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 .
Information Disclosure Statement
The information disclosure statement(s) (IDS) submitted on April 24, 2025 and July 16, 2026 are being considered by the examiner.
Claim Objections
Claim 5 and 13 are objected to because of the following informalities: Claim 5 and 13 should state “a user context” instead of “user context”.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 4, 8, 12, 16, and 20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claim 4, 12 and 20 the claims state ” fields that have been made available”. The phrase is unclear because the claim does not specify what makes fields available and where the available fields are identified. This fails to identify what component or configuration makes the fields available or the objective criteria by which such availability is determined.
Regarding claim 8 and 16, the claims state “ past elements of a conversation”. This phrase is unclear because the claim does not specify what encompass prior user messages, chatbot responses, generated queries, query results, etc.
Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim [1-20] rejected under 35 U.S.C. 101 because the claimed invention is directed to
mental process without significantly more.
Regarding claim 1, A system comprising: at least one hardware processor; a non-transitory computer-readable medium storing instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations comprising: receiving a natural language request via a chatbot user interface; matching the natural language request to a first scenario of a plurality of scenarios managed by a chatbot runtime, the first scenario defining three functions for accessing data in an Enterprise Resource Planning (ERP) system; executing a first function of the three functions, causing a query runtime to: generate a first prompt using the natural language request and the first scenario; send the first prompt to a Large Language Model (LLM); and receive a structured query, in a language corresponding to the ERP system, from the LLM; executing a second function of the three functions, causing the query runtime to run the structured query on the ERP system to retrieve ERP data; and executing a third function of the three functions, causing the query runtime to render the ERP data in the chatbot user interface.
[A person could receive a question, select the applicable scenario, formulate an ERP query according to scenario, submit the query, retrieve the results, and present to the requester. ].
As described above, these limitations can be carried out as a series of mental steps.
This judicial exception is not integrated into a practical application because the only additional elements recited are the processor, non-transitory computer-readable medium , chatbot user interface, LLM, and a ERP system and these additional elements are nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the processor, non-transitory computer-readable medium , chatbot user interface, LLM, and a ERP system, and these additional elements are nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 2, The system of claim 1, wherein the first scenario additionally defines a first user interface configuration, and wherein the executing of the third function further comprises altering display parameters of the chatbot user interface based on the first user interface configuration.
[A person could follow predetermined presentation instructions and arrange the retrieved information as a table, chart, or list, or another specified format.]
As described above, these limitations can be carried out as a series of mental steps.
This judicial exception is not integrated into a practical application because the only additional element recited are the user interface and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the user interface is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 3, The system of claim 1, wherein the executing the first function further causes the query runtime to post-process the structured query prior to execution of the second function.
[A person could review and correct a query before submitting it to the ERP system.]
As described above, these limitations can be carried out as a series of mental steps. This judicial exception is not integrated into a practical application because the only additional elements recited is the computer system and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the computer system is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 4, The system of claim 3, wherein the post-processing further comprises analyzing one or more statements in the structured query to ensure that only fields that have been made available for displaying or filtering are contained in the one or more statements.
[A person could compare the query fields against a list of approved display and filter fields and remove or reject unauthorized fields.].
As described above, these limitations can be carried out as a series of mental steps. This judicial exception is not integrated into a practical application because the only additional elements recited is the computer system and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the computer system is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 5, The system of claim 1, wherein the first prompt further comprises user context.
[A person could consider the requester’s identity, role, permissions, or preferences when preparing the request.]
As described above, these limitations can be carried out as a series of mental steps. This judicial exception is not integrated into a practical application because the only additional elements recited is the computer system and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the computer system is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 6, The system of claim 1, wherein the first prompt further comprises one or more hints provided by a designer of the first scenario, the one or more hints comprising at least one definition, not available in a data model of the first scenario, of one or more terms. prompting a third machine-learned language model to identify one or more claims associated with the first textual content; or prompting a third machine-learned language model to generate a query associated with at least one of the one or more claims.
[A person could consult designer provided definitions, instructions when translating unfamiliar business terminology].
As described above, these limitations can be carried out as a series of mental steps.
This judicial exception is not integrated into a practical application because the only additional elements recited is the computer system and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the computer system is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 7, The system of claim 1, wherein the first prompt further comprises application context.
[A person could consider the relevant applications’ purpose, configuration, or operating environment when interpreting the request].
As described above, these limitations can be carried out as a series of mental steps.
This judicial exception is not integrated into a practical application because the only additional elements recited is the computer system and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the computer system is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 8, The system of claim 1, wherein the first prompt further comprises past elements of a conversation in the chatbot user interface.
[A person could review earlier questions and answers to understand the current request and formulate the appropriate query. ]
As described above, these limitations can be carried out as a series of mental steps.
This judicial exception is not integrated into a practical application because the only additional element recited are a computer system and a chatbot user interface and these additional elements are nothing more than generic computer implementing the mental process using general-purpose software and general-purpose hardware. Chain of thought promoting uses a generally recited language model to automate human reasoning and query formulation and therefore does not add significantly more to the abstract idea.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the only additional elements recited are a chatbot user interface and a computer system and these additional elements are nothing more than instructions to apply the mental process using general-purpose software and hardware.
Regarding claim 9, A method comprising: receiving a natural language request via a chatbot user interface; matching the natural language request to a first scenario of a plurality of scenarios managed by a chatbot runtime, the first scenario defining three functions for accessing data in an Enterprise Resource Planning (ERP) system; executing a first function of the three functions, causing a query runtime to: generate a first prompt using the natural language request and the first scenario; send the first prompt to a Large Language Model (LLM); and receive a structured query, in a language corresponding to the ERP system, from the LLM; executing a second function of the three functions, causing the query runtime to run the structured query on the ERP system to retrieve ERP data; and executing a third function of the three functions, causing the query runtime to render the ERP data in the chatbot user interface. [A person could receive a question, select the applicable scenario, formulate an ERP query according to scenario, submit the query, retrieve the results, and present to the requester. ].
As described above, these limitations can be carried out as a series of mental steps.
This judicial exception is not integrated into a practical application because the only additional elements recited are the chatbot user interface, LLM, and a ERP system and these additional elements are nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, chatbot user interface, LLM, and a ERP system, and these additional elements are nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 10, The method of claim 9, wherein the first scenario additionally defines a first user interface configuration, and wherein the executing of the third function further comprises altering display parameters of the chatbot user interface based on the first user interface configuration.
[A person could follow predetermined presentation instructions and arrange the retrieved information as a table, chart, or list, or other specified format.]
As described above, these limitations can be carried out as a series of mental steps.
This judicial exception is not integrated into a practical application because the only additional element recited are the user interface and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the user interface is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 11, The method of claim 9, wherein the executing the first function further causes the query runtime to post-process the structured query prior to execution of the second function.
[A person could review and correct a query before submitting it to the ERP system.]
As described above, these limitations can be carried out as a series of mental steps. This judicial exception is not integrated into a practical application because the only additional elements recited is the computer system and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the computer system is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 12, The method of claim 11, wherein the post-processing further comprises analyzing one or more statements in the structured query to ensure that only fields that have been made available for displaying or filtering are contained in the one or more statements.
[A person could compare the query fields against a list of approved display and filter fields and remove or reject unauthorized fields.].
As described above, these limitations can be carried out as a series of mental steps. This judicial exception is not integrated into a practical application because the only additional elements recited is the computer system and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the computer system is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 13, The method of claim 9, wherein the first prompt further comprises user context.
[A person could consider the requester’s identity, role, permissions, or preferences when preparing the request.]
As described above, these limitations can be carried out as a series of mental steps. This judicial exception is not integrated into a practical application because the only additional elements recited is the computer system and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the computer system is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 14, The method of claim 9, wherein the first prompt further comprises one or more hints provided by a designer of the first scenario, the one or more hints comprising at least one definition, not available in a data model of the first scenario, of one or more terms.
[A person could consult designer provided definitions, instructions when translating unfamiliar business terminology].
As described above, these limitations can be carried out as a series of mental steps.
This judicial exception is not integrated into a practical application because the only additional elements recited is the computer system and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the computer system is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 15, The method of claim 9, wherein the first prompt further comprises application context.
[A person could consider the relevant applications’ purpose, configuration, or operating environment when interpreting the request].
As described above, these limitations can be carried out as a series of mental steps.
This judicial exception is not integrated into a practical application because the only additional elements recited is the computer system and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the computer system is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 16, The method of claim 9, wherein the first prompt further comprises past elements of a conversation in the chatbot user interface.
[A person could review earlier questions and answers to understand the current request and formulate the appropriate query. ]
As described above, these limitations can be carried out as a series of mental steps.
This judicial exception is not integrated into a practical application because the only additional element recited are a computer system and a chatbot user interface and these additional elements are nothing more than generic computer implementing the mental process using general-purpose software and general-purpose hardware. Chain of thought promoting uses a generally recited language model to automate human reasoning and query formulation and therefore does not add significantly more to the abstract idea.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the only additional elements recited are a chatbot user interface and a computer system and these additional elements are nothing more than instructions to apply the mental process using general-purpose software and hardware.
Regarding claim 17 , A non-transitory machine-readable medium storing instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising: receiving a natural language request via a chatbot user interface; matching the natural language request to a first scenario of a plurality of scenarios managed by a chatbot runtime, the first scenario defining three functions for accessing data in an Enterprise Resource Planning (ERP) system; executing a first function of the three functions, causing a query runtime to: generate a first prompt using the natural language request and the first scenario; send the first prompt to a Large Language Model (LLM); and receive a structured query, in a language corresponding to the ERP system, from the LLM; executing a second function of the three functions, causing the query runtime to run the structured query on the ERP system to retrieve ERP data; and executing a third function of the three functions, causing the query runtime to render the ERP data in the chatbot user interface.
[A person could receive a question, select the applicable scenario, formulate an ERP query according to scenario, submit the query, retrieve the results, and present to the requester. ].
As described above, these limitations can be carried out as a series of mental steps.
This judicial exception is not integrated into a practical application because the only additional elements recited are the processor, non-transitory computer-readable medium , chatbot user interface, LLM, and a ERP system and these additional elements are nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the processor, non-transitory computer-readable medium , chatbot user interface, LLM, and a ERP system, and these additional elements are nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 18, The non-transitory machine-readable medium of claim 17, wherein the first scenario additionally defines a first user interface configuration, and wherein the executing of the third function further comprises altering display parameters of the chatbot user interface based on the first user interface configuration.
[A person could follow predetermined presentation instructions and arrange the retrieved information as a table, chart, or list, or other specified format.]
As described above, these limitations can be carried out as a series of mental steps.
This judicial exception is not integrated into a practical application because the only additional element recited are the user interface and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the user interface is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 19, The non-transitory machine-readable medium of claim 17, wherein the executing the first function further causes the query runtime to post-process the structured query prior to execution of the second function.
[A person could review and correct a query before submitting it to the ERP system.]
As described above, these limitations can be carried out as a series of mental steps. This judicial exception is not integrated into a practical application because the only additional elements recited is the computer system and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the computer system is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
Regarding claim 20, The non-transitory machine-readable medium of claim 19, wherein the post-processing further comprises analyzing one or more statements in the structured query to ensure that only fields that have been made available for displaying or filtering are contained in the one or more statements.
[A person could compare the query fields against a list of approved display and filter fields and remove or reject unauthorized fields.].
As described above, these limitations can be carried out as a series of mental steps. This judicial exception is not integrated into a practical application because the only additional elements recited is the computer system and this additional element is nothing more than using a generic computer as a tool to implement the mental process.
This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception because, as described above, the computer system is the only additional element and this additional element is nothing more than instructions to apply the mental process using general-purpose hardware.
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 [ 1, 2, 3, 5, 7, 9, 10, 11, 13, 15, 17, 18, 19] are rejected under 35 U.S.C. 103 as being unpatentable over Modelo-Howard (US-20250284683-A1, hereinafter Modelo-Howard) in view of Chouta (US-12032564-B1, hereinafter Chouta) and in further view of Yaramada (US20200320133A1
, hereinafter Yaramada) and in further view of Siebal (US-12111859-B2, hereinafter Siebal).
Regarding claim 1,
Modelo-Howard teaches
A system comprising: at least one hardware processor; a non-transitory computer-readable
medium storing instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations comprising:
[Claim 16, "An apparatus comprising: a processor; and a machine-readable medium having instructions stored thereon that are executable by the processor to cause the apparatus to,"];
[Claim 11 "A non-transitory machine-readable medium having program code stored thereon, the program code comprising instructions to:"];
matching the natural language request to a first scenario of a plurality of scenarios managed by a chatbot runtime, the first scenario
generate a first prompt using the natural language request and the first scenario;
[0044 "At block 406, the converter generates an initial prompt for an LLM based on the retrieved metadata, example valid database queries, and the natural language query. The initial prompt comprises the retrieved metadata, the example valid database queries, the natural language query, a grammar for the domain-based query language. "];
[0044 "The initial prompt is generated according to an engineered prompt template that can depend on each domain, "]
[0023 "The relevant metadata 138 depends on the domain/intent predicted by the intent classifier 103." where initial prompt is the first prompt, the initial prompt includes natural language query, and the prompt template, metadata, grammar, and example queries depend on the selected domain. The selected domain corresponds to the scenario. ];
send the first prompt to a Large Language Model (LLM);
[0025 "At stage D, the prompt generator 105 prompts the LLM 107 with the initial prompt 102 to obtain the initial database query 104 as output." where initial prompt 102 is the first prompt, LLM 107 is the LLM, prompt generator 105 prompts LLM 107 with initial prompt 102. ]
and receive a structured query, in a language corresponding to the
[0025 "At stage D, the prompt generator 105 prompts the LLM 107 with the initial prompt 102 to obtain the initial database query 104 as output." ]
[0025 "At stage E, the lint program 109 determines that the initial database query 104 has valid syntax according to the domain-specific database query language."];
[0021 "Each predicted intent maps to a domain for a query language corresponding to the natural language query 130."]
However, Modelo-Howard does not teach
receiving a natural language request via a chatbot user interface;
executing a first function of the three functions, causing a query runtime to:
executing a second function of the three functions, causing the query runtime to run the structured query on the ERP system to retrieve ERP data;
and executing a third function of the three functions, causing the query runtime to render the ERP data in the chatbot user interface.
But Chouta teaches
receiving a natural language request via a chatbot user interface;
[Column 5, lines 46-50 "An initial display 610 includes a chatbot interface 620 into which a user may provide a natural language request “on-the-fly” (“show the number of API calls per response code in March 2025” as illustrated in FIG. 6 )."]
defining three functions for accessing data
[Column 5, lines 55-63 " The inference engine may run the fine-tuned GPT-J or T5 model (or another suitable ML model) 720 to automatically generate an appropriate OData query 730. That query is then executed to retrieve the relevant business data from a database 740. The relevant business data can then be used to generate one or more analytic charts 750 that are then rendered for the user in a response display." where the three functions include data query generation, query execution and retrieval and rendering the retrieved data];
executing a first function of the three functions, causing a query runtime to:
[Column 5, lines 3-6 "An OData query creation 354 component of the transformation framework 350 may use prior user requests and associated OData queries"]
[Column 5, lines 8-9 "The transformation framework 350 may receive a text request from a user device. The transformation framework 350 may then use the fine-tuned model to automatically change the text request into an appropriate OData query. "];
[Column 5, lines 54-56 "In particular, after receiving a query in natural language 710 via an initial display an inference engine may be called. " where OData query creation 354 is first function, calling the inference engine after receiving query is the mapped to executing a first function, transformation framework 350 and inference engine which operate at runtime to generate OData query map to query runtime and OData query creation, query execution, and results rendering are mapped to three functions. ].
executing a second function of the three functions, causing the query runtime to run the structured query on the
[[Column 5, lines 3-6 "An OData query creation 354 component of the transformation framework 350 may use prior user requests and associated OData queries “];
[Column 5, lines 59-60 "That query is then executed to retrieve the relevant business data from a database 740."];
[Column 3, lines 3-4 "The query can then be executed to fetch enterprise analytics data from an enterprise data store 130 at (D)."]
[Column 5, lines 54-56 "In particular, after receiving a query in natural language 710 via an initial display an inference engine may be called." where execution of generated Odata query is the second function, transformative framework/inference engine is query runtime, and query is structured query, and retrieving business information from database 740 is retrieve data]
and executing a third function of the three functions, causing the query runtime to render the
[Column 5, lines 60-63 "The relevant business data can then be used to generate one or more analytic charts 750 that are then rendered for the user in a response display."]
[Column 5, lines 46-50 "An initial display 610 includes a chatbot interface 620 into which a user may provide a natural language request “on-the-fly” (“show the number of API calls per response code in March 2025” as illustrated in FIG. 6 )." Responsive to the request, a response display 630 includes an analytic chart 640 containing the requested information."]
[Column 5, lines 14-17 "According to some embodiments, an analytic chart creation 356 component of the transformation framework 350 may generate a chart, based on the business information and data analytics, to be provided to the user" where analytic chart creation is the third function, framework 350 and creation component is query runtime, generating and rendering chart 750 is render the data, and chatbot interface 620 is chatbot user interface].
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard with Chouta to allow users unfamiliar with ERP query languages to accurately retrieve and view enterprise data through natural language requests.
Modelo-Howard in view of Chouta does not teach
matching the natural language request to a first scenario of a plurality of scenarios managed by a chatbot runtime,
But Yaramada teaches matching the natural language request to a first scenario of a plurality of scenarios managed by a chatbot runtime,
[0015"the AI routing framework can match the input statement to an example statement in the repository that is most semantically similar to the input statement. The AI routing framework can then extract, from the repository, information associated with the matched statement (including, e.g., a domain to which the matched statement belongs) and forward the input statement to a handler of particular back-end software system that is configured to process the domain associated with the matched statement."]
[0023 "Each back-end software system 218(1)-(N) comprises a domain-specific handler 220 that is configured to process user queries/requests for a particular domain, where a domain is a computing/business function or a set of related computing/business functions."]
[0024 "As described in further detail below, AI routing framework 202 can receive user queries/requests across different domains which are submitted to multi-domain chatbot 204 and can intelligently route these queries/requests to back-end software systems 218(1)-(N) in a manner that ensures user queries/requests belonging to a domain D are sent to the domain-specific handler of a back-end software system is that designed to process (i.e., is an expert for) statements in domain D" where verbal or text based maps to natural language request, the determined domain and its corresponding handler maps to first scenario, the multiple domains and domain specific handlers maps to plurality of scenarios]
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard in view of Chouta with Yaramada to route each request to the scenario configured for the relevant ERP task, thereby selecting the proper query generation, execution, and presentation functions.
Modelo-Howard in view of Chouta in view of Yaramada do not teach
Enterprise Resource Planning (ERP) system;
However, Siebal teaches
Enterprise Resource Planning (ERP) system;
[Column 9, lines 29-31 " Enterprise systems 404 can include, for example, CRM systems, EAM systems, ERP systems, FP&A systems, HRM systems, and SCADA systems."];
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard in view of Chouta in view of Yaramada with Siebal to permit users to access and analyze business data maintained in existing ERP systems without manually constructing specialized ERP queries.
Regarding claim 2, rejection of claim 1 is incorporated.
Modelo-Howard teaches the system of claim 1, wherein the first scenario additionally defines a first user interface configuration, and wherein the executing of the further comprises altering display parameters of the
[0050 "At block 504, the visualization/summarization module generates a graph structure of assets/vulnerabilities and presents the visualization to the user."]
[0050 "The graph structure can vary by domain." where selected domain is first scenario, the domain specific graph is first user interface configuration, varying the displayed graph structure according to the domain is altering display parameters]
However, Modelo-Howard does not teach a third function and a chatbot user interface
But Chouta teaches the third function
[Column 5, lines 60-63 "The relevant business data can then be used to generate one or more analytic charts 750 that are then rendered for the user in a response display."]
[Column 5, lines 46-50 "An initial display 610 includes a chatbot interface 620 into which a user may provide a natural language request “on-the-fly” (“show the number of API calls per response code in March 2025” as illustrated in FIG. 6 )." Responsive to the request, a response display 630 includes an analytic chart 640 containing the requested information."]
[Column 5, lines 14-17 "According to some embodiments, an analytic chart creation 356 component of the transformation framework 350 may generate a chart, based on the business information and data analytics, to be provided to the user" where analytic chart creation is the third function, framework 350 and creation component is query runtime, generating and rendering chart 750 is render the data, and chatbot interface 620 is chatbot user interface].
chatbot user interface
[Column 5, lines 46-50 "An initial display 610 includes a chatbot interface 620 into which a user may provide a natural language request “on-the-fly” (“show the number of API calls per response code in March 2025” as illustrated in FIG. 6 )." Responsive to the request, a response display 630 includes an analytic chart 640 containing the requested information."]
[Column 6, lines 4-7 "Note that there might 75 or more such parameters 800 that can be combined in various ways for a user request (and all such combinations may be handled by the fine-tuned ML model to create appropriate analytics charts)."]
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard in view of Chouta so that the chatbot automatically adjusts the presentation of retrieved data according to the selected scenario/domain, thereby presenting the results in a format appropriate to the type of information requested.
Regarding claim 3, rejection of claim 1 is incorporated.
Modelo-Howard teaches the system of claim 1, wherein the executing the first function further causes the query runtime to post-process the structured query prior to execution of the second function.
[0025 " At stage E, the lint program 109 determines that the initial database query 104 has valid syntax according to the domain-specific database query language."]
[0025 "The lint program 109 can comprise any tool that is able to identify syntax errors, stylistic errors, potential vulnerabilities, suspicious constructs, etc. in database queries according to the domain-specific database query language."]
[0015 "If the lint program determines the initial database query is valid, the lint program communicates the initial database query to a query language parser to retrieve domain-based data indicated by the natural language query." where query is sent to parser for data retrieval only after the lint program determines that it is valid].
Regarding claim 5, rejection of claim 1 is incorporated.
Modelo-Howard teaches the system of claim 1, wherein the first prompt further comprises user context.
[0024 "At stage C, the prompt generator 105 generates an initial prompt 102 for the LLM 107 based on the relevant metadata 138."]
[0024 "The initial template includes fields/sections to insert any vulnerabilities, asset metadata, example queries, and other metadata included in the relevant metadata 138, a description of grammar for the domain-specific query language (e.g., as specified in a grammar file or natural language description of a grammar file), and instructions for the LLM 107. "]
[0044 "At block 406, the converter generates an initial prompt for an LLM based on the retrieved metadata, example valid database queries, and the natural language query. The initial prompt comprises the retrieved metadata, the example valid database queries, the natural language query, a grammar for the domain-based query language." where metadata concerning user assets, vulnerabilities, etc. corresponds to user context].
Regarding claim 7, rejection of claim 1 is incorporated.
Modelo-Howard teaches the system of claim 1, wherein the first prompt further comprises
application context.
[0023 "…and relevant metadata for configuration analysis includes stored configuration files (e.g., configuration files for applications, processes, security policies, etc.)"];
[0024 "At stage C, the prompt generator 105 generates an initial prompt 102 for the LLM 107 based on the relevant metadata 138." where metadata itself (configurations for applications) included in the prompt corresponds to the application context.]
Regarding claim 9,
Modelo-Howard teaches
A method comprising:
[0061 “As will be appreciated, aspects of the disclosure may be embodied as a system, method or program code/instructions stored in one or more machine-readable media.”]
matching the natural language request to a first scenario of a plurality of scenarios managed by a chatbot runtime, the first scenario
generate a first prompt using the natural language request and the first scenario;
[0044 "At block 406, the converter generates an initial prompt for an LLM based on the retrieved metadata, example valid database queries, and the natural language query. The initial prompt comprises the retrieved metadata, the example valid database queries, the natural language query, a grammar for the domain-based query language. "];
[0044 "The initial prompt is generated according to an engineered prompt template that can depend on each domain, "]
[0023 "The relevant metadata 138 depends on the domain/intent predicted by the intent classifier 103." where initial prompt is the first prompt, the initial prompt includes natural language query, and the prompt template, metadata, grammar, and example queries depend on the selected domain. The selected domain corresponds to the scenario. ];
send the first prompt to a Large Language Model (LLM);
[0025 "At stage D, the prompt generator 105 prompts the LLM 107 with the initial prompt 102 to obtain the initial database query 104 as output." where initial prompt 102 is the first prompt, LLM 107 is the LLM, prompt generator 105 prompts LLM 107 with initial prompt 102. ]
and receive a structured query, in a language corresponding to the
[0025 "At stage D, the prompt generator 105 prompts the LLM 107 with the initial prompt 102 to obtain the initial database query 104 as output." ]
[0025 "At stage E, the lint program 109 determines that the initial database query 104 has valid syntax according to the domain-specific database query language."];
[0021 "Each predicted intent maps to a domain for a query language corresponding to the natural language query 130."]
However, Modelo-Howard does not teach
receiving a natural language request via a chatbot user interface;
executing a first function of the three functions, causing a query runtime to:
executing a second function of the three functions, causing the query runtime to run the structured query on the ERP system to retrieve ERP data;
and executing a third function of the three functions, causing the query runtime to render the ERP data in the chatbot user interface.
But Chouta teaches
receiving a natural language request via a chatbot user interface;
[Column 5, lines 46-50 "An initial display 610 includes a chatbot interface 620 into which a user may provide a natural language request “on-the-fly” (“show the number of API calls per response code in March 2025” as illustrated in FIG. 6 )."]
defining three functions for accessing data
[Column 5, lines 55-63 " The inference engine may run the fine-tuned GPT-J or T5 model (or another suitable ML model) 720 to automatically generate an appropriate OData query 730. That query is then executed to retrieve the relevant business data from a database 740. The relevant business data can then be used to generate one or more analytic charts 750 that are then rendered for the user in a response display." where the three functions include data query generation, query execution and retrieval and rendering the retrieved data];
executing a first function of the three functions, causing a query runtime to:
[Column 5, lines 3-6 "An OData query creation 354 component of the transformation framework 350 may use prior user requests and associated OData queries"]
[Column 5, lines 8-9 "The transformation framework 350 may receive a text request from a user device. The transformation framework 350 may then use the fine-tuned model to automatically change the text request into an appropriate OData query. "];
[Column 5, lines 54-56 "In particular, after receiving a query in natural language 710 via an initial display an inference engine may be called. " where OData query creation 354 is first function, calling the inference engine after receiving query is the mapped to executing a first function, transformation framework 350 and inference engine which operate at runtime to generate OData query map to query runtime and OData query creation, query execution, and results rendering are mapped to three functions. ].
executing a second function of the three functions, causing the query runtime to run the structured query on the
[[Column 5, lines 3-6 "An OData query creation 354 component of the transformation framework 350 may use prior user requests and associated OData queries “];
[Column 5, lines 59-60 "That query is then executed to retrieve the relevant business data from a database 740."];
[Column 3, lines 3-4 "The query can then be executed to fetch enterprise analytics data from an enterprise data store 130 at (D)."]
[Column 5, lines 54-56 "In particular, after receiving a query in natural language 710 via an initial display an inference engine may be called." where execution of generated Odata query is the second function, transformative framework/inference engine is query runtime, and query is structured query, and retrieving business information from database 740 is retrieve data]
and executing a third function of the three functions, causing the query runtime to render the
[Column 5, lines 60-63 "The relevant business data can then be used to generate one or more analytic charts 750 that are then rendered for the user in a response display."]
[Column 5, lines 46-50 "An initial display 610 includes a chatbot interface 620 into which a user may provide a natural language request “on-the-fly” (“show the number of API calls per response code in March 2025” as illustrated in FIG. 6 )." Responsive to the request, a response display 630 includes an analytic chart 640 containing the requested information."]
[Column 5, lines 14-17 "According to some embodiments, an analytic chart creation 356 component of the transformation framework 350 may generate a chart, based on the business information and data analytics, to be provided to the user" where analytic chart creation is the third function, framework 350 and creation component is query runtime, generating and rendering chart 750 is render the data, and chatbot interface 620 is chatbot user interface].
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard with Chouta to allow users unfamiliar with ERP query languages to accurately retrieve and view enterprise data through natural language requests.
Modelo-Howard in view of Chouta does not teach
matching the natural language request to a first scenario of a plurality of scenarios managed by a chatbot runtime,
But Yaramada teaches matching the natural language request to a first scenario of a plurality of scenarios managed by a chatbot runtime,
[0015"the AI routing framework can match the input statement to an example statement in the repository that is most semantically similar to the input statement. The AI routing framework can then extract, from the repository, information associated with the matched statement (including, e.g., a domain to which the matched statement belongs) and forward the input statement to a handler of particular back-end software system that is configured to process the domain associated with the matched statement."]
[0023 "Each back-end software system 218(1)-(N) comprises a domain-specific handler 220 that is configured to process user queries/requests for a particular domain, where a domain is a computing/business function or a set of related computing/business functions."]
[0024 "As described in further detail below, AI routing framework 202 can receive user queries/requests across different domains which are submitted to multi-domain chatbot 204 and can intelligently route these queries/requests to back-end software systems 218(1)-(N) in a manner that ensures user queries/requests belonging to a domain D are sent to the domain-specific handler of a back-end software system is that designed to process (i.e., is an expert for) statements in domain D" where verbal or text based maps to natural language request, the determined domain and its corresponding handler maps to first scenario, the multiple domains and domain specific handlers maps to plurality of scenarios]
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard in view of Chouta with Yaramada to route each request to the scenario configured for the relevant ERP task, thereby selecting the proper query generation, execution, and presentation functions.
Modelo-Howard in view of Chouta in view of Yaramada do not teach
Enterprise Resource Planning (ERP) system;
However, Siebal teaches
Enterprise Resource Planning (ERP) system;
[Column 9, lines 29-31 " Enterprise systems 404 can include, for example, CRM systems, EAM systems, ERP systems, FP&A systems, HRM systems, and SCADA systems."];
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard in view of Chouta in view of Yaramada with Siebal to permit users to access and analyze business data maintained in existing ERP systems without manually constructing specialized ERP queries.
Regarding claim 10, rejection of claim 9 is incorporated.
Modelo-Howard in view of Chouta teach the method of claim 9, wherein the first scenario additionally defines a first user interface configuration, and wherein the executing of the third function further comprises altering display parameters of the chatbot user interface based on the first user interface configuration.
Claim 10 is rejected for the same reasons as claim 2.
Regarding claim 11, rejection of claim 9 is incorporated.
Modelo-Howard teach The method of claim 9, wherein the executing the first function further causes the query runtime to post-process the structured query prior to execution of the second function.
Claim 11 is rejected for the same reasons as claim 3.
Regarding claim 13, rejection of claim 9 is incorporated.
Modelo-Howard teaches the method of claim 9, wherein the first prompt further comprises user context.
Claim 13 is rejected for the same reasons as claim 5.
Regarding claim 15, rejection of claim 9 is incorporated.
Modelo- Howard teaches The method of claim 9, wherein the first prompt further comprises application context.
Claim 15 is rejected for the same reasons as claim 7.
Regarding claim 17,
Modelo-Howard teaches
A non-transitory machine-readable medium storing instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising:
[Claim 11 "A non-transitory machine-readable medium having program code stored thereon, the program code comprising instructions to:"];
matching the natural language request to a first scenario of a plurality of scenarios managed by a chatbot runtime, the first scenario
generate a first prompt using the natural language request and the first scenario;
[0044 "At block 406, the converter generates an initial prompt for an LLM based on the retrieved metadata, example valid database queries, and the natural language query. The initial prompt comprises the retrieved metadata, the example valid database queries, the natural language query, a grammar for the domain-based query language. "];
[0044 "The initial prompt is generated according to an engineered prompt template that can depend on each domain, "]
[0023 "The relevant metadata 138 depends on the domain/intent predicted by the intent classifier 103." where initial prompt is the first prompt, the initial prompt includes natural language query, and the prompt template, metadata, grammar, and example queries depend on the selected domain. The selected domain corresponds to the scenario. ];
send the first prompt to a Large Language Model (LLM);
[0025 "At stage D, the prompt generator 105 prompts the LLM 107 with the initial prompt 102 to obtain the initial database query 104 as output." where initial prompt 102 is the first prompt, LLM 107 is the LLM, prompt generator 105 prompts LLM 107 with initial prompt 102. ]
and receive a structured query, in a language corresponding to the
[0025 "At stage D, the prompt generator 105 prompts the LLM 107 with the initial prompt 102 to obtain the initial database query 104 as output." ]
[0025 "At stage E, the lint program 109 determines that the initial database query 104 has valid syntax according to the domain-specific database query language."];
[0021 "Each predicted intent maps to a domain for a query language corresponding to the natural language query 130."]
However, Modelo-Howard does not teach
receiving a natural language request via a chatbot user interface;
executing a first function of the three functions, causing a query runtime to:
executing a second function of the three functions, causing the query runtime to run the structured query on the ERP system to retrieve ERP data;
and executing a third function of the three functions, causing the query runtime to render the ERP data in the chatbot user interface.
But Chouta teaches
receiving a natural language request via a chatbot user interface;
[Column 5, lines 46-50 "An initial display 610 includes a chatbot interface 620 into which a user may provide a natural language request “on-the-fly” (“show the number of API calls per response code in March 2025” as illustrated in FIG. 6 )."]
defining three functions for accessing data
[Column 5, lines 55-63 " The inference engine may run the fine-tuned GPT-J or T5 model (or another suitable ML model) 720 to automatically generate an appropriate OData query 730. That query is then executed to retrieve the relevant business data from a database 740. The relevant business data can then be used to generate one or more analytic charts 750 that are then rendered for the user in a response display." where the three functions include data query generation, query execution and retrieval and rendering the retrieved data];
executing a first function of the three functions, causing a query runtime to:
[Column 5, lines 3-6 "An OData query creation 354 component of the transformation framework 350 may use prior user requests and associated OData queries"]
[Column 5, lines 8-9 "The transformation framework 350 may receive a text request from a user device. The transformation framework 350 may then use the fine-tuned model to automatically change the text request into an appropriate OData query. "];
[Column 5, lines 54-56 "In particular, after receiving a query in natural language 710 via an initial display an inference engine may be called. " where OData query creation 354 is first function, calling the inference engine after receiving query is the mapped to executing a first function, transformation framework 350 and inference engine which operate at runtime to generate OData query map to query runtime and OData query creation, query execution, and results rendering are mapped to three functions. ].
executing a second function of the three functions, causing the query runtime to run the structured query on the
[[Column 5, lines 3-6 "An OData query creation 354 component of the transformation framework 350 may use prior user requests and associated OData queries “];
[Column 5, lines 59-60 "That query is then executed to retrieve the relevant business data from a database 740."];
[Column 3, lines 3-4 "The query can then be executed to fetch enterprise analytics data from an enterprise data store 130 at (D)."]
[Column 5, lines 54-56 "In particular, after receiving a query in natural language 710 via an initial display an inference engine may be called." where execution of generated Odata query is the second function, transformative framework/inference engine is query runtime, and query is structured query, and retrieving business information from database 740 is retrieve data]
and executing a third function of the three functions, causing the query runtime to render the
[Column 5, lines 60-63 "The relevant business data can then be used to generate one or more analytic charts 750 that are then rendered for the user in a response display."]
[Column 5, lines 46-50 "An initial display 610 includes a chatbot interface 620 into which a user may provide a natural language request “on-the-fly” (“show the number of API calls per response code in March 2025” as illustrated in FIG. 6 )." Responsive to the request, a response display 630 includes an analytic chart 640 containing the requested information."]
[Column 5, lines 14-17 "According to some embodiments, an analytic chart creation 356 component of the transformation framework 350 may generate a chart, based on the business information and data analytics, to be provided to the user" where analytic chart creation is the third function, framework 350 and creation component is query runtime, generating and rendering chart 750 is render the data, and chatbot interface 620 is chatbot user interface].
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard with Chouta to allow users unfamiliar with ERP query languages to accurately retrieve and view enterprise data through natural language requests.
Modelo-Howard in view of Chouta does not teach
matching the natural language request to a first scenario of a plurality of scenarios managed by a chatbot runtime,
But Yaramada teaches matching the natural language request to a first scenario of a plurality of scenarios managed by a chatbot runtime,
[0015"the AI routing framework can match the input statement to an example statement in the repository that is most semantically similar to the input statement. The AI routing framework can then extract, from the repository, information associated with the matched statement (including, e.g., a domain to which the matched statement belongs) and forward the input statement to a handler of particular back-end software system that is configured to process the domain associated with the matched statement."]
[0023 "Each back-end software system 218(1)-(N) comprises a domain-specific handler 220 that is configured to process user queries/requests for a particular domain, where a domain is a computing/business function or a set of related computing/business functions."]
[0024 "As described in further detail below, AI routing framework 202 can receive user queries/requests across different domains which are submitted to multi-domain chatbot 204 and can intelligently route these queries/requests to back-end software systems 218(1)-(N) in a manner that ensures user queries/requests belonging to a domain D are sent to the domain-specific handler of a back-end software system is that designed to process (i.e., is an expert for) statements in domain D" where verbal or text based maps to natural language request, the determined domain and its corresponding handler maps to first scenario, the multiple domains and domain specific handlers maps to plurality of scenarios]
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard in view of Chouta with Yaramada to route each request to the scenario configured for the relevant ERP task, thereby selecting the proper query generation, execution, and presentation functions.
Modelo-Howard in view of Chouta in view of Yaramada do not teach
Enterprise Resource Planning (ERP) system;
However, Siebal teaches
Enterprise Resource Planning (ERP) system;
[Column 9, lines 29-31 " Enterprise systems 404 can include, for example, CRM systems, EAM systems, ERP systems, FP&A systems, HRM systems, and SCADA systems."];
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard in view of Chouta in view of Yaramada with Siebal to permit users to access and analyze business data maintained in existing ERP systems without manually constructing specialized ERP queries.
Regarding claim 18, rejection of claim 17 is incorporated.
Modelo- Howard in view of Chouta teaches The non-transitory machine-readable medium of claim 17, wherein the first scenario additionally defines a first user interface configuration, and wherein the executing of the third function further comprises altering display parameters of the chatbot user interface based on the first user interface configuration.
Claim 18 is rejected for the same reasons as claim 2.
Regarding claim 19, rejection of claim 17 is incorporated.
Modelo- Howard teaches The non-transitory machine-readable medium of claim 17, wherein the executing the first function further causes the query runtime to post-process the structured query prior to execution of the second function.
Claim 19 is rejected for the same reasons as claim 3.
Claim [ 4, 12, 20 ] are rejected under 35 U.S.C. 103 as being unpatentable over Modelo-Howard (US-20250284683-A1, hereinafter Modelo-Howard) in view of Chouta (US-12032564-B1, hereinafter Chouta) and in further view of Yaramada (US 11275785 B2, hereinafter Yaramada) and in further view of Siebal (US-12111859-B2, hereinafter Siebal) and in further view of Khillar (US-11347802-B2, hereinafter Khillar).
Regarding claim 4, rejection of claim 3 is incorporated.
Modelo-Howard teaches the system of claim 3, wherein the post-processing further
comprises analyzing one or more statements in the structured query
[0025 " At stage E, the lint program 109 determines that the initial database query 104 has valid syntax according to the domain-specific database query language."]
[0025 "The lint program 109 can comprise any tool that is able to identify syntax errors, stylistic errors, potential vulnerabilities, suspicious constructs, etc. in database queries according to the domain-specific database query language." where analyzing query is being done before execution.]
But Modelo-Howard does not teach
to ensure that only fields that have been made available for displaying or filtering are contained in the one or more statements.
Chouta teaches
[Column 5, Column 6, lines 67, 1-7 " The parameters 800 include dimensions 810 (e.g., API name, developer name, application name, browser agent, etc.) and measures 820 (e.g., response time, response status, response latency, request method, etc.). Note that there might 75 or more such parameters 800 that can be combined in various ways for a user request (and all such combinations may be handled by the fine-tuned ML model to create appropriate analytics charts)."]
[Column 5, lines 60-63 "The relevant business data can then be used to generate one or more analytic charts 750 that are then rendered for the user in a response display."]
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard in view of Chouta to identify errors or invalid query constructs before execution, thereby improving query accuracy and preventing erroneous retrieval of data.
Modelo-Howard in view of Chouta in view of Yaramada in view of Siebal do not teach
to ensure that only fields are contained in the one or more statements.
But Khillar teaches
to ensure that only fields are contained in the one or more statements.
[Column 1, lines 59-63 "The generated query may be validated based on the database schema and, if the validation is successful, the query may be executed with respect to the database. For example, the generated and validated query may be transmitted to the database for execution."]
[Column 9 , lines 65-67 "or example, the database schema 303 may provide one or more indications of a structure of the database (e.g., a listing of columns in the database),"]
[Column 1 , lines 59-63 "The generated query may be validated based on the database schema and, if the validation is successful, the query may be executed with respect to the database. For example, the generated and validated query may be transmitted to the database for execution."]
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard in view of Chouta in view of Yaramada in view of Siebal with Khillar thereby ensuring that the query contains only configured dimensions and measures for displaying and preventing unauthorized or unsupported queries from being executed.
Regarding claim 12, rejection of claim 11 is incorporated.
Modelo-Howard in view of Chouta in view of Yaramada in view of Siebal in view of Khillar teach the method of claim 11, wherein the post-processing further comprises analyzing one or more statements in the structured query to ensure that only fields that have been made available for displaying or filtering are contained in the one or more statements.
Claim 12 is rejected for the same reasons as claim 4.
Regarding claim 20, rejection of claim 19 is incorporated.
Modelo-Howard in view of Chouta in view of Yaramada in view of Siebal in view of Khillar
teach the non-transitory machine-readable medium of claim 19, wherein the post-processing further comprises analyzing one or more statements in the structured query to ensure that only fields that have been made available for displaying or filtering are contained in the one or more statements.
Claim 20 is rejected for the same reasons as claim 4.
Claim [ 6, 14 ] are rejected under 35 U.S.C. 103 as being unpatentable over Modelo-Howard (US-20250284683-A1, hereinafter Modelo-Howard) in view of Chouta (US-12032564-B1, hereinafter Chouta) and in further view of Yaramada (US 11275785 B2, hereinafter Yaramada) and in further view of Siebal (US-12111859-B2, hereinafter Siebal) and in further view of Ho (US 12333256 B2, hereinafter Ho).
Regarding claim 6, rejection of claim 1 is incorporated.
Modelo-Howard teaches the system of claim 1, wherein the first prompt further
[0024 "At stage C, the prompt generator 105 generates an initial prompt 102 for the LLM 107 based on the relevant metadata 138"]
[0024 "The initial template includes fields/sections to insert any vulnerabilities, asset metadata, example queries, and other metadata included in the relevant metadata 138, a description of grammar for the domain-specific query language (e.g., as specified in a grammar file or natural language description of a grammar file), and instructions for the LLM 107. "]
However, Modelo-Howard in view of Chouta in view of Yaramada in view of Siebal does not teach one or more hints provided by a designer of the first scenario, the one or more hints comprising at least one definition, not available in a data model of the first scenario, of one or more terms.
But Ho teaches one or more hints provided by a designer of the first scenario, the one or more hints comprising at least one definition, not available in a data model of the first scenario, of one or more terms.
[Column 5, lines 63-67 "To add to those (sometimes incomprehensible) labels, the user provides the chatbot service with their equivalent natural language words: fruit, name, color, medium calories, etc. With these, questions containing those words can be associated to the relevant columns."]
[Column 6, lines 14-19 "Thus, according to an embodiment, to set up a database for use in a conversation, a description of what information the table stores is provided. This may be referred to as a “Schema Annotation” process. It is assumed that the table is a listing of items of a certain type, where each column represents some property of the items"]
[Column 6, lines 23-25 "Once the subject matter is identified, the chatbot needs to know, which column has values that best represent each specific item."]
[Column 6 , lines 64-67"The user may provide synonyms to the words that describe the main entity or its properties, and add the alternative words as labels for the main entity or the columns."]
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard in view of Chouta in view of Yaramada in view of Siebal with Ho to supply domain meanings not apparent from the database schema, thereby enabling the LLM to more accurately interpret user terminology and generate the appropriate structured database query.
Regarding claim 14, rejection of claim 9 is incorporated.
Modelo-Howard in view of Chouta in view of Yaramada in view of Siebal in view of Ho teach the method of claim 9, wherein the first prompt further comprises one or more hints provided by a designer of the first scenario, the one or more hints comprising at least one definition, not available in a data model of the first scenario, of one or more terms.
Claim 14 is rejected for the same reasons as claim 6.
Claim [ 8, 16 ] are rejected under 35 U.S.C. 103 as being unpatentable over Modelo-Howard (US-20250284683-A1, hereinafter Modelo-Howard) in view of Chouta (US-12032564-B1, hereinafter Chouta) and in further view of Yaramada (US 11275785 B2, hereinafter Yaramada) and in further view of Siebal (US-12111859-B2, hereinafter Siebal) and in further view of Russell (US2024/0296295, hereinafter Russell).
Regarding claim 8, rejection of claim 1 is incorporated.
Modelo-Howard teaches the system of claim 1, wherein the first prompt
[0024 "At stage C, the prompt generator 105 generates an initial prompt 102 for the LLM 107 based on the relevant metadata 138"]
However, Modelo-Howard does not teach prompt further comprises past
elements of a conversation in the chatbot user interface.
But Chouta teaches
[Column 4, lines 21-25 "The natural language request might be provided, for example, via an interactive chatbot, voice-to-text translation, language translation, a dynamic series of questions and answers, etc."];
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard with Chouta to allow users to conversationally request data and receive the retrieved results through the same interface.
Modelo-Howard in view of Chouta in view of Yaramada in view of Siebal do not teach
comprises past elements of a conversation in the
But Russell teach comprises past elements of a conversation in the
[0027 "The prompt may also include additional context that includes prior turns in response to user input"];
[0028 "The </Conversation History> provides additional context to the LLM about previous turns (e.g., questions or requests) for the document, and the {{Prior Questions/Answers}} is filled with those prior questions and, in some examples, the answers or responses provided to those questions."]
[0028 "In the above example template, the is filled with the question that is received from user interface, such as the application UI 106. "]
[0016 "The computing device 102 has an operating system that provides a graphical user interface (GUI) that allows users to interact with the computing device 102 via graphical elements, such as application windows (e.g., display areas), buttons, icons, and the like."];
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the Modelo-Howard in view of Chouta in view of Yaramada in view of Siebal with Russell to provide conversational context, thereby enabling the LLM to interpret follow-up requests more accurately and generate structured queries consistent with earlier portions of the chatbot conversations.
Regarding claim 16, rejection of claim 9 is incorporated.
Modelo-Howard in view of Chouta in view of Yaramada in view of Siebal in view of Russell teach the method of claim 9, wherein the first prompt further comprises past elements of a conversation in the chatbot user interface.
Claim 16 is rejected for the same reasons as claim 8.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHEZA ABDUL AZIZ whose telephone number is (571)272-9610. The examiner can normally be reached Monday-Friday 7:30am-5pm Alternate Fridays off.
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, Daniel Washburn can be reached at (571) 272-5551. 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.
/SHEZA ABDUL AZIZ/Examiner, Art Unit 2657
/DANIEL C WASHBURN/Supervisory Patent Examiner, Art Unit 2657
