DETAILED ACTION
Status of Claims
Claims 1-20 submitted on 04/03/2025 are pending and have been examined.
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
Acknowledgement is made of applicant’s claim for foreign priority under 35 U.S.C. 119(a)-(d). The certified copy has been filed in parent application No. CN202310212088.2, filed on 02/24/2023.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 04/03/2025 has been considered by the examiner.
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 1-20 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 process, claims 11-19 are directed to a machine, and claim 20 is directed to an article of manufacture (see MPEP 2106.03).
Step 2A, Prong 1
Claim 20, taken as representative, recites at least the following limitations that recite an abstract idea:
determining a category of a to-be-recommended item based on an item feature of the to-be- recommended item;
obtaining an association parameter between the category of the to-be-recommended item and a first object, the association parameter representing an association level between the category of the to-be-recommended item and the first object;
calculating a recommendation evaluation parameter of the to-be-recommended item based on the association parameter and the category of the to-be-recommended item; and
determining whether to recommend the to-be-recommended item to the first object based on the recommendation evaluation parameter.
The above limitation, under its broadest reasonable interpretation, falls within the “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. Claims 1 and 11 recites similar limitations as claim 20.
Thus, under Prong 1 of Step 2A, claims 1, 11, and 20 recite an abstract idea.
Step 2A, Prong 2
Claim 20 includes the following additional elements that are bolded:
A non-transitory computer-readable storage medium storing instructions which when executed by at least one processor cause the at least one processor to perform:
determining a category of a to-be-recommended item based on an item feature of the to-be- recommended item;
obtaining an association parameter between the category of the to-be-recommended item and a first object, the association parameter representing an association level between the category of the to-be-recommended item and the first object;
calculating a recommendation evaluation parameter of the to-be-recommended item based on the association parameter and the category of the to-be-recommended item; and
determining whether to recommend the to-be-recommended item to the first object based on the recommendation evaluation parameter.
Claim 1 does not include any additional elements.
Claim 11 includes additional elements such as an information processing apparatus, comprising processing circuitry configured to.
The additional elements recited in claims 11 and 20 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 processors and storage medium (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. 17 and ¶0007).
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 20 are directed to an abstract idea.
Step 2B
As noted above, while the recitation of the additional elements in independent claims 1, 11, and 20 are acknowledged, claims 1, 11, and 20 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 20 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 20 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 20 are ineligible.
Dependent claims 2-10 and 12-19 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 2-10 and 12-19 merely further define the abstract limitations of claims 1, 11, and 20 or provide further embellishments of the limitations recited in independent claims 1, 11, and 20. Claims 2-10 and 12-19 do not introduce any further additional elements. Thus, dependent claims 2-10 and 12-19 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, 5-7, 10, 11, 15-17, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Rao Karikurve et al. (US 2022/0335489 A1) in view of Hirooka et al. (US 2017/0366685 A1).
Regarding Claim 1, Rao Karikurve et al., hereinafter, Rao Karikurve, discloses a method of item recommendation, the method comprising: determining a category of a to-be-recommended item based on an item feature of the to-be- recommended item (Fig. 6[615 and 620]; ¶0058[Additionally, the online concierge system 102 generates 615 one or more collections of items offered by a warehouse 110. In some embodiments, the online concierge system 102 selects items offered by the warehouse 110 that have one or more common attributes for the collection. For example, a collection includes items offered by the warehouse 110 that are each associated with a common category by the online concierge system 102]; Examiner notes that item attributes are comparable to an “item feature”);
obtaining an association parameter between the category of the to-be-recommended item and a first object, the association parameter representing an association level between the category of the to-be-recommended item and the first object (Fig. 6[635]; ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user]; Examiner notes that the user is comparable to the "object");
calculating a recommendation evaluation parameter of the to-be-recommended item based on the association parameter and the category of the to-be-recommended item (Fig. 6; ¶0064[From the collection embedding and the embedding for the user, the trained purchase model outputs a probability of the user purchasing one or more items in the collection. The score for the collection is the probability of the user purchasing one or more items in the collection in such embodiments. In other embodiments, the online concierge system 102 generates a score for an item based on any suitable comparison of the embedding for the user and the embedding for the item (e.g., dot product, cosine similarity, Euclidian distance, etc.). As the collection includes one or more items, application of the trained purchase model to the collection embedding and the embedding for the user allows the online concierge system 102 to determine a probability of the user purchasing one or more items within the collection, enabling the online concierge system 102 to more efficiently determine if items in the collection are likely to be of interest to the user.]); and
recommend the to-be-recommended item to the first object based on the recommendation evaluation parameter (¶0065[the scores for collections are probabilities of the user purchasing one or more items in a collection from application of the trained model to the embedding for the user and to collection embeddings for one or more collections. The interface displays information identifying items and one or more collections in an order based on the corresponding scores of the items and scores of the one or more collections (e.g., the probabilities of the user purchasing items or purchasing an item from a collection). For example, the online concierge system 102 ranks items and one more collections based on the scores of the items and the scores of the collections, with items or collections having higher scores having higher positions in the ranking. The online concierge system 102 orders the items and the one or more collections based on the ranking and displays the items and the one or more collections in the interface according to the order. For example, the interface displays items or collections with higher positions in the ranking in more prominent locations in the interface. The online concierge system 102 transmits 645 the interface to a client device of the user for display, such as for display via the customer mobile application 106 executing on the client device.]).
Although Rao Karikurve discloses recommending items, Rao Karikurve does not explicitly disclose determining whether to recommend items.
However, Hirooka et al., hereinafter, Hirooka, teaches determining whether to recommend items (Fig. 3; ¶0041[The recommendation determination unit 310 uses these configuration elements (311 through 315) to determine whether to recommend the candidate item based on information of the candidate item obtained from the candidate item information obtainment unit 301 and information of the image obtained from the image management unit 302.]).
The method of Hirooka is applicable to the method of Rao Karikurve as they share characteristics and capabilities, namely, they are both targeted to product recommendations. 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 item recommendation as disclosed by Rao Karikurve to include determining whether to recommend items as taught by Hirooka. One of ordinary skill in the art would have been motivated to expand the method of Rao Karikurve in order to promote sales by recommending image capturing equipment such as cameras and lenses (¶0002).
Regarding Claim 5, Rao Karikurve in view of Hirooka teaches the method according to claim1, Rao Karikurve discloses wherein the calculating the recommendation evaluation parameter comprises:
obtaining one or more association features corresponding to the association parameter; obtaining an item category feature of the category of the to-be-recommended item (Fig. 6[635]; ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user]; Examiner notes that the user is comparable to the "object");
calculating a recommendation evaluation feature of the to-be-recommended item based on the one or more association features and the item category feature (Fig. 6; ¶0064[From the collection embedding and the embedding for the user, the trained purchase model outputs a probability of the user purchasing one or more items in the collection. The score for the collection is the probability of the user purchasing one or more items in the collection in such embodiments. In other embodiments, the online concierge system 102 generates a score for an item based on any suitable comparison of the embedding for the user and the embedding for the item (e.g., dot product, cosine similarity, Euclidian distance, etc.). As the collection includes one or more items, application of the trained purchase model to the collection embedding and the embedding for the user allows the online concierge system 102 to determine a probability of the user purchasing one or more items within the collection, enabling the online concierge system 102 to more efficiently determine if items in the collection are likely to be of interest to the user.]); and
using the recommendation evaluation feature as the recommendation evaluation parameter of the to-be-recommended item (¶0065[As described above, in some embodiments, the scores for collections are probabilities of the user purchasing one or more items in a collection from application of the trained model to the embedding for the user and to collection embeddings for one or more collections. The interface displays information identifying items and one or more collections in an order based on the corresponding scores of the items and scores of the one or more collections (e.g., the probabilities of the user purchasing items or purchasing an item from a collection). For example, the online concierge system 102 ranks items and one more collections based on the scores of the items and the scores of the collections, with items or collections having higher scores having higher positions in the ranking. The online concierge system 102 orders the items and the one or more collections based on the ranking and displays the items and the one or more collections in the interface according to the order. For example, the interface displays items or collections with higher positions in the ranking in more prominent locations in the interface. The online concierge system 102 transmits 645 the interface to a client device of the user for display, such as for display via the customer mobile application 106 executing on the client device.]).
Regarding Claim 6, Rao Karikurve in view of Hirooka teaches the method according to claim 5, Rao Karikurve discloses wherein: the one or more association features include a plurality of association features (Fig. 6; ¶0053[In some embodiments, for the identified user, the modeling engine 218 retrieves additional purchases previously made by the user from the transaction records database 208 and averages embeddings for items included in purchase previously made by the user, resulting in an embedding representing a purchase history of the user. Hence, the training data includes an embedding for an item, an embedding for a user, and a label indicating whether the item was purchased or was not purchased by the user]); and the calculating the recommendation evaluation feature comprises:
generating an object representation vector set based on the plurality of association features (¶0049[In some embodiments, an embedding for an item or for a user comprises a feature vector having multiple dimensions, with each dimension including a value describing one or more attributes of the item or characteristics of the user.]);
generating an item representation vector set of the to-be-recommended item based on the item category feature (¶0049[In some embodiments, an embedding for an item or for a user comprises a feature vector having multiple dimensions, with each dimension including a value describing one or more attributes of the item or characteristics of the user.]); and
calculating the recommendation evaluation feature of the to-be-recommended item based on the object representation vector set and the item representation vector set (Fig. 6; ¶0064[From the collection embedding and the embedding for the user, the trained purchase model outputs a probability of the user purchasing one or more items in the collection. The score for the collection is the probability of the user purchasing one or more items in the collection in such embodiments. In other embodiments, the online concierge system 102 generates a score for an item based on any suitable comparison of the embedding for the user and the embedding for the item (e.g., dot product, cosine similarity, Euclidian distance, etc.). As the collection includes one or more items, application of the trained purchase model to the collection embedding and the embedding for the user allows the online concierge system 102 to determine a probability of the user purchasing one or more items within the collection, enabling the online concierge system 102 to more efficiently determine if items in the collection are likely to be of interest to the user.]).
Regarding Claim 7, Rao Karikurve in view of Hirooka teaches the method according to claim 6, Rao Karikurve discloses wherein: the generating the object representation vector set comprises:
generating a plurality of object representation vectors based on the plurality of association features and a second object feature of the first object, the second object feature being a different feature from a first object feature for generating the plurality of association features; and generating the object representation vector set based on the plurality of object representation vectors (¶0049[In some embodiments, an embedding for an item or for a user comprises a feature vector having multiple dimensions, with each dimension including a value describing one or more attributes of the item or characteristics of the user.] in view of ¶0011[Additionally, one or more dimensions of the embedding for the user correspond to characteristics of the user maintained by the online concierge system. Example dimensions of the embedding for the user correspond to one or more dietary preferences or restrictions of the user, frequency of purchases from the warehouse by the user, and any other suitable information maintained by the online concierge system.]); and
the generating the item representation vector set comprises:
generating an item representation vector corresponding to the to-be-recommended item based on the item category feature and a second item feature of the to-be-recommended item, the second item feature being a different feature from the item feature that is used to determine the category of the to-be-recommended item (¶0058[n one embodiment, K-means clustering is used to cluster items offered by the warehouse 110 based on embeddings for the various items. Using K-means clustering causes an item to be clustered based on the distance of each dimension of an embedding for the item to a mean value associated with a dimension across all embeddings. For example, items having a value associated with a dimension that is within a specified distance to a mean value associated with the dimension are included in a cluster] in view of ¶0049[In some embodiments, an embedding for an item or for a user comprises a feature vector having multiple dimensions, with each dimension including a value describing one or more attributes of the item or characteristics of the user.]); and
generating the item representation vector set of the to-be-recommended item based on the item representation vector corresponding to the to-be-recommended item (¶0049[In some embodiments, an embedding for an item or for a user comprises a feature vector having multiple dimensions, with each dimension including a value describing one or more attributes of the item or characteristics of the user.]).
Regarding Claim 10, Rao Karikurve in view of Hirooka teaches the method according to claim 1, Rao Karikurve discloses wherein the determining whether to recommend the to-be-recommended item comprises:
comparing the recommendation evaluation parameter to a preset evaluation parameter threshold (¶0066[the online concierge system 102 determines scores for multiple collections based on comparisons between collection embeddings for the collections and the embedding for the user. For example, the online concierge system 102 applies the trained purchase model to collection embeddings for multiple collections generated by the online concierge system 102 and to the embedding for the user and uses the probabilities output by the trained purchased model as the scores. Based on the scores from the comparisons, the online concierge system 102 ranks the collections so collections having higher scores have higher positions in the ranking (e.g., collections with higher probabilities have higher positions in the ranking). The online concierge system 102 identifies a set of collections from the ranking, such as collections having at least a threshold position in the ranking. For each identified collection, the online concierge system 102 determines scores for different items in the collection and ranks items within the collection based on the scores for the different items. For example, the online concierge system 102 applies the trained purchase model to items included in the collection, generating probabilities of the user purchasing different items in the collection, and determines an item ranking of items within the collection based on the generated probabilities. The online concierge system 102 orders items within the collection based on the item ranking. The interface generated by the online concierge system 102 displays identifiers of at least the set of collections in a first direction in an order based on their ranking.]); and
determining to recommend the to-be-recommended item to the first object when the recommendation evaluation parameter is greater than the preset evaluation parameter threshold (¶0066[the online concierge system 102 determines scores for multiple collections based on comparisons between collection embeddings for the collections and the embedding for the user. For example, the online concierge system 102 applies the trained purchase model to collection embeddings for multiple collections generated by the online concierge system 102 and to the embedding for the user and uses the probabilities output by the trained purchased model as the scores. Based on the scores from the comparisons, the online concierge system 102 ranks the collections so collections having higher scores have higher positions in the ranking (e.g., collections with higher probabilities have higher positions in the ranking). The online concierge system 102 identifies a set of collections from the ranking, such as collections having at least a threshold position in the ranking. For each identified collection, the online concierge system 102 determines scores for different items in the collection and ranks items within the collection based on the scores for the different items. For example, the online concierge system 102 applies the trained purchase model to items included in the collection, generating probabilities of the user purchasing different items in the collection, and determines an item ranking of items within the collection based on the generated probabilities. The online concierge system 102 orders items within the collection based on the item ranking. The interface generated by the online concierge system 102 displays identifiers of at least the set of collections in a first direction in an order based on their ranking.]).
Regarding Claim 11, Rao Karikurve discloses an information processing apparatus, comprising processing circuitry configured to: determine a category of a to-be-recommended item based on an item feature of the to-be- recommended item (Fig. 6[615 and 620]; ¶0058[Additionally, the online concierge system 102 generates 615 one or more collections of items offered by a warehouse 110. In some embodiments, the online concierge system 102 selects items offered by the warehouse 110 that have one or more common attributes for the collection. For example, a collection includes items offered by the warehouse 110 that are each associated with a common category by the online concierge system 102] in view of Claim 13[A computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to]; Examiner notes that item attributes are comparable to an “item feature”);
obtain an association parameter between the category of the to-be-recommended item and a first object, the association parameter representing an association level between the category of the to-be-recommended item and the first object (Fig. 6[635]; ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user]; Examiner notes that the user is comparable to the "object");
calculate a recommendation evaluation parameter of the to-be-recommended item based on the association parameter and the category of the to-be-recommended item (Fig. 6; ¶0064[From the collection embedding and the embedding for the user, the trained purchase model outputs a probability of the user purchasing one or more items in the collection. The score for the collection is the probability of the user purchasing one or more items in the collection in such embodiments. In other embodiments, the online concierge system 102 generates a score for an item based on any suitable comparison of the embedding for the user and the embedding for the item (e.g., dot product, cosine similarity, Euclidian distance, etc.). As the collection includes one or more items, application of the trained purchase model to the collection embedding and the embedding for the user allows the online concierge system 102 to determine a probability of the user purchasing one or more items within the collection, enabling the online concierge system 102 to more efficiently determine if items in the collection are likely to be of interest to the user.]); and
recommend the to-be-recommended item to the first object based on the recommendation evaluation parameter (¶0065[the scores for collections are probabilities of the user purchasing one or more items in a collection from application of the trained model to the embedding for the user and to collection embeddings for one or more collections. The interface displays information identifying items and one or more collections in an order based on the corresponding scores of the items and scores of the one or more collections (e.g., the probabilities of the user purchasing items or purchasing an item from a collection). For example, the online concierge system 102 ranks items and one more collections based on the scores of the items and the scores of the collections, with items or collections having higher scores having higher positions in the ranking. The online concierge system 102 orders the items and the one or more collections based on the ranking and displays the items and the one or more collections in the interface according to the order. For example, the interface displays items or collections with higher positions in the ranking in more prominent locations in the interface. The online concierge system 102 transmits 645 the interface to a client device of the user for display, such as for display via the customer mobile application 106 executing on the client device.]).
Although Rao Karikurve discloses recommending items, Rao Karikurve does not explicitly disclose determine whether to recommend items.
However, Hirooka teaches determining whether to recommend items (Fig. 3; ¶0041[The recommendation determination unit 310 uses these configuration elements (311 through 315) to determine whether to recommend the candidate item based on information of the candidate item obtained from the candidate item information obtainment unit 301 and information of the image obtained from the image management unit 302.]).
The system of Hirooka is applicable to the system of Rao Karikurve as they share characteristics and capabilities, namely, they are both targeted to product recommendations. 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 item recommendation as disclosed by Rao Karikurve to include determining whether to recommend items as taught by Hirooka. One of ordinary skill in the art would have been motivated to expand the system of Rao Karikurve in order to promote sales by recommending image capturing equipment such as cameras and lenses (¶0002).
Regarding Claim 15, Rao Karikurve in view of Hirooka teaches the information processing apparatus according to claim 11, Rao Karikurve discloses wherein the processing circuitry is configured to: obtain one or more association features corresponding to the association parameter; obtain an item category feature of the category of the to-be-recommended item (Fig. 6[635]; ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user]; Examiner notes that the user is comparable to the "object");
calculate a recommendation evaluation feature of the to-be-recommended item based on the one or more association features and the item category feature (Fig. 6; ¶0064[From the collection embedding and the embedding for the user, the trained purchase model outputs a probability of the user purchasing one or more items in the collection. The score for the collection is the probability of the user purchasing one or more items in the collection in such embodiments. In other embodiments, the online concierge system 102 generates a score for an item based on any suitable comparison of the embedding for the user and the embedding for the item (e.g., dot product, cosine similarity, Euclidian distance, etc.). As the collection includes one or more items, application of the trained purchase model to the collection embedding and the embedding for the user allows the online concierge system 102 to determine a probability of the user purchasing one or more items within the collection, enabling the online concierge system 102 to more efficiently determine if items in the collection are likely to be of interest to the user.]); and
use the recommendation evaluation feature as the recommendation evaluation parameter of the to-be-recommended item (¶0065[As described above, in some embodiments, the scores for collections are probabilities of the user purchasing one or more items in a collection from application of the trained model to the embedding for the user and to collection embeddings for one or more collections. The interface displays information identifying items and one or more collections in an order based on the corresponding scores of the items and scores of the one or more collections (e.g., the probabilities of the user purchasing items or purchasing an item from a collection). For example, the online concierge system 102 ranks items and one more collections based on the scores of the items and the scores of the collections, with items or collections having higher scores having higher positions in the ranking. The online concierge system 102 orders the items and the one or more collections based on the ranking and displays the items and the one or more collections in the interface according to the order. For example, the interface displays items or collections with higher positions in the ranking in more prominent locations in the interface. The online concierge system 102 transmits 645 the interface to a client device of the user for display, such as for display via the customer mobile application 106 executing on the client device.]).
Regarding Claim 16, Rao Karikurve in view of Hirooka teaches the information processing apparatus according to claim 15, Rao Karikurve discloses wherein the one or more association features include a plurality of association features (Fig. 6; ¶0053[In some embodiments, for the identified user, the modeling engine 218 retrieves additional purchases previously made by the user from the transaction records database 208 and averages embeddings for items included in purchase previously made by the user, resulting in an embedding representing a purchase history of the user. Hence, the training data includes an embedding for an item, an embedding for a user, and a label indicating whether the item was purchased or was not purchased by the user]); and the processing circuitry is configured to:
generate an object representation vector set based on the plurality of association features (¶0049[In some embodiments, an embedding for an item or for a user comprises a feature vector having multiple dimensions, with each dimension including a value describing one or more attributes of the item or characteristics of the user.]);
generate an item representation vector set of the to-be-recommended item based on the item category feature (¶0049[In some embodiments, an embedding for an item or for a user comprises a feature vector having multiple dimensions, with each dimension including a value describing one or more attributes of the item or characteristics of the user.]); and
calculate the recommendation evaluation feature of the to-be-recommended item based on the object representation vector set and the item representation vector set (Fig. 6; ¶0064[From the collection embedding and the embedding for the user, the trained purchase model outputs a probability of the user purchasing one or more items in the collection. The score for the collection is the probability of the user purchasing one or more items in the collection in such embodiments. In other embodiments, the online concierge system 102 generates a score for an item based on any suitable comparison of the embedding for the user and the embedding for the item (e.g., dot product, cosine similarity, Euclidian distance, etc.). As the collection includes one or more items, application of the trained purchase model to the collection embedding and the embedding for the user allows the online concierge system 102 to determine a probability of the user purchasing one or more items within the collection, enabling the online concierge system 102 to more efficiently determine if items in the collection are likely to be of interest to the user.]).
Regarding Claim 17, Rao Karikurve in view of Hirooka teaches the information processing apparatus according to claim 16, Rao Karikurve discloses wherein the processing circuitry is configured to:
generate a plurality of object representation vectors based on the plurality of association features and a second object feature of the first object, the second object feature being a different feature from a first object feature for generating the plurality of association features; generate the object representation vector set based on the plurality of object representation vectors (¶0049[In some embodiments, an embedding for an item or for a user comprises a feature vector having multiple dimensions, with each dimension including a value describing one or more attributes of the item or characteristics of the user.] in view of ¶0011[Additionally, one or more dimensions of the embedding for the user correspond to characteristics of the user maintained by the online concierge system. Example dimensions of the embedding for the user correspond to one or more dietary preferences or restrictions of the user, frequency of purchases from the warehouse by the user, and any other suitable information maintained by the online concierge system.]);
generate an item representation vector corresponding to the to-be-recommended item based on the item category feature and a second item feature of the to-be-recommended item, the second item feature being a different feature from the item feature that is used for determining the category of the to-be-recommended item (¶0058[n one embodiment, K-means clustering is used to cluster items offered by the warehouse 110 based on embeddings for the various items. Using K-means clustering causes an item to be clustered based on the distance of each dimension of an embedding for the item to a mean value associated with a dimension across all embeddings. For example, items having a value associated with a dimension that is within a specified distance to a mean value associated with the dimension are included in a cluster] in view of ¶0049[In some embodiments, an embedding for an item or for a user comprises a feature vector having multiple dimensions, with each dimension including a value describing one or more attributes of the item or characteristics of the user.]); and
generate the item representation vector set of the to-be-recommended item based on the item representation vector corresponding to the to-be-recommended item (¶0049[In some embodiments, an embedding for an item or for a user comprises a feature vector having multiple dimensions, with each dimension including a value describing one or more attributes of the item or characteristics of the user.]).
Regarding Claim 20, Rao Karikurve discloses a non-transitory computer-readable storage medium storing instructions which when executed by at least one processor cause the at least one processor to perform: determining a category of a to-be-recommended item based on an item feature of the to-be- recommended item (Fig. 6[615 and 620]; ¶0058[Additionally, the online concierge system 102 generates 615 one or more collections of items offered by a warehouse 110. In some embodiments, the online concierge system 102 selects items offered by the warehouse 110 that have one or more common attributes for the collection. For example, a collection includes items offered by the warehouse 110 that are each associated with a common category by the online concierge system 102]; Examiner notes that item attributes are comparable to an “item feature”);
obtaining an association parameter between the category of the to-be-recommended item and a first object, the association parameter representing an association level between the category of the to-be-recommended item and the first object (Fig. 6[635]; ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user]; Examiner notes that the user is comparable to the "object");
calculating a recommendation evaluation parameter of the to-be-recommended item based on the association parameter and the category of the to-be-recommended item (Fig. 6; ¶0064[From the collection embedding and the embedding for the user, the trained purchase model outputs a probability of the user purchasing one or more items in the collection. The score for the collection is the probability of the user purchasing one or more items in the collection in such embodiments. In other embodiments, the online concierge system 102 generates a score for an item based on any suitable comparison of the embedding for the user and the embedding for the item (e.g., dot product, cosine similarity, Euclidian distance, etc.). As the collection includes one or more items, application of the trained purchase model to the collection embedding and the embedding for the user allows the online concierge system 102 to determine a probability of the user purchasing one or more items within the collection, enabling the online concierge system 102 to more efficiently determine if items in the collection are likely to be of interest to the user.]); and
recommend the to-be-recommended item to the first object based on the recommendation evaluation parameter (¶0065[the scores for collections are probabilities of the user purchasing one or more items in a collection from application of the trained model to the embedding for the user and to collection embeddings for one or more collections. The interface displays information identifying items and one or more collections in an order based on the corresponding scores of the items and scores of the one or more collections (e.g., the probabilities of the user purchasing items or purchasing an item from a collection). For example, the online concierge system 102 ranks items and one more collections based on the scores of the items and the scores of the collections, with items or collections having higher scores having higher positions in the ranking. The online concierge system 102 orders the items and the one or more collections based on the ranking and displays the items and the one or more collections in the interface according to the order. For example, the interface displays items or collections with higher positions in the ranking in more prominent locations in the interface. The online concierge system 102 transmits 645 the interface to a client device of the user for display, such as for display via the customer mobile application 106 executing on the client device.]).
Although Rao Karikurve discloses recommending items, Rao Karikurve does not explicitly disclose determining whether to recommend items.
However, Hirooka teaches determining whether to recommend items (Fig. 3; ¶0041[The recommendation determination unit 310 uses these configuration elements (311 through 315) to determine whether to recommend the candidate item based on information of the candidate item obtained from the candidate item information obtainment unit 301 and information of the image obtained from the image management unit 302.]).
The system of Hirooka is applicable to the system of Rao Karikurve as they share characteristics and capabilities, namely, they are both targeted to product recommendations. 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 item recommendation as disclosed by Rao Karikurve to include determining whether to recommend items as taught by Hirooka. One of ordinary skill in the art would have been motivated to expand the system of Rao Karikurve in order to promote sales by recommending image capturing equipment such as cameras and lenses (¶0002).
Claim(s) 2-4 and 12-14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Rao Karikurve in view of Hirooka in view of Wu et al. (US 2021/0279784 A1).
Regarding Claim 2, Rao Karikurve in view of Hirooka teaches the method according to claim 1, Rao Karikurve discloses wherein the obtaining the association parameter comprises: obtaining a association parameter, the association parameter comprising a plurality of item categories and respective association parameters of the plurality of item categories to objects including the first object (Fig. 6[635]; ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user] in view of ¶0053[the modeling engine 218 identifies users who made the purchases and retrieves characteristics of the identified users.]);
determining a item category to the category of the to-be-recommended item from the association parameter (¶0065[As described above, in some embodiments, the scores for collections are probabilities of the user purchasing one or more items in a collection from application of the trained model to the embedding for the user and to collection embeddings for one or more collections. The interface displays information identifying items and one or more collections in an order based on the corresponding scores of the items and scores of the one or more collections (e.g., the probabilities of the user purchasing items or purchasing an item from a collection). For example, the online concierge system 102 ranks items and one more collections based on the scores of the items and the scores of the collections, with items or collections having higher scores having higher positions in the ranking.); and
obtaining a association parameter between the item category and the first object from the association parameter (Fig. 6[635]; ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user] in view of ¶0053[the modeling engine 218 identifies users who made the purchases and retrieves characteristics of the identified users.]).
Although Rao Karikurve discloses obtaining an association parameter comprising item categories and objects, Rao Karikurve in view of Hirooka does not explicitly teach obtaining a preset association table, the preset association table and preset association, determining a matching item from the preset association table, and obtaining a preset association matching item from the preset association table.
However, Wu et al., hereinafter, Wu, teaches preset association tables and determining a matching item from the association table (Fig. 6; ¶0076[Specifically, sorting a plurality of similar items into a similar item table, searching in a preset similar item table after obtaining the primary item classification result, and judging that the primary item classification result is a similar item if the similar item matching the primary item classification result is found; and judging that the primary item classification result is not the similar item if no similar item matching the primary item classification result is found.]).
The method of Wu is applicable to the method of Rao Karikurve in view of Hirooka as they share characteristics and capabilities, namely, they are all targeted to product identification. 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 item and user association as taught by Rao Karikurve in view of Hirooka to include a preset table and finding a matching item as taught by Wu. One of ordinary skill in the art would have been motivated to expand the method of Rao Karikurve in view of Hirooka in order to improve the management efficiency and facilitating the managers to know all the item information on the supermarket shelf at a glance (Abstract).
Regarding Claim 3, Rao Karikurve in view of Hirooka in view of Wu teaches the method according to claim 2, Rao Karikurve discloses further comprising: obtaining an object feature of the first object;
obtaining respective item category features of the plurality of item categories (Fig. 6[635]; ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user]; Examiner notes that the “collection embedding” is comparable to an “item category feature”);
for each item category:
generating a respective association feature between the respective item category and the object feature based on respective item category feature and the object feature (Fig. 6[635]; ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user]; Examiner notes that the user embedding is comparable to the “object feature”); and
using the respective association feature between the respective item category and the object feature as a respective association parameter between the respective item category and the first object (Fig. 6; ¶0065[As described above, in some embodiments, the scores for collections are probabilities of the user purchasing one or more items in a collection from application of the trained model to the embedding for the user and to collection embeddings for one or more collections. The interface displays information identifying items and one or more collections in an order based on the corresponding scores of the items and scores of the one or more collections (e.g., the probabilities of the user purchasing items or purchasing an item from a collection). For example, the online concierge system 102 ranks items and one more collections based on the scores of the items and the scores of the collections, with items or collections having higher scores having higher positions in the ranking]).
Regarding Claim 4, Rao Karikurve in view of Hirooka in view of Wu teaches the method according to claim 3, Rao Karikurve discloses wherein: the object feature comprises a historical behavior feature of the first object (¶0053[In some embodiments, for the identified user, the modeling engine 218 retrieves additional purchases previously made by the user from the transaction records database 208 and averages embeddings for items included in purchase previously made by the user, resulting in an embedding representing a purchase history of the user]); and
the generating comprises:
obtaining an item feature associated with the historical behavior feature of the first object (¶0053[In some embodiments, for the identified user, the modeling engine 218 retrieves additional purchases previously made by the user from the transaction records database 208 and averages embeddings for items included in purchase previously made by the user, resulting in an embedding representing a purchase history of the user. Hence, the training data includes an embedding for an item, an embedding for a user, and a label indicating whether the item was purchased or was not purchased by the user]); and
performing feature crossing on the respective item category feature of the respective item category and the item feature to obtain the respective association feature between the respective item category and the object feature (Fig. 6[635]; ¶0060[Using the embeddings for various items in a collection, the online concierge system 102 generates 620 a collection embedding for the collection. For example, a collection embedding is generated 620 for each cluster generated 615 by the online concierge system 102 based on the embeddings corresponding to each item in a collection.] in view of ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user]).
Regarding Claim 12, Rao Karikurve in view of Hirooka teaches the information processing apparatus according to claim 11, Rao Karikurve discloses wherein the processing circuitry is configured to:
obtain a association parameter, the association parameter comprising a plurality of item categories and respective association parameters of the plurality of item categories to objects including the first object (Fig. 6[635]; ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user] in view of ¶0053[the modeling engine 218 identifies users who made the purchases and retrieves characteristics of the identified users.]);
determine a item category to the category of the to-be-recommended item from the association parameter (¶0065[As described above, in some embodiments, the scores for collections are probabilities of the user purchasing one or more items in a collection from application of the trained model to the embedding for the user and to collection embeddings for one or more collections. The interface displays information identifying items and one or more collections in an order based on the corresponding scores of the items and scores of the one or more collections (e.g., the probabilities of the user purchasing items or purchasing an item from a collection). For example, the online concierge system 102 ranks items and one more collections based on the scores of the items and the scores of the collections, with items or collections having higher scores having higher positions in the ranking.); and
obtain a association parameter between the item category and the first object from the association parameter (Fig. 6[635]; ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user] in view of ¶0053[the modeling engine 218 identifies users who made the purchases and retrieves characteristics of the identified users.]).
Although Rao Karikurve discloses obtaining an association parameter comprising item categories and objects, Rao Karikurve in view of Hirooka does not explicitly teach obtaining a preset association table, the preset association table and preset association, determining a matching item from the preset association table, and obtaining a preset association matching item from the preset association table.
However, Wu teaches preset association tables and determining a matching item from the association table (Fig. 6; ¶0076[Specifically, sorting a plurality of similar items into a similar item table, searching in a preset similar item table after obtaining the primary item classification result, and judging that the primary item classification result is a similar item if the similar item matching the primary item classification result is found; and judging that the primary item classification result is not the similar item if no similar item matching the primary item classification result is found.]).
The system of Wu is applicable to the system of Rao Karikurve in view of Hirooka as they share characteristics and capabilities, namely, they are all targeted to product identification. 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 item and user association as taught by Rao Karikurve in view of Hirooka to include a preset table and finding a matching item as taught by Wu. One of ordinary skill in the art would have been motivated to expand the system of Rao Karikurve in view of Hirooka in order to improve the management efficiency and facilitating the managers to know all the item information on the supermarket shelf at a glance (Abstract).
Regarding Claim 13, Rao Karikurve in view of Hirooka in view of Wu teaches the information processing apparatus according to claim 12, Rao Karikurve discloses wherein the processing circuitry is configured to: obtain an object feature of the first object; obtain respective item category features of the plurality of item categories (Fig. 6[635]; ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user]; Examiner notes that the “collection embedding” is comparable to an “item category feature”);
for each item category:
generate a respective association feature between the respective item category and the object feature based on respective item category feature and the object feature (Fig. 6[635]; ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user]; Examiner notes that the user embedding is comparable to the “object feature”); and
use the respective association feature between the respective item category and the object feature as a respective association parameter between the respective item category and the first object (Fig. 6; ¶0065[As described above, in some embodiments, the scores for collections are probabilities of the user purchasing one or more items in a collection from application of the trained model to the embedding for the user and to collection embeddings for one or more collections. The interface displays information identifying items and one or more collections in an order based on the corresponding scores of the items and scores of the one or more collections (e.g., the probabilities of the user purchasing items or purchasing an item from a collection). For example, the online concierge system 102 ranks items and one more collections based on the scores of the items and the scores of the collections, with items or collections having higher scores having higher positions in the ranking]).
Regarding Claim 14, Rao Karikurve in view of Hirooka in view of Wu teaches the information processing apparatus according to claim 13, Rao Karikurve discloses wherein the object feature comprises a historical behavior feature of the first object (¶0053[In some embodiments, for the identified user, the modeling engine 218 retrieves additional purchases previously made by the user from the transaction records database 208 and averages embeddings for items included in purchase previously made by the user, resulting in an embedding representing a purchase history of the user]); and
the processing circuitry is configured to: obtain an item feature associated with the historical behavior feature of the first object (¶0053[In some embodiments, for the identified user, the modeling engine 218 retrieves additional purchases previously made by the user from the transaction records database 208 and averages embeddings for items included in purchase previously made by the user, resulting in an embedding representing a purchase history of the user. Hence, the training data includes an embedding for an item, an embedding for a user, and a label indicating whether the item was purchased or was not purchased by the user]); and
perform feature crossing on the respective item category feature of the respective item category and the item feature to obtain the respective association feature between the respective item category and the object feature (Fig. 6[635]; ¶0060[Using the embeddings for various items in a collection, the online concierge system 102 generates 620 a collection embedding for the collection. For example, a collection embedding is generated 620 for each cluster generated 615 by the online concierge system 102 based on the embeddings corresponding to each item in a collection.] in view of ¶0064[Referring back to FIG. 6, the online concierge system 102 also determines a score for the collection by comparing the embedding for the user and the collection embeddings. In some embodiments, the online concierge system 102 determines the score for the collection by applying 630 the trained purchase model to the collection embedding and the embedding for the user]).
Claim(s) 8, 9, 18, and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Rao Karikurve in view of Hirooka in view of Navlakha et al. (US 2019/0171665 A1).
Regarding Claim 8, Rao Karikurve in view of Hirooka teaches the method according to claim 7, Rao Karikurve discloses wherein the generating the item representation vector set comprises: generating the item representation vector set with the item representation vector corresponding to the to-be-recommended item and with other item representation vectors in the item representation vector set (¶0049[In some embodiments, an embedding for an item or for a user comprises a feature vector having multiple dimensions, with each dimension including a value describing one or more attributes of the item or characteristics of the user.]).
Although Rao Karikurve discloses generating item representation vectors, Rao Karikurve in view of Hirooka does not explicitly teach item representation vectors being zeroed out.
However, Navlakha et al., hereinafter, Navlakha, teaches vectors being zeroed out (¶0117[The remaining (so-called “non-winning” or “losing” values) can be eliminated (e.g., set to zero in the vector)] in view of ¶0076[In practice, the matching technologies can be used for a variety of applications, such as… collaborative filtering (e.g., recommendation systems, such as video, music, or any type of product recommendation systems), plagiarism detection, matching chemical structures, or the like.]).
The method of Navlakha is applicable to the method of Rao Karikurve in view of Hirooka as they share characteristics and capabilities, namely, they are all targeted to product 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 item representation vector as taught by Rao Karikurve in view of Hirooka to include vectors being zeroed out as taught by Navlakha. One of ordinary skill in the art would have been motivated to expand the method of Rao Karikurve in view of Hirooka in order to assign a numerical value to features of the item, including features not detectable by manual observation (¶0079).
Regarding Claim 9, Rao Karikurve in view of Hirooka teaches the method according to claim 6, Rao Karikurve discloses wherein the calculating the recommendation evaluation feature comprises: the object representation vector set and the item representation vector set to obtain a product value (¶0049[In some embodiments, an embedding for an item or for a user comprises a feature vector having multiple dimensions, with each dimension including a value describing one or more attributes of the item or characteristics of the user.]); and
using the product value as the recommendation evaluation feature (Fig. 6; ¶0064[From the collection embedding and the embedding for the user, the trained purchase model outputs a probability of the user purchasing one or more items in the collection. The score for the collection is the probability of the user purchasing one or more items in the collection in such embodiments. In other embodiments, the online concierge system 102 generates a score for an item based on any suitable comparison of the embedding for the user and the embedding for the item (e.g., dot product, cosine similarity, Euclidian distance, etc.). As the collection includes one or more items, application of the trained purchase model to the collection embedding and the embedding for the user allows the online concierge system 102 to determine a probability of the user purchasing one or more items within the collection, enabling the online concierge system 102 to more efficiently determine if items in the collection are likely to be of interest to the user.]).
Although Rao Karikurve discloses object and item representation vectors, Rao Karikurve in view of Hirooka does not explicitly teach multiplying the vectors.
However, Navlakha teaches multiplying vectors (¶0179[For example, the dimension expander 1530 or 2830 can apply (e.g., multiply) any feature vector described herein, such as the normalized feature vector 1515 or 2815, to any matrix described herein, such as D×K matrix 1525 or 2825.] in view of ¶0076[In practice, the matching technologies can be used for a variety of applications, such as… collaborative filtering (e.g., recommendation systems, such as video, music, or any type of product recommendation systems), plagiarism detection, matching chemical structures, or the like.]).
The method of Navlakha is applicable to the method of Rao Karikurve in view of Hirooka as they share characteristics and capabilities, namely, they are all targeted to product 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 item representation vector as taught by Rao Karikurve in view of Hirooka to include multiplying vectors as taught by Navlakha. One of ordinary skill in the art would have been motivated to expand the method of Rao Karikurve in view of Hirooka in order to assign a numerical value to features of the item, including features not detectable by manual observation (¶0079).
Regarding Claim 18, Rao Karikurve in view of Hirooka teaches the information processing apparatus according to claim 17, Rao Karikurve discloses wherein the processing circuitry is configured to: generate the item representation vector set with the item representation vector corresponding to the to-be-recommended item and with other item representation vectors in the item representation vector set (¶0049[In some embodiments, an embedding for an item or for a user comprises a feature vector having multiple dimensions, with each dimension including a value describing one or more attributes of the item or characteristics of the user.]).
Although Rao Karikurve discloses generating item representation vectors, Rao Karikurve in view of Hirooka does not explicitly teach item representation vectors being zeroed out.
However, Navlakha teaches vectors being zeroed out (¶0117[The remaining (so-called “non-winning” or “losing” values) can be eliminated (e.g., set to zero in the vector)] in view of ¶0076[In practice, the matching technologies can be used for a variety of applications, such as… collaborative filtering (e.g., recommendation systems, such as video, music, or any type of product recommendation systems), plagiarism detection, matching chemical structures, or the like.]).
The system of Navlakha is applicable to the system of Rao Karikurve in view of Hirooka as they share characteristics and capabilities, namely, they are all targeted to product 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 item representation vector as taught by Rao Karikurve in view of Hirooka to include vectors being zeroed out as taught by Navlakha. One of ordinary skill in the art would have been motivated to expand the system of Rao Karikurve in view of Hirooka in order to assign a numerical value to features of the item, including features not detectable by manual observation (¶0079).
Regarding Claim 19, Rao Karikurve in view of Hirooka teaches the information processing apparatus according to claim 16, Rao Karikurve discloses wherein the processing circuitry is configured to: the object representation vector set and the item representation vector set to obtain a product value (¶0049[In some embodiments, an embedding for an item or for a user comprises a feature vector having multiple dimensions, with each dimension including a value describing one or more attributes of the item or characteristics of the user.]); and
use the product value as the recommendation evaluation feature (Fig. 6; ¶0064[From the collection embedding and the embedding for the user, the trained purchase model outputs a probability of the user purchasing one or more items in the collection. The score for the collection is the probability of the user purchasing one or more items in the collection in such embodiments. In other embodiments, the online concierge system 102 generates a score for an item based on any suitable comparison of the embedding for the user and the embedding for the item (e.g., dot product, cosine similarity, Euclidian distance, etc.). As the collection includes one or more items, application of the trained purchase model to the collection embedding and the embedding for the user allows the online concierge system 102 to determine a probability of the user purchasing one or more items within the collection, enabling the online concierge system 102 to more efficiently determine if items in the collection are likely to be of interest to the user.]).
Although Rao Karikurve discloses object and item representation vectors, Rao Karikurve in view of Hirooka does not explicitly teach multiply the vectors.
However, Navlakha teaches multiplying vectors (¶0179[For example, the dimension expander 1530 or 2830 can apply (e.g., multiply) any feature vector described herein, such as the normalized feature vector 1515 or 2815, to any matrix described herein, such as D×K matrix 1525 or 2825.] in view of ¶0076[In practice, the matching technologies can be used for a variety of applications, such as… collaborative filtering (e.g., recommendation systems, such as video, music, or any type of product recommendation systems), plagiarism detection, matching chemical structures, or the like.]).
The system of Navlakha is applicable to the system of Rao Karikurve in view of Hirooka as they share characteristics and capabilities, namely, they are all targeted to product 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 item representation vector as taught by Rao Karikurve in view of Hirooka to include multiplying vectors as taught by Navlakha. One of ordinary skill in the art would have been motivated to expand the system of Rao Karikurve in view of Hirooka in order to assign a numerical value to features of the item, including features not detectable by manual observation (¶0079).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Poon (US 8,275,673 B1) discloses communicating a recommended item to a user of a network-based transaction facility.
“A Recommender System Based on Omni-Channel Customer Data” discloses providing personalized suggestions to customers which products to buy or services to consume.
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
/ANNA MAE MITROS/Examiner, Art Unit 3689
Prosecution Insights