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 .
This Office Action is in response to correspondence filed 18 February 2025 in reference to application 19/056,511. Claims 1-16 are pending and have been examined.
Claim Rejections - 35 USC § 112
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.
Claim 11 is 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 11 recites the limitation "the query generation unit" and “the search unit” in the first limitation. There is insufficient antecedent basis for this limitation in the claim.
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 1-16 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claim(s) 1, 15, and 16 recite acquiring a question input by a user; generating a query based on the question; searching a search result related to the query from a plurality of information sources; determining consistency of the search result; generating an integration prompt in which a search result determined to have consistency and the question are integrated; and generating an answer to the question by inputting the integration prompt into a large language model.
The limitation of acquiring a question input by a user, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting “processing circuitry” in claim 1 and “a non-transitory computer readable storage medium” in claim 16 nothing in the claim element precludes the step from practically being performed in the mind. For example, but for computer components, “acquiring” in the context of this claim encompasses a person listening to a user speak a question.
The limitation of generating a query based on the question, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for computer components, “generating” in the context of this claim encompasses the person writing a google search query based on the question asked by the user.
The limitation of searching a search result related to the query from a plurality of information sources, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for computer components, “searching” in the context of this claim encompasses the person entering a search query into a search engine.
The limitation of determining consistency of the search result, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for computer components, “determining” in the context of this claim encompasses the person reading the search results and deciding if they are consistent with one another.
The limitation of generating an integration prompt in which a search result determined to have consistency and the question are integrated, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for computer components, “generating” in the context of this claim encompasses the person writing out a prompt including the question and the search result.
The limitation of generating an answer to the question by inputting the integration prompt into a large language model, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for computer components, “generating” in the context of this claim encompasses the person typing the prompt into the interface of an LLM.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claims recite an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claims only additionally recite “processing circuitry” in claim 1 and “a non-transitory computer readable storage medium” in claim 16. These computer components are recited at a high-level of generality such that it amounts no more than mere instructions to apply the exception using generic computer components. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element computer components amount to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are not patent eligible.
Claim 2 additionally recites generate a first query based on the question and a second query generation unit that generates a second query based on the question; search the first information source for a first search result related to the first query; search the second information source for a second search result related to the second query; determine consistency between the first search result and the second search result; and generate an integration prompt in which the question and a first search result and a second search result that are determined to have consistency are integrated. Similar to above these steps encompass a mental process as the person could perform the steps by writing a first query for a first search engine and providing the query to the first search engine, writing a second query for a second search engine and providing the query to the first second engine, deciding if the results are consistent, and writing the prompt accordingly. Similar to above, no additional limitations are recited that amount to significantly more than the abstract idea or provide a practical application. The claim is not patent eligible.
Claim 3 additionally recites the first information source is more reliable than the second information source, and the second information source has higher searchability than the first information source. However this added limitation does not prevent the recited step from being performed as a mental process because the person could search these sources by choosing them according to the claimed criteria. Similar to above, no additional limitations are recited that amount to significantly more than the abstract idea or provide a practical application. The claim is not patent eligible.
Claim 4 additionally recites generate the second query based on the first search result. Similar to above these steps encompass a mental process as the person could perform the steps by searching the first query first and then writing the second query according to the first results. Similar to above, no additional limitations are recited that amount to significantly more than the abstract idea or provide a practical application. The claim is not patent eligible.
Claim 5 additionally recites generate the second query based on the question and the first search result. Similar to above these steps encompass a mental process as the person could perform the steps by searching the first query first and then writing the second query according to the first results. Similar to above, no additional limitations are recited that amount to significantly more than the abstract idea or provide a practical application. The claim is not patent eligible.
Claim 6 additionally recites the query is a keyword extracted from the question, and to search the information source for information including the keyword. Similar to above these steps encompass a mental process as the person could perform the steps by thinking of a keyword related on the question and searching the keyword. Similar to above, no additional limitations are recited that amount to significantly more than the abstract idea or provide a practical application. The claim is not patent eligible.
Claim 7 additionally recites extract the keyword by inquiring a large language model about the keyword in the question. Similar to above these steps encompass a mental process as the person could perform the steps by typing the question into an LLM and prompting it to generate a keyword. Similar to above, no additional limitations are recited that amount to significantly more than the abstract idea or provide a practical application. The claim is not patent eligible.
Claim 8 additionally recites the query is an embedded expression of the question, and to search the information source for information similar to the embedded expression of the question. Similar to above these steps encompass a mental process as the person could perform the steps by reading the embedded expression in the question and searching for it. Similar to above, no additional limitations are recited that amount to significantly more than the abstract idea or provide a practical application. The claim is not patent eligible.
Claim 9 additionally recites determine consistency of the search result by inquiring a large language model whether the search result has consistency. Similar to above these steps encompass a mental process as the person could perform the steps by typing the search results into the interface of an LLM and prompting it to determine consistency. Similar to above, no additional limitations are recited that amount to significantly more than the abstract idea or provide a practical application. The claim is not patent eligible.
Claim 10 additionally recites determine consistency of the search result based on similarity of the search result. Similar to above these steps encompass a mental process as the person could perform the steps by reading the search results and deciding if they are similar. Similar to above, no additional limitations are recited that amount to significantly more than the abstract idea or provide a practical application. The claim is not patent eligible.
Claim 11 additionally recites repeatedly execute generation of the query and search until it is determined that the search result has consistency. Similar to above these steps encompass a mental process as the person could perform the steps by writing queries and searching them until the person decides the results are consistent. Similar to above, no additional limitations are recited that amount to significantly more than the abstract idea or provide a practical application. The claim is not patent eligible.
Claim 12 additionally recites determine that a combination of a search result having a maximum consistency score has consistency. Similar to above these steps encompass a mental process as the person could perform the steps by selecting search results with the most consistency. Similar to above, no additional limitations are recited that amount to significantly more than the abstract idea or provide a practical application. The claim is not patent eligible.
Claim 13 additionally recites generate an integration prompt in which the question and the first search result are integrated in a case where it is determined that the first search result and the second search result do not have consistency. Similar to above these steps encompass a mental process as the person could perform the steps by writing a prompt that include both search results if they are not consistent. Similar to above, no additional limitations are recited that amount to significantly more than the abstract idea or provide a practical application. The claim is not patent eligible.
Claim 14 additionally recites determine that a combination of a search result having a high consistency score or a combination of a search result having high subsidiarity has consistency. Similar to above these steps encompass a mental process as the person could perform the steps by deciding a score based on consistency and selecting the highest score. Similar to above, no additional limitations are recited that amount to significantly more than the abstract idea or provide a practical application. The claim is not patent eligible.
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.
Claim(s) 1, 10-12, and 14-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Peng et al. (Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback) in view of Azarmi et al. (US PAP 2025/0086190).
Consider claim 1, Peng teaches a question response apparatus comprising processing circuitry (abstract, built on code which requires a processor) configured to:
acquire a question input by a user (section 1, section 2.1, user query “q”);
generate a query based on the question (section 2.3.1, generating a set of search queries based on q);
search a search result related to the query from a plurality of information sources (section 2.3.1, calling various APIs to retrieve knowledge from various external searches );
generate an integration prompt in which a search result and the question are integrated (section 2.3.2, generating a prompt including the user query and the external knowledge); and
generate an answer to the question by inputting the integration prompt into a large language model (section 2.3.3 generating response using an LLM with the prompt).
Peng does not specifically teach
determine consistency of the search result;
generate an integration prompt in which a search result determined to be consistent and the question are integrated.
In the same field of retrieval augmented generation, Azarmi teaches
determine consistency of the search result (0056, Soc score, which includes continuity score for context which which measure consistency);
generate an integration prompt in which a search result determined to be consistent and the question are integrated (0071, threshold SoC for submitting context with the prompt to LLM).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to measure consistency as taught by Azarmi in the system of Peng in order to provide more effective context data on the LLM (Azarmi 0002).
Consider claim 10, Azarmi teaches The question response apparatus according to claim 1, wherein the processing circuitry is configured to determine consistency of the search result based on similarity of the search result (0046, determining continuity score using cosine similarity score).
Consider claim 11, Azarmi teaches The question response apparatus according to claim 1, wherein the processing circuitry is configured to repeatedly execute generation of the query by the query generation unit and search by the search unit until it is determined that the search result has consistency (0071-72, queries may be regenerated if SoC threshold is not met).
Consider claim 12, Azarmi teaches the question response apparatus according to claim 1, wherein the processing circuitry is configured to determine that a combination of a search result having a maximum consistency score has consistency (0076, low continuity score sources may be removed, thus a maximum score must have continuity.)
Consider claim 14, Azarmi teaches the question response apparatus according to claim 1, wherein the processing circuitry is configured to determine that a combination of a search result having a high consistency score or a combination of a search result having high subsidiarity has consistency (0076, low continuity score sources may be removed, thus a high score must have continuity.)
Consider claim 15, Peng teaches A method (abstract) comprising:
acquiring a question input by a user (section 1, section 2.1, user query “q”);
generating a query based on the question (section 2.3.1, generating a set of search queries based on q);
searching a search result related to the query from a plurality of information sources (section 2.3.1, calling various APIs to retrieve knowledge from various external searches );
generating an integration prompt in which a search result and the question are integrated (section 2.3.2, generating a prompt including the user query and the external knowledge); and
generating an answer to the question by inputting the integration prompt into a large language model (section 2.3.3 generating response using an LLM with the prompt).
Peng does not specifically teach
determining consistency of the search result;
generating an integration prompt in which a search result determined to be consistent and the question are integrated.
In the same field of retrieval augmented generation, Azarmi teaches
determining consistency of the search result (0056, Soc score, which includes continuity score for context which which measure consistency);
generating an integration prompt in which a search result determined to be consistent and the question are integrated (0071, threshold SoC for submitting context with the prompt to LLM).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to measure consistency as taught by Azarmi in the system of Peng in order to provide more effective context data on the LLM (Azarmi 0002).
Consider claim 16, Peng teaches A non-transitory computer-readable storage medium storing a program (abstract, built on code which must be stored to be executed) for causing a computer to execute functions of:
acquiring a question input by a user (section 1, section 2.1, user query “q”);
generating a query based on the question (section 2.3.1, generating a set of search queries based on q);
searching a search result related to the query from a plurality of information sources (section 2.3.1, calling various APIs to retrieve knowledge from various external searches );
generating an integration prompt in which a search result and the question are integrated (section 2.3.2, generating a prompt including the user query and the external knowledge); and
generating an answer to the question by inputting the integration prompt into a large language model (section 2.3.3 generating response using an LLM with the prompt).
Peng does not specifically teach
determining consistency of the search result;
generating an integration prompt in which a search result determined to be consistent and the question are integrated.
In the same field of retrieval augmented generation, Azarmi teaches
determining consistency of the search result (0056, Soc score, which includes continuity score for context which which measure consistency);
generating an integration prompt in which a search result determined to be consistent and the question are integrated (0071, threshold SoC for submitting context with the prompt to LLM).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to measure consistency as taught by Azarmi in the system of Peng in order to provide more effective context data on the LLM (Azarmi 0002).
Claim(s) 6, 7, and 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Peng and Azarmi as applied to claim 1 above, and further in view of Purwar et al.(Keyword Augmented Retrieval: Novel framework for Information Retrieval with integrated speech interface).
Consider claim 6, Peng and Azarmi teach the question response apparatus according to claim 1, but do not specifically teach wherein the query is a keyword extracted from the question, and the processing circuitry is configured to search the information source for information including the keyword.
In the same field of retrieval augmented generation Purwar teaches herein the query is a keyword extracted from the question, and the processing circuitry is configured to search the information source for information including the keyword (section 2.1, keyBERT used to extract keywords from user query and the keywords are compared to document to identify relevance, i.e.. search).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to extract keywords to use for searching as taught by Purwar in the system of Peng and Azarmi in order to reduce time and costs to find relevant context (Purwar abstract).
Consider claim 7, Purwar teaches The question response apparatus according to claim 6, wherein the processing circuitry is configured to extract the keyword by inquiring a large language model about the keyword in the question (section 2.1, using keyBERT to extract keywords).
Consider claim 8, Peng and Azarmi teach the question response apparatus according to claim 1, but do not specifically teach wherein the query is an embedded expression of the question, and the processing circuitry is configured to search the information source for information similar to the embedded expression of the question.
In the same field of retrieval augmented generation Purwar teaches wherein the query is an embedded expression of the question, and the processing circuitry is configured to search the information source for information similar to the embedded expression of the question (section 2.1, keyBERT used to extract keywords from user query and the keywords are compared to document to identify relevance, i.e.. search, Keywords can be considered a type of embedded expression).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to extract keywords to use for searching as taught by Purwar in the system of Peng and Azarmi in order to reduce time and costs to find relevant context (Purwar abstract).
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Peng and Azarmi as applied to claim 1 above, and further in view of Gekhman et al. (TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models).
Consider claim 9, Peng and Azarmi teach The question response apparatus according to claim 1, but do not specifically teach wherein the processing circuitry is configured to determine consistency of the search result by inquiring a large language model whether the search result has consistency.
In the same field of factual comparison, Gekhman teaches wherein the processing circuitry is configured to determine consistency of the search result by inquiring a large language model whether the search result has consistency (section 2, using an LLM to measure factual consistency between various sources).
It would have been obvious to one of ordinary skill in the art at the time of effective filing to use an LLM to measure consistency as taught by Gekhman in the system of Peng and Azarmi in order to more accurately insure the accuracy of the source data (Gekhman abstract).
Allowable Subject Matter
Claims 2-5 and 13 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims. The following is a statement of reasons for the indication of allowable subject matter:
Consider claim 2, Peng teaches The question response apparatus according to claim 1, wherein the information sources include a first information source and a second information source (section 2.3.1, various external searches), the processing circuitry is configured to:
generate a first query based on the question and a second query generation unit that generates a second query based on the question (section 2.3.1, generating “a set of search queries”);
search the first information source for a first search result related to the first query (section 2.3.1, calling various APIs to retrieve knowledge from various external searches);
search the second information source for a second search result related to the second query (section 2.3.1, calling various APIs to retrieve knowledge from various external searches).
However the prior art of record does not teach or fairly suggest the limitations of
“determine consistency between the first search result and the second search result; and
generate an integration prompt in which the question and a first search result and a second search result that are determined to have consistency are integrated” Azarmi teaches calculating consistency but does not specify determining consistency between data from different queries and different sources as claimed. Therefore claim contains allowable subject matter.
Claims 3-5 and 13 depend on and further limit claim 2 and therefore contain allowable subject matter as well.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Niu et al. (US Patent 12,602,377) teaches a similar method retrieval augmented generation with multiple sources.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DOUGLAS C GODBOLD whose telephone number is (571)270-1451. The examiner can normally be reached 6:30am-5pm Monday-Thursday.
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 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.
DOUGLAS GODBOLD
Examiner
Art Unit 2655
/DOUGLAS GODBOLD/Primary Examiner, Art Unit 2655
Prosecution Insights