DETAILED ACTION
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
2. This action is in response to application filed on 3/28/2025, in which claims 1 – 20 was presented for examination.
3. Claims 1 – 20 are pending in the application.
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.
4. Claims 1 - 7 are rejected under 35 U.S.C. 103 as being unpatentable over Lee et al (US 2025/0299675 A1), in view of Shevelev et al (US 2022/0391595 A1).
As per claim 1, Lee et al (US 2025/0299675 A1) discloses,
A computer-implemented method of generating questions in response to a user input (para.[0014]; “response is generated based on system-generated questions associated with the user input”).
the method comprising: receiving a natural language input from a graphical user interface of a client application operating on a client device (para.[0005]; “generating a natural language response to a user input”).
submitting a first request to a first service to obtain a first set of recommended data item queries (para.[0021]; “Based on the dialog history, the system may generate a first plurality of natural language questions corresponding to an entity represented in the dialog history”).
and submitting a second request to a knowledge-base service to obtain a second set of recommended data item queries (para.[0027]; “using a second trained ML component: (1) the first natural language user input and the first natural language question to determine the first natural language question is semantically similar to the first input”).
the second set of recommended data item queries generated by: identifying a knowledge base document of a set of knowledge base documents (para.[0022]; “the second natural language question to determine the second natural language question is semantically similar to the dialog history” and para.[0065]; “the knowledge data to determine natural language question data (e.g., 325) corresponding to a next natural language question corresponding”).
generating a data item query prompt comprising predetermined first query prompt text, text from the knowledge base document, and the natural language input (para.[0027]; “using a fourth trained ML component, the first natural language user input, the first natural language question, the second natural language question, the first natural language answer, and the second natural language answer to determine: (1) a first likelihood that that presentation of a first output associated with the first natural language answer will result in a satisfactory user experience”).;
providing the data item query prompt to a generative output engine and receiving, from the generative output engine, the second set of recommend data item queries (para.[0028]; “process the first natural language user input and the first natural language question to generate metadata associated with a context of the first natural language answer, where the metadata corresponds to natural language of a document” and para.[0039]; “filter (154) the first answer data based on responsiveness to determine the second answer data using an answer ranking component”).
analyzing the first and second sets of recommended data item queries to identify a subset of data item queries for which answers were not included in the natural language input (para.[0029]; “trained machine learning (ML) component configured to generate a natural language question configured to elicit a factual response, the first natural language user input to generate the first natural language question”).
for a data item query of the identified subset of data item queries, generating a natural language query string for eliciting, from a user, an answer to the data item query, comprising: generating a question generation prompt comprising predetermined second query prompt text and the data item query (para.[0028]; “process the first natural language user input and the first natural language question to generate metadata associated with a context of the first natural language answer, where the metadata corresponds to natural language of a document”).
providing the question generation prompt to the generative output engine and receiving the natural language query string from the generative output engine (para.[0030]; “processing, using a second trained ML component, dialog history and a third natural language answer to generate a third natural language question; (2) processing, using an third ML component, the dialog history to generate a fourth natural language question”).
causing display of the natural language query string to the user (claim 2; “display, the first system-generated natural language response data and the second system-generated natural language response data”).
receiving, from the user, a response including the answer to the data item query; generating an issue record including the answer to the data item query; and storing the issue record in association with an issue tracking system (para.[0056]; “stored in the knowledge source(s) storage 190, for example, in response to the knowledge data being used by the system 100 for processing with respect to a user input. In some embodiments, the knowledge source(s) storage 190 may include a knowledge graph representing associations between portions of knowledge data and example user inputs/system-generated responses (e.g., dialog history data 164) associated with the knowledge data”).
Lee does not specifically disclose analyzing the natural language input using a support-request analysis engine to determine a sufficiency condition, in accordance with a determination that the sufficiency condition is not satisfied.
However, Shevelev et al (US 2022/0391595 A1) in an analogous art discloses,
analyzing the natural language input using a support-request analysis engine to determine a sufficiency condition (para.[0038]; “the question and answer analysis engine 124 may analyze content in a question and determine that the question contains insufficient information to generate an answer …. the determination of the need for additional information to the question and answer generator engine 127 to generate a follow-up question” and para.[0059]; “system determines whether the question contains sufficient information to generate an answer”)
in accordance with a determination that the sufficiency condition is not satisfied (para.[0060]; “If the system determines that the question contains insufficient information to generate an answer, the system generates a clarifying question”)
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate process of identifying question in a discussion of the system of Shevelev into natural language processing of the system of Lee to provides the answer to the discussion environment and updates answers based on community members feedback.
As per claim 2, the rejection of claim 1 is incorporated and further Lee et al (US 2025/0299675 A1) discloses,
further comprising, prior to generating the natural language query string for eliciting the answer to the data item query (para.[0029]; “using a first trained machine learning (ML) component configured to generate a natural language question configured to elicit a factual response, the first natural language user input to generate the first natural language question”).
ranking the subset of data item queries for which answers were not included in the natural language input based on relevance of the data item queries to a subject of the natural language input (para.[0033]; “filtering the answers based on a relevance to the dialog and a responsiveness of the determined answer ( e.g., whether the answer is responsive to the question”).
comprising: generating a relevance inquiry prompt comprising predetermined third query prompt text, text from the subset of data item queries, and the natural language input (para.[0028]; “process the first natural language user input and the first natural language question to generate metadata associated with a context of the first natural language answer, where the metadata corresponds to natural language of a document”).
providing the relevance inquiry prompt to the generative output engine and receiving, from the generative output engine, a ranking of the data item queries of the subset of data item queries (para.[0033]; “the system generates a response to the user input based on the user input, a dialog history, the questions, and the answers, where the questions, answers, and any data contextually supportive of the answers are of a size that allow the system to perform cross-attention across the dialog history and the questions, answers, and contextually supportive data”).
and selecting, based on the ranking, at least one data item query from the subset of data item queries as the data item query (para.[0033]; “based on the responses being generated based on the answers and contextually supportive data, the system is capable of providing the coherent and engaging responses to the user inputs”).
As per claim 3, the rejection of claim 1 is incorporated and further Lee et al (US 2025/0299675 A1) and discloses,
further comprising: removing, from the subset of data item queries, data item queries that are not supported by a support-request interaction type associated with the natural language input, thereby creating a list of candidate data item queries; and selecting the data item query from the list of candidate data item queries (para.[0029]; “Using a second trained ML component configured to generate a natural language question configured to elicit a response including at least two words, the system may process the first natural language user input to generate the second natural language question”).
As per claim 4, the rejection of claim 1 is incorporated and further Shevelev et al (US 2022/0391595 A1) discloses,
wherein: the method further comprises, in accordance with a determination that the sufficiency condition is not satisfied (para.[0059]; “system determines whether the question contains sufficient information to generate an answer”)
Lee et al (US 2025/0299675 A1) discloses,
submitting a third request to a second service to obtain a third set of recommended data item queries, the third set of recommended data item queries associated with a term included in the natural language input (para.[0029]; “trained machine learning (ML) component configured to generate a natural language question configured to elicit a factual response, the first natural language user input to generate the first natural language question”).
and analyzing the first and second sets of recommended data item queries to identify the subset of data item queries for which answers were not included in the natural language input further comprises analyzing the third set of recommended data item queries to identify the subset of data item queries for which answers were not included in the natural language input (para.[0027]; “using a fourth trained ML component, the first natural language user input, the first natural language question, the second natural language question, the first natural language answer, and the second natural language answer to determine: (1) a first likelihood that that presentation of a first output associated with the first natural language answer will result in a satisfactory user experience”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate process of identifying question in a discussion of the system of Shevelev into natural language processing of the system of Lee to provides the answer to the discussion environment and updates answers based on community members feedback.
As per claim 5, the rejection of claim 1 is incorporated and further Shevelev et al (US 2022/0391595 A1) discloses,
wherein analyzing the natural language input to determine the sufficiency condition comprises providing the natural language input as an input to a machine learning model that is trained on a dataset including respective natural language inputs associated with respective sufficiency determinations (para.[0038]; “the question and answer analysis engine 124 may analyze content in a question and determine that the question contains insufficient information to generate an answer …. the determination of the need for additional information to the question and answer generator engine 127 to generate a follow-up question” and para.[0059]; “system determines whether the question contains sufficient information to generate an answer”)
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate process of identifying question in a discussion of the system of Shevelev into natural language processing of the system of Lee to provides the answer to the discussion environment and updates answers based on community members feedback.
As per claim 6, the rejection of claim 1 is incorporated and further Lee et al (US 2025/0299675 A1) discloses,
wherein identifying the knowledge base document of the set of knowledge base documents comprises determining that the knowledge base document is associated with the client application (para.[0022]; “the second natural language question to determine the second natural language question is semantically similar to the dialog history” and para.[0065]; “the knowledge data to determine natural language question data (e.g., 325) corresponding to a next natural language question corresponding”).
As per claim 7, the rejection of claim 1 is incorporated and further Lee et al (US 2025/0299675 A1) discloses,
wherein: the method further comprises receiving an identifier of the client application and the first service selects the first set of recommended data item queries based on the identifier of the client application (para.[0051]; “the dialog storage may be queried using a user identifier of the user 105 and/or a device identifier of the user device 110 and/or a dialog identifier associated with the user input data”).
5. Claims 8 – 20 are rejected under 35 U.S.C. 103 as being unpatentable over Lee et al (US 2025/0299675 A1), in view of Meeter et al (US 2025/0370992 A1)
As per claim 8, Lee et al (US 2025/0299675 A1) discloses,
A computer-implemented method of generating questions in response to a user input (para.[0014]; “response is generated based on system-generated questions associated with the user input”).
the method comprising: receiving a natural language input from a graphical user interface of a client application operating on a client device (para.[0005]; “generating a natural language response to a user input”).
submitting a first request to a first service to obtain a first set of recommended data item queries (para.[0021]; “Based on the dialog history, the system may generate a first plurality of natural language questions corresponding to an entity represented in the dialog history”).
submitting a second request to a knowledge-base service to obtain a second set of recommended data item queries (para.[0022]; “the dialog history and the second natural language question to determine the second natural language question is semantically similar to the dialog history” and para.[0056]; “query the knowledge source(s) storage 190 for knowledge data”).
the second set of recommended data item queries including text extracted from at least one knowledge base document of a set of knowledge base documents (para.[0022]; “the second natural language question to determine the second natural language question is semantically similar to the dialog history” and para.[0065]; “the knowledge data to determine natural language question data (e.g., 325) corresponding to a next natural language question corresponding”).
ranking a group of recommended data item queries from the first and second sets of recommended data item queries based on a relevance of the recommended data item queries to a subject of the natural language input (para.[0022]; “Based on determining the first natural language question is semantically similar to the dialog history and determining the second natural language question is semantically similar to the dialog history”, para.[0037]; “filter (150) the first question data based on relevance to determine the second question data using a question ranking component”, para.[0065]; “process the dialog history data and the knowledge data to determine natural language question data (e.g., 325) corresponding to a next natural language question corresponding to the dialog history data. The resulting natural language question data may be combined with the dialog history data to generate a dataset including the dialog history data and the natural language question data. The dataset may be used to train a ML model”).
comprising: generating a first prompt comprising predetermined first query prompt text, text from the group of recommended data item queries, and the natural language input (para.[0023]; “using a first trained machine learning (ML) component, the dialog history to generate the first plurality of natural language questions” and para.[0029]; “using a first trained machine learning (ML) component configured to generate a natural language question configured to elicit a factual response, the first natural language user input to generate the first natural language question”).
providing the first prompt to a generative output engine and receiving, from the generative output engine, a ranking of the recommended data item queries of the group of recommend data item queries (para.[0028]; “process the first natural language user input and the first natural language question to generate metadata associated with a context of the first natural language answer, where the metadata corresponds to natural language of a document” and para.[0039]; “filter (154) the first answer data based on responsiveness to determine the second answer data using an answer ranking component”).
for the selected at least one data item query, generating a natural language query string for eliciting, from a user, an answer to the at least one data item query (para.[0029]; “trained machine learning (ML) component configured to generate a natural language question configured to elicit a factual response, the first natural language user input to generate the first natural language question”).
causing display of the natural language query string to the user (claim 2; “display, the first system-generated natural language response data and the second system-generated natural language response data”).
receiving, from the user, a response including the answer to the at least one data item query and storing the answer to the at least one data item query in association with the natural language input (NOTE: para.[0021]; “After determining the first plurality of natural language questions, the system may generate a first natural language answer responsive to the first natural language question” and para.[0056]; “stored in the knowledge source(s) storage 190, for example, in response to the knowledge data being used by the system 100 for processing with respect to a user input. In some embodiments, the knowledge source(s) storage 190 may include a knowledge graph representing associations between portions of knowledge data and example user inputs/system-generated responses (e.g., dialog history data 164) associated with the knowledge data”).
Lee does not specifically disclose generating a first prompt comprising predetermined first query prompt text, text from the group of recommended data item queries, and the natural language input, providing the first prompt to a generative output engine and receiving, from the generative output engine, a ranking of the recommended data item queries of the group of recommend data item queries, selecting, based on the ranking, at least one data item query from the recommended data item queries.
However, Meeter et al (US 2025/0370992 A1) in an analogous art discloses,
comprising: generating a first prompt comprising predetermined first query prompt text, text from the group of recommended data item queries, and the natural language input (para.[0021]; “obtaining query contextual information for the first query and/or generating prompt data to prompt a user to provide clarification information” and para.[0181]; “Using natural language generation techniques to create an appropriate prompt (e.g., based on identified concepts associated with the possible answers that are creating the ambiguity”).
providing the first prompt to a generative output engine and receiving, from the generative output engine, a ranking of the recommended data item queries of the group of recommend data item queries (para.[0181] “para.[0181]; “message to the user may list the different computing systems, and ask the user to specify which one the user needs information for”).
selecting, based on the ranking, at least one data item query from the recommended data item queries (para.[0020]; “selecting at least one of the multiple matches based on the obtained disambiguation information relevant to the at least one of the one or more identified ambiguity categories” and para.[0181]; “message to the user may list the different computing systems, and ask the user to specify which one the user needs information for”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate process of disambiguating of user input of the system of Meeter into natural language processing of the system of Lee to achieve improved training and ingestion of machine learning Q-A systems, and improved question/query processing (see Meeter para.[0002]).
As per claim 9, the rejection of claim 8 is incorporated and further Lee et al (US 2025/0299675 A1) discloses,
wherein submitting the second request to the knowledge-base service comprises: identifying a knowledge base document of a set of knowledge base documents (para.[0022]; “the dialog history and the second natural language question to determine the second natural language question is semantically similar to the dialog history” and para.[0056]; “query the knowledge source(s) storage 190 for knowledge data”).
generating a data item query prompt comprising predetermined third query prompt text, text from the knowledge base document, and the natural language input (para.[0023]; “using a first trained machine learning (ML) component, the dialog history to generate the first plurality of natural language questions”)
providing the data item query prompt to the generative output engine; and receiving, from the generative output engine, the second set of recommend data item queries (para.[0028]; “process the first natural language user input and the first natural language question to generate metadata associated with a context of the first natural language answer, where the metadata corresponds to natural language of a document”).
As per claim 10, the rejection of claim 8 is incorporated and further Meeter et al (US 2025/0370992 A1) discloses,
further comprising, prior to ranking the group of recommended data item queries, selecting the group of recommended data item queries from the first and second sets of recommended data item queries by identifying, in the first and second sets of recommended data item queries, data item queries for which answers were not included in the natural language input (para.[0092]; “the processes relate to analyzing a query, prior to executing the query, to determine, and if possible, resolve, various issues of ambiguity related to the submitted query”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate process of disambiguating of user input of the system of Meeter into natural language processing of the system of Lee to achieve improved training and ingestion of machine learning Q-A systems, and improved question/query processing (see Meeter para.[0002]).
As per claim 11, the rejection of claim 8 is incorporated and further Lee et al (US 2025/0299675 A1) discloses,
further comprising: prior to ranking the group of recommended data item queries, analyzing the first and second sets of recommended data item queries to identify a subset of data item queries for which answers were not included in the natural language input; and selecting the subset of data item queries as the group of recommended data item queries (para.[0065]; “process the dialog history data and the knowledge data to determine natural language question data (e.g., 325) corresponding to a next natural language question corresponding to the dialog history data. The resulting natural language question data may be combined with the dialog history data to generate a dataset including the dialog history data and the natural language question data. The dataset may be used to train a ML model”).
As per claim 12, the rejection of claim 11 is incorporated and further Meeter et al (US 2025/0370992 A1) discloses,
wherein: the method further comprises submitting a third request to a second service to obtain a third set of recommended data item queries, the third set of recommended data item queries associated with a term included in the natural language input (para.[0006]; “alternative queries to those submitted by the user, or correcting deficiencies in the submitted queries. Those solutions include iterative refinements through disambiguation techniques, re-writing queries to generate supplemental queries”).
and analyzing the first and second sets of recommended data item queries to identify the subset of data item queries for which answers were not included in the natural language input further comprises analyzing the third set of recommended data item queries to identify the subset of data item queries for which answers were not included in the natural language input (para.[0157]; “activate a disambiguation process that requests further specificity from the user, or alternatively may infer the missing information (e.g., the model number) based on contextual information”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate process of disambiguating of user input of the system of Meeter into natural language processing of the system of Lee to achieve improved training and ingestion of machine learning Q-A systems, and improved question/query processing (see Meeter para.[0002]).
As per claim 13, the rejection of claim 8 is incorporated and further Meeter et al (US 2025/0370992 A1) discloses,
wherein the graphical user interface is a support request graphical user interface associated with the client application (para.[0170]; “This mechanism is referred to as visual QA. Because the answers for the next lower level are displayed, the user is given the option to select answers resulting from a deterministic process”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate process of disambiguating of user input of the system of Meeter into natural language processing of the system of Lee to achieve improved training and ingestion of machine learning Q-A systems, and improved question/query processing (see Meeter para.[0002]).
As per claim 14, the rejection of claim 8 is incorporated and further Lee et al (US 2025/0299675 A1) discloses,
further comprising: generating an issue record including the answer to the at least one data item query and storing the issue record in association with an issue tracking system (para.[0056]; “stored in the knowledge source(s) storage 190, for example, in response to the knowledge data being used by the system 100 for processing with respect to a user input. In some embodiments, the knowledge source(s) storage 190 may include a knowledge graph representing associations between portions of knowledge data and example user inputs/system-generated responses (e.g., dialog history data 164) associated with the knowledge data”).
As per claim 15, Lee et al (US 2025/0299675 A1) discloses,
A system of a support platform, the system comprising: one or more processing units; computer readable memory storing computer readable instructions that when executed by the one or more processing units cause the system to (para.[0140]; “systems may include computer-readable and computer-executable instructions that reside on the respective device”).
receive a natural language input, the natural language input provided to a support request graphical user interface of a client application operating on a client device (para.[0005]; “generating a natural language response to a user input”).
obtain a set of recommended data item queries (para.[0021]; “Based on the dialog history, the system may generate a first plurality of natural language questions corresponding to an entity represented in the dialog history”).
comprising: identifying a knowledge base document of a set of knowledge base documents (para.[0056]; “query the knowledge source(s) storage 190 for knowledge data”).
generating a first prompt comprising predetermined first query prompt text, text from the knowledge base document, and the natural language input (para.[0023]; “using a first trained machine learning (ML) component, the dialog history to generate the first plurality of natural language questions” and para.[0029]; “using a first trained machine learning (ML) component configured to generate a natural language question configured to elicit a factual response, the first natural language user input to generate the first natural language question”).
providing the first prompt to a generative output engine and receiving, from the generative output engine, at least a portion of the set of recommend data item queries (para.[0028]; “process the first natural language user input and the first natural language question to generate metadata associated with a context of the first natural language answer, where the metadata corresponds to natural language of a document” and para.[0039]; “filter (154) the first answer data based on responsiveness to determine the second answer data using an answer ranking component”).
analyze the set of recommended data item queries to identify a subset of data item queries for which answers were not included in the natural language input (para.[0029]; “trained machine learning (ML) component configured to generate a natural language question configured to elicit a factual response, the first natural language user input to generate the first natural language question”).
the analyzing comprising, for a recommended data item query of the set of recommended data item queries (para.[0027]; “using a fourth trained ML component, the first natural language user input, the first natural language question, the second natural language question, the first natural language answer, and the second natural language answer to determine: (1) a first likelihood that that presentation of a first output associated with the first natural language answer will result in a satisfactory user experience”).
generating a second prompt comprising predetermined second query prompt text, the recommended data item query, and the natural language input (para.[0028]; “process the first natural language user input and the first natural language question to generate metadata associated with a context of the first natural language answer, where the metadata corresponds to natural language of a document”).
providing the second prompt to the generative output engine (para.[0030]; “processing, using a second trained ML component, dialog history and a third natural language answer to generate a third natural language question; (2) processing, using an third ML component, the dialog history to generate a fourth natural language question”).
receiving, from the generative output engine, a generative response; and analyzing the generative response to determine whether an answer to the recommended data item query was included in the natural language input (para.[0064]; “question generator component 310 may be tasked with processing the natural language response data and the dialog history data to determine natural language question data (e.g., 315) corresponding to the natural language question that resulted in the natural language response corresponding to the natural language response data”).
and in accordance with a determination that the answer to the recommended data item query was not included in the natural language input: generate a natural language query string for eliciting the answer to the recommended data item query (para.[0029]; “Using a second trained ML component configured to generate a natural language question configured to elicit a response including at least two words, the system may process the first natural language user input to generate the second natural language question”).
cause display of the natural language query string in the support request graphical user interface (claim 2; “display, the first system-generated natural language response data and the second system-generated natural language response data”).
receive a response including the answer to the recommended data item query; and store the answer to the recommended data item query in association with the natural language input (para.[0056]; “stored in the knowledge source(s) storage 190, for example, in response to the knowledge data being used by the system 100 for processing with respect to a user input. In some embodiments, the knowledge source(s) storage 190 may include a knowledge graph representing associations between portions of knowledge data and example user inputs/system-generated responses (e.g., dialog history data 164) associated with the knowledge data”).
The Examiner believes Lee et al (US 2025/0299675 A1) fully anticipates each and every feature of claim 1. However to explicitly explained the process of generate a natural language query string for eliciting the answer to the recommended data item query (Meeter: para.[00157]; “determination that the query is not sufficiently specific, or is missing some query information (concepts)”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate process of disambiguating of user input of the system of Meeter into natural language processing of the system of Lee to achieve improved training and ingestion of machine learning Q-A systems, and improved question/query processing (see Meeter para.[0002]).
As per claim 16, the rejection of claim 15 is incorporated and further Lee et al (US 2025/0299675 A1) discloses,
wherein: generating the natural language query string comprises: generating a question generation prompt comprising predetermined second query prompt text and the recommended data item query (para.[0030]; “processing, using a second trained ML component, dialog history and a third natural
language answer to generate a third natural language question”).
providing the question generation prompt to the generative output engine; and receiving the natural language query string from the generative output engine (para.[0031]; “system may process, using a second ML component, the first natural language user input and the NLU output data to generate a second output”).
As per claim 17, the rejection of claim 15 is incorporated and further Lee et al (US 2025/0299675 A1) discloses,
wherein: the portion of the set of recommended data item queries is a first portion; obtaining the set of recommended data item queries further comprises: receiving an identifier of the client application; and submitting a request to a service to obtain a second portion of the set of recommended data item queries (para.[0051]; “the dialog storage may be queried using a user identifier of the user 105 and/or a device identifier of the user device 110 and/or a dialog identifier associated with the user input data”).
the request including the identifier of the client application and the service selects the second portion of the recommended data item queries based on the identifier of the client application (para.[0051]; “the dialog storage may be queried using a user identifier of the user 105 and/or a device identifier of the user device 110 and/or a dialog identifier associated with the user input data”).
As per claim 18, the rejection of claim 17 is incorporated and further Lee et al (US 2025/0299675 A1) discloses,
wherein obtaining the set of recommended data item queries further comprises submitting a second request to an additional service to obtain a third portion of the recommended data item queries, the third portion of the recommended data item queries associated with a term included in the natural language input (para.[0030]; “processing, using an third ML component, the dialog history to generate a fourth natural language question; (3) determining a similarity between the third natural language question and the third natural language question; and ( 4) based on the similarity, determining the first trained ML component as an update of the third ML component”).
As per claim 19, the rejection of claim 15 is incorporated and further Lee et al (US 2025/0299675 A1) discloses,
wherein the computer readable instructions further cause the system to: generate an issue record including the answer to the recommended data item query and store the issue record in association with an issue tracking system (para.[0056]; “stored in the knowledge source(s) storage 190, for example, in response to the knowledge data being used by the system 100 for processing with respect to a user input. In some embodiments, the knowledge source(s) storage 190 may include a knowledge graph representing associations between portions of knowledge data and example user inputs/system-generated responses (e.g., dialog history data 164) associated with the knowledge data”).
As per claim 20, the rejection of claim 15 is incorporated and further Meeter et al (US 2025/0370992 A1) discloses,
wherein the computer readable instructions further cause the system to, prior to analyzing the set of recommended data item queries to identify the subset of data item queries for which answers were not included in the natural language input, remove, from the set of recommended data item queries, recommended data item queries that are not supported by a support request interaction type associated with the natural language input (para.[0092]; “the processes relate to analyzing a query, prior to executing the query, to determine, and if possible, resolve, various issues of ambiguity related to the submitted query”).
Therefore, it would have been obvious to one of ordinary skill in the art before the invention was filed to incorporate process of disambiguating of user input of the system of Meeter into natural language processing of the system of Lee to achieve improved training and ingestion of machine learning Q-A systems, and improved question/query processing (see Meeter para.[0002]).
Conclusion
6. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
TITLE: Integrated self-evaluation and follow-up suggestion mechanism for RAG system, US 2026/0093722 A1 authors: Peter Gerardus Jansen (see para.[0020] and para.[0030).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AUGUSTINE KUNLE OBISESAN whose telephone number is (571)272-2020. The examiner can normally be reached 9:00am - 5:00.
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, Ajay Bhatia can be reached at (571) 272-3906. 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.
/AUGUSTINE K. OBISESAN/
Primary Examiner
Art Unit 2156
10/11/2026
Prosecution Insights