score that falls below some threshold, where the score generally represents the likelihood that the cluster represents an interest of the user] in view of Col. 6, lines 21-33 which discloses scoring each cluster; examiner notes that excluding items that fall under a threshold is comparable to identifying a group of the subset that have a par score that satisfy a threshold, and a cluster score is comparable to a par score).
Although Chan discloses determining a score, at least once benchmark and displaying products, Chan does not explicitly disclose determining a lift score for the third subset of the products as displayed with the increased frequency.
However, Byrne teaches determining a lift score for products based on engagement information (Fig. 2; ¶0029[The information may be provided to the supplier in any of a number of forms. For example, the information may be provided as raw data, such as in a table or in a trending graph (see, e.g., FIG. 6). The data and information may also be presented as analytical data such as by comparing it to other SKUs in a common category of goods, or it may be provided in the form of an index or performance score 206. The index or performance score 206 may represent, for example, the performance of a given SKU 202 relative to other SKUs in a given category or it may provide a formulaic representation of the SKUs performance in the view of the retailer (i.e., according the analysis performed by the retailer). In one particular embodiment, the index or performance score 206 may be represented as a percentage of average performance for a defined category of goods. In other words, a score of 100% indicates that the SKU is performing at least as well as the average SKU within the defined category. A score of less than 100% would indicate that the SKU is performing sub optimally, or less than average, relative to other SKUs within the goods category for the specified parameter (e.g., Impressions)] in view of ¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that ranking higher within search results is comparable to displaying the result with increased frequency and that a performance score is comparable to a lift score and impressions are comparable to engagement information).
The system of Byrne is applicable to the system of Chan as they share characteristics and capabilities, namely, they are both targeted to generating product recommendations online. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chan to include determining a lift score based on engagement information and displaying products with increased frequency as taught by Byrne. One of ordinary skill in the art would have been motivated to expand the system of Chan in order to improve the e-commerce experience including efforts to provide systems and methods that make the experience more effective and more profitable for those offering goods and services for sale (¶0006).
Although Chan teaches determining a group of products that satisfies a threshold and determining a lift score, Chan in view of Byrne in view of Kumar in view of Decker in view of Zhang does not explicitly teach an equation of a variable minus a variable over another variable (i.e.,
PNG
media_image5.png
30
172
media_image5.png
Greyscale
).
However, ExpertVillage Leaf Group teaches calculating relative error which is an equation that is in the form of (x-y)/y with x and y corresponding to experimental and real values respectively (The “Non-Patent Documents section of Form PTO-892 Notice of References Cited contains the link to the video of ExpertVillage Leaf Group teaching this equation).
The system of ExpertVillage Leaf Group is applicable to the system of Chan in view of Byrne in view of Kumar in view of Decker in view of Zhang as they share characteristics and capabilities, namely, they are all directed to using mathematic equations to determine the success and effectiveness of their respective systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the variables, determining lift score and cluster scores as taught by Chan in view of Byrne in view of Kumar in view of Decker in view of Zhang to include an equation of a variable minus another variable, divided by a variable as taught by ExpertVillage Leaf Group. One of ordinary skill in the art before the effective filing would have been motivated to expand the system of Chan in view of Byrne in view of Kumar in view of Decker in view of Zhang in order to determine the effectiveness of a method (minute 1:15-1:22).
Regarding Claim 20, Chan in view of Byrne in view of Kumar in view of Decker in view of Zhang in further view of ExpertVillage Leaf Group teaches the method of claim 19, Chan further discloses wherein determining the lift score for the third subset of the products based on the at least one benchmark and the engagement information for the third subset of the products, as displayed with the increaseddetermining the score for the group of the third subset of the products, as displayed, that has a par score that satisfies the threshold based on an equation comprising (Fig. 7; Col. 5, lines 20-35[an item may be treated as an outlier and excluded if some or all of the following conditions are met: (a) the item falls in a cluster having less than some threshold number of items, such as 5; (b) this cluster is significantly smaller than the largest cluster (e.g., less than 10% of its size); (c) the item is some threshold distance from the nearest non-outlier cluster, (d) the item falls in a cluster that consists primarily of items rated below a selected threshold by the target user; (e) the item falls within a cluster having a cluster score that falls below some threshold, where the score generally represents the likelihood that the cluster represents an interest of the user] in view of Col. 6, lines 21-33 which discloses scoring each cluster; examiner notes that excluding items that fall under a threshold is comparable to identifying a group of the subset that have a par score that satisfy a threshold, and a cluster score is comparable to a par score).
Although Chan discloses determining a score, at least once benchmark and displaying products, Chan does not explicitly disclose determining a lift score for the third subset of the products as displayed with the increased frequency.
However, Byrne teaches determining a lift score for products based on engagement information (Fig. 2; ¶0029[The information may be provided to the supplier in any of a number of forms. For example, the information may be provided as raw data, such as in a table or in a trending graph (see, e.g., FIG. 6). The data and information may also be presented as analytical data such as by comparing it to other SKUs in a common category of goods, or it may be provided in the form of an index or performance score 206. The index or performance score 206 may represent, for example, the performance of a given SKU 202 relative to other SKUs in a given category or it may provide a formulaic representation of the SKUs performance in the view of the retailer (i.e., according the analysis performed by the retailer). In one particular embodiment, the index or performance score 206 may be represented as a percentage of average performance for a defined category of goods. In other words, a score of 100% indicates that the SKU is performing at least as well as the average SKU within the defined category. A score of less than 100% would indicate that the SKU is performing sub optimally, or less than average, relative to other SKUs within the goods category for the specified parameter (e.g., Impressions)] in view of ¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that ranking higher within search results is comparable to displaying the result with increased frequency and that a performance score is comparable to a lift score and impressions are comparable to engagement information).
The method of Byrne is applicable to the method of Chan as they share characteristics and capabilities, namely, they are both targeted to generating product recommendations online. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chan to include determining a lift score based on engagement information and displaying products with increased frequency as taught by Byrne. One of ordinary skill in the art would have been motivated to expand the method of Chan in order to improve the e-commerce experience including efforts to provide systems and methods that make the experience more effective and more profitable for those offering goods and services for sale (¶0006).
Although Chan in view of Byrne teaches determining a group of products that satisfies a threshold and determining a lift score, Chan in view of Byrne in view of Kumar in view of Decker in view of Zhang does not explicitly teach an equation of a variable minus a variable over another variable (i.e.,
PNG
media_image5.png
30
172
media_image5.png
Greyscale
).
However, ExpertVillage Leaf Group teaches calculating relative error which is an equation that is in the form of (x-y)/y with x and y corresponding to experimental and real values respectively (The “Non-Patent Documents section of Form PTO-892 Notice of References Cited contains the link to the video of ExpertVillage Leaf Group teaching this equation).
The method of ExpertVillage Leaf Group is applicable to the method of Chan in view of Byrne in view of Kumar in view of Decker in view of Zhang as they share characteristics and capabilities, namely, they are all directed to using mathematic equations to determine the success and effectiveness of their respective systems. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the variables, determining lift score and cluster scores as taught by Chan in view of Byrne in view of Kumar in view of Decker in view of Zhang to include an equation of a variable minus another variable, divided by a variable as taught by ExpertVillage Leaf Group. One of ordinary skill in the art before the effective filing would have been motivated to expand the method of Chan in view of Byrne in view of Kumar in view of Decker in view of Zhang in order to determine the effectiveness of a method (minute 1:15-1:22).
Claim(s) 22 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson in view of Ollikainen in view of Zhang.
Regarding Claim 22, Chan in view of Byrne in view of Kumar in view of Decker teaches the non-transitory computer-readable medium storing the instructions of claim 21, Chan further discloses wherein determining the at least one benchmark for the first subset of the products based on the historical engagement information for the first subset of the products further comprises:
clustering the first subset of the products into age buckets based on lifecycle information for the first subset of the products, wherein the age buckets correspond to a plurality of time intervals (Col. 5, lines 43-53[Purchase date analysis. The purchase dates of the items may be taken into consideration in various ways. As one example, if most or all of the items in a given outlier cluster were purchased a relatively long time ago, an inference may be drawn that the outlier cluster represents a past interest of the user, or represents an interest of a past acquaintance of the user. As another example, if most or all of the items in an outlier cluster were purchased during a holiday season, or were purchased on approximately the same date over two or more years]; Examiner notes that clustering items with a similar purchase date is comparable to clustering a subset of products into an age group based on lifecycle information, also refer to applicant’s specification ¶0056 where they recite lifecycle information to correspond to product age/seasonality);
age buckets (Col. 5, lines 43-53);
ge buckets (Col. 5, lines 43-53);
determining an upper threshold for the benchmark (Col. 12, lines 7-12[Recommended items that are more than a threshold distance from the closest interest cluster may be filtered out (not displayed), or may be displayed under a category name (e.g., “more recommended items' or “all categories') that does not correspond to any particular interest cluster]; Examiner notes filtering items above a threshold is comparable to determining an upper threshold); and
determining a lower threshold for the benchmark (Fig. 6; Col 11, lines 32-41[FIG. 6 illustrates a second embodiment of a process of arranging the recommended items into mutually exclusive categories or clusters. In step 80, a clustering algorithm is applied to an appropriate item collection of the target user. In the context of a system that Supports item sales, this item collection may, for example, include or consist of items purchased and/or rated by the target user. In the context of a news web site, the item collection may, for example, include or consist of news articles viewed (or viewed for some threshold amount of time) by the target user] in view of Col. 22, lines 56-60[The various features and processes described above may be used independently of one another, or may be combined in various ways. All possible combinations are intended to fall within the scope of this disclosure]; Examiner notes that a threshold amount is comparable to a benchmark and “viewed for some threshold amount of time” is comparable to determining a lower threshold); and
wherein determining the lift score for the third subset of the products, as displayed with the increased frequency, based on the at least one benchmark and engagement information for the third subset of the products, as displayed with the increased frequency, further comprises
determining a par score for each product in the third subset of the products, as displayed, based on an equation comprising (Fig. 7[showing increased visibility]; Col. 5, lines 20-35[an item may be treated as an outlier and excluded if some or all of the following conditions are met: (a) the item falls in a cluster having less than some threshold number of items, such as 5; (b) this cluster is significantly smaller than the largest cluster (e.g., less than 10% of its size); (c) the item is some threshold distance from the nearest non-outlier cluster, (d) the item falls in a cluster that consists primarily of items rated below a selected threshold by the target user; (e) the item falls within a cluster having a cluster score that falls below some threshold, where the score generally represents the likelihood that the cluster represents an interest of the user] in view of Col. 6, lines 21-33 which discloses scoring each cluster; examiner notes that excluding items that fall under a threshold is comparable to identifying a group of the subset that have a par score that satisfy a threshold, and a cluster score is comparable to a par score).
Although Chan discloses displaying a subset of products on GUIs on the web-based marketplace based on web-based searches, Chan does not explicitly disclose displaying products with the increased frequency.
However, Byrne teaches displaying products with increased frequency (¶0038[Yet another modification option may be referred to as a “Boost” which provides the supplier with an opportunity to pay a premium in exchange for ensuring that their SKU is ranked or positioned higher within set of search results for a period of time.]; Examiner notes that ranking higher within search results is comparable to displaying the result with increased frequency).
The system of Byrne is applicable to the system of Chan as they share characteristics and capabilities, namely, they are all targeted to improving search. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chan to include products having lower discoverability than other products, displaying products with increased frequency, and determining a lift score based on engagement information as taught by Byrne. One of ordinary skill in the art would have been motivated to expand the system of Chan in order to improve the e-commerce experience including efforts to provide systems and methods that make the experience more effective and more profitable for those offering goods and services for sale (¶0006).
Although Chan discloses clustering products into age buckets, Chan in view of Byrne in view of Kumar in view of Decker does not explicitly teach time intervals from publication on the web-based marketplace.
However, Patterson teaches intervals from publication on a web-based marketplace (Col. 9, lines 60-65[The listing server is configured to track the first period of time by computing an elapsed time from the first time of the listing of the product to a subsequent time associated with termination of the listing]; Examiner notes that a listing is comparable to a publication).
The system of Patterson is applicable to the system of Chan in view of Byrne in view of Kumar in view of Decker as they share characteristics and capabilities, namely, they are all directed to managing online environments. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the clustering of products as taught by Chan in view of Byrne in view of Kumar in view of Decker to include intervals of time from a time of listing as taught by Patterson. One of ordinary skill in the art before the effective filing would have been motivated to expand the system of Chan in view of Byrne in view of Kumar in view of Decker in order to take into account the possibility of automatically adjusting the price so that the price will fall into a preferable price range or will rise and thus creating an urgency to buy (Col. 1, lines 20-35).
Although Chan discloses determining age buckets and thresholds, Chan in view of Byrne in view of Kumar in view of Decker in further view of Patterson does not explicitly teach determining a mean for each of the age buckets, determining a standard deviation based on the mean for each of the age buckets, determining an upper threshold for the benchmark based on: mean + SD, wherein SD is the standard deviation and determining a lower threshold for the benchmark based on: mean – SD.
However, Ollikainen teaches determining a mean, determining a standard deviation based on the mean and the equations, mean plus or minus standard deviation (Col. 12, lines 23-35[the seed centroids may be chosen by calculating a linear regression, and mean value and standard deviation with respect to the tokens. The first seed centroid for clustering is then chosen such that the token which is closest to mean value plus standard deviation will become one of the centroids. The second seed centroid for clustering will then be chosen such that the token which is closest to mean value minus standard deviation will become another of the centroids]).
The system of Ollikainen is applicable to the system of Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson as they share characteristics and capabilities, namely, they are all directed to managing online environments. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the age buckets and thresholds as taught by Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson to include determining mean, standard deviations and equations using those variables as taught by Ollikainen. One of ordinary skill in the art before the effective filing would have been motivated to expand the System of Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson because mathematical methods need also to be used for understanding the context of a user and thus making better and better recommendations thereof (Col. 1, lines 60-62).
Although Chan discloses upper and lower thresholds and determining a score for each product in a subset based on an equation, Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson in further view of Ollikainen does not explicitly teach determining whether a value is at, above or below thresholds or equaling zero/null (i.e.,
PNG
media_image1.png
24
163
media_image1.png
Greyscale
;
PNG
media_image2.png
22
158
media_image2.png
Greyscale
;
PNG
media_image3.png
26
230
media_image3.png
Greyscale
;
PNG
media_image4.png
22
279
media_image4.png
Greyscale
).
However, Zhang teaches values that are at, above or below thresholds or equaling zero (Col. 9, line 30 to Col 10, line 62[If the number of observations is less than a particular threshold, then the method proceeds to step 710. If the number of observations exceed the threshold, then the current values contained in the record can be used in the risk calculation… the obs count value was greater than or equal to the threshold value] in view of Col. 10, lines 36-47[if there is no mean values for the part at a line station or the obs count value is null, then the TBR cannot be calculated, but the removal date and time of removal are stored in a new record with a null TBR value and an obs count=0]).
The system of Zhang is applicable to the system of Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson in further view of Ollikainen as they share characteristics and capabilities, namely, they are all directed item inventory and item recommendation. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the determination of a score for products and the variables taught by Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson in further view of Ollikainen to include a determination of a value being above, below, equal to a threshold or equal to zero/null as taught by Zhang. One of ordinary skill in the art before the effective filing would have been motivated to expand the system of Chan in view of Byrne in view of Kumar in view of Decker in view of Patterson in further view of Ollikainen so that a particular facility might have a faster rate of usage (Col. 1, lines 15-20).
Response to Arguments
Applicant’s arguments on pages 12-22 of the remarks filed 09/24/2025, with respect to the previous 35 USC § 101 rejections have been fully considered but are not persuasive.
Applicant argues on pages 12-19 of the remarks that the amended claims are not directed to an abstract idea. Examiner respectfully disagrees. Applicant argues on pages 13-15 of the remarks that the previous Office Action dated 06/24/2025 did not identify specific claim limitations which recite the abstract idea nor did it clarify why the limitations were considered to recite abstract ideas and cites to the MPEP 2106.07(a). Furthermore, applicant asserts on page 13-15 of the remarks that the Office Action appeared to allege that all limitations recite both the mental process and organizing human activity enumerated groupings of abstract ideas without providing any explanation as to why the limitations are directed to an abstract idea. Examiner respectfully disagrees. Previous Office Action dated 06/24/2025 identified the limitations which are directed to the abstract idea. Specifically, pages 3 and 4 of the previous Office Action dated 06/24/2025 specified the limitations as they were recited in the claim. Furthermore, Page 4 of the Previous Office Action dated 06/24/2025 includes a detailed explanation as to why the claim limitations were directed to abstract ideas. In addition, the previous Office Action describes further why the limitations are directed to an abstract idea in the Response to Arguments section on pages 73 and 74. Additionally, ¶0002 of the instant specification was cited to provide additional details about the judicial exception. ¶0002 of the instant specification describes an improvement to the business concept of the discoverability of products to potential buyers which is also part to the abstract idea.
Applicant further argues on pages 16-18 of the remarks that the amended claims describe the abstract idea at too high a level of abstraction and do not recite any commercial, sales, or marketing activities or behaviors. Examiner respectfully disagrees. Applicant cites to Alice/Mayo test for support. Under the 101 Alice/Mayo test, the specification should disclose sufficient details such that one of ordinary skill in the art would recognize the claimed invention as providing an improvement, and the claim itself must reflect the improvement in technology (see MPEP 2106.04(a)(I)). The instant Specification does not disclose details such that one of ordinary skill in the art would recognize an improvement and to provide significant evidence that Applicant’s claims are unconventional and provide a specific technical solution beyond using generic computer components in a conventional way and the claims themselves, as currently claimed, does not reflect the improvement in technology.
Furthermore, the amended claims are directed to an abstract idea and are specifically categorized under the Certain methods of organizing human activity enumerated grouping. According to the MPEP 2106.04(a)(2)(II), the Certain methods of organizing human activity enumerated grouping relates to concepts of fundamental economic principles or practices (including hedging, insurance, mitigating risk), commercial or legal interactions (including agreements in the form of contracts, legal obligations, advertising, marketing or sales activities or behaviors, and business relations) and managing personal behavior or relationships or interactions between people, (including social activities, teaching, and following rules or instructions). Identifying, using a proactive low discoverability identification model, first products having discoverabilities within a marketplace that are low relative to discoverabilities of other products published on the marketplace by: receiving historical engagement information for products in the marketplace; clustering the products of a product type into clusters according to a set of attributes; identifying a cluster of the products with a highest quantity of the products as a first subset of the products; identifying a second subset of the products, from one or more clusters other than the identified cluster, that are similar to the first subset of the products based on at least one similarity criterion; and determining a third subset of the products by filtering the second subset of the products based on comparing the historical engagement information for the second subset of the products to the historical engagement information for the first subset of the products and identifying the third subset of the products as a portion of the second subset of the products that are less than an engagement threshold of an engagement for the first subset of the products; displaying the third subset of the products with increased frequency on the marketplace based on one or more searches in the marketplace; and determining, using an impact assessment model, an impact on the discoverabilities of the first products based on displaying the third subset of the products with increased frequency by: determining at least one benchmark for the first subset of the products based on the historical engagement information for the first subset of the products; and determining a lift score for the third subset of the products based on the at least one benchmark and engagement information for the third subset of the products, as displayed with the increased frequency is a form of commercial or legal interaction because it is directed to advertising, marketing, or sales activities or behaviors, and business relations, see MPEP 2106.04(a)(2)(II).
Applicant further claims on page 18 of the remarks that “discoverability (or visibility) is not related to advertisement or marketing, but is instead tied to retrieving products tagged with metadata relevant to searches.” Examiner respectfully disagrees. As noted previously, discoverability or visibility of products is a form of commercial or legal interaction because it relates to the advertising, marketing, or sales activities or behaviors, and business relations, see MPEP 2106.04(a)(2)(II). The cited ¶0002 of the instant specification describes an improvement to the business concept of the discoverability of products to potential buyers which is also directed to the abstract idea. Furthermore, the attributes and engagement information of products is also directed to the abstract idea because it is related to advertising, marketing, or sales, activities or behaviors, and business relations, see MPEP 2106.04(a)(2)(II).
Applicant argues on pages 18 and 19 of the remarks that the amended claims are not directed to the Mental Processes enumerated grouping of abstract ideas. Applicant adds that the human mind is not capable of handling or dealing with large datasets and cites to ¶0070 of the instant specification for support. Examiner respectfully disagrees. According to the MPEP 2106.04(a)(2)(III), the courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that require a human to use a physical aid to perform the claim limitation. Furthermore, the courts do not distinguish between claims that recite mental processes performed by humans and claims that recite mental processes performed on a computer. Examples of a claim that recites a mental process includes a claim to collecting information, analyzing it, and displaying results of the collection and analysis where the data analysis steps are recited at a high level of generality such that they could practically be performed in the human mind, see MPEP 2106.04(a)(2)(III)(A). The amended claim 1 recites identifying products having discoverabilities, receiving historical engagement information, clustering products, identifying a cluster of products, identifying a second subset of products, determining a third subset of products by filtering the second subset of products, displaying the third subset of the products, determining an impact on the discoverabilities of the first products, determining at least one benchmark, and determining a lift score. The aforementioned limitations are all part of the abstract idea and can be practically performed in the human mind as they are recited at a high level of generality. Furthermore, displaying products with increased visibility is also part of the abstract idea and merely applying the abstract idea on generic components such as a GUI does not overcome the rejection, see instant specification ¶0046 where the component is described at a high-level and as generic.
Applicant further argues on pages 19-21 that the amended claims integrate the abstract idea into a practical application. Examiner respectfully disagrees. Displaying the third subset of the products with increased frequency on the marketplace based on one or more searches in the marketplace is all part of the abstract idea. The mere execution of the abstract idea on high-level components such as a GUI, web-based marketplace, and web-based searches does not overcome the rejection. These components are described at a high-level and as generic in ¶0046, ¶0047, and ¶0051 of the instant specification. Furthermore, ¶0002 of the instant specification describes an improvement to the business concept of the discoverability of products to potential buyers which is also part to the abstract idea.
Applicant further argues on pages 20-22 of the remarks that the amended claims provide an improvement in the field of web-based marketplaces. Examiner respectfully disagrees. The instant claims which recite identifying and clustering products based on discoverabilities are not directed to improving “the technical field of online or web-based marketplaces” requiring the generic components to operate in an unconventional manner to achieve an improvement in computer functionality or requiring the non-conventional and non-generic arrangement of known, conventional pieces to improve a technical process. The additional elements are insufficient to integrate the abstract idea into a practical application because the claim fails to (i) reflect an improvement in the functioning of a computer, or an improvement to other technology or technical field, (ii) implement the judicial exception with, or use the judicial exception in conjunction with, a particular machine or manufacture that is integral to the claim, (iii) effect a transformation or reduction of a particular article to a different state or thing, or (iv) applies or uses the judicial exception in some other meaningful way beyond linking the use of the judicial exception to a particular technological environment. As currently recited, the instant claims are directed to improving the argued business task of identifying, using a proactive low discoverability identification model, first products having discoverabilities within a marketplace that are low relative to discoverabilities of other products published on the marketplace by: receiving historical engagement information for products in the marketplace; clustering the products of a product type into clusters according to a set of attributes; identifying a cluster of the products with a highest quantity of the products as a first subset of the products; identifying a second subset of the products, from one or more clusters other than the identified cluster, that are similar to the first subset of the products based on at least one similarity criterion; and determining a third subset of the products by filtering the second subset of the products based on comparing the historical engagement information for the second subset of the products to the historical engagement information for the first subset of the products and identifying the third subset of the products as a portion of the second subset of the products that are less than an engagement threshold of an engagement for the first subset of the products; displaying the third subset of the products with increased frequency on the marketplace based on one or more searches in the marketplace; and determining, using an impact assessment model, an impact on the discoverabilities of the first products based on displaying the third subset of the products with increased frequency by: determining at least one benchmark for the first subset of the products based on the historical engagement information for the first subset of the products; and determining a lift score for the third subset of the products based on the at least one benchmark and engagement information for the third subset of the products, as displayed with the increased frequency as recited in amended claim 1.
Applicant cites ¶0064 and ¶0069 for supporting the improvement argument. Examiner respectfully disagrees. Sending new products to content operations to provide the new products with data to allow them to be searchable in the marketplace, identifying products with low engagement and re-curating products to improve their engagement as described in ¶0064 is directed to improving the business idea and do not amount an improvement to existing technological systems. Applicant further argues that the amended claims increase computational efficiency however claiming the improved speed or efficiency inherent with applying the abstract idea on a computer does not integrate the judicial exception into a practical application or provide an inventive concept, refer to the MPEP 2106.05(f)(2).
Furthermore, applicant argues on page 21 of the remarks that the claims provide an improvement to the functioning of a computer and are therefore “significantly more” than the judicial exception. Examiner respectfully disagrees. As noted previously, the mere execution of the abstract idea on high-level components such as a GUI, web-based marketplace, and web-based searches does not overcome the rejection. These components are described at a high-level and as generic in ¶0046, ¶0047, and ¶0051 of the instant specification.
Accordingly, Examiner maintains that the invention is directed to a judicial exception without significantly more. The claims recite an abstract idea. This judicial exception is not integrated into a practical application. The claim(s) do not include additional elements that are sufficient to amount to significantly more than the judicial exception. Thus the 35 USC §101 rejections are maintained.
Applicant’s arguments on pages 22-25 filed 09/24/2025, with respect to the previous 35 USC § 103 rejections have been fully considered but are mostly moot in the view of the new 35 USC § 103 rejections applied to the applicant’s amended claims.
Applicant argues on page 23 of the remarks that Chan does not disclose “clustering the products of a product type into clusters according to a set of attributes” in amended claim 1. Examiner respectfully disagrees. Col. 4, lines 20-60 of Chan describe that a collection consist of items that are purchased by a user. Furthermore, Chan states that the collection can be based on item selection actions such as “rentals, views, downloads, shopping cart adds, wish list adds, Subscription purchases, etc.” in the same paragraph. ¶0052 of the instant specification describes that, “In some embodiments, the set of attributes includes at least one of the following: a number of reviews, an average rating, a quality score, a number of orders in a season, or a number of impressions in a season”. Examiner notes that the attributes disclosed by Chan such as “views”, “downloads”, or “rentals” are comparable to a number of orders or impressions in a season. Therefore, Examiner maintains that Chan discloses clustering the products of a product type into clusters according to a set of attributes.
Applicant further argues on page 24 of the remarks that Chan does not disclose “identifying a second subset of the products, from one or more clusters other than the identified cluster, that are similar to the first subset of the products based on at least one similarity criterion”. Examiner respectfully disagrees. Col. 7, lines 1-18 of Chan describe that a score is generated for each cluster that is used to select clusters from which items are obtained. Furthermore, Chan describes that the scores are based on factors such as “(1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster, (6) if applicable, the extent to which the items that the cluster contains are close to items that represent known gift purchases” in the same paragraph. Examiner notes that the factors listed by Chan are comparable to similarity criterions. Therefore, Chan discloses “identifying a second subset of the products, that are similar to the first subset of the products based on at least one similarity criterion”.
Chan does not explicitly disclose identifying “from one or more clusters other than the identified cluster”. However, the newly cited reference Kumar teaches identifying a subset of products from clusters other than an identified cluster (Fig. 28; ¶0120[Determining the one or more product clusters may comprise receiving (e.g., from a database stored on the server 102) a first plurality of product identifiers each sharing a common attribute. The common attribute may be based on clinical equivalence, intended use, size, quantity, a combination thereof, and the like.]).
The system of Kumar is applicable to the system of Chan as they share characteristics and capabilities, namely, they are all targeted to improving search. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of Chan to include identifying a subset of products from one or more cluster other than the identified cluster as taught by Kumar.
Furthermore, applicant argues on page 24 of the remarks that Chan does not disclose "determining a third subset of the products by filtering the second subset of the products based on comparing the historical engagement information for the second subset of the products to the historical engagement information for the first subset of the products and identifying the third subset of the products as a portion of the second subset of the products that are less than an engagement threshold of an engagement for the first subset of the products," in amended claim 1. Examiner respectfully disagrees. Col. 7, lines 1-18 of Chan describe that each cluster can be scored and the scores can be used to select clusters from which source items are obtained. Furthermore, the cluster scores are based on factors such as “(1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster.” Examiner notes that scoring clusters based on purchase dates of items in the clusters is comparable to determining a subset of products based on comparing the historical engagement information of subsets of products. Therefore, Chan discloses “determining a third subset of the products by filtering the second subset of the products based on comparing the historical engagement information for the second subset of the products to the historical engagement information for the first subset of the products and identifying the third subset of the products as a portion of the second subset of the products”.
Chan does not explicitly disclose products “that are less than an engagement threshold of an engagement for the first subset of the products.” However, reference Decker teaches determining products that are less than an engagement threshold of an engagement threshold of products (Fig. 1; ¶0033[The cold start search system 102 may adjust the position of the newly added item within the search results. The cold start search system 102 may adjust the position of the newly added item within the plurality of search results based on the engagement score assigned by the system to the newly added item. For example, the cold start search system 102 may adjust the position of the newly added item so that it appears earlier (e.g., one or more positions closer to the beginning) in the search results, based on the relative value of the engagement score assigned to the newly added item compared to the engagement scores of other (e.g., historical) items in the search result.]).
The system of Decker is applicable to the system of Chan as they share characteristics and capabilities, namely, they are all directed to improving search. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the filtering of products as taught by Chan to include determining products that are within an engagement threshold as taught by Decker.
Applicant argues on page 24 of the remarks that Chan does not disclose “determining a third subset of products from the second subset having historical engagement information that is less than a threshold of the engagement, which are displayed with increased visibility.” Examiner respectfully disagrees. As stated previously, Col. 7, lines 1-18 of Chan describe that each cluster can be scored and the scores can be used to select clusters from which source items are obtained. Furthermore, the cluster scores are based on factors such as “(1) the number of items in the cluster, (2) the distance of the cluster from other clusters, (3) the cluster's homogeneity, (4) the ratings, if any, of items included in the cluster, (5) the purchase dates, if any, of the items in the cluster.” Examiner notes that scoring clusters based on purchase dates of items in the clusters is comparable to determining a subset of products based on comparing the historical engagement information of subsets of products. Therefore, Chan discloses “determining a third subset of products from the second subset having historical engagement information”.
As stated previously, Chan does not explicitly disclose products “that is less than a threshold of the engagement, which are displayed with increased visibility.” However, reference Decker teaches determining products that are less than an engagement threshold of an engagement threshold of products (Fig. 1; ¶0033[The cold start search system 102 may adjust the position of the newly added item within the search results. The cold start search system 102 may adjust the position of the newly added item within the plurality of search results based on the engagement score assigned by the system to the newly added item. For example, the cold start search system 102 may adjust the position of the newly added item so that it appears earlier (e.g., one or more positions closer to the beginning) in the search results, based on the relative value of the engagement score assigned to the newly added item compared to the engagement scores of other (e.g., historical) items in the search result.]).
The system of Decker is applicable to the system of Chan as they share characteristics and capabilities, namely, they are all directed to improving search. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the filtering of products as taught by Chan to include determining products that are within an engagement threshold as taught by Decker.
Accordingly, references Chan, Byrne, Decker, Zhao, Patterson, Ollikainen, Zhang, ExpertVillage Leaf Group have been maintained and reference Kumar has been newly added, as necessitated by the claim amendments.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AHOORA LADONI whose email is Ahoora.Ladoni@uspto.gov and telephone number is (703) 756-5617. The examiner can normally be reached M-F 0900–1700 ET.
Examiner interviews are available via telephone, in-person and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/AHOORA LADONI/Examiner, Art Unit 3689
/VICTORIA E. FRUNZI/Primary Examiner, Art Unit 3689 11/21/2025
Prosecution Insights