DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Objections
Claims 2, 9, and 16 are objected to because of the following informalities: the acronym “API” should be spelled out the first time it is used in a claim set. Appropriate correction is required.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 8, and 15 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Larson et al. (US Pub 2025/0131289).
Regarding claim 1, Larson discloses a method comprising:
extracting, by a computing device, key content from a question prompt using key information extraction and lexical analysis (para 0047, 0052, 0079), wherein the question prompt is received from a client device (para 0099, 0132 – “receive the user query”; also see fig. 19, element 1902);
generating, by the computing device, an enriched question based on the question prompt and relevant node information, wherein the relevant node information is based on relevant graph nodes obtained by matching the key content with nodes in a knowledge graph (para 0081; para 0043-0044, 0047 – query plus node/relationship context is the “enriched question”);
processing, by the computing device, the enriched question with a machine learning model to generate an answer to the question prompt (para 0082, 0118-0120; fig. 20); and
transmitting, by the computing device, the answer to the question prompt received from the machine learning model to the client device (para 0097, 0099; figs. 9C, 10D).
Regarding claims 8 and 15, see rejection of claim 1.
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 2-7, 9-14, and 16-20 are rejected under 35 U.S.C. 103 as being unpatentable over Larson et al. (US Pub 2025/0131289) in view of Byrne et al. (US Pub 2023/0197070).
Regarding claim 2, Larson discloses the method of claim 1.
Larson does not disclose further comprising: providing, a function invocation response from an API to the machine learning model to integrate data from an internal system as predefined functions.
Byrne discloses further comprising: providing, a function invocation response from an API to the machine learning model to integrate data from an internal system (para 0031 – such as local device location via api) as predefined functions (para 0030-0033).
Therefore, it would have been obvious to a person of ordinary skilled in the art before the effective filing date of the claimed invention to modify Larson with the teachings of Byrne in order to predict both program invocations and user responses with high accuracy, thereby simplifying the architecture of the system and eliminating the need for hand-written rules (Byrne, para 0023).
Regarding claim 3, Byrne discloses wherein the providing the function invocation response to the machine learning model further comprises:
receiving, from the machine learning model by the computing device, a recommendation for a function invocation with corresponding parameters (para 0030);
in response to determining the machine learning model recommends the function invocation, providing, by the computing device, the function invocation with the corresponding parameters to the API (para 0030-0031; fig. 5, element 508); and
receiving, from the API by the computing device, a response to the function invocation (para 0032; fig. 5, element 510);
providing, to the machine learning model by the computing device, the enriched question with the response to the function invocation (para 0032-0033); and
providing, to the client device by the computing device, the answer, wherein the answer received from the machine learning model is determined using the enhanced question and the response to the function invocation (0034-0036 and 0040-0044).
Regarding claim 4, Larson discloses wherein the question prompt further comprises two or more question prompts, and wherein a graphical user interface is generated and transmitted to the client device comprising a chatbot configured to receive the two or more question prompts and provide one or more answers (fig. 10D and para 0045 – “What is Novorossiya and what are its targets?”).
Regarding claim 5, Larson discloses wherein the graphical user interface comprising the chatbot is generated and provided to one or more users at a respective one or more client devices, and wherein a report is generated to address the two or more question prompts from the one or more users to summarize a best solution to the two or more question prompts (fig. 10D and para 0045 – “What is Novorossiya and what are its targets?”).
Regarding claim 6, Larson discloses further comprising:
generating and transmitting, by the computing device, the report to one of the one or more client devices, wherein the report is generated by classifying and grouping the two or more question prompts using the knowledge graph, and wherein the one or more answers to the two or more question prompts is enhanced using the knowledge graph based on the grouping of the two or more question prompts (fig. 10D and para 0045 – 0048).
Regarding claim 7, Larson discloses wherein the knowledge graph is generated by extracting key points and relationships between the key points (para 0011, 0019, 0021) from internal and external resources (para 0013, 0018) and wherein the nodes and associations between the nodes in the knowledge graph are generated based on the key points and relationships (para 0021, 0026).
Regarding claims 9 and 16, see rejection of claim 2.
Regarding claims 10 and 17, see rejection of claim 3.
Regarding claims 11 and 18, see rejection of claim 4.
Regarding claims 12 and 19, see rejection of claim 5.
Regarding claim 13, see rejection of claim 6.
Regarding claims 14 and 20, see rejection of claim 7.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NAFIZ E HOQUE whose telephone number is (571)270-1811. The examiner can normally be reached M-F 8-5.
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, Ahmad Matar can be reached at (571)272-7488. 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.
/NAFIZ E HOQUE/ Primary Examiner, Art Unit 2693
Prosecution Insights