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 claim(s) 1-20 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.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-4, 7-12 & 15-20 are rejected under 35 U.S.C. 103 as being unpatentable over Tunstall-Pedoe, US Patent Pub. 20130262125 A1, in view of Bell et al, US Patent Pub. 20240406166 A1, in view of Shakarian et al, US Patent Pub. 20240427986 A1.
Re Claim 1, Tunstall-Pedoe discloses a method performed by at least one processor comprising: generating, based on inputting an input query into a large language model (LLM), N sample responses, N being an integer greater than zero (fig. 7; para 0038: multiple answers to a query question; wherein multiple answers imply more than zero different answers); determining, for each sample response, each fact statement included in a respective response (para 1057: answers with facts that exceed a fact threshold are selected for query answering); determining, for each determined fact statement, an endorsement score indicating an accuracy of the fact statement as a response to the input query (para 1057: answers with facts that exceed a fact threshold are selected for query answering); selecting each fact statement having an endorsement score greater than a threshold (para 1057: answers with facts that exceed a fact threshold are selected for query answering); and generating a final response to the input query based on each selected fact statement (para 1057: answers with facts that exceed a fact threshold are selected for query answering); but fails to disclose generating, based on inputting an input query into a large language model (LLM). However, Bell et al teaches the concept of a user input query being transmitted to a large language model to process for answers (Bell et al, para 0156). It would have been obvious to modify the Tunstall-Pedoe system such that a LLM is utilized to process the input queries as taught in Bell et al since LLM are more often used for question answering and also include the ability to condense large amounts of text into shorter, more concise summaries along with translation capabilities.
The combined teachings of Tunstall-Pedoe and Bell et al fail to disclose accuracy of the response fact statement to the input query being based on a degree of consistency with other sample responses from the N sample responses. However, Shakarian et al teaches the concept of outputting responses to input prompts where inconsistent responses are deemed as invalid responses/non-factual responses and being able to determine valid responses to input prompts is carried out by comparing the responses to determine inconsistency thus implying that less inconsistencies between responses deems a response as valid/factual response (Shakarian et al, para 0026). It would have been obvious to modify the Tunstall-Pedoe system such that factual responses(responses above the factual threshold of Tunstall-Pedoe) are compared to each other to select the responses with higher consistency between each other as taught in Shakarian et al for the purpose of making sure the selected factual responses are put through a robust process to select factual responses that are not only above a threshold but also more consistent.
Re Claim 2, the combined teachings of Tunstall-Pedoe, Bell et al and Shakarian et al disclose the method according to claim 1, wherein the input query is input into the LLM N times to generate the N sample responses, wherein each sample response is different from each other (Tunstall-Pedoe, fig. 7; para 0038: multiple answers to a query question; wherein multiple answers imply more than zero different answers).
Re Claim 3, the combined teachings of Tunstall-Pedoe, Bell et al and Shakarian et al disclose the method according to claim 1, wherein the determining, for each sample response, each fact statement comprises: inputting, into the LLM (Bell et al, para 0156: input query is transmitted to a LLM for processing of answers), the respective response and a predetermined instruction for identifying each fact statement in the respective response (Tunstall-Pedoe, para 1057: answers with facts that exceed a fact predetermined threshold are selected for query answering), and wherein the output of the LLM corresponds to each fact statement in the respective response (Tunstall-Pedoe, para 1057: answers with facts that exceed a fact predetermined threshold are selected for query answering).
Re Claim 4, the combined teachings of Tunstall-Pedoe, Bell et al and Shakarian et al disclose the method according to claim 1, wherein the instruction is a text string that instructs the LLM to determine each fact statement in the respective response (Tunstall-Pedoe, para 0211: query answer depends on context included in the input query).
Re Claim 7, the combined teachings of Tunstall-Pedoe, Bell et al and Shakarian et al disclose the method according to claim 1, wherein the generating the final response comprises selecting the response having the determined fact statements with the highest endorsement score (Tunstall-Pedoe, para 1057: answers with facts that exceed a fact predetermined threshold are selected for query answering).
Re Claim 8, the combined teachings of Tunstall-Pedoe, Bell et al and Shakarian et al disclose the method according to claim 1, wherein the generating the final response comprises inputting into the LLM the input query and each fact statement having an endorsement score above the threshold (Tunstall-Pedoe, para 1057: answers with facts that exceed a fact predetermined threshold are selected for query answering).
Claim 9 has been analyzed and rejected according to claim 1.
Claim 10 has been analyzed and rejected according to claim 2.
Claim 11 has been analyzed and rejected according to claim 3.
Claim 12 has been analyzed and rejected according to claim 4.
Claim 15 has been analyzed and rejected according to claim 7.
Claim 16 has been analyzed and rejected according to claim 8.
Claim 17 has been analyzed and rejected according to claim 1.
Claim 18 has been analyzed and rejected according to claim 2.
Claim 19 has been analyzed and rejected according to claim 3.
Claim 20 has been analyzed and rejected according to claim 4.
Claims 5-6 & 13-14 are rejected under 35 U.S.C. 103 as being unpatentable over Tunstall-Pedoe, US Patent Pub. 20130262125 A1, Bell et al, US Patent Pub. 20240406166 A1 and Shakarian et al, US Patent Pub. 20240427986 A1, as applied to claim 1 above, and further in view of Wald et al, US Patent 9396235 B1.
Re Claim 5, the combined teachings of Tunstall-Pedoe, Bell et al and Shakarian et al disclose the method according to claim 1, wherein the determining, for each determined fact statement, the endorsement score comprises: inputting, into the LLM for each determined fact statement (Bell et al, para 0156: input query is transmitted to a LLM for processing of answers), a respective fact statement with each other sample response that does not include the respective fact statement and a verification instruction, wherein the output of the LLM is a fact quality score of the respective fact statement for the respective sample response (Tunstall-Pedoe, para 1057: answers with facts that exceed a fact predetermined threshold are selected for query answering); but fail to explicitly disclose and wherein the endorsement score of the respective fact statement is an average of each fact quality score output of the LLM. However, Wald et al discloses a system that teaches the concept of where fact seeking score is average of fact seeking scores (Wald et al, col. 12, line 61 through col. 13, line 12). It would have been obvious to modify the Tunstall-Pedoe such that its facts scores include an average of fact scores as taught in Wald et al for the purpose of optimizing the fact identifying abilities.
Re Claim 6, the combined teachings of Tunstall-Pedoe, Bell et al, Shakarian et al and Wald et al disclose the method according to claim 5, wherein the verification instruction to determine the fact quality score instructs the LLM to identify the inputted sample response as a truth and identify the inputted respective fact statement as one of true, false, and inconclusive (Tunstall-Pedoe, para 0095: true and untrue facts).
Claim 13 has been analyzed and rejected according to claim 5.
Claim 14 has been analyzed and rejected according to claim 6.
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 GEORGE C MONIKANG whose telephone number is (571)270-1190. The examiner can normally be reached Mon. - Fri., 9AM-5PM, ALT. Fridays off.
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, Carolyn R Edwards can be reached at 571-270-7136. 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.
/GEORGE C MONIKANG/Primary Examiner, Art Unit 2692 3/26/2026
Prosecution Insights