DETAILED ACTION
This action is responsive to the application filed on 04/13/2026. Claims 1-2, 5-10, and 13-16, and 21-26 are pending and have been examined. This action is Final.
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 .
Response to Arguments
Argument 1: Applicant argues on pages 10-13 that claims 1 to 20 (now, 1-2, 5-10, 13-16, and 21-26) are not patent ineligible under 35 U.S.C. 101 because the claims, as amended, are not directed to an abstract idea and, even if considered to recite an abstract idea, integrate the alleged abstract idea into a practical application. The applicant argues under Step 2A Prong 1 that limitations such as inserting the set of cross-pollinated items into the interface and transmitting the interface to a user device cannot practically be performed in the human mind because a human mind is not equipped to insert elements into interfaces or transmit data to user devices. The applicant further argues under Step 2A Prong 2 that the claims improve interface technology by determining a number of cross-pollinated items based on a cross-pollination score and threshold, inserting cross-pollinated items associated with a second intent into an interface for a first intent, reducing user inputs needed to access cross-pollinated items, and efficiently allocating interface space based on score values. The applicant analogizes the claims to Example 37 of the Revised Patent Subject Matter Eligibility Guidance and contends that the claimed interface-generation features provide a specific improvement to an interface, rather than merely using generic computer components to implement an abstract idea. The applicant also argues that claim 9 is analogous to claim 1 and that the dependent claims are eligible for at least the same reasons.
Response to Argument 1: The applicant’s arguments regarding 35 U.S.C. 101 have been considered but are not persuasive. The applicant argues that the claims cannot be performed in the human mind because the claims recite inserting cross-pollinated items into an interface and transmitting the interface to a user device. However, the rejection does not rely on those interface transmission limitations as the abstract idea itself. Rather, the abstract idea is found in the score-based recommendation, prediction, evaluation, and selection process, including generating a cross-pollination score, selecting cross-pollinated items based on the score, and determining a number of cross-pollinated items by comparing the score to at least one threshold value. These limitations recite mathematical concepts and abstract evaluation because they require generating a score representing a likelihood, comparing that score to a threshold, and determining how many items to include based on the comparison. The additional limitations relating to receiving a request, receiving features, generating an interface, inserting selected items into the interface, and transmitting the interface merely use generic computer components to collect data and present the result of the abstract recommendation process. Such limitations do not improve the functioning of a computer, graphical user interface technology, display technology, network operation, memory structure, or any other technology. The applicant’s reliance on Example 37 is not persuasive because the claims do not recite a specific asserted improvement to graphical user interface operation comparable to an automatically relocating icon or changing how the computer interface itself functions. Instead, the alleged improvement is to the selection and presentation of recommended commercial content based on an abstract score and threshold comparison. Accordingly, the claims do not integrate the judicial exception into a practical application and do not recite significantly more than the judicial exception, and the rejection under 35 U.S.C. 101 is maintained.
Argument 2: The applicant argues on pages 13-15 that the pending claims are not obvious under 35 U.S.C. 103 over Dicker in view of Liu and Kang because amended independent claim 1 now incorporates the subject matter of canceled dependent claims 3 and 4 and further clarifies that the set of cross-pollinated items includes a first non-zero number of items when the cross-pollination score is below the at least one threshold value and a second non-zero number of items when the cross-pollination score is equal to or above the at least one threshold value. The applicant relies on the specification example in paragraph [0076], arguing that the at least one threshold value corresponds to the second predetermined threshold, the first non-zero number corresponds to one cross-pollinated interface element, and the second non-zero number corresponds to two or more cross-pollinated interface elements. The applicant contends that Liu does not teach this amended limitation because Liu threshold is used to validate whether item pairs should be included at all, such that pairs below the threshold are not included, rather than being included as a first non-zero number of items. The applicant therefore argues that Liu teaches the opposite of the claimed below-threshold non-zero inclusion, and that Dicker, Liu, and Kang fail to teach or suggest the amended independent claims. The applicant further argues that new claim 21 recites analogous subject matter to claims 1 and 9, and that new dependent claims 22 to 26 recite analogous features to dependent claims 2 and 5 to 8, and therefore are allowable for at least the same reasons.
Response to Argument 2: The applicant’s arguments regarding the prior art rejection have been considered but are not persuasive. The applicant's argument is directed primarily to amended independent claim 1, and more specifically to the newly added limitation requiring determining a number of elements in the set of cross-pollinated items by comparing the cross-pollination score to at least one threshold value, wherein the set includes a first non-zero number of items when the score is below the threshold and a second non-zero number of items when the score is equal to or above the threshold. The applicant also argues that independent claims 9 and 21 are allowable for the same reasons because they recite analogous method and non-transitory computer readable medium limitations. However, the rejection is based on the combined teachings of Dicker, Liu, and Kang, rather than Liu in isolation. Liu teaches generating cross-category item recommendations, selecting a number of item pairs to recommend together as a collection, selecting recommendations based on user personalization factors and confidence scores, and validating pairs using a purchase-together probability score that satisfies a threshold. Dicker further teaches generating a recommendation interface in which recommendation sections are selected dynamically from a larger set of recommendation sections and the page rendering process may vary the number of recommendation sections or recommended items displayed on the page. Therefore, even assuming Liu's threshold is described in the context of validating item pairs for inclusion, Liu's score and threshold-based cross-category recommendation selection, in combination with Dicker's dynamic variation of the number of displayed recommendation sections or items, renders obvious determining different non-zero numbers of cross-pollinated items based on whether the score is below or equal to or above a threshold. A person of ordinary skill in the art would have been motivated to display fewer cross-category recommendations when the score indicates lower confidence or relevance and more cross-category recommendations when the score indicates higher confidence or relevance in order to improve recommendation relevance and efficiently allocate interface space. Kang further teaches using a trained sequential recommendation model to generate an interaction or relevance score used to rank recommendations, thereby supplying the claimed trained sequential prediction model and score-generation features. Accordingly, the combination of Dicker, Liu, and Kang teaches or renders obvious amended independent claims 1, 9, and 21. The applicant's arguments regarding dependent claims 2, 5-8, 10, 13-16, and 22-26 are likewise unpersuasive because those claims were not argued separately with particularity and remain unpatentable for the reasons set forth in the claim-by-claim rejections below. Hence, the rejection under 103 is maintained.
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 1-2, 5-10, and 13-16, and 21-26 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Regarding claim 1:
Step 1:The claim is directed to a system, which falls under the category of machine. Therefore, The claim satisfies Step 1.
Step 2A Prong 1:(a) “generate a set of cross-pollinated items associated with a second intent, wherein the set of cross-pollinated items are selected based on a cross-pollination score…generate the cross-pollination score using a trained sequential prediction model,” - This limitation is directed to selecting recommended items based on a score. The limitation is directed to an abstract evaluation, prediction, and selection process, and involves a mathematical concept because the selection of items is based on a generated score representing a quantitative relationship or value, so the limitation can be directed to math and mental process.
(b) “determine a number of elements in the set of cross-pollinated items by comparing the cross-pollination score to at least one threshold value, wherein the set of cross-pollinated items includes a first non-zero number of items when the cross-pollination score is below the at least one threshold value, and wherein the set of cross-pollinated items includes a second non-zero number of items when the cross-pollination score is equal to or above the at least one threshold value” -This limitation is directed to a mathematical concept because it requires comparing a score to at least one threshold value and determining a number of items based on the result of that score-threshold comparison. The limitation recites a mathematical relationship or calculation used to determine how many items are included in a set, and thus the limitation is directed to math. Furthermore, the limitation is directed to a process that can be performed in the human mind using evaluation, observation, and judgement, and thus the limitation is also directed to a mental process.
Step 2A Prong 2 and Step 2B:
“A system comprising: a processing resource; a communications interface…a non-transitory memory storing instructions, that when executed, cause the processing resource to…a cross-pollination engine configured to:” - These limitations recite generic computer components, including a processing resource, communications interface, and non-transitory memory, performing their ordinary functions. These elements are recited at a high level of generality and amount to no more than instructions to apply the judicial exception using generic computer components, which does not integrate the exception into a practical application and does not provide significantly more than the judicial exception (see MPEP 2106.05(f)).
“receive a request for an interface for a first intent, wherein the request includes a user identifier that is stored in the non-transitory memory…receive a set of features associated with the user identifier and the first intent…wherein the trained sequential prediction model is configured to receive the set of features associated with the user identifier and output the cross-pollination score, wherein the cross-pollination score represents a likelihood of a user associated with the user identifier interacting with at least one cross-pollinated item” - These limitations are directed to receiving and storing data, including a request, user identifier, and feature data. Receiving, collecting, and storing data are insignificant extra-solution activity and do not integrate the judicial exception into a practical application (see MPEP 2106.05(g)). Furthermore, receiving and storing data using generic computer components is well-understood, routine, and conventional activity and does not provide significantly more than the judicial exception (see MPEP 2106.05(d)(II)).
“generate an interface including a set of first items associated with the first intent,…insert the set of cross-pollinated items into the interface…transmit the interface to a user device associated with the user identifier” - These limitations are directed to generating, displaying, inserting, and transmitting information using generic computer components. The limitations merely use a computer as a tool to present the results of the abstract score-based recommendation and selection process, and are no more than insignificant post-solution activity or generic computer implementation. These limitations do not recite a particular improvement to computer functionality, graphical user interface technology, display technology, network operation, memory structure, or any other technology or technical field. Rather, the limitations merely present selected information to a user based on the abstract recommendation score and threshold comparison, which does not integrate the judicial exception into a practical application (see MPEP 2106.05(a), MPEP 2106.05(f), MPEP 2106.05(g)). Furthermore, under Step 2B, the act of sending/receiving data over a network is a well-understood, routine, and conventional activity (WURC) that cannot provide significantly more than the judicial exception (see MPEP 2106.05(d)(II)).
Therefore, claim 1 is non-patent eligible. Claim 9 and 21 are analogous to claim 1 aside from claim type, and thus would face the same rejection as above.
Regarding claim 2,
Step 1:
The claim is directed to a system, which is one of the four statutory categories of invention (machine). Therefore, the claim satisfies Step 1.
There are no elements to be evaluated under Step 2A Prong 1.
Step 2A Prong 2 and Step 2B:
“The system of claim 1, wherein the trained sequential prediction model comprises one of a SASRec model or a TiSASRec model.” -- The limitation is merely further limiting to a field of use/environment, and thus the limitation does not integrate to practical application, nor provides significantly more than the judicial exception (see MPEP 2106.05(h)).
Therefore, claim 2 is non-patent eligible. Claims 10 and 22 are analogous to claim 2 (aside from claim type), and thus all the claims can be rejected similarly as above.
Regarding claim 5,
Step 1:
The claim is directed to a system, which is one of the four statutory categories of invention (machine). Therefore, the claim satisfies Step 1.
There are no elements to be evaluated under Step 2A Prong 1.
Step 2A Prong 2 and Step 2B:
“The system of claim 1, wherein the instructions, when executed, further cause the processing resource to:” -- The limitation recites instructions will cause the processing resource to do the remainder of the claim when executed. The limitation amounts to no more than mere instructions to apply onto a computer, and thus it does not integrate to a practical application, nor provide significantly more than the judicial exception (see MPEP 2106.05(f)).
Therefore, claim 5 is non-patent eligible. Claims 13 and 23 are analogous to claim 5 (aside from claim type), and thus all the claims can be rejected similarly as above.
Regarding claim 6,
Step 1:
The claim is directed to a system, which is one of the four statutory categories of invention (machine). Therefore, the claim satisfies Step 1.
There are no elements to be evaluated under Step 2A Prong 1.
Step 2A Prong 2 and Step 2B:
(a) “The system of claim 1, wherein, wherein the instructions, when executed, further cause the processing resource to receive, via the communications interface, interaction data for the generated interface” - This limitation is directed to receiving interaction data via a communications interface. The limitation merely recites receiving or collecting data using generic computer components and does not improve computer functionality, interface technology, network operation, memory structure, or any other technology or technical field. Receiving interaction data for a generated interface is insignificant extra-solution activity and does not integrate the judicial exception into a practical application (see MPEP 2106.05(g)). Furthermore, under Step 2B, receiving data via a generic communications interface using generic instructions executed by a processing resource is well-understood, routine, and conventional activity and does not provide significantly more than the judicial exception (see MPEP 2106.05(d)(II)).
Therefore, claim 6 is non-patent eligible. Claims 14 and 24 is analogous to claim 6 (aside from claim type), and thus all the claims can be rejected similarly as above.
Regarding claim 7,
Step 1:
The claim is directed to a system, which is one of the four statutory categories of invention (machine). Therefore, claim 1 satisfies Step 1.
There are no elements to be evaluated under Step 2A Prong 1.
Step 2A Prong 2 and Step 2B:
“The system of claim 1, wherein the trained sequential prediction model comprises an aggregation layer including a concatenation process and an element wise sum multiply process.” -- The limitation recites that the prediction model will further comprise an aggregation layer including concatenation/ element-wise multiply. The limitation of concatenation/element-wise multiply is merely applying mathematical, abstract concepts onto a computer, and it does not integrate to a practical application, nor provides significantly more than the judicial exception (see MPEP 210.05(f)).
Therefore, claim 7 is non-patent eligible. Claims 15 and 25 is analogous to claim 7 (aside from claim type), and thus all the claims can be rejected similarly as above.
Regarding claim 8,
Step 1:
The claim is directed to a system, which is one of the four statutory categories of invention (machine). Therefore, claim 1 satisfies Step 1.
There are no elements to be evaluated under Step 2A Prong 1.
Step 2A Prong 2 and Step 2B:
“The system of claim 1, wherein the trained sequential prediction model comprises a linear layer and an attention layer.” -- The limitation recites a trained model will further comprise two types of layers: linear and attention, which is merely limiting the claim without practical application, nor significantly more than the judicial exception (see MPEP 2106.05(h)).
Therefore, claim 8 is non-patent eligible. Claim 16 and 26 is analogous to claim 8 (aside from claim type), and thus all the claims can be rejected similarly as above.
Claim Rejections - 35 USC § 103
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are
summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1, 5-9, 13-16, 21,23-26 is/are rejected under 35 U.S.C. 103 as being unpatentable over US7720723B2, by Dicker et al. (referred herein as Dicker) in view of US 10861077 B1, by Liu et. al. (referred herein as Liu) further in view of NPL reference “Self-attentive sequential recommendation.”, by Kang et. al. (referred herein as Kang).
Regarding claim 1, Dicker teaches:
A system comprising: a processing resource; a communications interface, configured to receive a request for an interface for a first intent, wherein the request includes a user identifier that is stored in the non-transitory memory; ([Dicker, col. 9, lines 3-19] “the Web site 30 includes a Web server application 32 (‘Web server’) which processes HTTP (Hypertext Transfer Protocol) requests received over the Internet from user computers 34,” AND [Dicker, page 24, col 9, lines 19-22], “the Web site 30 also includes a ‘user profiles’ database 38 which stores account-specific information about users of the site,” AND [Dicker, col. 27, lines 4-9], “passes a session_ID … in response to the click stream event,” wherein the examiner interprets Dicker’s Web server application that processes HTTP requests received over the Internet from user computers as teaching “A system comprising: a processing resource; a communications interface, configured to receive a request for an interface for a first intent,” and interprets Dicker’s session_ID and user profiles database as teaching “wherein the request includes a user identifier that is stored in the non-transitory memory” because both are directed to using a user/session identifier and stored user-specific information)
a non-transitory memory storing instructions, that when executed, cause the processing resource to: generate an interface including a set of first items associated with the first intent; ([Dicker, page 24, col 9, lines 8-11], “the Web site 30 includes a Web server application 32 (‘Web server’) which processes HTTP (Hypertext Transfer Protocol) requests received over the Internet from user computers 34,” AND [Dicker, 24, col 9, lines 50-54], “the term ‘process’ is used herein to refer generally to one or more code modules that are executed by a computer system to perform a particular task or set of related tasks,” AND [Dicker, page 38, col 36, lines 33-44], “generating a page for presentation to the user” and “generate a first set of item recommendations for the user,” AND [Dicker, page 32, lines line 14-18] “The click stream table is preferably stored in a cache memory 39 (volatile RAM) of a physical server computer, and can therefore be rapidly and efficiently accessed by the Session Recommendations application 52 and other real time personalization components.”, wherein the examiner interprets Dicker’s Web server application/code modules executed by a computer system and “The click stream table is preferably stored in a cache memory 39 (volatile RAM) of a physical server computer” as teaching “a non-transitory memory storing instructions, that when executed, cause the processing resource to,” and interprets Dicker’s generated page and first set of item recommendations as teaching “generate an interface including a set of first items associated with the first intent” because both are directed to generating a user-facing page/interface including item recommendations.)
insert the set of cross-pollinated items into the interface; and transmit the interface to a user device associated with the user identifier; ([Dicker, col. 30, lines 4-8], “The remaining portion of the shopping cart add page, and particularly the portion adjacent to the condensed shopping cart view 600, is dedicated primarily or exclusively to the display of recommendations,” [Dicker, col. 14, lines 8-11], “Finally, in step 94, a list of the top M (e.g., 15) items of the recommendations list are returned to the Web server 32 (FIG. 1). The Web server incorporates this list into one or more Web pages that are returned to the user,” AND [Dicker, col. 31, lines 7-9], “the particular set of recommendation sections 610-618 displayed on the shopping cart add page may be selected dynamically from a larger set of recommendation sections,” wherein the examiner interprets Dicker’s display of recommendations in a portion of the shopping cart add page as teaching the interface-insertion aspect of “insert the set of cross-pollinated items into the interface,” and interprets Dicker’s Web pages returned to the user as teaching “transmit the interface to a user device associated with the user identifier” because both are directed to placing recommendation content into a generated interface and sending the generated interface to a user device).
Dicker does not teach generate a set of cross-pollinated items associated with a second intent, wherein the set of cross-pollinated items are selected based on a cross-pollination score; determine a number of elements in the set of cross-pollinated items by comparing the cross-pollination score to at least one threshold value, wherein the set of cross-pollinated items includes a first non-zero number of items when the cross-pollination score is below the at least one threshold value, and wherein the set of cross-pollinated items includes a second non-zero number of items when the cross-pollination score is equal to or above the at least one threshold value; and a cross-pollination engine configured to: receive a set of features associated with the user identifier and the first intent; and generate the cross-pollination score using a trained sequential prediction model, wherein the trained sequential prediction model is configured to receive the set of features associated with the user identifier and output the cross-pollination score, wherein the cross-pollination score represents a likelihood of a user associated with the user identifier interacting with at least one cross-pollinated item.
Liu teaches:
generate a set of cross-pollinated items associated with a second intent, wherein the set of cross-pollinated items are selected based on a cross-pollination score; ([Liu, page 10-11, col. 2-3, lines 67-4], “the source item is dress 105, and the collection of cross-category item recommendations includes shoes 120, handbag 125, belt 130, and ring 135. Each of these items in collection 115 is selected from a different respective category,” AND [Liu, col. 6, lines 24-31], “The recommendation presenter 250 can select a number of <item, item> pairs to recommend together as a collection to users. In some examples these can be pre-stored collections in the collections data repository 245. In other examples these recommendations can include elements of user personalization, and can be selected based on user personalization factors as well as the confidence scores associated with <item, item> pairs in the collections data repository 245,” AND [Liu, col. 19, lines 30-35], “a plurality of cross-category item pairs each including a source item and a recommended item associated with a different category than the source item,” wherein the examiner interprets Liu’s cross-category item recommendations as teaching “generate a set of cross-pollinated items associated with a second intent” because both are directed to recommended items drawn from a different category/context than the primary/source item, and interprets Liu’s confidence scores associated with <item, item> pairs as teaching “wherein the set of cross-pollinated items are selected based on a cross-pollination score” because both are directed to selecting recommended items based on a score);
determine a number of elements in the set of cross-pollinated items by comparing the cross-pollination score to at least one threshold value, wherein the set of cross-pollinated items includes a first non-zero number of items when the cross-pollination score is below the at least one threshold value, and wherein the set of cross-pollinated items includes a second non-zero number of items when the cross-pollination score is equal to or above the at least one threshold value; ([Liu, col. 6, lines 23-25], “The recommendation presenter 250 can select a number of <item, item> pairs to recommend together as a collection to users,” AND [Liu, col. 6, lines 24-31], “In other examples these recommendations can include elements of user personalization , and can be selected based on user personalization factors as well as the confidence scores associated with <item, item> pairs in the collections data repository 245,” AND [Liu, col. 4, lines 43-46], “Validated pairs (e.g., pairs having a ‘purchase together’ probability score that satisfies a threshold) from different categories can be combined into cross-category collection sets based on category combination rules,” wherein the examiner interprets Liu’s selecting a number of <item, item> pairs to recommend together and “Validated pairs (e.g., pairs having a ‘purchase together’ probability score that satisfies a threshold) from different categories can be combined into cross-category collection sets based on category combination rules,” as teaching “determine a number of elements in the set of cross-pollinated items,” and interprets Liu’s probability/confidence score satisfying a threshold as teaching “by comparing the cross-pollination score to at least one threshold value.”)
Dicker and Liu do not teach a cross-pollination engine configured to: receive a set of features associated with the user identifier and the first intent; and generate the cross-pollination score using a trained sequential prediction model, wherein the trained sequential prediction model is configured to receive the set of features associated with the user identifier and output the cross-pollination score, wherein the cross-pollination score represents a likelihood of a user associated with the user identifier interacting with at least one cross-pollinated item.
Kang teaches:
a cross-pollination engine configured to: receive a set of features associated with the user identifier and the first intent; ([Kang, page 3, sec 3], “In the setting of sequential recommendation, we are given a user’s action sequence Su = (Su_1, Su_2, ..., Su_|Su|), and seek to predict the next item,” wherein the examiner interprets Kang’s user’s action sequence as teaching “receive a set of features associated with the user identifier and the first intent” because both are directed to receiving user-associated sequential input information used for recommendation prediction).
and generate the cross-pollination score using a trained sequential prediction model, ([Kang, page 4, sec 3], “After b self-attention blocks that adaptively and hierarchically extract information of previously consumed items, we predict the next item (given the first t items) based on F(b)t. Specifically, we adopt an MF layer to predict the relevance of item i: ri,t = F(b)t Nᵀi, where ri,t is the relevance of item i being the next item given the first t items (i.e., s1, s2, ..., st), and N ∈ R|I|×d is an item embedding matrix. Hence, a high interaction score ri,t means a high relevance, and we can generate recommendations by ranking the scores,” wherein the examiner interprets Kang’s trained self-attention sequential recommendation model and interaction/relevance score as teaching “generate the cross-pollination score using a trained sequential prediction model” because both are directed to using a trained sequential model to output a recommendation score for an item.)
wherein the trained sequential prediction model is configured to receive the set of features associated with the user identifier and output the cross-pollination score, ([Kang, page 3, sec 3], “During the training process, at time step t, the model predicts the next item depending on the previous t items. As shown in Figure 1, it will be convenient to think of the model’s input as (Su 1,Su 2,...,Su |Su|-1) and its expected output as a ‘shifted’ version of the same sequence: (Su 2, Su 3, . . . , Su |Su|).” wherein the examiner interprets Kang’s model predicting the next item based on previous user-associated items as teaching “wherein the trained sequential prediction model is configured to receive the set of features associated with the user identifier and output the cross-pollination score” because both are directed to a trained sequential model receiving user-associated sequence features and outputting a score/prediction)
wherein the cross-pollination score represents a likelihood of a user associated with the user identifier interacting with at least one cross-pollinated item. ([Kang, page 4, sec 3], “we adopt an MF layer to predict the relevance of item i: ri,t = F(b)t Nᵀi”… Hence, a high interaction score ri,t means a high relevance, and we can generate recommendations by ranking the scores.” wherein the examiner interprets Kang’s interaction/relevance score for item i as teaching “wherein the cross-pollination score represents a likelihood of a user associated with the user identifier interacting with at least one cross-pollinated item” because both are directed to a score indicating relevance or likely future user interaction with a recommended item).
Dicker, Liu, Kang, and the instant application are analogous art because they are all directed to generating and presenting personalized item recommendations to users using user-specific information, recommendation scoring, and user-interface presentation.
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify Dicker’s web interface recommendation system to incorporate Liu’s cross-category recommendation and score-based selection technique. One would have been motivated to do so to diversify and improve the relevance of recommendations presented within the generated user interface by including recommendations from different categories or contexts based on confidence/probability scores, as suggested by Liu ([Liu, col. 6, lines 23-25], “The recommendation presenter 250 can select a number of <item, item> pairs to recommend together as a collection to users,” AND [Liu, col. 6, lines 24-31], “In other examples these recommendations can include elements of user personalization , and can be selected based on user personalization factors as well as the confidence scores associated with <item, item> pairs in the collections data repository 245,” AND [Liu, col. 4, lines 43-46], “Validated pairs (e.g., pairs having a ‘purchase together’ probability score that satisfies a threshold) from different categories can be combined into cross-category collection sets based on category combination rules,”)
It would also have been obvious to modify the recommendation scoring of Dicker and Liu to use Kang’s trained sequential prediction model to generate the score for candidate recommended items, because Kang teaches that sequential user-interaction information can be used to generate interaction/relevance scores and rank recommendations, thereby improving the ability to identify items likely to be interacted with by the user. One would be motivated to combine Kang’s generation of interaction/relevance scores and then rank to identify user interaction as suggested by Kang ([Kang, page 4, sec 3], “we adopt an MF layer to predict the relevance of item i: ri,t = F(b)t Nᵀi”… Hence, a high interaction score ri,t means a high relevance, and we can generate recommendations by ranking the scores.”)
Claim(s) 2, 10, and 22 are rejected under 35 U.S.C. 103 as being unpatentable over Dicker in view of Liu in view of Kang in view of NPL reference “Time interval aware self-attention for sequential recommendation.” by Wang et. al (referred herein as Wang).
Regarding claim 2, Dicker, Liu and Kang teach The system of claim 1, (see rejection of claim 1)
Kang further teaches wherein the trained sequential prediction model comprises one of a SASRec model ([Kang, page 1] “proposing a self-attention based sequential model (SASRec)”, wherein the examiner interprets a self-attention based sequential model (SASRec) to be the same as a SASRec model because they are both directed to the same named sequential model (SASRec).)
Dicker, Liu, Kang, and the instant application are analogous art because they are all directed to comprising of a SASRec model for prediction.
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the system of claim 1 disclosed by Dicker, Liu, and Kang to include the “self-attention based sequential model (SASRec)” disclosed by Kang. One would be motivated to do so to effectively model sequential user interaction behavior for generating recommendation scores, as suggested by Kang ([Kang, page 1] “proposing a self-attention based sequential model (SASRec)”).
Dicker, Liu, and Kang et al do not teach, or a TiSASRec model.
Wang teaches or a TiSASRec model. ([Wang, page 322-323], “We propose TiSASRec (Time Interval aware Self-attention based sequential recommendation) … our approaches to obtain time intervals and components of TiSASRec”, wherein the examiner interprets TiSASRec (Time Interval aware Self-attention based sequential recommendation) to be the same as a TiSASRec model because they are both directed to the same named sequential model (TiSASRec).)
Dicker, Liu, Kang, Wang, and the instant application are analogous art because they are all directed to training a sequential prediction model comprising a self-attention based sequential recommendation model.
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the method claim 1 disclosed by Dicker, Liu, and Kang to include the TiSASRec model disclosed by Wang. One would be motivated to do so to efficiently obtain time intervals and components, as suggested by Wang ([Wang, page 322-323] “our approaches to obtain time intervals and components of TiSASRec.”). Claims 10 and 22 are analogous to claim 2 (aside from claim type), and thus all the claims can be rejected similarly as above.
Regarding claim 5, Dicker, Liu, and Kang teach The system of claim 1, (see rejection of claim 1).
Liu further teaches:
wherein the instructions, when executed, further cause the processing resource to: obtain an interface template; select at least one container for insertion into the interface template; and insert the set of first items and the set of cross-pollinated items into the at least one container. ([Liu, col. 6, lines 42-51], “Such recommendations can be presented to users at other times, for instance upon logging in to the shopping site, via email or other electronic messaging, or as advertisements when the user is visiting other web sites. The depicted page layout in user interfaces 100 is provided for illustrative purposes, and other user interface embodiments capable of providing cross-category item collection recommendations can include more or fewer sections, combined sections, different sections, other page element arrangements,” AND [Liu, col. 6, lines 23-25, 26-31], “The recommendation presenter 250 can select a number of <item, item> pairs to recommend together as a collection to users… In other examples, these recommendations can include elements of user personalization, and can be selected based on user personalization factors as well as the confidence scores associated with <item, item> pairs in the collections data repository 245,” wherein the examiner interprets Liu’s “depicted page layout in user interfaces 100” and other user interface embodiments as teaching “obtain an interface template,” and interprets Liu’s “sections,” “combined sections,” “different sections,” and “other page element arrangements” as teaching “select at least one container for insertion into the interface template” because both are directed to selecting one or more user-interface regions/sections for presenting recommendation content. The examiner further interprets the source item and cross-category recommended item collection as teaching “insert the set of first items and the set of cross-pollinated items into the at least one container” because both are directed to presenting a primary/source item and associated cross-category/cross-pollinated recommendation items together in a user-interface section/container.)
Dicker further teaches:
obtain an interface template; select at least one container for insertion into the interface template; and insert the set of first items and the set of cross-pollinated items into the at least one container. ([Dicker, col. 30, lines 1-10], “The remaining portion of the shopping cart add page, and particularly the portion adjacent to the condensed shopping cart view 600, is dedicated primarily or exclusively to the display of recommendations,” AND [Dicker, col. 39, lines 7-18], “the particular set of recommendation sections 610-618 displayed on the shopping cart add page may be selected dynamically from a larger set of recommendation sections,” wherein the examiner interprets Dicker’s shopping cart add page as teaching “obtain an interface template,” and interprets Dicker’s dynamically selected recommendation sections as teaching “select at least one container for insertion into the interface template” and “insert the set of first items and the set of cross-pollinated items into the at least one container” because both are directed to selecting portions/sections of a generated page and populating those sections with recommendation content.)
Dicker, Liu, Kang, and the instant application are analogous art because they are all directed to generating and presenting personalized item recommendations to users using user-specific information, recommendation scoring, and user-interface presentation.
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of claim 1 disclosed by Dicker, Liu, and Kang to include Liu’s interface layout, sections, and page element arrangements for presenting recommendation content. One would have been motivated to do so to control where and how the set of first items and the set of cross-pollinated items are displayed within the generated interface, as suggested by Liu (([Liu, col. 6, lines 42-51], “Such recommendations can be presented to users at other times, for instance upon logging in to the shopping site, via email or other electronic messaging, or as advertisements when the user is visiting other web sites. The depicted page layout in user interfaces 100 is provided for illustrative purposes, and other user interface embodiments capable of providing cross-category item collection recommendations can include more or fewer sections, combined sections, different sections, other page element arrangements,” AND [Liu, col. 6, lines 23-25, 26-31], “The recommendation presenter 250 can select a number of <item, item> pairs to recommend together as a collection to users… In other examples, these recommendations can include elements of user personalization, and can be selected based on user personalization factors as well as the confidence scores associated with <item, item> pairs in the collections data repository 245,)
Furthermore, the motivation is reasonable to include Dicker’s teaching that the recommendation sections displayed on a shopping cart add page may be selected dynamically. ([Dicker, col. 39, lines 7-18], “the particular set of recommendation sections 610-618 displayed on the shopping cart add page may be selected dynamically from a larger set of recommendation sections,”) Claims 13 and 23 are analogous to claim 5 (aside from claim type), and thus all the claims can be rejected similarly as above.
Regarding claim 6, Dicker, Liu, and Kang teach The system of claim 1, (see rejection of claim 1).
Liu further teaches wherein the instructions, when executed, further cause the processing resource to receive, via the communications interface, interaction data for the generated interface. ([Liu, col. 16, lines 29-37], “The interactive computing system 500 may also include a user interface 516. The user interface 516 may be utilized by a user to access portions of the interactive computing system 500. In some examples, the user interface 516 may include a graphical user interface, web-based applications, programmatic interfaces such as application programming interfaces (APIs), or other user interface configurations. The user interface 516 can include displays of the recommendations described herein,” AND [Liu, page 17, col. 16, lines 53-56], “The item interaction data repository 524 can store logged user behaviors with respect to the items currently and/or previously in the item inventory database,” AND [Liu, page 17-18, col. 16-17, lines 66-67, 1-2], “Users can access the interactive computing system 500 and interact with items therein via the network 504 and can be provided with recommendations via the network 504,” AND [Liu, page 14, col. 10, lines 7-12], “Other embodiments can use item interaction data including events other than or in addition to purchases. Item interaction events can include item detail page views, adding items to a digital shopping cart or wish list, item reviews, sharing of item detail pages, and saving an item for later purchase,” wherein the examiner interprets Liu’s user interface 516, network 504, item interaction data repository 524, logged user behaviors, and item interaction events as teaching “receive, via the communications interface, interaction data for the generated interface” because both are directed to receiving user interaction data/logged user behaviors generated through interaction with a recommendation interface.)
Dicker, Liu, Kang, and the instant application are analogous art because they are all directed to generating and presenting personalized item recommendations to users using user-specific information, recommendation scoring, user interactions, and user-interface presentation.
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention to modify the system of claim 1 disclosed by Dicker, Liu, and Kang to receive, via the communications interface, interaction data for the generated interface, disclosed by Liu. One would have been motivated to do so to log user behaviors, update user interaction information, and improve future recommendation generation based on how users interact with the generated recommendation interface, as suggested by Liu (see Liu quotes and mapping above.) Claims 14 and 24 is analogous to claim 6 (aside from claim type), and thus all the claims can be rejected similarly as above.
Regarding claim 7, Dicker, Liu and Kang teach The system of claim 1, (see rejection of claim 1).
Kang further teaches:
wherein the trained sequential prediction model comprises an aggregation layer including a concatenation process ([Kang, page 5, sec 3], “Following the reduction operations above for FMC, and adding an explicit user embedding (via concatenation), SASRec is equivalent to FPMC.”, wherein the examiner interprets “adding an explicit user embedding (via concatenation)” to be the same as including a concatenation process because they are both directed to concatenating an embedding/feature vector with another representation as part of the sequential recommendation/prediction model process.)
and an element wise sum multiply process. ([Kang, page 4] “Specifically, we adopt an MF layer to predict the relevance of item i: r_{i,t} = F_t^{(b)} N^T i”), wherein the examiner interprets “MF layer” and “r_{i,t} = F_t^{(b)} N^T i” to be the same as an element wise sum multiply process because they are both directed to computing a prediction score using element-wise multiplication and summation between latent representations in a trained sequential prediction model.)
Dicker, Liu, Kang, and the instant application are analogous art because they are all directed to generating personalized item recommendations for users using predictive models and presenting those recommendations within a user interface.
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the system claim 1 disclosed by Dicker, Liu, and Kang to include the recommendation embedding approach disclosed by Kang. One would be motivated to do so to effectively improve the representation and aggregation of user-related information within the trained sequential prediction model, as suggested by Kang (Kang, [page 5] “Following the reduction operations above for [Personalized Markov Chains] FMC, and adding an explicit user embedding (via concatenation), SASRec is equivalent to [Factorized Personalized Markov Chains] FPMC”). Claims 15 and 25 is analogous to claim 7 (aside from claim type), and thus all the claims can be rejected similarly as above.
Regarding claim 8, Dicker, Liu and Kang teach The system of claim 1, (see rejection of claim 1).
Kang further teaches:
wherein the trained sequential prediction model comprises a linear layer and an attention layer. ([Kang, page 3] “In our case, the self-attention operation takes the embedding Eb as input, converts it to three matrices through linear projections, and feeds them into an attention layer:”, wherein the examiner interprets “linear projections” to be the same as “a linear layer” because they are both directed to applying a learned linear transformation to representations in the model, and wherein the examiner interprets “an attention layer” to be the same as “an attention layer” because they are both directed to an attention mechanism layer that processes the projected representations.)
Dicker, Liu, Kang, and the instant application are analogous art because they are all directed to generating personalized item recommendations for users using predictive models.
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the invention to modify the system claim 1 disclosed by Dicker, Liu and Kang to include linear projections disclosed by Kang. One would be motivated to do so to effectively improve the modeling of user interaction dependencies and attention within the prediction model, as suggested by Kang ([Kang, page 3] “linear projections, and feeds them into an attention layer”). Claim 16 and 26 is analogous to claim 8 (aside from claim type), and thus all the claims can be rejected similarly as above.
Conclusion
THIS ACTION IS MADE FINAL. The applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DEVAN KAPOOR whose telephone number is (703)756-1434. The examiner can normally be reached Monday - Friday: 9:00AM - 5:00 PM EST (times may vary).
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.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, David Yi can be reached at (571) 270-7519. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
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/apply/patent-center for more information about Patent Center and 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.
/DEVAN KAPOOR/Examiner, Art Unit 2126
/DAVID YI/Supervisory Patent Examiner, Art Unit 2126
Prosecution Insights