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 .
Priority
Applicant’s claim for the benefit of a prior-filed Provisional application 63/597657, filed November 9th, 2023, is acknowledged. Claims 1-21 have been granted the benefit of the earlier filing date of the Provisional application.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on November 7th, 2024 and February 5th, 2025 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Double Patenting
A rejection based on double patenting of the “same invention” type finds its support in the language of 35 U.S.C. 101 which states that “whoever invents or discovers any new and useful process... may obtain a patent therefor...” (Emphasis added). Thus, the term “same invention,” in this context, means an invention drawn to identical subject matter. See Miller v. Eagle Mfg. Co., 151 U.S. 186 (1894); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Ockert, 245 F.2d 467, 114 USPQ 330 (CCPA 1957).
The non-statutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A non-statutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on non-statutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a non-statutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-21 are rejected under 35 U.S.C. 101 as claiming the same invention as that of claims 1-21 of prior U.S. Patent No. 12,393,620. This is a non-statutory double patenting rejection, as the broadest reasonable interpretation of the instant claims include the limitations of the Patent claims.
18/940680 claims
U.S. 12,393,620 claims
1. A system, comprising:
one or more processors configured to: receive a question;
identify a type of the question;
construct a prompt to provide to a generative model based on the identified type of the question; and
provide output based on a generative response provided by the generative model, wherein the output further comprises a citation, and wherein the citation is based at least in part on one or more contextual passages; and
a memory coupled to the one or more processors and configured to provide the one or more processors with instructions.
1. A system, comprising:
one or more processors configured to: receive a question;
identify a type of the question;
construct a prompt to provide to a generative model based on the identified type of the question; and
provide output based on a generative response provided by the generative model, wherein the output further comprises a citation, wherein the citation is based at least in part on one or more contextual passages, and wherein:
the one or more contextual passages are determined at least in part by conducting a search of a passage store using an answer and an explanation to the question, wherein the passage store comprises a vector database including passage embedding vectors, and wherein the search of the vector database is conducted based at least in part on generating of an answer-explanation embedding vector representing text of the answer and the explanation to the question; and
providing the output comprises including, in the output, links to internal documents from which the one or more contextual passages were extracted; and
a memory coupled to the one or more processors and configured to provide the one or more processors with instructions.
2. The system of claim 1, wherein the output comprises the question, an answer, and an accompanying explanation, and wherein at least one of the answer or the accompanying explanation is provided by the generative model.
2. The system of claim 1, wherein the output comprises the question, the answer, and the explanation, and wherein at least one of the answer or the explanation is provided by the generative model.
3. The system of claim 1, wherein prior to constructing the prompt, a search for at least one of an internal answer or an internal explanation is conducted.
3. The system of claim 1, wherein prior to constructing the prompt, a search for at least one of an internal answer or an internal explanation is conducted.
4. The system of claim 3, wherein constructing of the prompt is based at least in part on an absence of at least one of the internal answer or the internal explanation.
4. The system of claim 3, wherein constructing of the prompt is based at least in part on an absence of at least one of the internal answer or the internal explanation.
5. The system of claim 1, wherein identifying the type of the question comprises determining whether the question is a multiple-choice question.
5. The system of claim 1, wherein identifying the type of the question comprises determining whether the question is a multiple-choice question.
6. The system of claim 5, wherein in response to identifying the type of the question as a multiple-choice question, the one or more processors are further configured to determine whether the question is complete.
6. The system of claim 5, wherein in response to identifying the type of the question as a multiple-choice question, the one or more processors are further configured to determine whether the question is complete.
7. The system of claim 6, wherein constructing of the prompt is based at least in part on determining that the question is complete.
7. The system of claim 6, wherein constructing of the prompt is based at least in part on determining that the question is complete.
8. The system of claim 1, wherein the one or more contextual passages are determined at least in part by conducting a search of a passage store using an answer and an explanation to the question, and wherein providing the output comprises including, in the output, links to internal documents from which the one or more contextual passages were extracted.
8. (Cancelled)
9. The system of claim 1, wherein the one or more contextual passages are determined at least in part by conducting a search of a passage store using the question, and wherein the prompt is constructed to include the one or more contextual passages.
9. The system of claim 1, wherein the prompt is constructed to include the one or more contextual passages.
10. The system of claim 9, wherein the prompt is constructed to include a command to the generative model to provide the citation based on the one or more contextual passages included in the constructed prompt.
10. The system of claim 9, wherein the prompt is constructed to include a command to the generative model to provide the citation based on the one or more contextual passages included in the constructed prompt.
11. A method, comprising:
receiving a question;
identifying a type of the question;
constructing a prompt to provide to a generative model based on the identified type of the question; and
providing output based on a generative response provided by the generative model, wherein the output further comprises a citation, and wherein the citation is based at least in part on one or more contextual passages.
11. A method, comprising:
receiving a question;
identifying a type of the question;
constructing a prompt to provide to a generative model based on the identified type of the question; and
providing output based on a generative response provided by the generative model, wherein the output further comprises a citation, wherein the citation is based at least in part on one or more contextual passages, and wherein:
the one or more contextual passages are determined at least in part by conducting a search of a passage store using an answer and an explanation to the question, wherein the passage store comprises a vector database including passage embedding vectors, and
wherein the search of the vector database is conducted based at least in part on generating of an answer-explanation embedding vector representing text of the answer and the explanation to the question; and
providing the output comprises including, in the output, links to internal documents from which the one or more contextual passages were extracted.
12. The method of claim 11, wherein the output comprises the question, an answer, and an accompanying explanation, and wherein at least one of the answer or the accompanying explanation is provided by the generative model.
12. The method of claim 11, wherein the output comprises the question, the answer, and the explanation, and wherein at least one of the answer or the explanation is provided by the generative model.
13. The method of claim 11, wherein prior to constructing the prompt, a search for at least one of an internal answer or an internal explanation is conducted.
13. The method of claim 11, wherein prior to constructing the prompt, a search for at least one of an internal answer or an internal explanation is conducted.
14. The method of claim 13, wherein constructing of the prompt is based at least in part on an absence of at least one of the internal answer or the internal explanation.
14. The method of claim 13, wherein constructing of the prompt is based at least in part on an absence of at least one of the internal answer or the internal explanation.
15. The method of claim 11, wherein identifying the type of the question comprises determining whether the question is a multiple-choice question.
15. The method of claim 11, wherein identifying the type of the question comprises determining whether the question is a multiple-choice question.
16. The method of claim 15, wherein in response to identifying the type of the question as a multiple-choice question, further comprising determining whether the question is complete.
16. The method of claim 15, wherein in response to identifying the type of the question as a multiple-choice question, further comprising determining whether the question is complete.
17. The method of claim 16, wherein constructing of the prompt is based at least in part on determining that the question is complete.
17. The method of claim 16, wherein constructing of the prompt is based at least in part on determining that the question is complete.
18. The method of claim 11, wherein the one or more contextual passages are determined at least in part by conducting a search of a passage store using an answer and an explanation to the question, and wherein providing the output comprises including, in the output, links to internal documents from which the one or more contextual passages were extracted.
18. (Cancelled)
19. The method of claim 11, wherein the one or more contextual passages are determined at least in part by conducting a search of a passage store using the question, and wherein the prompt is constructed to include the one or more contextual passages.
19. The method of claim 11, wherein the prompt is constructed to include the one or more contextual passages.
20. The method of claim 19, wherein the prompt is constructed to include a command to the generative model to provide the citation based on the one or more contextual passages included in the constructed prompt.
20. (Original) The method of claim 19, wherein the prompt is constructed to include a command to the generative model to provide the citation based on the one or more contextual passages included in the constructed prompt.
21. A computer program product embodied in a non-transitory computer readable storage medium, and comprising computer instructions for:
receiving a question;
identifying a type of the question;
constructing a prompt to provide to a generative model based on the identified type of the question; and
providing output based on a generative response provided by the generative model, wherein the output further comprises a citation, and wherein the citation is based at least in part on one or more contextual passages.
21. A computer program product embodied in a non-transitory computer readable storage medium, and comprising computer instructions for:
receiving a question;
identifying a type of the question;
constructing a prompt to provide to a generative model based on the identified type of the question; and
providing output based on a generative response provided by the generative model, wherein the output further comprises a citation, wherein the citation is based at least in part on one or more contextual passages, and wherein:
the one or more contextual passages are determined at least in part by conducting a search of a passage store using an answer and an explanation to the question, wherein the passage store comprises a vector database including passage embedding vectors, and wherein the search of the vector database is conducted based at least in part on generating of an answer-explanation embedding vector representing text of the answer and the explanation to the question; and
providing the output comprises including, in the output, links to internal documents from which the one or more contextual passages were extracted.
Claim Rejections - 35 USC § 101
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 1-21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claims recite a mental process that can be performed in the human mind or with the aid of pen and paper. This judicial exception is not integrated into a practical application because a computer is invoked merely as a tool to execute an abstract idea. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because an abstract idea is merely applied on a generic computer without any element that would otherwise preclude performance of the abstrac.
Regarding claim 1, the claim recites “A system, comprising:one or more processors configured to:receive a question;identify a type of the question;construct a prompt to provide to a generative model based on the identified type of the question; andprovide output based on a generative response provided by the generative model, wherein the output further comprises a citation, and wherein the citation is based at least in part on one or more contextual passages; anda memory coupled to the one or more processors and configured to provide the one or more processors with instructions.”
The limitations of “receive a question,” “identify a type of the question,” and “provide output based on a generative response…” as drafted cover mental activities which can be performed in the mind or with the aid of pen and paper. Taken individually, or as a whole, these limitations describe acts which are equivalent to human mental work of answering questions and looking up information.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the steps of the claimed invention can be performed mentally, and the inclusion of a generic processor and memory does not preclude them from being performed as such; the included generative model is called to perform steps that may be embodied by a human actor (that of research and response generation), or may be interpreted as merely a tool used by an individual performing the steps of the claim (a person receives a question and types into an LLM prompt). Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 2, the claim depends from claim 1, and thus recites the limitations of claim 1, “wherein the output comprises the question, an answer, and an accompanying explanation, and wherein at least one of the answer or the accompanying explanation is provided by the generative model.”
Taken individually, or as a whole with claim 1, these limitations describe acts which are equivalent to human mental work of answering questions. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 3, the claim depends from claim 1, and thus recites the limitations of claim 1, “wherein prior to constructing the prompt, a search for at least one of an internal answer or an internal explanation is conducted.”
Taken individually, or as a whole with claim 1, these limitations describe acts which are equivalent to human mental work of answering questions. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 4, the claim depends from claim 3, and thus recites the limitations of claims 1 and 3, “wherein constructing of the prompt is based at least in part on an absence of at least one of the internal answer or the internal explanation.”
Taken individually, or as a whole with the preceding claims, these limitations describe acts which are equivalent to human mental work of answering questions. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 5, the claim depends from claim 1, and thus recites the limitations of claim 1, “wherein identifying the type of the question comprises determining whether the question is a multiple-choice question.”
Taken individually, or as a whole with claim 1, these limitations describe acts which are equivalent to human mental work of answering questions. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 6, the claim depends from claim 5, and thus recites the limitations of claims 1 and 5, “wherein in response to identifying the type of the question as a multiple-choice question, the one or more processors are further configured to determine whether the question is complete.”
Taken individually, or as a whole with the preceding claims, these limitations describe acts which are equivalent to human mental work of answering questions. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 7, the claim depends from claim 6, and thus recites the limitations of claims 1 and 5-6, “wherein constructing of the prompt is based at least in part on determining that the question is complete.”
Taken individually, or as a whole with the preceding claims, these limitations describe acts which are equivalent to human mental work of answering questions. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 8, the claim depends from claim 1, and thus recites the limitations of claim 1, “wherein the one or more contextual passages are determined at least in part by conducting a search of a passage store using an answer and an explanation to the question, and wherein providing the output comprises including, in the output, links to internal documents from which the one or more contextual passages were extracted.”
Taken individually, or as a whole with claim 1, these limitations describe acts which are equivalent to human mental work of answering questions and citing research sources. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 9, the claim depends from claim 1, and thus recites the limitations of claim 1, “wherein the one or more contextual passages are determined at least in part by conducting a search of a passage store using the question, and wherein the prompt is constructed to include the one or more contextual passages.”
Taken individually, or as a whole with claim 1, these limitations describe acts which are equivalent to human mental work of answering questions and citing research sources. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 10, the claim depends from claim 9, and thus recites the limitations of claims 1 and 9, “wherein the prompt is constructed to include a command to the generative model to provide the citation based on the one or more contextual passages included in the constructed prompt.”
Taken individually, or as a whole with the preceding claims, these limitations describe acts which are equivalent to human mental work of answering questions and citing research sources. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claims 11-20, method claims 11-20 and system claims 1-10 are related as a method and system of using the same, with each system element’s function corresponding to the method step. Accordingly, claims 11-20 are similarly rejected under the same rationale as applied to claims 1-10.
Regarding claim 21, computer-readable medium claim 21 and system claim 1 are related as method and computer-readable medium for performing the same, with each computer-readable medium element’s function corresponding to the method step. Accordingly, claim 21 is similarly rejected under the same rationale as applied to claim 1.
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.
Claims 1-3, 8-13 and 18-21 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Application Publication 2024/0256615 to Liu et al. (hereinafter, "Liu") in view of U.S. Patent 12,608,548 to Goligorsky (hereinafter, "Goligorsky").
Regarding claims 1, 11 and 21, Liu teaches a system, method and computer-readable medium comprising one or more processors (paragraph [0034], "The computing system 100 includes a processor 106 and memory 108, where the memory 108 includes instructions that are executed by the processor 106.") configured to:
receive a question (paragraph [0040], "The client computing device 102 is executing an application such as a web browser, and the application receives a query (user input) that is to be transmitted to the search engine 110 executing at the computing system 100. For instance, the web browser can load a homepage of the search engine and the web browser receives a query from a user in a text entry field. In another example, the web browser can receive a query in an address field of the web browser.");
identify a type of the question (paragraph [0080], "In another example, the classifier is configured to assign a class label to an input received from the client computing device 1002 that identifies a topic related to the input. The computing system 1000 selects a generative model from amongst the generative models 1010-1012 that is trained with data pertaining to such topic based upon the class label assigned to the input. For instance, the computing system 1000 receives the input 'how many home runs did Babe Ruth hit before he turned 30' and the classifier 1008 assigns a class label of 'sports' to such input.");
provide output based on a generative response provided by the generative model, wherein the output further comprises a citation, and wherein the citation is based at least in part on one or more contextual passages (paragraph [0047], "The generative model 112 generates output based upon the search information provided thereto at 204 and the input transmitted to the generative model 112 at 208. Thus, the prompt employed by the generative model 112 to generate the output includes the search information provided to the generative model 112 by the search engine 110 at 204 and the input received from the client computing device 102 at 208. The generative model 112 outputs the output, and the output is provided to the client computing device 102 for presentment to the user thereof. Moreover, the generative model can include citations to sources used by the generative model to generate the output."); and
a memory coupled to the one or more processors and configured to provide the one or more processors with instructions (paragraph [0034], "The computing system 100 includes a processor 106 and memory 108, where the memory 108 includes instructions that are executed by the processor 106.").
Liu teaches prompt construction, but not as related to input type; however, Goligorsky teaches construct a prompt to provide to a generative model based on the identified type of the question (column 25, line 3, "From block 720, once text is received, the process proceeds to block 730 in which the text is analyzed to identify feature inputs and prompt instructions. In particular, this may be accomplished by separating text snippets between those that include a tag and those that do not. Once the text has been analyzed and divided into feature inputs and prompt instructions, the divided text can be provided to a prompt generator at block 740.").
Liu and Goligorsky are considered analogous because they are each concerned with generative model prompting. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the query input of Liu with the additional processing steps of Goligorsky for the purpose of improving generative model performance. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Regarding claims 2 and 12, Liu further teaches a system and method wherein the output comprises the question, an answer, and an accompanying explanation, and wherein at least one of the answer or the accompanying explanation is provided by the generative model (Figure 3 and paragraph [0051], "The search engine 110 searches at least one of the data stores 114-120 based upon the query, and the SERP constructor module 132 constructs the SERP depicted in FIG. 3, where the SERP includes a list of links 302 that point to webpages identified by the search engine 110 as being relevant to the query, an image 304 identified by the search engine 110 as being relevant to the query, supplemental content 306 and 308 identified as being relevant to the query, and so forth.").
Regarding claims 3 and 13, Liu further teaches a system and method wherein prior to constructing the prompt, a search for at least one of an internal answer or an internal explanation is conducted (paragraph [0037], "The search engine 110 includes a web search module 124, an instant answer search module 125, a knowledge module 128, a supplemental content search module 130, and a SERP constructor module 132. The web search module 124 is configured to search the web index data store 114 based upon queries received by users, queries generated by the search engine 110 based upon queries received by users, and/or queries generated by the generative model 112 based upon interactions of users with the generative model 112. Similarly, the instant answer search module 126 is configured to search the instant answers data store 116 based upon queries received by users, queries generated by the search engine 110 based upon queries received by users, and/or queries generated by the generative model 112 based upon interactions of users with the generative model 112," and paragraph [0043], "Optionally, at 206, the search engine 110 returns the search results (or a portion thereof) to the client computing device 102, whereupon the search results are presented to the user. While the communications diagram 200 depicts the search information being provided to the generative model 112 before the search results are provided to the client computing device 102, it is to be understood that the search engine 110 can provide the search results to the client computing device 102 prior to providing the search information to the generative model 112.").
Regarding claims 8 and 18, Liu further teaches a system and method wherein the one or more contextual passages are determined at least in part by conducting a search of a passage store using an answer and an explanation to the question, and wherein providing the output comprises including, in the output, links to internal documents from which the one or more contextual passages were extracted (paragraph [0051], "The search engine 110 searches at least one of the data stores 114-120 based upon the query, and the SERP constructor module 132 constructs the SERP depicted in FIG. 3, where the SERP includes a list of links 302 that point to webpages identified by the search engine 110 as being relevant to the query, an image 304 identified by the search engine 110 as being relevant to the query, supplemental content 306 and 308 identified as being relevant to the query, and so forth.").
Regarding claims 9 and 19, Liu further teaches a system and method wherein the one or more contextual passages are determined at least in part by conducting a search of a passage store using the question, and wherein the prompt is constructed to include the one or more contextual passages (paragraph [0045], "Optionally, the generative model 112 generates a second query that is well-suited for use by the search engine 110 in connection with identifying further search results that are relevant to the input, where the generative model 112 generates the second query based upon the search information received at 204 and the input received at 208. Thus, in contrast to conventional approaches, the generative model 112 generates the second query based not only upon the input, but generates the second query based further upon search results identified by the search engine 110… The search engine 110 identifies second search results based upon the second query and provides information extracted from the second search results as second search information to the generative model 112 at 212, where the second search information is included in a prompt for the generative model 112.").
Regarding claims 10 and 20, Liu further teaches a system and method wherein the prompt is constructed to include a command to the generative model to provide the citation based on the one or more contextual passages included in the constructed prompt (paragraph [0047], "Moreover, the generative model can include citations to sources used by the generative model to generate the output. Thus, when the generative model is 112 provided with content from a webpage by the search engine 110 and generates output based upon such content, the generative model 112 can include a citation to the webpage in the output, thereby informing the user of source of the output generated by the generative model 112.").
Claims 4 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Liu and Goligorsky as applied to claims 1 and 11 above, and further in view of U.S. Patent Application Publication 2025/0005050 to Krishnan et al. (hereinafter, "Krishnan").
Regarding claims 4 and 14, the combination of Liu and Goligorsky does not teach a method or system “wherein constructing of the prompt is based at least in part on an absence of at least one of the internal answer or the internal explanation,” and thus, Krishnan is introduced.
Krishnan teaches a method for generative summarization with information retrieval wherein constructing of the prompt is based at least in part on an absence of at least one of the internal answer or the internal explanation (paragraph [0101], "In some implementations, the search prompt can include any one or more of the following: a specific instruction to perform a set of steps in a specific order (e.g., “to build the search query, follow these steps”), a specific instruction to analyze the user's input and determine the user's intent (e.g., “analyze the user's message to understand their question or the sub-topics they're interested in.”), a specific instruction for how the large language model should respond to a lack of information in the user's input (e.g., “if no question is present, use the current sub-topic”), one or more specific examples of how the large language model should formulate output (e.g., “Example: ‘I would recommend the user learn the following skills: Skill1, Skill2, . . . , SkillN’”), one or more constraints, such as a specific limit on the length of the search query to be generated…").
Liu, Goligorsky and Krishnan are considered analogous because they are each concerned with generative model prompting. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the combined method of Liu and Goligorsky with the contingency considerations of Krishnan for the purpose of improving generative model performance. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Claims 5-7 and 15-17 are rejected under 35 U.S.C. 103 as being unpatentable over Liu and Goligorsky as applied to claims 1 and 11 above, and further in view of U.S. Patent Application Publication 2022/0188661 to Tappin (hereinafter, "Tappin").
Regarding claims 5 and 15, the combination of Liu and Goligorsky does not teach a system or method “wherein identifying the type of the question comprises determining whether the question is a multiple-choice question,” and thus, Tappin is introduced.
Tappin teaches a system for data analytics wherein identifying the type of the question comprises determining whether the question is a multiple-choice question (paragraph [0044], "Query Type Processing 304: The query processing pipeline 300 may include the query type processing module as shown in 304 for identifying specific types of queries to assist the pattern machine in generating more accurate predictive answers. In some implementations, the query type processing module 304 may be configured to classify user queries into, for example, three categories of regular, out of scope (OOS), and biased queries," and paragraph [0047], "Additionally, in the query processing section, all improper words may be automatically removed from the query... If there is not enough of a query after bias is removed, then the user may receive a multiple-choice option page to select further topics suggested by the system to continue with a proper and formalized question, or alternatively receive a fallback response indicating their question will not be answered.").
Liu, Goligorsky and Tappin are considered analogous because they are each concerned with generative model prompting. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the combined method of Liu and Goligorsky with the input classification of Tappin for the purpose of improving generative model performance. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Regarding claims 6 and 16, Tappin further teaches a system and method wherein in response to identifying the type of the question as a multiple-choice question, the one or more processors are further configured to determine whether the question is complete (paragraph [0048], "Query Refinement 306: Query refinement component 306 of the query processing pipeline 300 may be optionally configured to ensure that the user query is complete and in a format that is usable for identifying related events and signals in the subsequent data analytics by the signal processing component 220.").
Liu, Goligorsky and Tappin are considered analogous because they are each concerned with generative model prompting. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the combined method of Liu and Goligorsky with the input processing of Tappin for the purpose of improving generative model performance. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Regarding claims 7 and 17, Tappin further teaches a system and method wherein constructing of the prompt is based at least in part on determining that the question is complete (paragraph [0055], "Query information extraction 310: The query information extraction component 310 of the query processing pipeline 300 of FIG. 3 may be configured to extract relevant information from the preprocessed, refined, and de-duplicated query in order to better understand the user intent… The query information extraction component 310 may be configured to perform a query expansion in order to identify the entities in the query and either disambiguate or augment these entities. In addition, the query information extraction component 310 may be further configured to extract relevant information from the user query in order to facilitate matching it with pre-computed signals by creating a detailed and structured format of the query which can be more conveniently used to perform matching with the information available in the pre-computed signals.").
Liu, Goligorsky and Tappin are considered analogous because they are each concerned with generative model prompting. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the combined method of Liu and Goligorsky with the input processing of Tappin for the purpose of improving generative model performance. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
U.S. Patent Application Publication 2023/0034344 to Jain teaches converting a natural language prompt into a machine-readable semantic representation including information retrieval.
U.S. Patent Application Publication 2023/0080974 to Attali et al. teaches passage and question generation using a transformer-based language model.
U.S. Patent Application Publication 2024/0412226 to Mathur et al. teaches information retrieval and query classification.
U.S. Patent Application Publication 2025/0036695 to De Barros et al. teaches prompt generation based on input classification.
U.S. Patent Application Publication 2025/0124060 to Hackman teaches prompt generation for language model question answering.
U.S. Patent 11,982,223 to DeFoor et al. teaches prompt generation and reference citation using large language models.
U.S. Patent Application Publication 2022/0366333 to Lollo et al. teaches natural language processing for evaluating documents that include multiple-choice questions and responses.
China Invention Application 116881426 to Zhang et al. teaches explainable question answering with information retrieval.
China Invention Application 116383370 to Chen et al. teaches explainable question answering with information retrieval.
China Invention Application 114153961 to Ji et al. teaches explainable question answering with information retrieval.
Korea Invention Application 10-2022-0114157 to Tack et al. teaches explainable question answering from knowledge graphs.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SEAN T SMITH whose telephone number is (571)272-6643. The examiner can normally be reached Monday - Friday 8:00am - 5:00pm.
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, PIERRE-LOUIS DESIR can be reached at (571) 272-7799. 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.
/SEAN THOMAS SMITH/Examiner, Art Unit 2659
/PIERRE LOUIS DESIR/Supervisory Patent Examiner, Art Unit 2659
Prosecution Insights