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 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.
Claim(s) 1-3, 7, 8-10, 14, and 15-17 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by U.S. Patent Application Publication 20110119212 by De Bruin et. al. (hereafter De Bruin).
Claim 1:
De Bruin discloses:
“processing an intermediary structured document generated by a first generative artificial intelligence (Al) model using a plurality of predefined prompts;”[ processing an intermediary structured document generated(0123, produces diagnosis/treatment planning report) by a first generative artificial intelligence (Al) model (0123, digital clinician or the medical digital expert system; fig. 7 medical system analysis of data set 1) using a plurality of predefined prompts (0123, first a set of clinical laboratory data and symptomatic information are input into the software 165. …processes the data)]
“comparing the intermediary structured document with a curated structured document;”[ comparing (fig. 7 168, need for more reliability and confidence) the intermediary structured document (0123, diagnosis/treatment-planning report) with a curated structured document (0123, accompanied with confidence values or decision likelihood values)]
“generating a scoring of the intermediary structured document based upon, at least in part, the comparing of the intermediary structured document with a curated structured document; and”[ generating a scoring (0123, decision reliability) of the intermediary structured document (0123, produces diagnosis/treatment planning report;) based upon, at least in part, the comparing(0123, user may need more decision reliability; fig. 7 168) of the intermediary structured document (0123, diagnosis/treatment-planning report; fig. 7 167) with a curated structured document(0123, accompanied with confidence values or decision likelihood values)]
“generating one or more revisions for the plurality of predefined prompts by processing the scoring of the intermediary structured document using a second generative Al model.”[ generating one or more revisions for the plurality of predefined prompts (fig. 7 171, data set 1 and 2)by processing the scoring (0123, decision reliability; fig. 7 168) of the intermediary structured document (0123, diagnosis/ treatment planning report) using a second generative Al model (fig. 7 medical expert system analysis of data sets 1 and 2)]
Claim 2:
De Bruin discloses: “The computer-implemented method of claim 1, wherein the intermediary structured document is a medical record generated by the first generative Al model using the plurality of predefined prompts and medical data.”[ wherein the intermediary structured document (0123, produces diagnosis/treatment planning report;)is a medical record((0123, produces diagnosis/treatment planning;)) generated by the first generative Al model(0123, digital clinician or the medical digital expert system; fig. 7 medical system analysis of data set 1) using the plurality of predefined prompts (0123, first a set of clinical laboratory data and symptomatic information are input into the software 165. …processes the data) and medical data (0123, symptomatic information/laboratory data)]
Claim 3:
De Bruin discloses: “The computer-implemented method of claim 2, wherein the curated structured document is a medical record annotated by a medical professional.”[ wherein the curated structured document is a medical record(0123, accompanied with confidence values or decision likelihood values) annotated by a medical professional (0123, user may need more decision reliability)]
Claim 7:
De Bruin discloses:”The computer-implemented method of claim 1, wherein generating the one or more revisions for the plurality of predefined prompts includes generating a plurality of revisions to be applied incrementally to the plurality of predefined prompts over a plurality of updates of the plurality of predefined prompts using a predefined relative prioritization.”[ wherein generating the one or more revisions (fig. 7 171 data sets 1 and 2) for the plurality of predefined prompts(0123, first a set of clinical laboratory data and symptomatic information are input into the software 165. …processes the data) includes generating a plurality of revisions to be applied incrementally (fig. 7 170, in addition to data set 1 or as revised version of it) to the plurality of predefined prompts (0123, first a set of clinical laboratory data and symptomatic information are input into the software 165. …processes the data) over a plurality of updates (fig. 7 170, 175) of the plurality of predefined prompts (0123, first a set of clinical laboratory data and symptomatic information are input into the software 165. …processes the data) using a predefined relative prioritization (fig. 7, data set 1, data set 2, data set 3; 1 before 2, 2 before 3, and 1 and 2 before 3)]
Claim 8-10 and 14:
Claims 8-10 and 14 recite similar limitations as that of claims 1-3 and 7 except that claims 8-10 and 14 are directed to a system instead of a method. Claims 8-10 and 14 are rejected under similar rationale as that of claims 1-3 and 7. Regarding memory and processor, De Bruin discloses this at 0132 as a computer.
Claim 15-17:
Claims 15-17 recite similar limitations as that of claims 1-3 except that claims 15-17 are directed to a computer program product instead of a method. Claims 15-17 are rejected under similar rationale as that of claims 1-3. De Bruin further discloses a non-transitory computer readable medium and processor at 0132 as a computer.
Claim(s) 1, 8, and 15 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by “Enhancing AI Decision-Making with Multi-AI voting mechanism: Large Action Model and Java” by Vishal Mysore (hereafter Mysore).
Claim 1:
Mysore discloses:
“processing an intermediary structured document generated by a first generative artificial intelligence (Al) model using a plurality of predefined prompts;”[ processing an intermediary structured document generated(page 4, appropriate action) by a first generative artificial intelligence (Al) model (page 4, gemini) using a plurality of predefined prompts (page 4 prompt; page 4 once the action is determined, the AI systems examine the parameters associated with it)]
“comparing the intermediary structured document with a curated structured document;”[ comparing (page 4, voting process) the intermediary structured document (page 4, appropriate action) with a curated structured document (page 4, open ai determination & local ai selection of action)]
“generating a scoring of the intermediary structured document based upon, at least in part, the comparing of the intermediary structured document with a curated structured document; and”[ generating a scoring (page 4 consensus on chosen action) of the intermediary structured document (page 4 action) based upon, at least in part, the comparing(page 4 voting process) of the intermediary structured document (page 4, appropriate action) with a curated structured document(page 4, open ai determination & local ai selection of action)]
“generating one or more revisions for the plurality of predefined prompts by processing the scoring of the intermediary structured document using a second generative Al model.”[ generating one or more revisions for the plurality of predefined prompts (page 6, parameters for event title, date and attendees, parameters for the room, date, and duration))by processing the scoring (page 6, doesn’t reach consensus) of the intermediary structured document (page 5, gemini action) using a second generative Al model (page 5, openai / localai)]
Claim 8:
Claim 8 recites similar limitations as that of claim 1except that claim 8 is directed to a system instead of a method. Claim 8 is rejected under similar rationale as that of claim 1. Regarding memory and processor, Mysore discloses this at page 1 as a mechanism.
Claim 15:
Claim 15 recites similar limitations as that of claim 1 except that claim 15 is directed to a computer program product instead of a method. Claim 15 is rejected under similar rationale as that of claim 1. Mysore further discloses a non-transitory computer readable medium and processor at page 1 as a mechanism.
Allowable Subject Matter
Claims 4-6, 11-13, and 18-20 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
U.S. 12541545 by Thanvantri Vasudevan et. al. provides some relevance at figure 13 wherein there is a ground truth document generated from a trained ML model and a summary of the electronic document generated from another ml model, there is further comparison of the ground truth document and summary of the electronic document, and there is also a match determination. Document generated from a first generative ai model appears disclosed, comparing generated document from a first generative ai model to another document appears to be disclosed, and a scoring of the generated document appears to be disclosed as there is a match; however Thanvantri does not appear to revise predefined prompts.
Pct/us2025/037496 lists U.S. 20180113676 as teaching elements of the claimed limitations; however, while the prior art is of some relevance, the cited portions do not appear to be specific enough teach the claimed elements.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL PHAM whose telephone number is (571)272-3924. The examiner can normally be reached M-F 11-730pm Eastern.
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, Kavita Stanley can be reached at 571-272-8352. 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.
/MICHAEL PHAM/Primary Examiner, Art Unit 2153
Prosecution Insights