CTFR 18/490,426 CTFR 89908 Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia 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 Amendment Claims 1, 10, 11, 19 and 20 are amended. Claims 2, 6, 8, 12, 16, and 18 are cancelled. Claims 25-26 are added. Claims 1, 3-5, 7, 9-11, 13-15, 17 and 19-26 are presented for examination. Response to Arguments Applicant’s arguments with respect to claims 1, 11 and 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 07-20-aia AIA 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. 07-23-aia AIA 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. 07-21-aia AIA Claim s 1, 4-5, 7, 9-11, 14-15, 17 ,19- 20 and 22-26 are rejected under 35 U.S.C. 103 as being unpatentable over Ghosh ( US 20250124022) and further in view of Austin ( US 20240420012) and further in view of Kotikalapudi ( US 20240378394) Regarding claim 1, Ghosh teaches a method, comprising: receiving a user prompt via a user interface, wherein the user prompt is for a generative artificial intelligence system and is specified as natural language ( user prompt 402, prompt includes natural language, Para 0030, 0051-0052 ( RAG method for received prompt) ; choosing a selected prompt class (intent) ( select a prompt template based on the intent, Para 0042) from a plurality of prompt classes by matching a natural language processing analysis of the user prompt to a prompt template of the selected prompt class ( conditioned prompt, Fig 6; the system prompt constructor 416 uses the classified intent to look up system-provided prompts in a prompt template library. For example, the system prompt constructor 416 can search a prompt template library based on the intent and identify the system-provided prompts from the library that correspond to the intent; system provided prompts that corresponds to the intent, Para 0042,0060) , and wherein the prompt template specifies an expected prompt structure ( structured prompt , Para 0066) , and wherein the selected prompt class includes: one or more predefined conditioning instructions specific to the selected prompt class ( Given the user prompt 402, the task of predicting an intent (represented by a text-class label) to the user prompt 402 is transformed to generating a predefined textual response (e.g., positive, negative, etc.), Para 0041); and one or more predetermined evaluation questions ( evaluation criteria based on intent, Para 0039, 0045, 0050) ; creating a well-structured prompt by transforming the user prompt based on the expected prompt structure of the selected prompt class ( step 604 conditioned prompts with the received prompts, Fig 6) ; generating a conditioned prompt by adding the one or more predefined conditioning instructions to the well-structured prompt ( step 604 conditioned prompts with the received prompts, Fig 6) ; and submitting the conditioned prompt to the generative artificial intelligence system ( step 604 conditioned prompts with the received prompts, Fig 6) , wherein the conditioned prompt is configured to evoke a response including a structured output from the generative artificial intelligence system ( output the response, Fig 4-6); submitting the response from the generative artificial intelligence system and accessing the one or more evaluation questions to an evaluation system ( ( By evaluating multiple generated outcomes from the generative artificial intelligence form builder 400 based on the same user input (intent), system evaluation metrics can measure whether the instructions provided to the generative artificial intelligence form builder 400 are followed for the same user input (intent), such as adhering to produce a diverse set of questions in outcomes, Para 0050; the outcome validator 420 evaluates the generative AI model 412 to eliminate or reduce harmful content in the output and aligns the intention of the customer with the forms creation scenario, rather than prompt injection (jail break) or any invalid asks, Para 0039, 0045) ; and obtaining feedback from the evaluation system based on the one or more evaluation questions, wherein the feedback indicates one or more additional conditioning instructions to be added to the selected prompt class, one or more replacement conditioning instructions to replace a predetermined conditioning instruction of the one or more predetermined conditioning instructions, or instructions to remove the predetermined conditioning instruction of the one or more predetermined conditioning instructions ( The results of evaluations of the system evaluation metrics and/or the semantic metrics are input to an iterative refinement system 512, which may include developer-implemented and/or automated refinement of program code of the generative artificial intelligence form builder 504 (e.g., by a developer), adjustment of system-provided prompts, adjustment of refinement instructions, etc. in an effort to improve the robustness and valid performance of the generative artificial intelligence form builder 504., Para 0057, Fig 5; wherein the predetermined condition is a system received prompts which is being modified here) While Ghosh does not explicitly teach choosing a selected prompt class from a plurality of prompt classes by matching a natural language processing analysis of the user prompt to a prompt of the selected prompt class; and a prompt model parameter specific to the selected prompt class, wherein the prompt model parameter specifies a generative artificial intelligence system from a plurality of generative artificial intelligence models; one or more predetermined evaluation questions associated with the selected prompt class ; and selecting the generative artificial intelligence system of the plurality of generative artificial intelligence models using the prompt model parameter However, Austin teach choosing a selected prompt class from a plurality of prompt classes by matching a natural language processing analysis of the user prompt to a prompt of the selected prompt class ( prompt class LLM1 or LL2 etc, Fig 2b, Para 0046-0047) ; and a prompt model parameter specific to the selected prompt class, wherein the prompt model parameter specifies a generative artificial intelligence system from a plurality of generative artificial intelligence models (prompts for different LLMS for e.g. llm 1,2 or custom etc., Fig 2b, Para 0051-0060); one or more predetermined evaluation questions associated with the selected prompt class (evaluation based on the prompt for e.g. code is checked based on copyright etc., Fig 2c) ; and selecting the generative artificial intelligence system of the plurality of generative artificial intelligence models using the prompt model parameter ( answer by different LLM, Para 0051-0060); accessing the response from the generative artificial intelligence system and the one or more evaluation questions to an evaluation system ( Fig 2c, generative answers are checked based on their content moderation triggers, Para 0037 or for copywrite for code etc., Para 0049) It would have been obvious having the teachings of Ghosh to further include the concept of Austin before effective filing date so to give use proprietary information and use models based on their functionality ( Para 0052-0060, Austin) Although both Ghosh and Austin mentions evaluation are done based class, for e.g. Ghosh teaches evaluation is done based on the intent and Austin teaches evaluation based on the type of input for e.g. content moderation for a type of input, copyright for code etc., and these metric are embodied within the system and are being accessed, they don’t explicitly teach submitting the response from the generative artificial intelligence system and the one or more evaluation questions to an evaluation system However, Kotikalapudi teaches submitting the response from the generative artificial intelligence system and the one or more evaluation questions to an evaluation system ( a critique response 240 can include a comparison measure determined based on comparing the set of response evaluation criteria 232 to the corresponding candidate response 230, using the LLM. The comparison measure can be indicative of the number of response evaluation criteria 232 the corresponding candidate response 230 is determined to comply with and/or an extent to which the corresponding candidate response 230 complies with a given criterion included in the response evaluation criteria 232, Para 0060-0061, Fig 2A) It would have been obvious having the teachings of Ghosh and Austin to further include the concept of Kotikalapudi before effective filing date to receive an evaluation criteria vs sending the answer to the evaluation system which already has an evaluation criteria is mere obvious variation of the concept and it would be obvious to try to yield the predictable result of reducing computational resources to generate the answers which complied with the evaluation criteria before being outputted or modified Regarding claim 4, Ghosh as above in claim 1, teaches wherein the generative artificial intelligence system is a large language model ( LLM, Para 0041) Regarding claim 5, Ghosh as above in claim 1 ,wherein the structured output of the generative artificial intelligence system is compatible with a particular computer system and is specific to the selected prompt class ( renderable form based on intent, Para 0091, 0042, 0050) Regarding claim 7, Ghosh as above in claim 1 ,, wherein the conditioned prompt is configured to reduce non-determinism in the response generated by the generative artificial intelligence system ( the prompt identifying operation 604 searches a prompt template library based on the intent and identifies the system-provided prompts that correspond to the intent, Para 0060- since its based on intent it will reduce the non-determinism) Regarding claim 9, Austin as above in claim 8, teaches wherein the evaluation system is a generative artificial intelligence system ( checks are performed by orchestration layer 102 which is AI based, Para 00011, 0059) Regarding claim 10, Ghosh as above in claim 8, teaches further comprising: modifying the one or more predefined conditioning instructions based on an evaluation result generated by the evaluation system (iterative changes to the prompts, Fig 5) Regarding claim 11, arguments analogous to claim 1, are applicable. In addition, Ghosh teaches A system, comprising: one or more processors configured to execute operations as described in claim 1 ( Para 0003) Regarding claim 14, arguments analogous to claim 4, are applicable. Regarding claim 15, arguments analogous to claim 5, are applicable. Regarding claim 17, arguments analogous to claim 7, are applicable. Regarding claim 19, arguments analogous to claim 10, are applicable. Regarding claim 20, arguments analogous to claim 1, are applicable. In addition, Ghosh teaches A computer program product comprising one or more computer readable storage mediums having program instructions embodied therewith, wherein the program instructions are executable by one or more processors to cause the one or more processors to execute operations as described in claim 1 ( Para 0004) Regarding claim 22, arguments analogous to claim 4, are applicable. Regarding claim 23, arguments analogous to claim 5, are applicable. Regarding claim 24, arguments analogous to claim 7, are applicable. Regarding claim 25, arguments analogous to claim 9, are applicable. Regarding claim 26, arguments analogous to claim 10, are applicable . 07-21-aia AIA Claim s 3, 13 and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Ghosh ( US 20250124022) and further in view of Austin ( US 20240420012) and further in view of Kotikalapudi ( US 20240378394) and further in view of Heller ( US 20240273309) Regarding claim 3, Ghosh modified by Austin as above in claim 1, does not explicitly teach wherein the prompt template includes a field that is populated by a keyword obtained from the natural language processing analysis of the user prompt However, Heller teaches wherein the prompt template includes a field that is populated by a keyword obtained from the natural language processing analysis of the user prompt (A prompt template may also include one or more fillable portions that may be filled based on information determined by the orchestrator 230, Para 0051) It would have been obvious having the teachings of Ghosh and Austin to further include the concept of Heller before effective filing date so to improve the quality of the text being inputted ( Para 0003, Heller) Regarding claim 13, arguments analogous to claim 3, are applicable. Regarding claim 21, arguments analogous to claim 3, are applicable. Conclusion 07-39 AIA THIS ACTION IS MADE FINAL. 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 Richa Sonifrank whose telephone number is (571)272-5357. The examiner can normally be reached M-T 7AM - 5:30PM. 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, Phan Hai can be reached at (571)272-6338. 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. /Richa Sonifrank/Primary Examiner, Art Unit 2654 Application/Control Number: 18/490,426 Page 2 Art Unit: 2654 Application/Control Number: 18/490,426 Page 3 Art Unit: 2654 Application/Control Number: 18/490,426 Page 4 Art Unit: 2654 Application/Control Number: 18/490,426 Page 5 Art Unit: 2654 Application/Control Number: 18/490,426 Page 6 Art Unit: 2654 Application/Control Number: 18/490,426 Page 7 Art Unit: 2654
Prosecution Insights