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 .
Examiner’s Note
Examiner has cited particular columns and line numbers or figures in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant, in preparing the responses, to
fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner.
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(s) 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Zadeh et al. (US 2025/0315691) and in view of Sassak et al. (US 2025/0272506).
As to claim 1, Zadeh teaches a system (Figs.1-2), comprising: at least one processor; and at least one memory that stores executable instructions that, when executed by the at least one processor, facilitate performance of operations, comprising: generation, by a system (LLM130/180) embeddings from documents (Pars.15-20);
based on receiving 210 a user input and a tag (identified content/intent in user input110) at a large language model 130, wherein the input and the at least one tag are associated with a user account 170, performing, by the system 130, a similarity search (240) between the at least one tag 110 and the auto-tags (predesigned prompts 120/220) to identify the embeddings 140 that correspond to the prompt 110, and ranking, the embeddings that correspond to the prompt based on a degree of similarity between the at least one tag and the respective auto-tags, to produce ranked embeddings (The set of embeddings are ranked based on the generated similarity scores. A highest ranked embedding, in the set of embeddings, that corresponds to a particular prompt in the subset is identified. The particular prompt may be automatically input to the second LLM )(140/160); identifying, by the system (150), a context based on the ranked embeddings (0025 the identified content in user input 110 is matched to identified context from a prompt in prompt bank 120 in order to determine context); prompting 295, by the system 150, the large language model (180) with the prompt and the context to produce a result ([0057] At block 295, the selected prompt(s) are used as input to a target LLM, which may be different than the LLM that performed the contextual analysis. The selected prompt(s) serve as input for generating responses or content that aligns with the context extracted from the initial text input); and making, by the system 170, the result available to the user account (Abstract; Pars.24-33, 43-52; Figs.1-2).
PNG
media_image1.png
296
786
media_image1.png
Greyscale
It is noted that Zadeh doesn’t explicitly teach the details of generating the embeddings. However, Sassak in same field teaches obtaining an input (that is formatted/tagged) embedding associated with the user input; retrieving a synthetic question embedding (auto-tags) from an embeddings database, based on a similarity to the input embedding; obtaining a source text based on a stored mapping between the synthetic question embedding and the source text; using a large language model (LLM), generating a textual response to the user input, based on the user input and the source text; and providing the generated textual response for display, wherein generating the embedding comprises splitting the documents into chunks/tokens and converting the tokens into embeddings (Figs.1-5; Pars. 64, 94-105).
The combination of the analogous arts would be obvious to one of ordinary skill in the art before the time of applicant’s invention for the purpose of efficiently generating the embedding database.
As to claim 2, it is inherent that for a second/subsequent prompt similarity search between the second prompt and the auto-tags 120/135 will be performed at system 150 to identify the embeddings 140 that correspond to the second prompt and the group of the auto-tags that corresponds to the embeddings.
As to claim 3, Zadeh teaches wherein making the result available via the user account comprises: attaching at least one auto-tag (prompt) of the respective auto-tags to the result (Fig.3, 280).
As to claim 4, Zadeh teaches receiving ranking preference data via the user account that indicates a preference of rankings of the at least one auto-tag (Fig.290; Pars.31-32).
As to claim 5, Zadeh teaches where contexts are determined for the user input and results are generated based on the input and determined context as addressed above.
As to claims 6-7, Sassak teaches an operation comprising storing respective first associations between the respective auto-tags (synthetic prompts) and the respective chunks as respective key-value pairs comprising the respective auto-tags and the respective chunks (Fig.6; Pars.95, 118-119)
Regarding claims 8-12, 15-17, the corresponding instructions and method comprising the steps similar to the claims addressed above are analogous, therefore rejected as being unpatentable over Zadeh and in view of Sassak for the foregoing reasons..
As to claims 13-14, Zadeh teaches wherein the document comprises a table, and wherein the respective auto-tags 120 identify table name keywords of the table, column name keywords of the table, or row name keywords of the table (Pars.50-51) and Sassak teaches a stored mapping where the mapping includes information identifying the source document from which the synthetic prompt was generated, including the specific portion of the source documents from which the associated synthetic question was produced. (Pars.10, 94-95,106).
As to claims 18-20, Sassak teaches storing respective associations between the auto-tags and the embeddings as respective triplets comprising respective keys/tokens, the auto-tags, and respective vectors (Pars.38, 60-66, 106-107).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DANIEL DEMELASH ABEBE whose telephone number is (571)272-7615. The examiner can normally be reached monday-friday 7-4.
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.
/DANIEL ABEBE/Primary Examiner, Art Unit 2657