DETAILED ACTION
The following is a Final Office Action in response to communications filed February 20, 2026. Claims 1, 7–8, and 16–18 are amended, and claims 5–6 are canceled. Currently, claims 1–4 and 7–18 are pending.
Response to Amendment/Argument
Applicant’s Response is sufficient to overcome the previous rejection of claims 7–8 under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention. As a result, the previous rejection of claims 7–8 under 35 U.S.C. 112(b) is withdrawn.
Applicant’s Response is sufficient to overcome the previous rejection of claims 1–18 under 35 U.S.C. 101 as being directed to non-statutory subject matter. More particularly, the elements for “applying a second large language model comprising one or more heuristics for summarizing vectors in natural language to the plurality of vectors to generate the summarized operational data comprising a natural language description of the plurality of vectors” and “prompting a first large language model using the user query and the summarized operational data comprising the natural language description of the plurality of vectors,” as recited in independent claims 1 and 17–18, integrate the abstract idea into a practical application under Step 2A Prong Two because the additional elements apply or use the recited abstract idea in some other meaningful way beyond generally linking the abstract idea to a particular technological environment. As a result, the previous rejection of claims 1–18 under 35 U.S.C. 101 is withdrawn.
With respect to the previous rejections under 35 U.S.C. 103, Applicant’s remarks have been fully considered but are moot in view of the updated grounds of rejection asserted below.
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.
Claims 1–4 and 7–18 are rejected under 35 U.S.C. 103 as being unpatentable over Jaganmohan (U.S. 10,943,072) in view of MOHANTY et al. (U.S. 2025/0200281), and in further view of Vadapandeshwara et al. (U.S. 2024/0061883) and Carbune et al. (U.S. 2025/0069617).
Claims 1 and 17–18: Jaganmohan discloses a method for generating insights into operational data using a model, the method comprising:
receiving a user query (See col. 2, ll. 49–51, wherein a user request is received);
receiving summarized operational data, wherein the summarized operational data is generated (See FIG. 8) by: receiving operational data (See col. 8, ll. 35–53, wherein operational data is received to generate a knowledge graph summarizing operational data);
generating an operational data graph, wherein the operational data graph comprises a plurality of nodes and a plurality of edges (See col. 13, ll. 38–61, wherein a knowledge graph is generated, and wherein the knowledge graph includes nodes and links between nodes);
generating a plurality of vectors characterizing relationships between the plurality of nodes and the plurality of edges in the operational graph (See col. 17, ll. 40–55 and col. 18, ll. 11–17, wherein word embeddings are generated with respect to the knowledge graph); and
applying a model for summarizing vectors in natural language to the plurality of vectors to generate the summarized operational data comprising a natural language description of the plurality of vectors (See col. 20, ll. 4–22, in view of col. 14, ll. 40–45 and col. 19, ll. 58–66, wherein text matching techniques are used in conjunction with structural and semantic matching to evaluate the knowledge graph and generate a response, and wherein each word embedding is associated with specific terminologies);
prompting using the user query and the summarized operational data comprising the natural language description of the plurality of vectors (See col. 16, ll. 59–66, wherein prompts are generated based on the request and the knowledge graph);
receiving a natural language response, in response to the prompting (See col. 16, l. 59–col. 17, l. 6, in view of FIG. 2B, wherein natural language responses are generated in response to received prompts); and
generating, based on the natural language response and one or more properties of the operational data graph, one or more visualizations corresponding to the natural language response (See FIG. 2B and col. 16, ll. 4–30, wherein visualizations are generated based on the model response and knowledge graph). Jaganmohan does not expressly disclose the remaining claim elements.
Mohanty discloses applying a second large language model to generate the summarized operational data (See paragraph 27, wherein the knowledge graph building model is implemented by an LLM);
prompting a first large language model using the user query and the summarized operational data (See FIG. 1 and paragraph 21, wherein a prompt to the language model, which “is a separate model than the model used to generate the knowledge graph,” is generated based on the request and the knowledge graph; see also FIG. 6 and paragraph 66); and
receiving a response, in response to the prompting from the first large language model (See FIG. 1 and paragraph 21, wherein content is generated in response to the prompt; see also FIG. 6 and paragraph 66).
Jaganmohan discloses a system directed to processing requests to generate insights according to a knowledge graph. Mohanty discloses a system directed to generating content recommendations using a knowledge graph. Each reference discloses a system directed to generating insights using a knowledge graph. The technique of utilizing an intermediary LLM is applicable to the system of Jaganmohan as they each share characteristics and capabilities; namely, they are directed to generating insights using a knowledge graph.
One of ordinary skill in the art would have recognized that applying the known technique of Mohanty would have yielded predictable results and resulted in an improved system. It would have been recognized that applying the technique of Mohanty to the teachings of Jaganmohan would have yielded predictable results because the level of ordinary skill in the art demonstrated by the references applied shows the ability to incorporate insight generation into similar systems. Further, applying an LLM to Jaganmohan would have been recognized by those of ordinary skill in the art as resulting in an improved system that would allow more detailed analysis and more reliable results. Jaganmohan and Mohanty do not expressly disclose the remaining claim elements.
Vadapandeshwara discloses, generating, based on the data graph, a plurality of vectors characterizing relationships between the plurality of nodes and the plurality of edges in the data graph (See paragraphs 75–76 and 80–81, wherein vectors defining relationships within a knowledge graph are generated using an embedding model; see also paragraph 7).
As disclosed above, Jaganmohan discloses a system directed to processing requests to generate insights according to a knowledge graph, and Mohanty discloses a system directed to generating content recommendations using a knowledge graph. Vadapandeshwara discloses a system directed to managing business decisions by generating and analyzing a knowledge graph. Each reference discloses a system directed to generating insights. The technique of generating vectors from a data graph is applicable to the systems of Jaganmohan and Mohanty as they each share characteristics and capabilities; namely, they are directed to generating insights.
One of ordinary skill in the art would have recognized that applying the known technique of Vadapandeshwara would have yielded predictable results and resulted in an improved system. It would have been recognized that applying the technique of Vadapandeshwara to the teachings of Jaganmohan and Mohanty would have yielded predictable results because the level of ordinary skill in the art demonstrated by the references applied shows the ability to incorporate insight generation into similar systems. Further, applying data graph-based vector generation to Jaganmohan and Mohanty would have been recognized by those of ordinary skill in the art as resulting in an improved system that would allow more detailed analysis and more reliable results. Jaganmohan, Mohanty, and Vadapandeshwara do not expressly disclose the remaining claim elements.
Carbune discloses applying a model comprising one or more heuristics (See paragraph 62, wherein heuristics are used by the LLM to generate insights and prompts).
As disclosed above, Jaganmohan discloses a system directed to processing requests to generate insights according to a knowledge graph, Mohanty discloses a system directed to generating content recommendations using a knowledge graph, and Vadapandeshwara discloses a system directed to managing business decisions by generating and analyzing a knowledge graph. Carbune discloses a system directed to generating response content based on natural language queries. Each reference discloses a system directed to generating insights. The technique of utilizing heuristics is applicable to the systems of Jaganmohan, Mohanty, and Vadapandeshwara as they each share characteristics and capabilities; namely, they are directed to generating insights.
One of ordinary skill in the art would have recognized that applying the known technique of Carbune would have yielded predictable results and resulted in an improved system. It would have been recognized that applying the technique of Carbune to the teachings of Jaganmohan, Mohanty, and Vadapandeshwara would have yielded predictable results because the level of ordinary skill in the art demonstrated by the references applied shows the ability to incorporate insight generation into similar systems. Further, applying heuristics to Jaganmohan, Mohanty, and Vadapandeshwara would have been recognized by those of ordinary skill in the art as resulting in an improved system that would allow more detailed analysis and more reliable results.
With respect to claim 17, Jaganmohan discloses a system comprising one or more processors and memory storing one or more programs for execution by the one or more processors, the one or more programs comprising instructions that, when executed by the one or more processors, cause the system to perform a method (See FIG. 15–16 and col. 2, ll. 49–55).
With respect to claim 18, Jaganmohan discloses a computer-readable storage medium storing instructions that, when executed by one or more processors of an electronic device, cause the device to perform operations (See FIG. 15–16 and col. 2, ll. 49–55).
Claim 2: Jaganmohan discloses the method of claim 1, wherein the user query is a natural language query (See FIG. 2B, col. 16, ll. 4–30, and col. 19, ll. 58–66).
Claim 3: Jaganmohan discloses the method of claim 1, wherein the operational data comprises numerical data about operation of a device or system (See col. 9, ll. 11–20 and col. 13, ll. 24–36, wherein the operational data is quantitative).
Claim 4: Jaganmohan discloses the method of claim 1, wherein the operational data comprises data from a sensor, a customer relationship management system, an enterprise resource planning system, or a point-of-sale system (See col. 8, ll. 35–53, wherein operational data is obtained from ERP and CRM systems).
Claim 6: Jaganmohan does not expressly disclose the elements of claim 6.
Mohanty discloses wherein the data model comprises a second large language model (See claims 1–4 and paragraphs 27 and 62, wherein the second machine learning model is an LLM, and wherein the LLM generates embeddings from received data).
One of ordinary skill in the art would have recognized that applying the known technique of Mohanty would have yielded predictable results and resulted in an improved system for the same reasons as stated above with respect to claim 1.
Claim 7: Jaganmohan discloses the method of claim 1, wherein prompting the model using the user query and the summarized operational data comprising the natural language description of the plurality of vectors comprises:
selecting a subset of the summarized operational data that semantically matches one or more words or phrases in the user query (See col. 20, ll. 4–22, wherein a prompt is generated by applying text matching techniques in conjunction with structural and semantic matching to identify data from the knowledge graphs that matches the request); and
generating a prompt comprising the subset of the summarized operational data and the user query (See col. 20, ll. 4–22, wherein a prompt is generated by applying text matching techniques in conjunction with structural and semantic matching to identify data from the knowledge graphs that matches the request). Jaganmohan does not expressly disclose the remaining claim elements.
Mohanty discloses prompting the first large language model (See FIG. 1 and paragraph 21, wherein a prompt to the language model is generated based on the request and the knowledge graph).
One of ordinary skill in the art would have recognized that applying the known technique of Mohanty would have yielded predictable results and resulted in an improved system for the same reasons as stated above with respect to claim 1.
Claim 8: Jaganmohan discloses the method of claim 1, wherein generating, based on the natural language response and the one or more properties of the operational data graph, the one or more visualizations corresponding to the natural language response comprises: selecting the one or more visualizations from a pre-determined set of visualizations (See col. 11, ll. 26–35, wherein data points and bar charts are visualized “when appropriate”; see also col. 16, ll. 4–30).
Claim 9: Jaganmohan discloses the method of claim 1, wherein the one or more properties of the operational data graph comprise an amount of data in the operational data graph (See FIG. 2B and col. 11, ll. 26–35, wherein data points and bar charts are visualized according to an amount of data).
Claim 10: Jaganmohan discloses the method of claim 1, wherein the one or more visualizations corresponding to the natural language response comprise histograms, line graphs, or bar charts (See FIG. 2B, col. 11, ll. 26–35, and col. 16, ll. 4–30).
Claim 11: Jaganmohan discloses the method of claim 1, further comprising: providing the natural language response to a user (See FIG. 2B).
Claim 12: Jaganmohan discloses the method of claim 1, further comprising: providing the one or more visualizations to a user (See FIG. 2B).
Claim 13: Examiner notes that the elements of claim 13 are afforded limited patentable weight. First, the elements do not affect any of the recited method steps, and as a result, the elements are afforded limited patentable weight. Second, the recited systems are merely “associated” with a venue comprising a plurality of sensors, such that none of the operational data necessarily comes from either the venue or any of the plurality of sensors. As a result, the elements are addressed only in the interest of compact prosecution.
Jaganmohan discloses the method of claim 1, wherein the operational data is generated by one or more systems associated with a venue comprising a plurality of sensors (See col. 8, ll. 35–53, wherein operational data is obtained from ERP and CRM systems).
Claim 14: Examiner notes that the elements of claim 14 are similarly afforded limited patentable weight. More particularly, the elements do no more than describe a field of use and do not affect any of the recited method steps. As a result, the elements are addressed only in the interest of compact prosecution. Jaganmohan does not expressly disclose the elements of claim 14.
Mohanty discloses wherein the venue is a stadium (See paragraph 23, wherein insights and content are disclosed in the context of sports).
One of ordinary skill in the art would have recognized that applying the known technique of Mohanty would have yielded predictable results and resulted in an improved system for the same reasons as stated above with respect to claim 1.
Claim 15: Jaganmohan discloses the method of claim 1, wherein: receiving the user query comprises receiving a first user input executed via a graphical user interface (See FIG. 2B and col. 16, ll. 4–30);
displaying the one or more visualizations corresponding to the natural language response comprises displaying the one or more visualizations on the graphical user interface (See FIG. 2B and col. 16, ll. 4–30).
Claim 16: Jaganmohan discloses the method of claim 15, comprising:
receiving a second user input via the graphical user interface comprising an interaction with the displayed visualization (See FIG. 2B and col. 2, ll. 49–51, wherein a second user request is received);
generating, based on the second user input, a second user query (See FIG. 2B and col. 2, ll. 49–51, wherein a second user request is received);
prompting the model using the second user query and the summarized operational data comprising the natural language description of the plurality of vectors (See FIG. 2B and col. 16, ll. 59–66, wherein prompts are generated based on the request and the knowledge graph);
receiving, in response to the prompting using the second user query, a second natural language response (See col. 16, l. 59–col. 17, l. 6, in view of FIG. 2B, wherein natural language responses are generated in response to received prompts); and
generating, based on the second natural language response and one or more properties of the operational data graph, an updated version of the or more visualizations corresponding to the second natural language response (See FIG. 2B and col. 16, ll. 4–30, wherein visualizations are generated based on the model response and knowledge graph). Jaganmohan does not expressly disclose the remaining claim elements.
Mohanty discloses prompting the first large language model using the second user query and the summarized operational data (See FIG. 1 and paragraph 21, wherein a prompt to the language model is generated based on the request and the knowledge graph; see also FIG. 6 and paragraph 66); and
receiving, in response to the prompting using the second user query, a second response to the prompting, a second response from the first large language model (See FIG. 1 and paragraph 21, wherein content is generated in response to the prompt; see also FIG. 6 and paragraph 66).
One of ordinary skill in the art would have recognized that applying the known technique of Mohanty would have yielded predictable results and resulted in an improved system for the same reasons as stated above with respect to claim 1.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WILLIAM S BROCKINGTON III whose telephone number is (571)270-3400. The examiner can normally be reached M-F, 8am-5pm, EST.
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, Rutao Wu can be reached at 571-272-6045. 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.
/WILLIAM S BROCKINGTON III/Primary Examiner, Art Unit 3623