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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 4/30/2026 has been entered.
Status of Claims
Claims 1-23 are currently pending in the present application.
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.
Claim(s) 1-3, 13, 15, 17 and 19-23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Paiz (US Patent No. 11,941,058; Date of Patent: Mar. 26, 2024) in view of Gray et al. (US Patent No.: 11,769,017; Date of Patent: Sep. 26, 2023).
Regarding independent claim 1,
Paiz discloses a system, comprising: a communication interface; See Abstract, (Disclosing a search engine optimizer working independently and in parallel with a browser and search engine to gather, analyze and distill input information interactively. The optimizer reorganizes an input to produce an optimized output that is delivered to the search engine which responds to the end user with search results.) See Col. 37 , lines 48-51, (The system comprises a parallel distributed supercomputer including a large data warehouse that stores a CORE List that consists of statistics for each keyword or cluster used to perform the method of optimizing the Cholti software application, i.e. a system, comprising: a communication interface (e.g. the system is directed to an internet search engine);)
and a processor coupled to the communication interface and configured to: receive a user input data via the communication interface; See Col. 3, lines 45-49, (A user may interact with the Cholti Search Engine Optimizer by providing an end user request comprising keywords, i.e. a processor coupled to the communication interface (e.g. a user interacts with a client device to provide a search request) and configured to: receive a user input data via the communication interface (e.g. the internet search query);)
use the user input data as an input to a knowledge retrieval engine configured to generate in response to the input a generated response that is derived at least in part from a set of proprietary data; See Col. 26, lines 6-11, (A user may submit an end user request comprising a sequence of keywords, which triggers a search engine to perform the search.) See Col. 37 , lines 48-51, (The system stores a CORE List that consists of statistics for each keyword or cluster used to perform the method of optimizing the Cholti software application, i.e. use the user input data as an input to a knowledge retrieval engine configured to generate in response to the input a generated response that is derived at least in part from a set of proprietary data (e.g. processing a user input includes executing Cholti software which requires the clusters and information stored in the CORE List);)
wherein the knowledge retrieval engine is a system that provides a response to a natural language chat prompt and/or a search query by leveraging proprietary data to improve an input to a web search engine, wherein the web search engine provides hyperlinks to web and/or internet content in response to a query; See Abstract, (The search query optimizer reorganizes an input to produce an optimized output that is delivered to the search engine which responds to the end user with search results.) See Col. 26, lines 3-11, (Cholti may process a user's request comprising natural language text to generate an optimal input.) See Col. 16, lines 58-65, (Cholti identifies, validates and verifies an input query and rearranges each request go generate an optimal query request.) See FIG. 3 & Col. 26, lines 12-27, (FIG. 3 illustrates a search tool where users may use Cholti to provide search keywords. The interface comprises lists of top sites and top pages retrieved in response to a search request, i.e. wherein the knowledge retrieval engine is a system that provides a response to a natural language chat prompt and/or a search query by leveraging proprietary data (e.g. Note Col. 6, lines 51-54 wherein the process uses clusters comprising groups of keywords that filter the size of the search environment) to improve an input to a web search engine (e.g. Note Abstract wherein the search engine optimizer may reorganize a natural language input to provide an optimized version as output), wherein the web search engine provides hyperlinks to web and/or internet content in response to a query (e.g. the system is directed to an internet search engine, i.e. internet content retrieved in response to a query );)
wherein proprietary data comprises any data unique to an organization or individual, comprising at least one of the following: word processor documents, spreadsheets, slide presentations, natural language documents, tabular data, or knowledge bases; See Col. 37 , lines 48-51, (The system comprises a parallel distributed supercomputer including a large data warehouse that stores a CORE List that consists of statistics for each keyword or cluster used to perform the method of optimizing the Cholti software application, i.e. wherein proprietary data comprises any data unique to an organization or individual (e.g. data stored in the data warehouse of the search application), comprising at least knowledge bases (e.g. the CORE List comprise statistics for each keyword or cluster used to generate optimized inputs to a search engine );)
wherein leveraging proprietary data to improve the input to the web search engine comprises adding a structural context and/or a contextual hint that is derived at least in part from the set of proprietary data to the generated response; See Col. 4, lines 36-39, (Disclosing a search engine optimizer working independently and in parallel with a browser and search engine to gather, analyze and distill input information interactively. The optimizer reorganizes an input to produce an optimized output that is delivered to the search engine which responds to the end user with search results. Users interact with a Cholti Search Engine Optimizer via a client device which wherein the Cholti software uses mathematical parameters to create smaller, primed and valid and environments that take into account that any given request is not optimal.) See Col. 6, lines 16-39, (The Cholti software performs the following steps: A) identifying each keyword to be valid or invalid and assigns each keyword a raw vector value based on a raw magnitude; B) creating auxiliary variables and a cluster list; C) validating independent variables belonging to a request based on raw hits to see if they are valid by being below a lower limit of page results; D) plotting maps and keywords into a Basic Glyph configuration and determining the estimated Boolean Algebra search value and determining the best preprocessed Basic Glyph, i.e. wherein leveraging proprietary data to improve the input to the web search engine comprises adding a structural context and/or a contextual hint that is derived at least in part from the set of proprietary data to the generated response (e.g. generating an optimized input includes using Cholti software to filter a search space, identify keywords and assign vector values to said keywords);)
and use the generated response comprising the structural context and/or the contextual hint to generate a set of web search results at least in part by using the web search engine. See Col. 6, lines 16-39, (The Cholti software performs the following steps: A) identifying each keyword to be valid or invalid and assigns each keyword a raw vector value based on a raw magnitude; B) creating auxiliary variables and a cluster list; C) validating independent variables belonging to a request based on raw hits to see if they are valid by being below a lower limit of page results; D) plotting maps and keywords into a Basic Glyph configuration and determining the estimated Boolean Algebra search value and determining the best preprocessed Basic Glyph, i.e. use the generated response comprising the structural context and/or the contextual hint (e.g. the Cholti software may reorganize keywords in an input as part of generating an optimized input for a search engine such as by including missing keywords such as in Col. 11, lines 21-23.) to generate a set of web search results at least in part by using the web search engine (e.g. Note Abstract wherein the optimized input is submitted to the search engine to retrieve search results ).)
Paiz does not disclose the step wherein the knowledge retrieval engine comprises a large language model (LLM) configured for generating web search engine input based at least in part on proprietary data, in part by using the proprietary data to fine-tune the LLM or using the proprietary data to create a searchable index to return extractions to be input to the LLM;
Gray discloses the step wherein the knowledge retrieval engine comprises a large language model (LLM) configured for generating web search engine input based at least in part on proprietary data, in part by using the proprietary data to fine-tune the LLM or using the proprietary data to create a searchable index to return extractions to be input to the LLM; See FIG. 3 & Col. 20, lines 28-34, (FIG. 3 illustrates method 300 comprising step 352 of receiving a query followed by step 354 comprising step 354A wherein the system may generate content based on the query and/or a rewrite of the input query.) See Col. 37 & lines 36-43, (Candidate generative models include an LLM fine-tuned based on an information summarization prompt and a creative LLM fine-tuned based on a creative generation prompt, i.e. wherein the knowledge retrieval engine comprises a large language model (LLM) configured for generating web search engine input based at least in part on proprietary data (e.g. the LLM may be used to rewrite a query), in part by using the proprietary data to fine-tune the LLM or using the proprietary data to create a searchable index to return extractions to be input to the LLM (e.g. Note Col. 8, lines 48-54 context determined by a context engine 113 may be used to rewrite a query formulated based on user input);)
Paiz and Gray are analogous art because they are in the same field of endeavor, search optimization. It would have been obvious to anyone having ordinary skill in the art before the effective filing date to modify the system of Paiz to include the method of re-writing user queries via LLMs as disclosed by Gray. Col. 3, lines 43-55 of Gray disclose that the system may provide augmented LLM prompts that do not rely on hard to codify experience of prompt engineering to enhance search result identification and retrieval.
Regarding dependent claim 2,
As discussed above with claim 1, Paiz-Gray discloses all of the limitations.
Gray further discloses the step the step wherein the knowledge retrieval engine is a fine-tuned LLM. See Col. 37 & lines 36-43, (Candidate generative models include an LLM fine-tuned based on an information summarization prompt and a creative LLM fine-tuned based on a creative generation prompt, i.e. wherein the knowledge retrieval engine is a fine-tuned LLM.)
Regarding dependent claim 3,
As discussed above with claim 2, Paiz-Gray discloses all of the limitations.
Gray further discloses the step wherein the generated response is a hypothetical answer of the fine-tuned LLM. See Col. 8, lines 48-54, (Context determined by a context engine 113 may be used to rewrite a query formulated based on user input.) See Col. 10, lines 54-56, (Search system 160 may comprise an SRD engine 162 configured for identifying search result documents responsive to queries, i.e. wherein the generated response is a hypothetical answer of the fine-tuned LLM.)
Paragraph [0041] of Applicant's Specification defines a "hypothetical answer" as "an answer that provides an answer format and/or structure with contextual content associated with the proprietary data". The search result documents of Gray are retrieved and presented to the user based on the LLM output by incorporating context data from context engine 113.
Regarding dependent claim 13,
As discussed above with claim 1, Paiz-Gray discloses all of the limitations.
Gray further discloses the step wherein the user input data comprises a natural language prompt or a search query for a chatbot or a search query. See Abstract, (Disclosing a search engine optimizer working independently and in parallel with a browser and search engine to gather, analyze and distill input information interactively. The optimizer reorganizes an input to produce an optimized output that is delivered to the search engine which responds to the end user with search results.) See Col. 26, lines 3-11, (Cholti may process a user's request comprising natural language text to generate an optimal input, i.e. wherein the user input data comprises a natural language prompt or a search query for a chatbot or a search query (e.g. a search query).)
Regarding dependent claim 15,
As discussed above with claim 1, Paiz-Gray discloses all of the limitations.
Paiz further discloses the step wherein the set of web search results is presented to a user via a chatbot or via a search engine results page or via a link to a search engine results page. See FIG. 3 & Col. 26, lines 12-27, (FIG. 3 illustrates a search tool where users may use Cholti to provide search keywords. The interface comprises lists of top sites and top pages retrieved in response to a search request, i.e. wherein the set of web search results is presented to a user via a search engine results page.)
Regarding independent claim 17,
Paiz discloses a system, comprising: a communication interface; See Abstract, (Disclosing a search engine optimizer working independently and in parallel with a browser and search engine to gather, analyze and distill input information interactively. The optimizer reorganizes an input to produce an optimized output that is delivered to the search engine which responds to the end user with search results.) See Col. 37 , lines 48-51, (The system comprises a parallel distributed supercomputer including a large data warehouse that stores a CORE List that consists of statistics for each keyword or cluster used to perform the method of optimizing the Cholti software application, i.e. a system, comprising: a communication interface (e.g. the system is directed to an internet search engine);)
and a processor coupled to the communication interface and configured to: receive a user input data via the communication interface; See Col. 3, lines 45-49, (A user may interact with the Cholti Search Engine Optimizer by providing an end user request comprising keywords, i.e. a processor coupled to the communication interface (e.g. a user interacts with a client device to provide a search request) and configured to: receive a user input data via the communication interface (e.g. the internet search query);)
use the user input data as a first input to a first knowledge retrieval engine configured to generate in response to the first input an intermediate response that is derived at least in part from a set of proprietary data; See Col. 26, lines 6-11, (A user may submit an end user request comprising a sequence of keywords, which triggers a search engine to perform the search.) See Col. 37 , lines 48-51, (The system stores a CORE List that consists of statistics for each keyword or cluster used to perform the method of optimizing the Cholti software application, i.e. use the user input data as an input to a knowledge retrieval engine configured to generate in response to the input a generated response that is derived at least in part from a set of proprietary data (e.g. processing a user input includes executing Cholti software which requires the clusters and information stored in the CORE List);)
wherein the knowledge retrieval engine is a system that provides a response to a natural language chat prompt and/or a search query by leveraging proprietary data to improve an input to a web search engine, wherein the web search engine provides hyperlinks to web and/or internet content in response to a query; See Abstract, (The search query optimizer reorganizes an input to produce an optimized output that is delivered to the search engine which responds to the end user with search results.) See Col. 26, lines 3-11, (Cholti may process a user's request comprising natural language text to generate an optimal input.) See Col. 16, lines 58-65, (Cholti identifies, validates and verifies an input query and rearranges each request go generate an optimal query request.) See FIG. 3 & Col. 26, lines 12-27, (FIG. 3 illustrates a search tool where users may use Cholti to provide search keywords. The interface comprises lists of top sites and top pages retrieved in response to a search request, i.e. wherein the knowledge retrieval engine is a system that provides a response to a natural language chat prompt and/or a search query (e.g. users may submit internet search queries comprising keywords) by leveraging proprietary data (e.g. Note Col. 6, lines 51-54 wherein the process uses clusters comprising groups of keywords that filter the size of the search environment) to improve an input to a web search engine (e.g. Note Abstract wherein the search engine optimizer may reorganize a natural language input to provide an optimized version as output), wherein the web search engine provides hyperlinks to web and/or internet content in response to a query (e.g. the system is directed to an internet search engine, i.e. internet content retrieved in response to a query );)
wherein proprietary data comprises any data unique to an organization or individual, comprising at least one of the following: word processor documents, spreadsheets, slide presentations, natural language documents, tabular data, or knowledge bases; See Col. 37 , lines 48-51, (The system comprises a parallel distributed supercomputer including a large data warehouse that stores a CORE List that consists of statistics for each keyword or cluster used to perform the method of optimizing the Cholti software application, i.e. wherein proprietary data comprises any data unique to an organization or individual, comprising at least knowledge bases (e.g. the CORE List comprise statistics for each keyword or cluster used to generate optimized inputs to a search engine );)
wherein leveraging proprietary data to improve the input to the web search engine comprises adding a structural context and/or a contextual hint that is derived at least in part from the set of proprietary data to the intermediate response; See Col. 4, lines 36-39, (The optimizer reorganizes an input to produce an optimized output that is delivered to the search engine which responds to the end user with search results. Users interact with a Cholti Search Engine Optimizer via a client device which wherein the Cholti software uses mathematical parameters to create smaller, primed and valid and environments that take into account that any given request is not optimal.) See Col. 6, lines 16-39, (The Cholti software performs the following steps: A) identifying each keyword to be valid or invalid and assigns each keyword a raw vector value based on a raw magnitude; B) creating auxiliary variables and a cluster list; C) validating independent variables belonging to a request based on raw hits to see if they are valid by being below a lower limit of page results; D) plotting maps and keywords into a Basic Glyph configuration and determining the estimated Boolean Algebra search value and determining the best preprocessed Basic Glyph, i.e. wherein leveraging proprietary data to improve the input to the web search engine comprises adding a structural context and/or a contextual hint that is derived at least in part from the set of proprietary data to the intermediate response (e.g. generating an optimized input includes using Cholti software to filter a search space, identify keywords and assign vector values to said keywords);)
Paiz does not disclose the step wherein the knowledge retrieval engine comprises an LLM configured for generating web search engine input based at least in part on proprietary data, in part by using the proprietary data to fine-tune the LLM or using the proprietary data to create a searchable index to return extractions to be input to the LLM;
and use the intermediate response comprising the structural context and/or the contextual hint as a second input to a second knowledge retrieval engine configured to generate in response to the second input a generated response that is derived at least in part from the set of proprietary data
Gray discloses the step wherein the knowledge retrieval engine comprises an LLM configured for generating web search engine input based at least in part on proprietary data, in part by using the proprietary data to fine-tune the LLM or using the proprietary data to create a searchable index to return extractions to be input to the LLM; See FIG. 3 & Col. 20, lines 28-34, (FIG. 3 illustrates method 300 comprising step 352 of receiving a query followed by step 354 comprising step 354A wherein the system may generate content based on the query and/or a rewrite of the input query.) See Col. 37 & lines 36-43, (Candidate generative models include an LLM fine-tuned based on an information summarization prompt and a creative LLM fine-tuned based on a creative generation prompt, i.e. wherein the knowledge retrieval engine comprises a large language model (LLM) configured for generating web search engine input based at least in part on proprietary data (e.g. the LLM may be used to rewrite a query), in part by using the proprietary data to fine-tune the LLM (e.g. Note Col. 8, lines 48-54 context determined by a context engine 113 may be used to rewrite a query formulated based on user input);)
and use the intermediate response comprising the structural context and/or the contextual hint as a second input to a second knowledge retrieval engine configured to generate in response to the second input a generated response that is derived at least in part from the set of proprietary data. See Col. 8, lines 43-50, (Context engine 113 may determine a current content based on an active application in the foreground of client device 110 which may be used during the process of supplementing or rewriting a query based on user input, i.e. use the intermediate response comprising the structural context and/or the contextual hint as a second input to a second knowledge retrieval engine (e.g. the rewritten query is used to retrieve data) configured to generate in response to the second input a generated response that is derived at least in part from the set of proprietary data (e.g. the context data ).)
Paiz and Gray are analogous art because they are in the same field of endeavor, search optimization. It would have been obvious to anyone having ordinary skill in the art before the effective filing date to modify the system of Paiz to include the method of re-writing user queries via LLMs as disclosed by Gray. Col. 3, lines 43-55 of Gray disclose that the system may provide augmented LLM prompts that do not rely on hard to codify experience of prompt engineering to enhance search result identification and retrieval.
Regarding dependent claim 19,
As discussed above with claim 17, Paiz-Gray discloses all of the limitations.
Paiz further discloses the step wherein the processor is further configured to use the generated response to generate a set of web search results. See Abstract, (The optimizer reorganizes an input to produce an optimized output that is delivered to the search engine which responds to the end user with search results, i.e. wherein the processor is further configured to use the generated response to generate a set of web search results (e.g. Note FIG. 3 illustrating a list of search results of an internet search including a list of websites).)
Regarding independent claim 20,
The claim is analogous to the subject matter of independent claim 1 directed to a method or process and is rejected under similar rationale.
Regarding independent claim 21,
The claim is analogous to the subject matter of independent claim 17 directed to a method or process and is rejected under similar rationale.
Regarding independent claim 22,
The claim is analogous to the subject matter of independent claim 1 directed to a non-transitory, computer readable medium and is rejected under similar rationale.
Regarding independent claim 23,
The claim is analogous to the subject matter of independent claim 17 directed to a computer system and is rejected under similar rationale.
Claim(s) 7-8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Paiz in view of Grey as applied to claim 1 above, and further in view of Samdani et al. (US Patent No. 11,803,556; Date of Patent: Oct. 31, 2023)
Regarding dependent claim 7,
As discussed above with claim 1, Paiz-Gray discloses all of the limitations.
Paiz-Gray does not disclose the step wherein the proprietary data comprises customer-owned data.
Samdani discloses the step wherein the proprietary data comprises customer-owned data. See Col. 35, lines 35-40, (The system is configured to search a private corpus containing articles available only to users affiliated with the organization that controls the knowledge base, i.e. wherein the proprietary data comprises customer-owned data.)
Paiz, Gray and Samdani are analogous art because they are in the same field of endeavor, search optimization. It would have been obvious to anyone having ordinary skill in the art before the effective filing date to modify the system of Paiz-Gray to include the method of re-writing user queries based on organizational data as disclosed by Samdani. Col. 3, lines 35-41 of Samdami discloses that the process of searching a private corpus allows the system to identify a correct article if it is determined to exist in the knowledge base or route a query to a location that may respond to said query.
Regarding dependent claim 8,
As discussed above with claim 7, Paiz-Gray-Samdani discloses all of the limitations.
Samdani further discloses the step wherein the customer-owned data is associated with a first customer included in a plurality of customers associated with the system, and the customer-owned data is used as the proprietary data only for a subset of the plurality of customers that includes the first customer. See Col. 35, lines 35-40, (The system is configured to search a private corpus containing articles available only to users affiliated with the organization that controls the knowledge base, i.e. wherein the proprietary data comprises customer-owned data (e.g. the knowledge base is associated with an organization comprising users that have access to the private corpus of a knowledge base), and the customer-owned data is used as the proprietary data only for a subset of the plurality of customers that includes the first customer (e.g. the system may provide a SaaS to multiple organizations where users may request information from an organization they are affiliated with).)
Claim(s) 4-6 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Paiz in view of Gray as applied to claim 1 above, and further in view of Hosseini et al. (US PGPUB No. 2023/0297860; Pub. Date: Sep. 21, 2023).
Regarding dependent claim 4,
As discussed above with claim 1, Paiz-Gray discloses all of the limitations.
Paiz-Gray does not disclose the step wherein the knowledge retrieval engine is a searchable index which returns extractions to an LLM.
Hosseini discloses the step wherein the knowledge retrieval engine is a searchable index which returns extractions to an LLM. See Paragraph [0069], (Disclosing a system for generating and transmitting insight according to machine learning models. A service request to perform an action may be received from a client agent, wherein a service request includes a plurality of attributes specified by a user using a graphical user interface of a client device.) See Paragraph [0070], (A service request may be associated with an objective which may be represented as one or more vectors, such that it may be expressed using multiple sets of values or dimensions representing specific aspects or characteristics of the objective. The one or more vectors may be stored and managed in a vector database. A Large Language Model (LLM) is used to embed the context of the service request into a vector, which is then used to query the vector database to find the list of vectors that have a similarity score above a threshold. The list of vectors is then used to select the vectors that best match the criteria for fulfilling the service request, i.e. wherein the knowledge retrieval engine is a searchable index which returns extractions to an LLM (e.g. the large language model is used in conjunction with the vector database to process data contained in service requests).)
Paiz, Gray and Hosseini are analogous art because they are in the same field of endeavor, machine learning models for search systems. It would have been obvious to anyone having ordinary skill in the art before the effective filing date to modify the system of Paiz-Gray to include the method of processing vector data via a large language model in order to process service requests as disclosed by Hosseini. Paragraph [0070] of Hosseini discloses that the use of a large language model allows the system to determine vectors most similar to an input service request such that the ML model selects the best matches for fulfilling said requests. This represents an improvement in the process of servicing user requests.
Regarding dependent claim 5,
As discussed above with claim 4, Paiz-Gray-Hosseini discloses all of the limitations.
Gray further discloses the step wherein the generated response is a hypothetical answer of the LLM to the user input data. See Col. 8, lines 48-54, (Context determined by a context engine 113 may be used to rewrite a query formulated based on user input.) See Col. 10, lines 54-56, (Search system 160 may comprise an SRD engine 162 configured for identifying search result documents responsive to queries, i.e. wherein the generated response is a hypothetical answer of the fine-tuned LLM.)
Paragraph [0041] of Applicant's Specification defines a "hypothetical answer" as "an answer that provides an answer format and/or structure with contextual content associated with the proprietary data". The search result documents of Gray are retrieved and presented to the user based on the LLM output by incorporating context data from context engine 113.
Regarding dependent claim 6,
As discussed above with claim 4, Paiz-Gray-Hosseini discloses all of the limitations.
Gray further discloses the step wherein the generated response is a summary of returned extractions to the LLM. See Co. 10, lines 17-19, (LLM response generation engine 136 may process an LLM input generated by the LLM input engine 134 using an LLM to generate an NL-based summary, i.e. wherein the generated response is a summary of returned extractions to the LLM.)
Regarding dependent claim 18,
As discussed above with claim 17, Paiz-Gray discloses all of the limitations.
Gray further discloses the step wherein the first knowledge retrieval engine is a fine-tuned LLM, See Col. 37 & lines 36-43, (Candidate generative models include an LLM fine-tuned based on an information summarization prompt and a creative LLM fine-tuned based on a creative generation prompt, i.e. wherein the knowledge retrieval engine is a fine-tuned LLM.)
Paiz-Gray does not disclose the step wherein the second knowledge retrieval engine is a searchable index which returns extractions to an LLM.
Hosseini discloses the step wherein the second knowledge retrieval engine is a searchable index which returns extractions to an LLM. See Paragraph [0069], (Disclosing a system for generating and transmitting insight according to machine learning models. A service request to perform an action may be received from a client agent, wherein a service request includes a plurality of attributes specified by a user using a graphical user interface of a client device.) See Paragraph [0070], (A service request may be associated with an objective which may be represented as one or more vectors, such that it may be expressed using multiple sets of values or dimensions representing specific aspects or characteristics of the objective. The one or more vectors may be stored and managed in a vector database. A Large Language Model (LLM) is used to embed the context of the service request into a vector, which is then used to query the vector database to find the list of vectors that have a similarity score above a threshold. The list of vectors is then used to select the vectors that best match the criteria for fulfilling the service request, i.e. wherein the knowledge retrieval engine is a searchable index which returns extractions to an LLM (e.g. the large language model is used in conjunction with the vector database to process data contained in service requests).)
Paiz, Gray and Hosseini are analogous art because they are in the same field of endeavor, machine learning models for search systems. It would have been obvious to anyone having ordinary skill in the art before the effective filing date to modify the system of Paiz-Gray to include the method of processing vector data via a large language model in order to process service requests as disclosed by Hosseini. Paragraph [0070] of Hosseini discloses that the use of a large language model allows the system to determine vectors most similar to an input service request such that the ML model selects the best matches for fulfilling said requests. This represents an improvement in the process of servicing user requests.
Claim(s) 9-12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Paiz in view of Grey as applied to claim 1 above, and further in view of Bloom (US PGPUB No. 2024/0020771; Pub. Date: Jan. 18, 2024).
Regarding dependent claim 9,
As discussed above with claim 1, Paiz-Gray discloses all of the limitations.
Paiz-Gray does not disclose the step wherein the processor is further configured to concatenate the generated response with a second input.
Bloom discloses the step wherein the processor is further configured to concatenate the generated response with a second input. See FIG. 6, (Disclosing a system for generating a pecuniary program generated using machine learning processes. FIG. 6 illustrates method 600 comprising step 605 of receiving a user input relating to a user. Step 635 additionally comprises a step of receiving further feedback.) See Paragraph [0040], (The method may include generating an updated pecuniary program as a function of user feedback by combining all the feedback from a user, i.e. wherein the processor is further configured to concatenate the generated response with a second input (e.g. the combination of first and second feedback used to generate the updated pecuniary program).)
Paiz, Gray and Bloom are analogous art because they are in the same field of endeavor, optimization and usage of generative machine models. It would have been obvious to anyone having ordinary skill in the art before the effective filing date to modify the system of Paiz-Gray to include the method of generating an updated second machine learning model according to a combination of various stages of feedback as disclosed by Bloom. Paragraph [0042] of Bloom discloses that the user feedback is used to indicate what parts of the generated pecuniary program were good, bad and/or how to improve target datasets in order to improve the quality of the generated machine learning models over time.
Regarding dependent claim 10,
As discussed above with claim 9, Paiz-Gray-Bloom discloses all of the limitations.
Bloom further discloses the step wherein the second input is a second generated response of a second knowledge retrieval engine that uses the user input data as input. See Paragraph [0040], (Computing device 104 may train a second machine learning model 156 wherein pecuniary program 144 and user feedback 148 are used as inputs to output updated pecuniary program 152, i.e. wherein the second input is a second generated response of a second knowledge retrieval engine that uses the user input data as input.)
Regarding dependent claim 11,
As discussed above with claim 9, Paiz-Gray-Bloom discloses all of the limitations.
Bloom further discloses the step wherein the second input is the user input data. See FIG. 6 & Paragraph [0064], (FIG. 6 illustrates method 600 comprising step 605 of receiving a user input relating to a user. Step 635 additionally comprises a step of receiving further feedback wherein user feedback may be uploaded and received by the computing device through a user database, i.e. wherein the second input is the user input data.)
Claim(s) 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Paiz in view of Gray and Bloom as applied to claim 9 above, and further in view of Jain et al. (US Patent No. 11,947,923; Date of Patent: Apr. 2, 2024).
Regarding dependent claim 12,
As discussed above with claim 9, Paiz-Gray-Bloom discloses all of the limitations.
Paiz-Gray-Bloom does not disclose the step wherein the second input is a reformulated user input data that reflects context of a user input data history.
Jain discloses the step wherein the second input is a reformulated user input data that reflects context of a user input data history. See FIG. 3 & Col. 17, lines 7-14, (Method 300 comprises step 354 of generating an LLM input from the NL based input and including a context for processing by the LLM. Note Coo. 6, lines 12-25 wherein context data may be determined by a context engine 113 and may include user interaction data that characterizes current or recent interactions of client device 110 and/or a user of the client device 110, i.e. wherein the second input (e.g. the LLM input includes the NL based input and context data) is a reformulated user input data that reflects context of a user input data history (e.g. context data includes current or recent interaction data).)
Paiz, Gray, Bloom and Jain are analogous art because they are in the same field of endeavor, AI-based search systems. It would have been obvious to anyone having ordinary skill in the art before the effective filing date to modify the system of Paiz-Gray-Bloom to include the method of re-writing user queries via LLMs as disclosed by Jain. Col. 11, lines 5-18 of Jain disclose that the multimedia content management system 120 is rendered at client device 110 to ensure data security for a user s maintained in order to mitigate and/or eliminate occurrences of nefarious activity. The system may also process requests via parallel processing which results in a reduction in latency in causing responses to be rendered at the client device.
Claim(s) 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Paiz in view of Gray as applied to claim 1 above, and further in view of PELED (US PGPUB No. 2024/0037170; Pub. Date: Feb. 1, 2024).
Regarding dependent claim 14,
As discussed above with claim 1, Paiz-Gray discloses all of the limitations.
Paiz-Gray does not disclose the step wherein the set of proprietary data is at least one of: a set of customer defined data and a set of customer owned data.
PELED discloses the step wherein the set of proprietary data is at least one of: a set of customer defined data and a set of customer owned data. See Paragraph [0202], (The value-based search may derive benefit parameters that could be useful or of interest to a user 202 based on one or more data points identified and/or assumed for the user according to trends, correlation, past usage, user data, etc., i.e. wherein the set of proprietary data is at least a set of customer owned data (e.g. Note [0182] wherein user attribute data is stored in client device 200.)
Paiz, Gray and PELED are analogous art because they are in the same field of endeavor, knowledge base data retrieval. It would have been obvious to anyone having ordinary skill in the art before the effective filing date to modify the system of Paiz-Gray to include the method of using a large language model to retrieve data as disclosed by PELED. Paragraph [0201] of PELED discloses that the system may identify a particular users interests, which allows the search engine to identify and select consumable items that are more appropriate and/or fitting for the identified user in terms of knowledge, language, style and/or needs specific to the respective user.
Claim(s) 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Paiz in view of Gray as applied to claim 1 above, and further in view of DeLuca et al. (US PGPUB No. 2018/0067912; Pub. Date: Mar. 8, 2018).
Regarding dependent claim 16,
As discussed above with claim 1, Paiz-Gray discloses all of the limitations.
Paiz-Gray does not disclose the step wherein the processor is further configured to provide query compression in an event the generated response is larger than a specified limit.
DeLuca discloses the step wherein the processor is further configured to provide query compression in an event the generated response is larger than a specified limit. See Paragraph [0003], (Disclosing a system for enabling reduction of characters in a character-limited scenario by minimally editing a text to remain within a character limit. A user may enter text into a character-limited field wherein the system may shorten the text entered by the user to bring the entered text within the character limit of the character-limited field. Note [0070] wherein machine learning models may be used to derive emotion scores from text in order to improve the accuracy of the character reduction alternatives, i.e. wherein the processor is further configured to provide query compression in an event the generated response is larger than a specified limit.
Paiz, Gray and DeLuca are analogous art because they are in the same field of endeavor, optimization and usage of generative machine models. It would have been obvious to anyone having ordinary skill in the art before the effective filing date to modify the system of Paiz-Gray to include the method of editing a user-input text to maintain a particular character limit as disclosed by DeLuca. Paragraph [0060] of DeLuca discloses that the process presents the following advantages: maintaining an author's original tone, adjusting character reduction as an author writes, and enhancing and optimizing user experiences by not requiring a user to consciously limit characters while typing. Embodiments of the present invention reduce the characters in a message to fit within a prescribed length by removing as little material as required from the original content.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1, 17 and 20-23 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant’s amendments necessitated the new grounds of rejection presented in this Office Action.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Fernando M Mari whose telephone number is (571)272-2498. The examiner can normally be reached Monday-Friday 7am-4pm.
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, Ann J. Lo can be reached at (571) 272-9767. 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.
/FMMV/Examiner, Art Unit 2159
/ANN J LO/Supervisory Patent Examiner, Art Unit 2159
Prosecution Insights