CTNF 18/925,430 CTNF 80676 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. Drawings 06-37 AIA The drawings were received on 10/24/2024 . These drawings are accepted . Claim Rejections - 35 USC § 101 07-04-01 AIA 07-04 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 1-8 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea in the form of mental process without significantly more. The claim(s) recite(s) creating a request prompt with instructions and data for an answer. Such is directed towards mental process of receiving a request with information and providing an answer. This judicial exception is not integrated into a practical application because the claim fails to recited positively recited language integrating the abstract idea into practical application. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the claim fails to recite positively recited language indicating significantly more than the judicial exception. Claims 2-8 recite language adding to the abstract idea without positively recited language integrating the abstract idea into practical application and/or indicating significantly more than the judicial exception. Although the claimed language includes “a large scale language processing model”, such is generic device performing the abstract idea, hence does not indicate significantly more than the judicial exception and/or integrate the abstract idea into practical application. Claims 9-11 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea in the form of mental process without significantly more. The claim(s) recite(s) creating a request prompt with instructions and data for an answer. Such is directed towards mental process of receiving a request with information and providing an answer along with additional limitations adding to the abstract idea. This judicial exception is not integrated into a practical application because the claim fails to recited positively recited language integrating the abstract idea into practical application. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the claim fails to recite positively recited language indicating significantly more than the judicial exception. Claim Rejections - 35 USC § 112 07-30-02 AIA The following is a quotation of 35 U.S.C. 112(b): (b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention. The following is a quotation of 35 U.S.C. 112 (pre-AIA), second paragraph: The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention. 07-34-05 AIA Claim 2 recites the limitation " the partial prompt " in claim 1 . There is insufficient antecedent basis for this limitation in the claim. 07-34-05 AIA Claim 4 recites the limitation " the partial prompt " in claims 1,2 . There is insufficient antecedent basis for this limitation in the claim. 07-34-05 AIA Claim 5 recites the limitation " the partial prompt " in claims 1,2 . There is insufficient antecedent basis for this limitation in the claim. 07-34-05 AIA Claim 6 recites the limitation " the partial prompt" in claims 1,2, “the reconstructed prompts” in limitation “in put the reconstructed prompts …” . There is insufficient antecedent basis for this limitation in the claim. 07-34-01 Claims 9,10 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. Claim 9 recites the limitation “the prompt creation device according to claim 1” and Claim 10 recites the limitation of “the response system according to claim 8”. It is unclear and indefinite as to what limitations of claim 1 is incorporated into claim 9 and what limitations of claim 8, which is dependent on claims 1,2 is incorporated into claim 10. For these reasons, the claims fail to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. Claim Rejections - 35 USC § 102 07-06 AIA 15-10-15 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. 07-07-aia AIA 07-07 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 – 07-12-aia AIA (a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention. 07-15-03-aia AIA Claim(s) 1-11 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Mishra et al (US Publication No.: 20250086405) . Claim 1, Mishra et al discloses at least one memory configured to store instructions (Paragraph 123 discloses memory storing instructions.); and at least one processor configured to execute the instructions to (Paragraph 123 discloses processor executing instructions.) create a requesting prompt (Paragraph 55 discloses LLM prompt or requesting prompt.), from an input prompt (Paragraph 55 discloses the LLM prompt comprises simple sub-prompts. Paragraph 42 discloses the simple sub-prompts are generated from an input prompt.) including an instruction and at least one of background or input data (Paragraph 55 discloses the requesting prompt includes instruction such as “Respond to the following query …” and input data such as input query with prompt tree. Paragraph 65 discloses sub-prompts included in the requesting query has information or input data by disclosing an application may extract pertinent information from the sub-prompts.), the requesting prompt requesting an answer only to the instruction and the input data indicating the content of the instruction (Paragraph 55 discloses the requesting prompt requests an answer to only the instruction “respond to the following query …” and the input data such as the information in the sub-prompts.) and content of the instruction (Paragraph 55 discloses the LLM is instructed to answer the content (query) of the instruction “Respond to the following query …”.). Claim 2, Mishra et al discloses wherein the at least one processor is configured to execute the instructions to (Paragraph 123 discloses processor executing instructions.): decompose the input prompt into partial prompts by natural language processing (Paragraph 42 discloses the decomposition model 208 iteratively decomposes the input prompt into the simple sub-prompts. Paragraph 16 discloses 120 as a natural language-based response system indicating natural language processing. Paragraph 42 discloses the decomposition model decomposes the input prompt into sub-prompts where Fig. 4 shows the sub-prompts are further questions or further information regarding the input query or input prompt, indicating natural language processing to determine such information.); and create the requesting prompt (Paragraph 55 discloses an LLM prompt or requesting prompt is generated including the instruction and sub-prompts.) using the partial prompt having a simplest structure among the partial prompts having only the instruction and the content of the instruction (Paragraph 55 discloses the generation of the LLM prompt is performed using the simple sub-prompts. Paragraphs 42-43 discloses the decomposition model generates the sub-prompts with a target simplicity, indicating the simplest structure of sub-prompts are used to generate the LLM prompt. A number of sub-prompts used and generated by the decomposition model Depending on the decomposition model and prompt tree decomposing the input query or input prompt.) having only the instruction (Paragraph 55’s example of “Respond to the following query …”) and content of the instruction (sub-prompts).). Claim 3, Mishra et al discloses wherein the at least one processor is configured to execute the instructions to (Paragraph 123 discloses processor executing instructions.): decompose the input prompt into partial prompts by natural language processing (Paragraph 42 discloses the decomposition model 208 iteratively decomposes the input prompt into the simple sub-prompts. Paragraph 16 discloses 120 as a natural language-based response system indicating natural language processing. Paragraph 42 discloses the decomposition model decomposes the input prompt into sub-prompts where Fig. 4 shows the sub-prompts are further questions or further information regarding the input query or input prompt, indicating natural language processing to determine such information.); analyze a hierarchical structure of the partial prompts (Fig. 4 shows the hierarchical structure of the sub-prompts (prompt tree). The decomposition model iteratively decomposes the input prompt to ensure the prompts are simple enough such as at least at a target simplicity. This indicates analyzing the prompt tree (hierarchical structure) of the sub-prompts.); and create the prompt using the partial prompt in the deepest level of the hierarchical structure (Paragraph 55 discloses the LLM prompt comprises the sub-prompts and instruction, wherein the sub-prompts include the deepest level of hierarchical structure such as shown in the prompt tree of Fig. 4.). Claim 4, Mishra et al discloses wherein the at least one processor is configured to execute the instructions to (Paragraph 123 discloses processor executing instructions.): decompose the input prompt into partial prompts by natural language processing (Paragraph 42 discloses the decomposition model 208 iteratively decomposes the input prompt into the simple sub-prompts. Paragraph 16 discloses 120 as a natural language-based response system indicating natural language processing. Paragraph 42 discloses the decomposition model decomposes the input prompt into sub-prompts where Fig. 4 shows the sub-prompts are further questions or further information regarding the input query or input prompt, indicating natural language processing to determine such information.); analyze a hierarchical structure of the partial prompts (Fig. 4 shows the hierarchical structure of the sub-prompts (prompt tree). The decomposition model iteratively decomposes the input prompt to ensure the prompts are simple enough such as at least at a target simplicity. This indicates analyzing the prompt tree (hierarchical structure) of the sub-prompts.); and create the prompt using the partial prompt in a deepest level of the hierarchical structure (Paragraph 55 discloses the LLM prompt comprises the sub-prompts and instruction, wherein the sub-prompts include the deepest level of hierarchical structure such as shown in the prompt tree of Fig. 4.). Claim 5, Mishra et al discloses wherein the at least one processor is configured to execute the instructions to (Paragraph 123 discloses processor executing instructions.): generate a reconstructed prompt that takes the partial prompt as question content and instructs a large-scale language processing model to answer the question content (Paragraph 55 discloses the LLM prompt, as the final prompt, is generated using sub-prompts, number depending on the decomposition model described in paragraphs 42-43, as question content and instructions such as “Respond to the following query …”, instructing the LLM to answer the question content. Paragraphs 42 discloses the decomposition model iteratively decomposes the input prompt or query in order to generate sub-prompt(s) reaching the target simplicity, indicating low complexity. Due to the decomposition model’s iterative process, the LLM prompt is a final drafted prompt, indicating a reconstructed prompt.); input the generated reconstructed prompt to the large-scale language processing model (Fig. 2, label 218, prompt, 220); and in a case where there is even one reconstructed prompt that cannot be answered, determine that the input prompt cannot be answered (Fig. 2, label 222 as the response, wherein depending the LLM, the response can be a determination the input prompt cannot be answered.). Claim 6, Mishra et al discloses wherein the at least one processor is configured to execute the instructions to (Paragraph 123 discloses processor executing instructions.): Generate, for the partial prompt having a least structural complexity (Paragraph 42-43 discloses target simplicity is reached when the decomposition model determines that a sub-prompt cannot be broken down into simpler sub-prompts.), a reconstructed prompt having the partial prompt as the question content and instructing an answer to the question content (Paragraph 55 discloses the LLM prompt includes sub-prompts, wherein the sub-prompts are considered reconstructed prompts due to such prompts are generated by the decomposition model decomposing an input prompt. The sub-prompt includes a question content and instructs the LLM to answer the sub-prompt. Paragraphs 59-60 discloses the LLM answering the sub-prompts.); Generate, for other partial prompt, a reconstructed prompt having the partial prompt as the question content and instructing an answer to the question content (Fig. 4, label 606c as a reconstructed prompt or sub-prompt having the partial prompt, label 404b, as the question content and instructing the LLM to answer the question. Paragraphs 59-60 discloses the LLM answering the sub-prompts.), with the condition of answering only if an answer is possible to the reconstructed prompt (Fig. 2, label response from LLM. Depending on the LLM, the LLM response indicates possible answer.) related to the partial prompt having a lower complexity than the complexity included in the other partial prompt (Fig. 4 shows the prompt tree generated by the decomposition model, where the sub-prompt at the lowest level is simpler than the sub-prompts above. For example, label 406c,406d is simpler than label 404b.); and input the reconstructed prompts related to the partial prompts in ascending order of complexity into a large-scale language processing model (Fig. 2, label LLM and prompt, wherein the prompt includes the sub-prompts or reconstructed prompts, where paragraph 55 discloses the LLM prompt includes the prompt tree. Fig. 4 shows the sub-prompts or reconstructed prompts with complexity in ascending order when reading the tree from bottom to top.). Claim 7, Mishra et al discloses wherein the at least one processor is configured to execute the instructions to (Paragraph 123 discloses processor executing instructions.): generate, for the partial prompt at a deepest level in the hierarchical structure of the partial prompts (Fig. 4 shows the prompt tree with deepest level being the bottom or last level of the tree.), a reconstructed prompt having the partial prompt as the question content and instructing an answer to the question content (Paragraph 55 discloses the LLM prompt includes sub-prompts, wherein the sub-prompts are considered reconstructed prompts due to such prompts are generated by the decomposition model decomposing an input prompt. The sub-prompt includes a question content and instructs the LLM to answer the sub-prompt. Paragraphs 59-60 discloses the LLM answering the sub-prompts.); generate, for other partial prompt, a reconstructed prompt having the partial prompt as the question content and instructing an answer to the question content (Fig. 4, label 606c as a reconstructed prompt or sub-prompt having the partial prompt, label 404b, as the question content and instructing the LLM to answer the question. Paragraphs 59-60 discloses the LLM answering the sub-prompts.), with the condition of answering only if an answer is possible to the reconstructed prompt (Fig. 2, label response from LLM. Depending on the LLM, the LLM response indicates possible answer.) related to the partial prompt with a depth in the hierarchical structure deeper than the depth in the hierarchical structure included in the other partial prompt (Fig. 4 shows the prompt tree with last layer being the deepest layer of the tree. Sub-prompts at the last layer have a depth deeper than the sub-prompt above. For example, label 406c,406d have a depth deeper than 404b.); and input the reconstructed prompts related to the partial prompts in descending order of depth of the hierarchical structure into a large-scale language processing model (Fig. 2, label LLM and prompt, wherein the prompt includes the sub-prompts or reconstructed prompts, where paragraph 55 discloses the LLM prompt includes the prompt tree.). Claim 8, Mishra et al discloses wherein the at least one processor is configured to execute the instructions to (Paragraph 123 discloses processor executing instructions.): generate a reconstructed prompt that takes the requesting prompt as question content and instructs an answer to the question content (Paragraph 55 discloses the LLM prompt, as the final prompt, is generated using sub-prompts, number depending on the decomposition model described in paragraphs 42-43, as question content and instructions such as “Respond to the following query …”, instructing the LLM to answer the question content. Paragraphs 42 discloses the decomposition model iteratively decomposes the input prompt or query in order to generate sub-prompt(s) reaching the target simplicity, indicating low complexity. Due to the decomposition model’s iterative process, the LLM prompt is a final drafted prompt, indicating a reconstructed prompt.); input the generated reconstructed prompt to a large-scale language processing model (Fig. 2, label 218, prompt, 220); and in a case where unanswerable, determine that an answer to the input prompt is not possible (Fig. 2, label 222 as the response, wherein depending the LLM, the response can be a determination the input prompt cannot be answered.). Claim 9, Mishra et al discloses The prompt creation device according to claim 1 (please see claim 1); At least one memory configured to store instructions (Paragraph 123 discloses memory storing instructions.) and a large scale language processing model (Fig. 2, label LLM); and At least one processor configured to execute the instructions to (Paragraph 123 discloses processor executing instructions.): Obtain an input prompt (Fig. 2, label 204,208,210,218); and Output an answer generated by the large scale language processing model (Fig. 2, label LLM, response). Claim 10, Mishra et al discloses the response system according to claim 8 (Please see claim 1,2,8.). Claim 11, Mishra et al discloses create a requesting prompt (Paragraph 55 discloses LLM prompt or requesting prompt.), from an input prompt (Paragraph 55 discloses the LLM prompt comprises simple sub-prompts. Paragraph 42 discloses the simple sub-prompts are generated from an input prompt.) including an instruction and at least one of background or input data (Paragraph 55 discloses the requesting prompt includes instruction such as “Respond to the following query …” and input data such as input query with prompt tree. Paragraph 65 discloses sub-prompts included in the requesting query has information or input data by disclosing an application may extract pertinent information from the sub-prompts.), the requesting prompt requesting an answer only to the instruction and the input data indicating the content of the instruction (Paragraph 55 discloses the requesting prompt requests an answer to only the instruction “respond to the following query …” and the input data such as the information in the sub-prompts.) and content of the instruction (Paragraph 55 discloses the LLM is instructed to answer the content (query) of the instruction “Respond to the following query …”.). Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to LINDA WONG whose telephone number is (571)272-6044. The examiner can normally be reached 9-5. 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, Andrew C Flanders can be reached at 571-272-7516. 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. /LINDA WONG/Primary Examiner, Art Unit 2655 Application/Control Number: 18/925,430 Page 2 Art Unit: 2655 Application/Control Number: 18/925,430 Page 3 Art Unit: 2655 Application/Control Number: 18/925,430 Page 4 Art Unit: 2655 Application/Control Number: 18/925,430 Page 5 Art Unit: 2655 Application/Control Number: 18/925,430 Page 6 Art Unit: 2655 Application/Control Number: 18/925,430 Page 7 Art Unit: 2655
Prosecution Insights