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 .
Claim Rejections - 35 USC § 102
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.
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 –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-3, 6-8, 10-13, 16-18 and 20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Hintz (US 2025/0200100).
With respect to claim 1 (similarly claim 11), Hintz teaches a method (e.g. method of Fig 4-6 [0086]) for optimizing information retrieval, comprising:
receiving, from a user, a query (e.g. receiving a query S402 Fig 4 [0087]);
in response to the query, retrieving information that comprises documents relevant to the query (e.g. in response to the query, extract information that comprises documents relevant to the query, [0093]-[0094]);
calculating a respective information value (IV) for each of the retrieved documents (e.g. calculating/generating a respective relevancy score for each of the retrieved documents, [0023], [0094]);
counting a token length for each of the retrieved documents (e.g. computing a score for each token pair [0031]-[0032], Some of the documents will be small enough that their raw token length is less than their final prompt allocation l.sub.i<L.sub.i when s.sub.i=1 (where l.sub.i is the allocated length and L.sub.i is the raw content length) [0076] suggest counting a token length for each of the retrieved documents);
selecting, from among the retrieved documents, an optimal document set that includes a set of the retrieved documents that maximizes an amount of information (e.g. the top K number (based on the K-Cutoff value) of the documents in the search results (ordered by relevancy score) are extracted or selected.[0108] Fig 5 S508), while respecting a token budget (e.g. while respecting token budget, as suggested in [0073]-[0076]); and
inserting the optimal document set into a context window (e.g. inserting the optimal document set into static segments and dynamic segments [0099]) so as to enhance an output of an LLM with documents of the optimal document set (e.g. so as to enhance an output of an LLM 108 with documents of the optimal document set as suggested in [0100]-[0101])).
With respect to claim 2 (similarly claim 12), Hintz teaches the method as recited in claim 1, wherein the query is received from the user as part of a session between the user and a virtual entity (e.g. query 201 Fig 2A is received from the user as part of a session between the user and a virtual entity, see Fig 2A [0042] and [0087]).
With respect to claim 3 (similarly claim 13), Hintz teaches the method as recited in claim 1, wherein a lexical and/or semantic similarity search is used to determine the information values for the retrieved documents (e.g. the search query of S410-S412 Fig 4 [0093]-[0094] suggest a lexical and/or semantic similarity search is used to determine the information values for the retrieved documents).
With respect to claim 6 (similarly claim 16), Hintz teaches the method as recited in claim 1, wherein the optimal document set is returned to the user (e.g. the optimal document set is returned to the user as suggested in [0101]).
With respect to claim 7 (similarly claim 17), Hintz teaches the method as recited in claim 1, wherein the optimal document set is identified using respective tuples (IV, s) for each of the retrieved documents, where IV is the information value of the document, and s is the token length of the document (e.g. [0128] suggest the optimal document set is identified using respective tuples (IV, s) for each of the retrieved documents, where IV is the information value of the document, and s is the token length of the document).
With respect to claim 8 (similarly claim 18), Hintz teaches the method as recited in claim 1, wherein the LLM performs the retrieving, calculating, counting, and selecting, as part of a RAG (retrieval augmented generation) process (e.g. LLM 108 Fig 2A performs the retrieving, calculating, counting, and selecting, as part of a RAG (retrieval augmented generation) process, as suggested in Figs 4-6).
With respect to claim 10 (similarly claim 20), Hintz teaches the method as recited in claim 1, wherein the output of the LLM comprises a prompt [instruction] + [optimal document set] + [query] (e.g. the output of LLM 108 Fig 2A comprises a prompt [instruction] + [optimal document set] + [query] included in the grounding data, see Fig 4 S420 [0100]-[0101]).
Claim Rejections - 35 USC § 103
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.
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) 4-5, 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over Hintz (US 2025/0200100) in view of Hara (US 2024/0048850).
With respect to claim 4 (similarly claim 14), Hintz teaches the method as recited in claim 1 including to search for those documents, among the retrieved documents, that maximize the amount of information, see Fig 5 S508 [0108].
However, Hintz fails to teach wherein a metaheuristic is used to search for those documents, among the retrieved documents, that maximize the amount of information.
Hara teaches Branch-and-Bound method and metaheuristics (simulated annealing, genetic algorithms, tabu search, or the like) can be used to solve the integer programming problem, [0081].
Hintz and Hara are analogous art because they all pertain to solving an optimization problem. Therefore, it would have been obvious to people having ordinary skill in the art before the effective filing date of the claimed invention to modify Hintz with the metaheuristic method of Hara to include: wherein a metaheuristic is used to search for those documents, among the retrieved documents, that maximize the amount of information, as suggested in [0081] of Hara. The benefit of the modification would be to find the most relevant documents using the metaheuristic method of Hara.
With respect to claim 5 (similarly claim 15), Hintz in view of Hara teaches the method as recited in claim 4, wherein the metaheuristic comprises BnB (branch and bound) (Hara e.g. the branch-and-bound method of [0081]).
Claim(s) 9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Hintz (US 2025/0200100) in view of Hart (US 2008/0235585).
With respect to claim 9 (similarly claim 19), Hintz teaches the method as recited in claim 1 including selecting the optimal document set, see Fig 2A and method of Fig 4-6).
However, Hintz fails to teach wherein selecting the optimal document set is a combinatorial optimization problem.
Hart teaches wherein selecting the optimal document set is a combinatorial optimization problem (e.g. selecting document elements is a combinatorial optimization problem, see [0066]-[0072]).
Hintz and Hart are analogous art because they all pertain to solving an optimization problem. Therefore, it would have been obvious to people having ordinary skill in the art before the effective filing date of the claimed invention to modify Hintz with the optimization module of Hart to include: wherein selecting the optimal document set is a combinatorial optimization problem, as suggested in [0066]-[0072] of Hart. The benefit of the modification would be to find the most relevant documents using the optimization module of Hart.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to IBRAHIM SIDDO whose telephone number is (571)272-4508. The examiner can normally be reached 9:00-5:30PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Akwasi Sarpong can be reached at 5712703438. 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.
/IBRAHIM SIDDO/Primary Examiner, Art Unit 2681
Prosecution Insights