DETAILED ACTION
1. This office action is in response to Applicant’s submission filed on 1/31/2025. Claims 1-20 are pending in the application and have been examined.
Notice of Pre-AIA or AIA Status
2. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
3. The information disclosure statements (IDSs) submitted on 1/31/2025 and 11/11/2025 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
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 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.
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.
5. Claims 1, 2, 6-15, and 17-20 are rejected under 35 U.S.C. 103 as unpatentable over U.S. Pat. Ap. Pub. No. 20250363146 (Jayaraman, hereinafter “Jay”) in view of U.S. Pat. Ap. Pub. No. 20250284888 (Khullar et al., hereinafter “Khu”).
With regard to Claim 1, Jay describes:
“A non-transitory computer readable medium having program instructions stored therein that are executable by a computing system to perform operations comprising:
receiving a request to populate multiple fields of a data structure with data extracted from text of a document; (Paragraph 92 describes that data parsed from a document is added to fields of a data structure.)
parsing the text using a large language model (LLM), (Paragraph 55 describes that an LLM is used to parse a main document. Paragraph 92 describes that fields such as page, line, and section numbers are parsed.)
applying a validation algorithm to results received from the LLM in response to the sequence of queries, wherein the validation algorithm confirms a presence of results in the text of the document; and (Paragraph 90 describes that validation rules are used to ensure extracted numbers follow a logical sequence throughout the document.)
populating the data structured with the validated results. (Paragraph 92 describes that fields such as page, line, and section numbers are added to the data structure.)
Jay does not explicitly describe “wherein the parsing includes issuing, to the LLM, a sequence of queries targeting individual ones of the multiple fields.” However, paragraph 34 of Khu describes generating multiple prompts for extracting data from the document.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the multiple queries as described by Khu into the system of Jay to extract all the relevant content, as described in paragraph 34 of Khu.
With respect to Claim 2, Jay describes “applying the validation algorithm includes: performing a word search of the text for ones of the results.” Paragraph 90 describes that the validation includes ensure the numbering is correct. The numbers constitute text.
With respect to Claim 6, Jay does not explicitly describe this subject matter. However, Khu describes “applying the validating algorithm includes: issuing a second sequence of queries asking the LLM to confirm the presence of results in the text of the document.” Paragraph 34 of Khu describes generating multiple prompts for extracting data from the document.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the multiple queries as described by Khu into the system of Jay to extract all the relevant content, as described in paragraph 34 of Khu.
With respect to Claim 7, Jay describes “the operations further comprising: prior to parsing the text, performing an optical character recognition (OCR) on the document to determine the text.” Paragraph 90 describes that the document can be scanned using OCR.
With respect to Claim 8, Jay describes “the OCR identifies text in one or more tables included in the document.” Paragraph 90 describes that the OCR is done using parameters allowing for different formatting situations. Data in a table is such a formatting situation.
With respect to Claim 9, Jay describes “the sequence of queries includes one or more queries asking the LLM to correct errors in the text determined from the OCR.” Paragraph 90 describes that the OCR is done using parameters that can handle errors such as missing page numbers.
With respect to Claim 10, Jay does not explicitly describe this subject matter. However, Khu describes “the document includes a contract; and wherein the multiple fields include a contract term of the contract.” Paragraph 107 of Khu describes the data structure being filled can include data parsed from a contract document, such as TradingContractType, which is cited as a “contract term.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the contract data as described by Khu into the system of Jay to allow the parsing of contract data, as described in paragraph 107 of Khu.
With respect to Claim 11, Jay does not explicitly describe this subject matter. However, Khu describes “the document includes a contract; and wherein the multiple fields include a number value associated with the contract.” Paragraph 107 of Khu describes the data structure being filled can include data parsed from a contract document, such as TradingContractNumber, which is cited as a “number value.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the contract data as described by Khu into the system of Jay to allow the parsing of contract data, as described in paragraph 107 of Khu.
With respect to Claim 12, Jay describes “A method, comprising:
receiving a request to validate multiple populated fields in a data structure with data extracted from text of a document; (Paragraph 92 describes that data parsed from a document is added to fields of a data structure.)
parsing the text using a large language model (LLM), (Paragraph 55 describes that an LLM is used to parse a main document. Paragraph 92 describes that fields such as page, line, and section numbers are parsed.)
applying a validation algorithm to results received from the LLM in response to the sequence of queries, wherein the validation algorithm confirms a presence of results in the text of the document; and (Paragraph 90 describes that validation rules are used to ensure extracted numbers follow a logical sequence throughout the document.)
comparing the validated results with data included in the multiple populated fields. (Paragraph 92 describes that fields added to the data structure are equal to the validated data parsed from the text.)
Jay does not explicitly describe “wherein the parsing includes issuing, to the LLM, a sequence of queries targeting individual ones of the multiple populated fields.” However, paragraph 34 of Khu describes generating multiple prompts for extracting data from the document.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the multiple queries as described by Khu into the system of Jay to extract all the relevant content, as described in paragraph 34 of Khu.
With respect to Claim 13, Jay does not explicitly describe this subject matter. However, Khu describes “altering data in one or more of the populated fields in the data structure in response to the data in the one or more populated fields not matching one or more of the validated results.” Paragraph 133 describes that an API query includes a populated data structure. Paragraph 134 describes that the data structure is validated, and any errors are corrected.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the validated data structure as described by Khu into the system of Jay to provide correct query results, as described in paragraph 134 of Khu.
With respect to Claim 14, Jay does not explicitly describe this subject matter. However, Khu describes “in response to the comparing including a mismatch, triggering a need to take a corrective action associated with the document.” Paragraph 133 describes that an API query includes a populated data structure. Paragraph 134 describes that the data structure is validated, and any mismatches are corrected.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the validated data structure as described by Khu into the system of Jay to provide correct query results, as described in paragraph 134 of Khu.
With respect to Claim 15, Jay does not explicitly describe this subject matter. However, Khu describes “sending a sequence of follow-up queries asking the LLM to confirm the presence of results in the text of the document.” However, paragraph 34 of Khu describes generating multiple prompts for extracting data from the document.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the multiple queries as described by Khu into the system of Jay to extract all the relevant content, as described in paragraph 34 of Khu.
With respect to Claim 17, Jay describes “A non-transitory computer readable medium having program instructions stored therein that are executable by a device to perform operations comprising:
parsing text of a document using a large language model (LLM), (Paragraph 55 describes that an LLM is used to parse a main document. Paragraph 92 describes that fields such as page, line, and section numbers are parsed.)
applying a validation algorithm to results received from the LLM in response to the sequence of queries, wherein the validation algorithm confirms a presence of results in the text of the document; and (Paragraph 90 describes that validation rules are used to ensure extracted numbers follow a logical sequence throughout the document.)
Jay does not explicitly describe “wherein the parsing includes issuing, to the LLM, a sequence of queries targeting multiple fields associated with the document” or “based on the validated results, issuing one or more instructions to perform one or more actions in accordance with the document.”
However, paragraph 34 of Khu describes generating multiple prompts for extracting data from the document.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the multiple queries as described by Khu into the system of Jay to extract all the relevant content, as described in paragraph 34 of Khu.
Paragraph 107 further describes that actions can be taken based on the parsed document. For example, the action to CreateContractFromBid can be taken.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the contract data as described by Khu into the system of Jay to allow the parsing and execution of contract data, as described in paragraph 107 of Khu.
With respect to Claim 18, Jay describes “the one or more actions include modifying a data structure including multiple fields populated with data extracted from the text of the document. Paragraph 92 describes that fields added to the data structure are equal to the validated data parsed from the text.
With respect to Claim 19, Jay describes “applying the validation algorithm includes searching the text for ones of the results.” Paragraph 90 describes that the validation includes ensure the numbering is correct. The numbers constitute text.
With respect to Claim 20, Jay describes “applying the validating algorithm includes asking the LLM to confirm the presence of results in the text of the document.” Paragraph 90 describes that validation rules are used to ensure extracted numbers follow a logical sequence throughout the document.
6. Claims 3-5 and 16 are rejected under 35 U.S.C. 103 as unpatentable over Jay in view of Khu and further in view of U.S. Pat. Ap. Pub. No. 20220164364 (Funk et al., hereinafter “Funk”).
With respect to Claim 3, Jay in view of Khu does not explicitly describe this subject matter. However, Funk describes “parsing uses a plurality of parsing algorithms including a first algorithm based on the LLM.” Paragraph 120 describes the user of multiple parsers.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the multiple parsers as described by Funk into the system of Jay in view of Khu to allow comparison of results, as described in paragraph 120 of Funk.
With respect to Claim 4, Jay in view of Khu does not explicitly describe this subject matter. However, Funk describes “the plurality of parsing algorithms includes a second algorithm based on regular expressions targeting individual ones of the multiple fields.” Paragraph 120 describes the user of multiple parsers for parsing various fields of the document.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the multiple parsers as described by Funk into the system of Jay in view of Khu to allow comparison of results, as described in paragraph 120 of Funk.
With respect to Claim 5, Jay in view of Khu does not explicitly describe this subject matter. However, Funk describes “applying the validation algorithm includes: determining whether a consensus exists among the plurality of parsing algorithms.” Paragraph 120 describes the user of multiple parsers whose results are compared to determine a consensus.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the multiple parsers as described by Funk into the system of Jay in view of Khu to allow comparison of results, as described in paragraph 120 of Funk.
With respect to Claim 16, Jay in view of Khu does not explicitly describe this subject matter. However, Funk describes “the parsing includes using a plurality of parsing algorithms, wherein using the LLM is one of the plurality of parsing algorithms; and wherein applying the validation algorithm includes determining whether a consensus exists among the plurality of parsing algorithms.” Paragraph 120 describes the user of multiple parsers whose results are compared to determine a consensus.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to include the multiple parsers as described by Funk into the system of Jay in view of Khu to allow comparison of results, as described in paragraph 120 of Funk.
Conclusion
7. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
U.S. Pat. No. 12,141,161 (Singhal) also describes parsing data and adding it to data structures.
8. Any inquiry concerning this communication or earlier communications from the examiner should be directed to EDWARD TRACY whose telephone number is (571)272-8332. The examiner can normally be reached Monday-Friday 9 AM- 5PM.
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, Bhavesh Mehta can be reached on 571-272-7453. 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.
/EDWARD TRACY JR./Examiner, Art Unit 2656
Prosecution Insights