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 .
DETAILED ACTION
2. This communication is responsive to the amendment filed on 04/13/2026.
3. Claims 1-23 are currently pending in this Office action. This action is made Final.
Claim Rejections - 35 USC § 103
4. In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
5. 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.
6. Claims 1-5, 7-8, 11-16, 18-19 and 22-23 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. 12,353,469 (hereinafter Mahabadi) in view of U.S. 12,259,913 (hereinafter Muschett).
Regarding claims 1, 12 or 23, Mahabadi discloses a computer-implemented method comprising:
detecting, by a computing device, an updated iteration of a source document (col. 2, lns. 55-64; “…Furthermore, where a document includes multiple versions or editions that are generated or updated periodically, or where questions to be answered based on such documents or conclusions to be drawn from such documents change over time, the tasks of reading and understanding such documents, or searching such documents for relevant sections, must often be repeated for each version or edition, and for each such question or conclusion”);
comparing, by the computing device, the updated iteration of the source document to a prior iteration of the source document to identify a given chunk of the updated iteration of the source document that differs from the corresponding chunk of the prior iteration of the source document, the prior iteration of the source document for generating a set of questions [synthetic question and answer pairs] using a large language model (col. 16, lns. 51-64; fig, 3 as shown below; “At box 320, the first embedding generated at box 315 is compared to embeddings or other vectors that are associated with documents of a knowledge base and stored in a data store, e.g., a vector store. In some implementations, a plurality of documents may be uploaded or otherwise provided to a processing system, and the documents may be divided into chunks and supplemented with metadata before being converted to embeddings…”);
responsive to identifying that the given chunk of the updated iteration of the source document differs from the corresponding chunk of the prior iteration of the source document, triggering generation, using the LLM, of a new set of questions [synthetic question and answer pairs] associated with corresponding text in the given chunk of the updated iteration of the source document (col. 8, lns. 1-51; col. 17, lns. 13-54;” At box 325, a set of documents relevant to the query is identified based on the first embedding and the embeddings associated with the knowledge base, such as by a similarity analysis of such embeddings… At box 330, the query is augmented to include additional information regarding a context of the query, including but not limited to temporal information regarding the query, e.g., or one or more relevant times or other attributes or features associated with the query, as well as any synopses, themes or other information or data regarding the query…”); and
replacing, in a database, at least a subset of the set of questions [synthetic question and answer pairs] associated with the source document, with the [new set of synthetic question and answer pairs], based on mapping that maps the given chunk of the updated iteration of the source document with the corresponding chunk of the prior iteration of the source document (col. 17, lns. 55-col. 18, lns. 48; “At box 330, the query is augmented to include additional information regarding a context of the query, including but not limited to temporal information regarding the query, e.g., or one or more relevant times or other attributes or features associated with the query, as well as any synopses, themes or other information or data regarding the query….”; “At box 350, the augmented query is provided as one or more inputs to a language model, such as an LLM, one or more natural language processing (or “NLP”), or natural language understanding (or “NLU”) models, or other models. For example, the augmented query may be provided to a modeling module…”; and “At box 360, a response to the query and one of the relevant documents identified as a source for the response are identified based on the output. The source document may be identified based on outputs received from language models, e.g., according to a retrieval-augmented generation (or “RAG”) technique…”).
Mahabadi does not explicitly disclose the system utilizing a set of synthetic question and answer pairs. However, Muschett discloses that “A system and method for improving computer functionality by retrieving answers/responses to questions/input such as those used with chatbots and generative AI systems…” (col. 1, lns. 33-43; col. 4, lns. 23-30) and it would have been obvious for one with ordinary skill in the art to utilize the teachings of Muschett in the system of Mahabadi in view of the desire to enhance the question answering system by utilizing the synthetic question-answer resulting in improving the efficiency of the document retrieving process. Additionally, Mahabadi discloses a non-transitory computer-readable medium (col. 12, lns. 1-9; fig. 2).
Regarding claims 2 and 13, Mahabadi in view of Muschett discloses the method further comprising: providing the new set of synthetic question and answer pairs to the LLM to cause the LLM to generate a response to a user query (Muschett: col. 1, lns. 33-43; col. 6, lns. 56-62). Therefore, the limitations of claims 2 and 13 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis.
Regarding claims 3 and 14, Mahabadi in view of Muschett discloses the method wherein generating the response further comprises:
generating, by the LLM, a textual response to the user query based on a similarity of the user query to at least one synthetic question of the set of synthetic question and answer pairs and the new set of synthetic question and answer pairs (Mahabadi: col. 6, lns. 63-col. 7, lns. 3; col. 16, lns. 51-64) and (Muschett: col. 7, lns. 29-41). Therefore, the limitations of claims 3 and 14 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis.
Regarding claims 4 and 15, Mahabadi in view of Muschett discloses the method wherein triggering generation of the new set of synthetic question and answer pairs is further based upon detecting a degree of difference between the given chunk of the updated iteration of the source document and the corresponding chunk of the prior iteration of the source document that exceeds a defined threshold (Mahabadi: col. 20, lns. 6-31) and (Muschett: col. 1, lns. 64-col. 2, lns. 12; col. 8, lns. 17-26). Therefore, the limitations of claims 4 and 15 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis.
Regarding claims 5 and 16, Mahabadi in view of Muschett discloses the method wherein identifying specific segments of text within the given chunk of the updated iteration of the source document which are modified compared to the corresponding chunk in the prior iteration of the source document; and triggering the generation of the new set of synthetic question and answer pairs for the specific segments of text (Mahabadi: col. 20, lns. 21-31) and (Muschett: col. 4, lns. 23-30; col. 9, lns. 46-50). Therefore, the limitations of claims 5 and 16 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis.
Regarding claims 7 and 18, Mahabadi in view of Muschett discloses the method wherein the degree of difference is based on at least one of a distance measure or a cosine similarity (Mahabadi: col. 6, lns. 6-26).
.
Regarding claims 8 and 19, Mahabadi in view of Muschett discloses the method further comprising:
providing a user interface configured to receive the user query; determining a similarity between the user query and synthetic questions of the set of synthetic question and answer pairs and the new set of synthetic question and answer pairs, to retrieve corresponding synthetic answers for providing to the LLM for generating the textual response to the user query; and displaying the textual response on a visual display of the user interface (Mahabadi: col. 15, lns. 56-col. 16, lns. 17; col. 18, lns. 49-61) and (Muschett: col. 6, lns. 56-62; col. 8, lns. 17-26). Therefore, the limitations of claims 8 and 19 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis.
Regarding claim 11 and 22, Mahabadi in view of Muschett discloses the method wherein generating the textual response to the user query comprises:
generating a prompt to the LLM, the prompt including the user query and a relevant set of question and answer pairs obtained from the set of synthetic question and answer pairs and the new set of synthetic question and answer pairs; providing the prompt to the LLM; and receiving, from the LLM, the generated textual response (Mahabadi: col. 25, lns. 8-27) and (Muschett: col. 2, lns. 14-17; col. 12, lns. 37-47). Therefore, the limitations of claims 11 and 22 are rejected in the analysis of claims 1 or 12, and the claims are rejected on that basis.
7. Claims 6 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Mahabadi in view of Muschett, and further in view of WO 2020/256754 (hereinafter De Matos).
Regarding claims 6 and 17, Mahabadi in view of Muschett discloses the method further comprising the features of utilizing the updated iteration of the source document; triggering the generation of the new set of synthetic question and answer pairs for the differing chunks (Mahabadi: col. 2, lns. 55-63) and (Muschett: col. 2, lns. 14-17; col. 12, lns. 37-47).
The references do not explicitly disclose the features of prior to performing the comparison, performing an initial checksum on an entire textual content [of the updated iteration] of the source document to determine whether an update exists in textual content of the source document as a whole; computing a hash on each chunk [of the updated iteration] of the source document; computing the hash on each chunk of the prior iteration of the source document; and comparing the hash on each chunk [of the updated iteration of the source document] to a corresponding chunk of the prior iteration of the source document to determine differing chunks. However, De Matos discloses that “Using the functionality of Fig. 6, a requester may verify if a record is valid using a third party validator by performing two simple steps: (1) compute a checksum hash of the record…” ([0073]); and “…One is to compare their text, without the last transaction, to make sure they all have the same identical original portion. Another way, is used in the embodiment of Fig. 9, is to take all checksums that were produced in step 3, and make sure they all match…” ([0094]). De Matos also discloses that “The verification functionality can be performed in any order,…(4) Verify signature and rule compliance for each transaction, one transaction at a time…” ([0061-0062]) and it would have been obvious for one with ordinary skill in the art to utilize the teachings of De Matos in the modified system of Mahabadi in view of the desire to enhance the feature of revising input prompts by applying the hashing scheme resulting in improving the efficiency of the document retrieving process.
8. Claims 9-10 and 20-21 are rejected under 35 U.S.C. 103 as being unpatentable over Mahabadi in view of Muschett, and further in view of U.S. 2024/0338659 (hereinafter Balasubramanian).
Regarding claims 9 and 20, Mahabadi in view of Muschett discloses the method further comprising:
performing content aware chunking on the updated iteration of the source document and the prior iteration of the source document by: accessing document metadata: and chunking based on the document structure relationships, the chunking for identifying differing chunks between the updated iteration of the source document and the prior iteration of the source document (Mahabadi: col. 12, lns. 10-38; col. 21, lns. 50-60) and (Muschett: col. 12, lns. 37-47).
The references do not expliiclty disclose the feature of accessing document metadata comprising document structure relationships providing at least one of section headers, subheaders and document boundaries. However, such feature is well known in the art as disclosed by Balasubramanian ([0052]; “At step 503, section headers of the business requirements document are identified. Step 503 can include using text related information such as font size, font style, text position, spacing or tabs in a document, etc. and/or other document type and layout metadata information as inputs to one or more natural language processing and/or machine learning models…For example, headers may be recognized based on bold font size, greater font size compared to a majority of other text in a business requirements document, enumeration or other outline structure (e.g., bullet points), alignment, etc.”) and it would have been obvious for one with ordinary skill in the art to utilize the teachings of Balasubramanian in the modified system of Mahabadi in view of the desire to enhance the question answering system by utilizing the document structure resulting in improving the efficiency of the document retrieving process.
Regarding claims 10 and 21, Mahabadi in view of Muschett and Balasubramanian disclose the method wherein chunking based on the document structure relationship comprises:
determining, via natural language processing, whether one or more sentences corresponding to a prior chunk and preceding a current chunk has a similar context; and responsive to determining that the one or more sentences has a similar context, merging the prior chunk and the current chunk into a single chunk for comparing between iterations (Mahabadi: col. 2, lns. 55-63; col. 21, lns. 50-60; col. 25, lns. 28-44) and (Muschett: col. 2, lns. 14-17; col. 12, lns. 37-47). Therefore, the limitations of claims 10 and 21 are rejected in the analysis of claims 9 or 20, and the claims are rejected on that basis.
Response to Arguments
9. Applicant’s arguments have been considered but are deemed to be moot in view of new grounds of rejection presented in this Office action.
Conclusion
10. 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 MONICA M PYO whose telephone number is (571)272-8192. The examiner can normally be reached Monday-Friday 8am-4pm.
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, APU MOFIZ can be reached at 571-272-4080. 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.
/MONICA M PYO/ Primary Examiner, Art Unit 2161
Prosecution Insights