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 .
Response to Arguments
Applicant’s arguments with respect to claims 1 - 21 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant argues that Hunter et al. do not teach based on a response to the first LLM query, construct and output a second LLM query asking for modified software code (Amendment, pages 6 – 9).
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 – 21 are rejected under 35 U.S.C. 103 as being unpatentable over Hunter et al. (US PAP 2025/0298816) in view of Gandhi et al. (US PAP 2024/0378399).
As per claims 1, 14, and 19, Hunter et al. teach a system, comprising:
a user data store containing items of software code, each item being associated with an item identifier (“The document metadata can include a document title, a document date, or information indicating one or more parties party to the document.”; paragraphs 4, 5, 76 - 79); and
a context enhancement platform, coupled to the user data store, including (“LLM maximum context window”; paragraphs 24, 43):
a computer processor, and a computer memory storing instructions that when executed by the computer processor cause the context enhancement platform to (paragraphs 80 – 82):
receive a user request to perform a software coding task from a user device (“receiving, from a user, a query related to a document… The computer 1302 can respond to the received requests by processing the received requests using software applications”; paragraphs 4, 76 - 79);
construct and output a first Large Language Model ("LLM") query, from a context selector to a first LLM, the first LLM query being designed identified relevant items of software code from the user data store (“submitting the document to a first large language model along with a first prompt prompting the first large language model to generate an outline of the document”; paragraphs 3 – 5, 76 - 79), and
based on a response to the first LLM query, construct and output a second LLM query, from a prompt generator to a second LLM, the second LLM query including information about the relevant items (“submitting the document to a first large language model along with a first prompt prompting the first large language model to generate an outline of the document; receiving a document outline of the document from the first large language model; submitting the document to a second large language model along with a second prompt prompting the second large language model to generate metadata of the document…The computer 1302 can respond to the received requests by processing the received requests using software applications.;”; paragraphs 3 – 5, 30 – 32, 76 - 79).
However, Hunter et al. do not specifically teach based on a response to the first LLM query, construct and output a second LLM query asking for modified software code.
Gandhi et al. disclose generating a first prompt for a first large language model (LLM) based on the first natural language query and the document context information; providing the first prompt to the first LLM to obtain a first program code, which when executed, causes the first application to perform the one or more actions, the first program code being implemented in a domain specific language (DSL); analyzing a syntax of the first program code to identify syntax errors in the first program code by parsing the first program code into an abstract syntax tree structure which represents the structure of the first program code; and comparing the abstract syntax tree structure with a syntax definition for the DSL to identify the syntax errors; correcting the syntax errors in the first program code to generate corrected program code by updating the abstract syntax tree structure according to the syntax definition for the DSL; and causing the first client device to execute the first program code to perform the one or more actions in the first application on the first client device… The prompt concatenation unit 614 then concatenates the natural language query, the document context information (if any), the DSL program code sample or samples, and the grounded textual content into the prompt to be provided to the LLM 222 to cause the LLM 222 to generate the DSL program code that includes knowledge-grounded information… generating a first prompt for a first large language model (LLM) based on the first natural language query from the first user and the one or more DSL program code samples. As discussed in the preceding examples, the application services platform 210 analyzes the natural language query and document content information (if modifying existing content), identifies sample DSL program code that implements the user intent expressed in the natural language query and the document content information, and provides the prompt to the LLM 222. (paragraphs 3, 68 – 78).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective date of the claimed invention to modify the software code as taught by Gandhi et al. in Hunter et al., so that the correctness of the DSL program code output by the LLM 222 is improved by ordering the samples in the prompt (paragraph 61).
As per claims 2, 20, Hunter et al. further disclose that information about a response to the second LLM is transmitted to the user device (“The second LLM 116 can, in response to the second prompt, generate document metadata, such as a document title, a document date, and information regarding parties that are party to the document”; paragraphs 3 – 6, 25- 32).
As per claim 3, Hunter et al. further disclose the items are documents and the item identifiers are document titles (“The document metadata can include a document title, a document date, or information indicating one or more parties party to the document.”; paragraphs 5, 66).
As per claim 4, Hunter et al. further disclose the documents comprise files and the document titles are file names (“A document may be stored in a portion of a file that holds other documents, in a single file dedicated to the document in question, or in multiple coordinated files.”; paragraphs 28, 39, 66).
As per claims 5, 15, Hunter et al. further disclose the items in the user data store are arranged in a hierarchy and the first LLM query is further based on information about the hierarchy (“Each LLM can be selected for a task or sub-task based on different features or capabilities of the LLM, such as size limits, speed, and/or ability to perform certain types of tasks. An output of one LLM selected for one task may be fed as an input to another LLM that is selected for a next task or sub-task, for eventual generation of the natural language response to the query.”; paragraphs 3 – 6, 24, 25).
As per claims 6, 16, Hunter et al. further disclose the context enhancement platform is associated with an Artificial Intelligence ("AI") coding assistant (“The structured data can provide semantic context for the LLM, such as a document overview and/or document structure relevant to the query, which can result in a more accurate and meaningful answer than may be generated if a single LLM was used to generate an answer based just on the user's query and the document. In general, the different LLMs that are selected, either for intermediate tasks or for generating the natural language response, can be selected based on LLM processing speed, LLM maximum context window, LLM proficiency for certain tasks or types of subject matter, LLM resource usage or cost, or other factors.”; paragraphs 2 - 6, 24, 76 – 79).
As per claims 7, 17, Hunter et al. further disclose the second LLM query is further based on (i) a user selected code portion, and (ii) user selected open code window tabs (paragraphs 2 - 6, 76 – 79).
As per claims 8, 21, Hunter et al. further disclose the second LLM query includes information about (i) a user request history, (ii) instructions about how the items interact, and (iii) a requested output format (“Each LLM can be selected for a task or sub-task based on different features or capabilities of the LLM, such as size limits, speed, and/or ability to perform certain types of tasks. An output of one LLM selected for one task may be fed as an input to another LLM that is selected for a next task or sub-task, for eventual generation of the natural language response to the query.”; paragraphs 2 - 6, 76 – 79).
As per claim 9, Hunter et al. further disclose the user device is associated with an automated Artificial Intelligence ("AI") agent (“generative artificial intelligence. These technologies generally involve using a set of multiple large language models (LLMs) to generate a natural language response regarding, e.g., in response to, a query relevant to a document.”; paragraphs 2 – 6).
As per claim 10, Hunter et al. further disclose the first and second LLM comprise a single LLM (paragraphs 3 – 6, 24).
As per claim 11, Hunter et al. further disclose the second LLM is a different model than, and independent of, the first LLM(“an improved document question answering system can use a set of layered LLMs, where different LLMs can be selected and used for different tasks.”; paragraphs 3 – 6, 24).
As per claim 12, Hunter et al. further disclose the first LLM is internal to the context enhancement platform and the second LLM is external to the context enhancement platform (paragraphs 24 – 27, 30 – 38).
As per claim 13, Hunter et al. further disclose the user data store contains a user table and the items are portions of the user table (paragraphs 36, 49 -54).
As per claim 18, Hunter et al. further disclose the internal and external LLMs comprise one of: (i) a single LLM, and (ii) an external LLM different than, and independent of, the internal LLM (paragraphs 3 – 6, 24).
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 LEONARD SAINT-CYR whose telephone number is (571)272-4247. The examiner can normally be reached Monday- Friday.
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, Richemond Dorvil can be reached at (571)272-7602. 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.
/LEONARD SAINT-CYR/ Primary Examiner, Art Unit 2658