DETAILED ACTION
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 Amendment
This Office action is in response to Applicant's amendment filed on 2/11/2026.
Claim 1-20 are pending. Claim 1, 9-12 and 17-20 are amended. Claim 1-20 are rejected.
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 1-10, 12-18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Ben-Bassat, Ilan et al (PGPUB Document No. 20250315616), hereafter referred as to “Ben-Bassat”, in view of Jain, Shailesh Hiralal et al (PGPUB Document No. 20250045810), hereafter, referred to as “Jain”, in further view of Ferev, Milen et al (PGPUB Document No. 20260119700), hereafter, referred to as “Ferev”.
Claim 1(Currently Amended), Ben-Bassat teaches A method, performed at a computer system comprising a processor and a computer-readable medium, comprising: receiving, via a network from a device associated with a user of an online system, a query submitted by the user during a session of the user at the online system(Ben-Bassat, Fig. 5G discloses query (element 506) submitted by an user in a search session at an online system);
responsive to receiving the query, generating a prompt for input into a plurality of language models(Ben-Bassat, Fig. 5C-E discloses user query (element 510) generating prompt (element 513) into language models (element 536 “Language Model 1”, element 546 “Language Model 2” and element 558 “Language Model 3”)),
each of the plurality of language models tuned to infer a respective type of context of a plurality of types of context of the query, (Ben-Bassat, Fig. 5C-E discloses user query (element 510) generating prompt (element 513) into language models (element 536 “Language Model 1”, element 546 “Language Model 2” and element 558 “Language Model 3”; para 0044 discloses first language model (536) inferring first context (entity) “the first language model 536 may (i) determine the first entity 538 based upon the first query 510 and/or (ii) output an indication of the first entity 538. In an example, the first prompt 513 may comprise: <You are a helpful tool for question answering. Extract the main entity the query is asking about.>”; para 0045 discloses inferring second context (classification/categorization of the intended item) “5D illustrates use of a second language model 546 to determine a first relevance classification 548 associated with a first content item 544 of the pool of content items 530”’; para 0050 discloses identifying third context (deriving the submitted query); “the third language model 558 may (i) analyze the first query 510 to derive a question and/or request posed by the first query 510”);
requesting each of the plurality of language models to generate, based on the prompt input into each of the plurality of language models, a respective response of a plurality of responses that includes information about the respective type of context of the query(Ben-Bassat, Fig. 5C-E discloses language models (element 536 “Language Model 1”, element 546 “Language Model 2” and element 558 “Language Model 3” generating their respective responses inferring entity context type (element 538), inferring category of item context (element 548) and indicative to answer context (element 560));
generating, using the plurality of responses, a query understanding string for the query, the query understanding string including information about the plurality of types of context of the query(Ben-Bassat, Fig. 5F discloses generation of an input (query input) deriving from plurality of contexts (element 570));
identifying, from a database of the online system and using the information about the plurality of types of context, a set of one or more items (Ben-Bassat, para 0056-0057 discloses generation of response from online databases using contextual query information “the fourth language model 572 may (i) analyze the first query 510 to derive a question and/or request posed by the first query 510, (ii) analyze the first contextual information profile 570 to determine an answer to the question and/or request posed by the first query 510, and/or (iii) generate the first response 574 to be indicative of the answer”);
generating, using information about the set of one or more items, a first user interface signal; and sending, via the network, the first user interface signal to the device associated with the user, wherein sending the first user interface signal causes the device associated with the user to display a user interface with the information about the set of one or more items and one or more user interface elements for use by the user to order the set of one or more items(Ben-Bassat, Fig. 5G and para 0060 discloses generation of query response (element 580) on the user device “FIG. 5G illustrates the representation (shown with reference number 580) of the first response 574 being displayed via the first interface 502. In some examples, the representation 580 may comprise (i) an indication 582 of the amount spent on groceries during the time period and/or (ii) one or more reference items corresponding to one or more reference identifiers indicated by the first response 574”).
But Ben-Bassat does not explicitly teach storing, at the computer-readable medium and during the session, information about the session, wherein generating the prompt comprises: requesting a language model to generate, based on the query and the information about the session, a response including a processed version of the query and a processed version of the information about the session, and including the response into the prompt;
However in the same field of endeavor of utilization of user search session data for content recommendation Jain teaches storing, at the computer-readable medium and during the session, information about the session (Jain , para 0042 discloses storing user search session data in a database “The search-based recommendation computing device 102 may also receive from the web server 104 user session data identifying events associated with browsing sessions, and may store the user session data in the database 116”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the feature of storing and using user search session data for content recommendation of Jain into generation of response based on user query contexts of Ben-Bassat to produce an expected result of deriving user search context from the user session data. The modification would be obvious because one of ordinary skill in the art would be motivated to improve the item discoverability by including items in its variant-level (Jain, para 0028-0029).
But Ben-Bassat and Jain don’t explicitly teach wherein generating the prompt comprises: requesting a language model to generate, based on the query and the information about the session, a response including a processed version of the query and a processed version of the information about the session, and including the response into the prompt;
However in the same field of endeavor of utilization of user search context data for prompt generation Ferev teaches wherein generating the prompt comprises: requesting a language model to generate, based on the query and the information about the session, a response including a processed version of the query and a processed version of the information about the session, and including the response into the prompt(Ferev, Fig. 2 and para 0036 disclose prompt comprising of query, context (session data) “This anonymization prompt 242 may include an explicit natural language query issued by the user, as well as other data that was incorporated into the generative model input prompt explicitly by the user and/or automatically (e.g., based on the user query, the context, etc.)”; same para 0036 further discloses inclusion of initial prompt response in the requested prompt “at least a portion of the generative model input prompt and/or response 240 may be assembled into an “anonymization prompt” 242,”);
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the feature of prompt generation by language model of Ferev into generation of response based on user query contexts of Ben-Bassat and Jain to produce an expected result of language model prompt generation for obtaining results. The modification would be obvious because one of ordinary skill in the art would be motivated to improve protection of user provided input data by anonymizing the contents (Ferev, para 0036).
Regarding Claim 2(Original), Ben-Bassat, Jain and Ferev teach all the limitations of claim 1 and Jain further teaches wherein storing the information about the session comprises: receiving, from the device associated with the user and via the network, real time session data including at least one of information about one or more searches conducted by the user during the session, information about one or more items requested by the user during the session, information about a source associated with the session, or information about an event associated with the session(Jain, para 0038 discloses search session data containing user searches, interacted/requested items “The web server 104 may transmit user session data related to a customer's activity (e.g., interactions) on the website. ….The customer may, via the web browser, search for items, view item advertisements for items displayed on the website, and click on item advertisements and/or items in the search result, for example”; para 0042 further teaches session data comprising event information “The search-based recommendation computing device 102 may also receive from the web server 104 user session data identifying events associated with browsing sessions”);
and storing, at the computer-readable medium, the real time session data(Jain, para 0042 discloses storing user search session data in a database “The search-based recommendation computing device 102 may also receive from the web server 104 user session data identifying events associated with browsing sessions, and may store the user session data in the database 116”).
Regarding Claim 3(Original), Ben-Bassat, Jain and Ferev teach all the limitations of claim 1 and Jain further teaches responsive to receiving the query, retrieving, from the database, user data including information about one or more features of the user (Jain, para 0038 discloses retrieving user data “The website may capture these activities as user session data, and transmit the user session data to the search-based recommendation computing device 102 over the communication network 118. The website may also allow the operator to add one or more of the items to an online shopping cart, and allow the customer to perform a “checkout” of the shopping cart to purchase the items. In some examples, the web server 104 transmits purchase data identifying items the customer has purchased from the website to the search-based recommendation computing device 102”); wherein storing the information about the session comprises storing, at the computer-readable medium, the user data(Jain, para 0042 discloses storing user search session data in a database “The search-based recommendation computing device 102 may also receive from the web server 104 user session data identifying events associated with browsing sessions, and may store the user session data in the database 116”).
Regarding Claim 4(Original), Ben-Bassat, Jain and Ferev teach all the limitations of claim 1 and Ben-Bassat further teaches wherein requesting each of the plurality of language models to generate the respective response comprises: requesting each of the plurality of language models to generate the respective response (Ben-Bassat, Fig. 5C-E discloses language models (element 536 “Language Model 1”, element 546 “Language Model 2” and element 558 “Language Model 3” generating their respective responses inferring entity context type (element 538), inferring category of item context (element 548) and indicative to answer context (element 560)) including a set of one or more fields with one or more identifiers for the respective type of context of the query (Ben-Bassat, para 0054 further discloses obtained item context information may have identifier “The item data may include item identifiers for items that are available and may include quantities of items associated with each item identifier. Additionally, item data may also include attributes of items such as the size, color, weight, stock keeping unit (SKU), or serial number for the item”).
Regarding Claim 5(Original), Ben-Bassat, Jain and Ferev teach all the limitations of claim 1 and Ben-Bassat further teaches wherein generating the query understanding string comprises: packaging the plurality of responses into the query understanding string that includes a plurality of sets of one or more fields (Ben-Bassat, Fig. 5F and para 0056 disclose generation of an input (query input) deriving from plurality of contexts (element 570) where plurality of context responses are getting aggregated (packaged) for response generation “Language Model 4” (element 572) “the content system may aggregate the plurality of sets of contextual information to generate the first contextual information profile 570. The first contextual information profile 570 may comprise the plurality of sets of contextual information and/or reference identifiers associated with the plurality of sets of contextual information. The reference identifiers may be indicative of content items associated with the plurality of sets of contextual information”) each of the plurality of sets including one or more identifiers for the respective type of context of the query (Ben-Bassat, para 0056 further discloses obtained item context information may have identifier “The first contextual information profile 570 may comprise the plurality of sets of contextual information and/or reference identifiers associated with the plurality of sets of contextual information. The reference identifiers may be indicative of content items associated with the plurality of sets of contextual information””).
Regarding Claim 6(Original), Ben-Bassat, Jain and Ferev teach all the limitations of claim 1 and Ben-Bassat further teaches retrieving, from the database, classification data including information about classification of a collection of items(Ben-Bassat, Fig. 5D and para 0046 further discloses the classification context is getting inferred from a large language model (element 546) “in response to the second set of information 543, the second language model 546 may (i) determine the first relevance classification 548 indicative of whether the first content item 544 is relevant to the first entity 538 and/or (ii) output an indication of the first entity 538”); and tuning, using the classification data, a first language model of the plurality of language models to infer, from the query, a category of an item associated with the query, the category of the item representing a first type of context of the plurality of types of context(Ben-Bassat, element 561 (Prompt) of Fig. 5F discloses all contextual information including classification context to form a updated input/query(re-writing) for response generation; and further generating updated response).
Regarding Claim 7(Original), Ben-Bassat, Jain and Ferev teach all the limitations of claim 6 and Ben-Bassat further teaches further comprising: retrieving, from the database, catalog data including information about a collection of features associated with the collection of items(Ben-Bassat, Fig. 5C and para 0044 discloses retrieving response as entity with providing features such as main theme, salient entity information about the items “the first language model 536 may determine the first entity 538 based upon a first set of information 511 provided to the first language model 536………..the first set of information 511 comprises the first query 510 and/or a first prompt 513. In some examples, the first prompt 513 may comprise an instruction to provide an indication of the first entity 538 (e.g., main theme, salient entity, one or more topics, etc.) associated with the first query 510”; para 0043 further teaches information extraction from database, catalog (informational database) “the first language model 536 comprises a knowledge base (e.g., a database of resources) comprising at least one of one or more dictionaries, one or more lists of terms, one or more encyclopedias, one or more online encyclopedias, one or more news channel resources, one or more news websites, one or more websites, one or more books, one or more research articles, one or more research article databases, one or more informational databases, etc”);
and tuning, using the catalog data, a second language model of the plurality of language models to rewrite the query into a rewritten version of the query including a set of fields with a set of candidate items associated with the query, the rewritten version of the query representing a second type of context of the plurality of types of context (Ben-Bassat, element 561 (Prompt) of Fig. 5F discloses all contextual information to form a updated input/query(re-writing) for response generation; para 0057 further discloses converting (normalized) the query from the user input “the fourth language model 572 may (i) analyze the first query 510 to derive a question and/or request posed by the first query 510, (ii) analyze the first contextual information profile 570 to determine an answer to the question and/or request posed by the first query 510” ).
Regarding Claim 8(Original), Ben-Bassat, Jain and Ferev teach all the limitations of claim 7 and Ben-Bassat further teaches retrieving, from the database, attribute data including information about a collection of attributes associated with the collection of items (Ben-Bassat, Fig. 5D and para 0046 further discloses attribute data such as item relevance classification with respect to other items in a classification is getting retrieved “in response to the second set of information 543, the second language model 546 may (i) determine the first relevance classification 548 indicative of whether the first content item 544 is relevant to the first entity 538 and/or (ii) output an indication of the first entity 538”);
and tuning, using the attribute data, a third language model of the plurality of language models to infer, from the query, one or more attributes associated with the query, the one or more attributes representing a third type of context of the plurality of types of context(Ben-Bassat, para 0047 discloses inter and retrieve relevance classification attributes as search context “determining the first relevance classification 548 associated with the first content item 544. In some examples, for each content item of one, some and/or all of the pool of content items 530, the content system may (i) determine a relevance classification (e.g., the first relevance classification 548) based upon the content item and the first entity 538, and/or (ii) determine whether to include the content item in the first set of content items”).
Regarding Claim 9(Currently Amended), Ben-Bassat, Jain and Ferev teach all the limitations of claim 1 and Ben-Bassat further teaches wherein generating the prompt comprises: processing the query by converting the query into the processed version of the query having a normalized format(Ben-Bassat, element 561 (Prompt) of Fig. 5F discloses all contextual information to form a new input/query for response generation; para 0057 further discloses converting (normalized) the query from the user input “the fourth language model 572 may (i) analyze the first query 510 to derive a question and/or request posed by the first query 510, (ii) analyze the first contextual information profile 570 to determine an answer to the question and/or request posed by the first query 510” );
Using the broadest reasonable interpretation consistent with the specification (paragraph 0081) as it would be interpreted by one of ordinary skill in the art, examiner is interpreting the limitation “query having a normalized format” to mean updated query format after incorporating query contexts which is to be used for obtaining query response.
processing the information about the session by converting the information about the session into the contextual data having a structured format(Ben-Bassat, Fig. 5D and para 0046 further discloses query contextual data is getting converted into structural data such as search content’s classification data “in response to the second set of information 543, the second language model 546 may (i) determine the first relevance classification 548 indicative of whether the first content item 544 is relevant to the first entity 538 and/or (ii) output an indication of the first entity 538””);
and including, into the prompt, the processed version of the query having the normalized format and the contextual data having the structured format (Ben-Bassat, element 561 (Prompt) of Fig. 5F discloses all contextual information to form a new input/query for response generation; para 0057 further discloses converting (normalized) the query from the user input “the fourth language model 572 may (i) analyze the first query 510 to derive a question and/or request posed by the first query 510, (ii) analyze the first contextual information profile 570 to determine an answer to the question and/or request posed by the first query 510” ).
Regarding Claim 10 (Currently Amened), Ben-Bassat, Jain and Ferev teach all the limitations of claim 1 and Ben-Bassat further teaches wherein generating the prompt further comprises: generating an initial prompt for input into a language model, the initial prompt including the query and the information about the session(Ben-Bassat, element 561 (Prompt) of Fig. 5F discloses prompt (element 561) with user query information (element 510); where Jain in para 0038 discloses session having query information);
requesting the language model to generate, based on the initial prompt input into the language model, the response including the processed version of the query having a normalized format and the processed version of the information about the session having a structured format; and including, into the prompt, the processed version of the query having the normalized format and the processed version of the information about the session having the structured format (Ben-Bassat, element 561 (Prompt) of Fig. 5F discloses all contextual information to form a new input/query for response generation; para 0057 further discloses converting (normalized) the query from the prompt (element 561) “the fourth language model 572 may (i) analyze the first query 510 to derive a question and/or request posed by the first query 510, (ii) analyze the first contextual information profile 570 to determine an answer to the question and/or request posed by the first query 510” ).
Using the broadest reasonable interpretation consistent with the specification (paragraph 0081) as it would be interpreted by one of ordinary skill in the art, examiner is interpreting the limitation “contextual data having the structured format” to mean incorporating contextual data in a way so that generated response reflects the context.
Claim 12 (Currently Amended), Ben-Bassat teaches 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 perform steps comprising(Ben-Bassat, para 0073 discloses storing executable instructions on a non-transitory medium “The non-transitory machine readable medium 602 may comprise processor-executable instructions 612 that when executed by a processor 616 cause performance (e.g., by the processor 616) of at least some of the provisions herein (e.g., embodiment 614)”):
receiving, via a network from a device associated with a user of an online system, a query submitted by the user during a session of the user at the online system (Ben-Bassat, Fig. 5G discloses query (element 506) submitted by an user in a search session at an online system);
responsive to receiving the query, generating a prompt for input into a plurality of language models (Ben-Bassat, Fig. 5C-E discloses user query (element 510) generating prompt (element 513) into language models (element 536 “Language Model 1”, element 546 “Language Model 2” and element 558 “Language Model 3”)), each of the plurality of language models tuned to infer a respective type of context of a plurality of types of context of the query (Ben-Bassat, Fig. 5C-E discloses user query (element 510) generating prompt (element 513) into language models (element 536 “Language Model 1”, element 546 “Language Model 2” and element 558 “Language Model 3”; para 0044 discloses first language model (536) inferring first context (entity) “the first language model 536 may (i) determine the first entity 538 based upon the first query 510 and/or (ii) output an indication of the first entity 538. In an example, the first prompt 513 may comprise: <You are a helpful tool for question answering. Extract the main entity the query is asking about.>”; para 0045 discloses inferring second context (classification/categorization of the intended item) “5D illustrates use of a second language model 546 to determine a first relevance classification 548 associated with a first content item 544 of the pool of content items 530”’; para 0050 discloses identifying third context (deriving the submitted query); “the third language model 558 may (i) analyze the first query 510 to derive a question and/or request posed by the first query 510”); requesting each of the plurality of language models to generate, based on the prompt input into each of the plurality of language models, a respective response of a plurality of responses that includes information about the respective type of context of the query (Ben-Bassat, Fig. 5C-E discloses language models (element 536 “Language Model 1”, element 546 “Language Model 2” and element 558 “Language Model 3” generating their respective responses inferring entity context type (element 538), inferring category of item context (element 548) and indicative to answer context (element 560)); generating, using the plurality of responses, a query understanding string for the query, the query understanding string including information about the plurality of types of context of the query (Ben-Bassat, Fig. 5F discloses generation of an input (query input) deriving from plurality of contexts (element 570)); identifying, from a database of the online system and using the information about the plurality of types of context, a set of one or more items (Ben-Bassat, para 0056-0057 discloses generation of response from online databases using contextual query information “the fourth language model 572 may (i) analyze the first query 510 to derive a question and/or request posed by the first query 510, (ii) analyze the first contextual information profile 570 to determine an answer to the question and/or request posed by the first query 510, and/or (iii) generate the first response 574 to be indicative of the answer”); generating, using information about the set of one or more items, a first user interface signal; and sending, via the network, the first user interface signal to the device associated with the user, wherein the sending the first user interface signal causes the device associated with the user to display a user interface with the information about the set of one or more items and one or more user interface elements for use by the user to order the set of one or more items (Ben-Bassat, Fig. 5G and para 0060 discloses generation of query response (element 580) on the user device “FIG. 5G illustrates the representation (shown with reference number 580) of the first response 574 being displayed via the first interface 502. In some examples, the representation 580 may comprise (i) an indication 582 of the amount spent on groceries during the time period and/or (ii) one or more reference items corresponding to one or more reference identifiers indicated by the first response 574”).
But Ben-Bassat does not explicitly teach storing, at the non-transitory computer readable storage medium and during the session, information about the session; wherein generating the prompt comprises: requesting a language model to generate, based on the query and the information about the session, a response including a processed version of the query and a processed version of the information about the session, and including the response into the prompt;
However in the same field of endeavor of utilization of user search session data for content recommendation Jain teaches storing, at the non-transitory computer readable storage medium and during the session, information about the session (Jain , para 0042 discloses storing user search session data in a database “The search-based recommendation computing device 102 may also receive from the web server 104 user session data identifying events associated with browsing sessions, and may store the user session data in the database 116”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the feature of storing and using user search session data for content recommendation of Jain into generation of response based on user query contexts of Ben-Bassat to produce an expected result of deriving user search context from the user session data. The modification would be obvious because one of ordinary skill in the art would be motivated to improve the item discoverability by including items in its variant-level (Jain, para 0028-0029).
But Ben-Bassat and Jain don’t explicitly teach wherein generating the prompt comprises: requesting a language model to generate, based on the query and the information about the session, a response including a processed version of the query and a processed version of the information about the session, and including the response into the prompt;
However in the same field of endeavor of utilization of user search context data for prompt generation Ferev teaches wherein generating the prompt comprises: requesting a language model to generate, based on the query and the information about the session, a response including a processed version of the query and a processed version of the information about the session, and including the response into the prompt (Ferev, Fig. 2 and para 0036 disclose prompt comprising of query, context (session data) “This anonymization prompt 242 may include an explicit natural language query issued by the user, as well as other data that was incorporated into the generative model input prompt explicitly by the user and/or automatically (e.g., based on the user query, the context, etc.)”; same para 0036 further discloses inclusion of initial prompt response in the requested prompt “at least a portion of the generative model input prompt and/or response 240 may be assembled into an “anonymization prompt” 242,”);
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the feature of prompt generation by language model of Ferev into generation of response based on user query contexts of Ben-Bassat and Jain to produce an expected result of language model prompt generation for obtaining results. The modification would be obvious because one of ordinary skill in the art would be motivated to improve protection of user provided input data by anonymizing the contents (Ferev, para 0036).
Claim 20 (Currently Amended), Ben-Bassat teaches A computer system comprising: a processor; and a non-transitory computer-readable storage medium having instructions that, when executed by the processor, cause the computer system to perform steps comprising: receiving, via a network from a device associated with a user of an online system (Ben-Bassat, para 0073 discloses a computing system having storage to store executable instructions on a non-transitory medium “The non-transitory machine readable medium 602 may comprise processor-executable instructions 612 that when executed by a processor 616 cause performance (e.g., by the processor 616) of at least some of the provisions herein (e.g., embodiment 614)”):
a query submitted by the user during a session of the user at the online system (Ben-Bassat, Fig. 5G discloses query (element 506) submitted by an user in a search session at an online system);
responsive to receiving the query, generating a prompt for input into a plurality of language models (Ben-Bassat, Fig. 5C-E discloses user query (element 510) generating prompt (element 513) into language models (element 536 “Language Model 1”, element 546 “Language Model 2” and element 558 “Language Model 3”)), each of the plurality of language models tuned to infer a respective type of context of a plurality of types of context of the query (Ben-Bassat, Fig. 5C-E discloses user query (element 510) generating prompt (element 513) into language models (element 536 “Language Model 1”, element 546 “Language Model 2” and element 558 “Language Model 3”; para 0044 discloses first language model (536) inferring first context (entity) “the first language model 536 may (i) determine the first entity 538 based upon the first query 510 and/or (ii) output an indication of the first entity 538. In an example, the first prompt 513 may comprise: <You are a helpful tool for question answering. Extract the main entity the query is asking about.>”; para 0045 discloses inferring second context (classification/categorization of the intended item) “5D illustrates use of a second language model 546 to determine a first relevance classification 548 associated with a first content item 544 of the pool of content items 530”’; para 0050 discloses identifying third context (deriving the submitted query); “the third language model 558 may (i) analyze the first query 510 to derive a question and/or request posed by the first query 510”); requesting each of the plurality of language models to generate, based on the prompt input into each of the plurality of language models, a respective response of a plurality of responses that includes information about the respective type of context of the query (Ben-Bassat, Fig. 5C-E discloses language models (element 536 “Language Model 1”, element 546 “Language Model 2” and element 558 “Language Model 3” generating their respective responses inferring entity context type (element 538), inferring category of item context (element 548) and indicative to answer context (element 560)); generating, using the plurality of responses, a query understanding string for the query, the query understanding string including information about the plurality of types of context of the query (Ben-Bassat, Fig. 5F discloses generation of an input (query input) deriving from plurality of contexts (element 570)); identifying, from a database of the online system and using the information about the plurality of types of context, a set of one or more items (Ben-Bassat, para 0056-0057 discloses generation of response from online databases using contextual query information “the fourth language model 572 may (i) analyze the first query 510 to derive a question and/or request posed by the first query 510, (ii) analyze the first contextual information profile 570 to determine an answer to the question and/or request posed by the first query 510, and/or (iii) generate the first response 574 to be indicative of the answer”); generating, using information about the set of one or more items, a first user interface signal; and sending, via the network, the first user interface signal to the device associated with the user, wherein the sending the first user interface signal causes the device associated with the user to display a user interface with the information about the set of one or more items and one or more user interface elements for use by the user to order the set of one or more items (Ben-Bassat, Fig. 5G and para 0060 discloses generation of query response (element 580) on the user device “FIG. 5G illustrates the representation (shown with reference number 580) of the first response 574 being displayed via the first interface 502. In some examples, the representation 580 may comprise (i) an indication 582 of the amount spent on groceries during the time period and/or (ii) one or more reference items corresponding to one or more reference identifiers indicated by the first response 574”).
But Ben-Bassat does not explicitly teach storing, at the non-transitory computer-readable storage medium and during the session, information about the session; wherein generating the prompt comprises: requesting a language model to generate, based on the query and the information about the session, a response including a processed version of the query and a processed version of the information about the session, and including the response into the prompt;
However in the same field of endeavor of utilization of user search session data for content recommendation Jain teaches storing, at the non-transitory computer-readable storage medium and during the session, information about the session (Jain, para 0042 discloses storing user search session data in a database “The search-based recommendation computing device 102 may also receive from the web server 104 user session data identifying events associated with browsing sessions, and may store the user session data in the database 116”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the feature of storing and using user search session data for content recommendation of Jain into generation of response based on user query contexts of Ben-Bassat to produce an expected result of deriving user search context from the user session data. The modification would be obvious because one of ordinary skill in the art would be motivated to improve the item discoverability by including items in its variant-level (Jain, para 0028-0029).
But Ben-Bassat and Jain don’t explicitly teach wherein generating the prompt comprises: requesting a language model to generate, based on the query and the information about the session, a response including a processed version of the query and a processed version of the information about the session, and including the response into the prompt;
However in the same field of endeavor of utilization of user search context data for prompt generation Ferev teaches wherein generating the prompt comprises: requesting a language model to generate, based on the query and the information about the session, a response including a processed version of the query and a processed version of the information about the session, and including the response into the prompt (Ferev, Fig. 2 and para 0036 disclose prompt comprising of query, context (session data) “This anonymization prompt 242 may include an explicit natural language query issued by the user, as well as other data that was incorporated into the generative model input prompt explicitly by the user and/or automatically (e.g., based on the user query, the context, etc.)”; same para 0036 further discloses inclusion of initial prompt response in the requested prompt “at least a portion of the generative model input prompt and/or response 240 may be assembled into an “anonymization prompt” 242,”);
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the feature of prompt generation by language model of Ferev into generation of response based on user query contexts of Ben-Bassat and Jain to produce an expected result of language model prompt generation for obtaining results. The modification would be obvious because one of ordinary skill in the art would be motivated to improve protection of user provided input data by anonymizing the contents(Ferev, para 0036).
Regarding Claim 13(Original), Ben-Bassat, Jain and Ferev teach all the limitations of claim 12 and Jain further teaches wherein the instructions further cause the processor to perform steps comprising: receiving, from the device associated with the user and via the network, real time session data including at least one of information about one or more searches conducted by the user during the session, information about one or more items requested by the user during the session, information about a source associated with the session, or information about an event associated with the session (Jain, para 0038 discloses search session data containing user searches, interacted/requested items “The web server 104 may transmit user session data related to a customer's activity (e.g., interactions) on the website. ….The customer may, via the web browser, search for items, view item advertisements for items displayed on the website, and click on item advertisements and/or items in the search result, for example”; para 0042 further teaches session data comprising event information “The search-based recommendation computing device 102 may also receive from the web server 104 user session data identifying events associated with browsing sessions”);
and storing the information about the session by storing, at the non-transitory computer readable storage medium, the real time session data(Jain, para 0042 discloses storing user search session data in a database “The search-based recommendation computing device 102 may also receive from the web server 104 user session data identifying events associated with browsing sessions, and may store the user session data in the database 116”).
Regarding Claim 14(Original), Ben-Bassat, Jain and Ferev teach all the limitations of claim 12 and Ben-Bassat further teaches wherein the instructions further cause the processor to perform steps comprising: requesting each of the plurality of language models to generate the respective response (Ben-Bassat, Fig. 5C-E discloses language models (element 536 “Language Model 1”, element 546 “Language Model 2” and element 558 “Language Model 3” generating their respective responses inferring entity context type (element 538), inferring category of item context (element 548) and indicative to answer context (element 560)) including a set of one or more fields with one or more identifiers for the respective type of context of the query (Ben-Bassat, para 0054 further discloses obtained item context information may have identifier “The item data may include item identifiers for items that are available and may include quantities of items associated with each item identifier. Additionally, item data may also include attributes of items such as the size, color, weight, stock keeping unit (SKU), or serial number for the item”).
Regarding Claim 15(Original), Ben-Bassat, Jain and Ferev teach all the limitations of claim 12 and Ben-Bassat further teaches wherein the instructions further cause the processor to perform steps comprising: packaging the plurality of responses into the query understanding string that includes a plurality of sets of one or more fields (Ben-Bassat, Fig. 5F and para 0056 disclose generation of an input (query input) deriving from plurality of contexts (element 570) where plurality of context responses are getting aggregated (packaged) for response generation “Language Model 4” (element 572) “the content system may aggregate the plurality of sets of contextual information to generate the first contextual information profile 570. The first contextual information profile 570 may comprise the plurality of sets of contextual information and/or reference identifiers associated with the plurality of sets of contextual information. The reference identifiers may be indicative of content items associated with the plurality of sets of contextual information”) each of the plurality of sets including one or more identifiers for the respective type of context of the query (Ben-Bassat, para 0056 further discloses obtained item context information may have identifier “The first contextual information profile 570 may comprise the plurality of sets of contextual information and/or reference identifiers associated with the plurality of sets of contextual information. The reference identifiers may be indicative of content items associated with the plurality of sets of contextual information”).
Regarding Claim 16(Original), Ben-Bassat, Jain and Ferev teach all the limitations of claim 12 and Ben-Bassat further teaches wherein the instructions further cause the processor to perform steps comprising: retrieving, from the database, classification data including information about classification of a collection of items(Ben-Bassat, Fig. 5D and para 0046 further discloses the classification context is getting inferred from a large language model (element 546) “in response to the second set of information 543, the second language model 546 may (i) determine the first relevance classification 548 indicative of whether the first content item 544 is relevant to the first entity 538 and/or (ii) output an indication of the first entity 538”);
tuning, using the classification data, a first language model of the plurality of language models to infer, from the query, a category of an item associated with the query, the category of the item representing a first type of context of the plurality of types of context(Ben-Bassat, element 561 (Prompt) of Fig. 5F discloses all contextual information including classification context to form a updated input/query(re-writing) for response generation; and further generating updated response);
retrieving, from the database, catalog data including information about a collection of features associated with the collection of items(Ben-Bassat, Fig. 5C and para 0044 discloses retrieving response as entity with providing features such as main theme, salient entity information about the items “the first language model 536 may determine the first entity 538 based upon a first set of information 511 provided to the first language model 536………..the first set of information 511 comprises the first query 510 and/or a first prompt 513. In some examples, the first prompt 513 may comprise an instruction to provide an indication of the first entity 538 (e.g., main theme, salient entity, one or more topics, etc.) associated with the first query 510”; para 0043 further teaches information extraction from database, catalog (informational database) “the first language model 536 comprises a knowledge base (e.g., a database of resources) comprising at least one of one or more dictionaries, one or more lists of terms, one or more encyclopedias, one or more online encyclopedias, one or more news channel resources, one or more news websites, one or more websites, one or more books, one or more research articles, one or more research article databases, one or more informational databases, etc”); tuning, using the catalog data, a second language model of the plurality of language models to rewrite the query into a rewritten version of the query including a set of fields with a set of candidate items associated with the query, the rewritten version of the query representing a second type of context of the plurality of types of context(Ben-Bassat, element 561 (Prompt) of Fig. 5F discloses all contextual information to form a updated input/query(re-writing) for response generation; para 0057 further discloses converting (normalized) the query from the user input “the fourth language model 572 may (i) analyze the first query 510 to derive a question and/or request posed by the first query 510, (ii) analyze the first contextual information profile 570 to determine an answer to the question and/or request posed by the first query 510” );
retrieving, from the database, attribute data including information about a collection of attributes associated with the collection of items(Ben-Bassat, Fig. 5D and para 0046 further discloses attribute data such as item relevance classification with respect to other items in a classification is getting retrieved “in response to the second set of information 543, the second language model 546 may (i) determine the first relevance classification 548 indicative of whether the first content item 544 is relevant to the first entity 538 and/or (ii) output an indication of the first entity 538”); and tuning, using the attribute data, a third language model of the plurality of language models to infer, from the query, one or more attributes associated with the query, the one or more attributes representing a third type of context of the plurality of types of context(Ben-Bassat, para 0047 discloses inter and retrieve relevance classification attributes as search context “determining the first relevance classification 548 associated with the first content item 544. In some examples, for each content item of one, some and/or all of the pool of content items 530, the content system may (i) determine a relevance classification (e.g., the first relevance classification 548) based upon the content item and the first entity 538, and/or (ii) determine whether to include the content item in the first set of content items”).
Regarding Claim 17(Currently Amended), Ben-Bassat, Jain and Ferev teach all the limitations of claim 12 and Ben-Bassat further teaches wherein the instructions further cause the processor to perform steps comprising: processing the query by converting the query into the processed version of the query having a normalized format (Ben-Bassat, element 561 (Prompt) of Fig. 5F discloses all contextual information to form a new input/query for response generation; para 0057 further discloses converting (normalized) the query from the user input “the fourth language model 572 may (i) analyze the first query 510 to derive a question and/or request posed by the first query 510, (ii) analyze the first contextual information profile 570 to determine an answer to the question and/or request posed by the first query 510” );
Using the broadest reasonable interpretation consistent with the specification (paragraph 0081) as it would be interpreted by one of ordinary skill in the art, examiner is interpreting the limitation “query having a normalized format” to mean updated query format after incorporating query contexts which is to be used for obtaining query response.
processing the information about the session by converting the information about the session into the contextual data having a structured format (Ben-Bassat, Fig. 5D and para 0046 further discloses query contextual data is getting converted into structural data such as search content’s classification data “in response to the second set of information 543, the second language model 546 may (i) determine the first relevance classification 548 indicative of whether the first content item 544 is relevant to the first entity 538 and/or (ii) output an indication of the first entity 538””);
and generating the prompt by including, into the prompt, the processed of the query having the normalized format and the contextual data having the structured format (Ben-Bassat, element 561 (Prompt) of Fig. 5F discloses all contextual information to form a new input/query for response generation; para 0057 further discloses converting (normalized) the query from the prompt (element 561) “the fourth language model 572 may (i) analyze the first query 510 to derive a question and/or request posed by the first query 510, (ii) analyze the first contextual information profile 570 to determine an answer to the question and/or request posed by the first query 510” ).
Using the broadest reasonable interpretation consistent with the specification (paragraph 0081) as it would be interpreted by one of ordinary skill in the art, examiner is interpreting the limitation “contextual data having the structured format” to mean incorporating contextual data in a way so that generated response reflects the context.
Regarding Claim 18(Currently Amended), Ben-Bassat, Jain and Ferev teach all the limitations of claim 12 and Ben-Bassat further teaches wherein the instructions further cause the processor to perform steps comprising: generating an initial prompt for input into the language model, the initial prompt including the query and the information about the session (Ben-Bassat, element 561 (Prompt) of Fig. 5F discloses prompt (element 561) with user query information (element 510); where Jain in para 0038 discloses session having query information);
requesting the language model to generate, based on the initial prompt input into the language model, the response including the processed version of the query having a normalized format and the processed version of the information about the session having a structured format; and generating the prompt by including, into the prompt, the processed version of the query having the normalized format and the processed version of the information about the session having the structured format (Ben-Bassat, element 561 (Prompt) of Fig. 5F discloses all contextual information to form a new input/query for response generation; para 0057 further discloses converting (normalized) the query from the prompt (element 561) “the fourth language model 572 may (i) analyze the first query 510 to derive a question and/or request posed by the first query 510, (ii) analyze the first contextual information profile 570 to determine an answer to the question and/or request posed by the first query 510” ).
Using the broadest reasonable interpretation consistent with the specification (paragraph 0081) as it would be interpreted by one of ordinary skill in the art, examiner is interpreting the limitation “contextual data having the structured format” to mean incorporating contextual data in a way so that generated response reflects the context.
Claim 11 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Ben-Bassat, Ilan et al (PGPUB Document No. 20250315616), hereafter referred as to “Ben-Bassat”, in view of Jain, Shailesh Hiralal et al (PGPUB Document No. 20250045810), hereafter, referred to as “Jain”, in view of Ferev, Milen et al (PGPUB Document No. 20260119700), hereafter, referred to as “Ferev”, in further view of Jiang, Rui et al (PGPUB Document No. 20210118036), hereafter, referred to as “Jiang”.
Regarding Claim 11(Currently Amended), Ben-Bassat, Jain and Ferev teach all the limitations of claim 1 and Ben-Bassat further teaches further comprising: identifying, from the database and using the information about the plurality of types of context within the query understanding string, a plurality of items(Ben-Bassat, Fig. 5F and para 0056 disclose generation of an input (query input) deriving from plurality of contexts (element 570) where plurality of context responses are getting aggregated (packaged) for response generation “Language Model 4” (element 572) “the content system may aggregate the plurality of sets of contextual information to generate the first contextual information profile 570. The first contextual information profile 570 may comprise the plurality of sets of contextual information and/or reference identifiers associated with the plurality of sets of contextual information. The reference identifiers may be indicative of content items associated with the plurality of sets of contextual information”);
But Ben-Bassat, Jain and Ferev don’t explicitly teach ranking, using the information about the plurality of types of context within the query understanding string, the plurality of items to generate a ranked list of items;
generating, using information about the ranked list of items, a second user interface signal; and sending, via the network, the second user interface signal to the device associated with the user, wherein sending the second user interface signal causes the device associated with the user to display the user interface with the ranked list of items and a plurality of interface elements for use by the user to order each item from the ranked list of items.
However, in the same field of endeavor of content recommendation Jiang teaches ranking, using the information about the plurality of types of context within the query understanding string, the plurality of items to generate a ranked list of items(Jiang, para 0098 ranking products based on context “search cluster 402 may be configured to rank the products within the defined context. In some embodiments, search cluster 402 may be configured to rank the products based on a score generated for each product”; where para 0008 further discloses that query context having plurality of contexts “the context associated with the search query may comprise at least one of product associated with the search query, a timestamp of the search query, a product category associated with the search query, or user information associated with the search query”);
generating, using information about the ranked list of items, a second user interface signal; and sending, via the network, the second user interface signal to the device associated with the user, wherein the sending the second user interface signal causes the device associated with the user to display the user interface with the ranked list of items (Jiang, para 0085 discloses sending ranked product list to user interface “Based on the score generated for each product, one or more processors 305 may automatically rank the products to be recommended. Then, one or more processors 305 may display a number of the ranked products on the user's user device”)and a plurality of interface elements for use by the user to order each item from the ranked list of items(Jiang, Fig. 1C further discloses a displayed list of products that user can order).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the feature of providing ranked product list to user interface of Jiang into generation of response based on user query contexts of Ben-Bassat, Jain and Ferev to produce an expected result of deriving product list to user based on query contexts. The modification would be obvious because one of ordinary skill in the art would be motivated to improve the product recommendation by considering features associated with users and contextual information related to products(Jiang, para 0026-0027).
Regarding Claim 19(Currently Amended), Ben-Bassat, Jain and Ferev teach all the limitations of claim 12 and Ben-Bassat further teaches wherein the instructions further cause the processor to perform steps comprising: identifying, from the database and using the information about the plurality of types of context within the query understanding string, a plurality of items (Ben-Bassat, Fig. 5F and para 0056 disclose generation of an input (query input) deriving from plurality of contexts (element 570) where plurality of context responses are getting aggregated (packaged) for response generation “Language Model 4” (element 572) “the content system may aggregate the plurality of sets of contextual information to generate the first contextual information profile 570. The first contextual information profile 570 may comprise the plurality of sets of contextual information and/or reference identifiers associated with the plurality of sets of contextual information. The reference identifiers may be indicative of content items associated with the plurality of sets of contextual information”);
But Ben-Bassat, Jain and Ferev don’t explicitly teach ranking, using the information about the plurality of types of context within the query understanding string, the plurality of items to generate a ranked list of items; generating, using information about the ranked list of items, a second user interface signal; and sending, via the network, the second user interface signal to the device associated with the user, wherein sending the second user interface signal causes the device associated with the user to display the user interface with the ranked list of items and a plurality of interface elements for use by the user to order each item from the ranked list of items.
However, in the same field of endeavor of content recommendation Jiang teaches ranking, using the information about the plurality of types of context within the query understanding string, the plurality of items to generate a ranked list of items (Jiang, para 0098 ranking products based on context “search cluster 402 may be configured to rank the products within the defined context. In some embodiments, search cluster 402 may be configured to rank the products based on a score generated for each product”; where para 0008 further discloses that query context having plurality of contexts “the context associated with the search query may comprise at least one of product associated with the search query, a timestamp of the search query, a product category associated with the search query, or user information associated with the search query”);
generating, using information about the ranked list of items, a second user interface signal; and sending, via the network, the second user interface signal to the device associated with the user, wherein the sending the second user interface signal causes the device associated with the user to display the user interface with the ranked list of items (Jiang, para 0085 discloses sending ranked product list to user interface “Based on the score generated for each product, one or more processors 305 may automatically rank the products to be recommended. Then, one or more processors 305 may display a number of the ranked products on the user's user device”) and a plurality of interface elements for use by the user to order each item from the ranked list of items(Jiang, Fig. 1C further discloses a displayed list of products that user can order).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate the feature of providing ranked product list to user interface of Jiang into generation of response based on user query contexts of Ben-Bassat, Jain and Ferev to produce an expected result of deriving product list to user based on query contexts. The modification would be obvious because one of ordinary skill in the art would be motivated to improve the product recommendation by considering features associated with users and contextual information related to products(Jiang, para 0026-0027).
Response to Arguments
I. 35 U.S.C §103
Applicant’s arguments filed on 2/11/2026 have been fully considered but are
moot because the independent claim 1, 12 and 20 have been amended with newly added features which applicant’s arguments are directed towards. Since claims have been amended with new features, a new ground of rejection is presented.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 ABDULLAH A DAUD whose telephone number is (469)295-9283. The examiner can normally be reached M~F: 9:30 am~6:30 pm.
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, Amy Ng can be reached at 571-270-1698. 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.
/ABDULLAH A DAUD/Examiner, Art Unit 2164
/AMY NG/Supervisory Patent Examiner, Art Unit 2164
Prosecution Insights