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 communication is responsive to the application filed on November 3, 2025. Claims 1-20 are pending at the time of examination.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on December 1, 2025 was considered by the examiner. See attached PTO-form 1449.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
The claim 1 recites “A computer-implemented method for information retrieval, the method comprising: obtaining, by a computing system comprising one or more computing devices, a query; generating, by the computing system, a model input comprising a combination of the query and a model prompt, wherein the model prompt comprises a chain of thought prompt that instructs a machine-learned language model to provide a rationale for its output; processing, by the computing system, the model input with the machine-learned language model to generate, as an output of the machine-learned language model, a model output; generating, by the computing system, an expanded query based on the query and the model output; and providing, by the computing system, the expanded query as an input to an information retrieval system to receive a set of results as an output of the information retrieval system.”.
Claim 5 recites “A computing system for information retrieval, the computing system comprising: one or more processors; and one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising: obtaining, by the computing system, a query; generating, by the computing system, a model input comprising a combination of the query and a model prompt, wherein the model prompt comprises a zero-shot model prompt that specifies a task to be performed without providing any additional training data or examples; processing, by the computing system, the model input with a machine-learned language model to generate, as an output of the machine-learned language model, a model output; generating, by the computing system, an expanded query based on the query and the model output; and providing, by the computing system, the expanded query as an input to an information retrieval system to receive a set of results as an output of the information retrieval system.”.
The claim 11 recites One or more non-transitory computer-readable media that collectively store instructions that, when executed by a computing system, cause the computing system to perform operations, the operations comprising: obtaining, by the computing system, a query; generating, by the computing system, a model input comprising a combination of the query and a model prompt, wherein the model prompt instructs a machine-learned language model to generate a list of keywords for the query; processing, by the computing system, the model input with the machine-learned language model to generate, as an output of the machine-learned language model, a model output; generating, by the computing system, an expanded query based on the query and the model output; and providing, by the computing system, the expanded query as an input to an information retrieval system to receive a set of results as an output of the information retrieval system.)
The limitation of claims 1, 5 and 11, 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 “a computer,” nothing in the claim element precludes the step from practically being performed in the mind. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind and/or manually performed, but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites one additional element – using “a computer to perform the claims steps. The “computer” in these steps is recited at a high-level of generality (i.e., as a computer” performing a generic computer functions) such that it amounts no more than mere instructions to apply the exception using a generic computer component. The claim also recites the additional elements “generating, by the computing system, an expanded query based on the query and the model output; providing, by the computing system, the expanded query as an input to an information retrieval system to receive a set of results as an output of the information retrieval system” that are the insignificant extra-solution activity of data gathering and/or output, and can be understood as activities incidental to the primary process or product that are merely a nominal or tangential addition to the claim (see MPEP 2106.05(g)). Accordingly, these 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 claim is directed to an abstract idea. (see 2019 Revised Patent Subject Matter Eligibility Guidance, Step 2A, Prong Two. See also MPEP 2106.04(II)(A)(2), MPEP 2106.04(d).
The claims 1,5 and 11 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 of using “a computer” to perform the claimed steps amounts 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. see 2019 Revised Patent Subject Matter Eligibility Guidance, Step 2B. See also MPEP 2106.05
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 –
Claims 11-14, 16-20 are rejected under 35 U.S.C. 102(2)(2) as being anticipated by Heller et al. (US Patent No. 12,067,366).
As per claim 11, Heller discloses One or more non-transitory computer-readable media that collectively store instructions that (Fig. 7), when executed by a computing system, cause the computing system to perform operations, the operations comprising:
obtaining, by the computing system, a query; generating, by the computing system, a model input comprising a combination of the query and a model prompt, wherein the model prompt instructs a machine-learned language model to generate a list of keywords for the query; processing, by the computing system, the model input with the machine-learned language model to generate, as an output of the machine-learned language model, a model output; generating, by the computing system, an expanded query based on the query and the model output; and providing, by the computing system, the expanded query as an input to an information retrieval system to receive a set of results as an output of the information retrieval system.
the one or more documents comprising the plurality of query expansion terms; wherein the machine-learned language model attends over the plurality of query expansion terms in the one or more documents to generate the model output comprising the plurality of query expansion terms (col. 29, lines 20-67, as a query expansion prompt is created based on the query request and a query expansion prompt template.. large language model to generate keywords; col. 30, lines 6-22, as the query expansion prompt 1304 may include one or more specialized requests to perform context-specific mapping of one or more elements of the query request to context-specific information. For example, in the context of a legal research query, the query expansion prompt 1304 may include a request to map the text of the query request onto one or more jurisdiction codes corresponding to legal jurisdictions in the United States or elsewhere in the world. As another example, the query expansion prompt 1304 may include a request to map the text of the query request onto one or more geographic codes corresponding to geographic regions. The query expansion prompt is sent to the text generation modeling system 270 at 1306, where it is analyzed and completed by the text generation model 276. At 1308, the text generation modeling system 270 sends a query expansion response to the text generation interface system 210.).
As per claim 12, Heller further teaches wherein the machine-learned language model comprises a general-purpose model that has not been fine-tuned on a query expansion task (col. 16, lines 1-7).
As per claim 13, Heller further teaches wherein the model input further comprises one or more pseudo-relevance feedback documents that have been retrieved based on the query (col. 4, lines 40-52, col. 5, lines 1-5).
As per claim 14, Heller further teaches the expanded query based on the query and the model output comprises concatenating, by the computing system, the query and the model output to generate the expanded query (col. 30, lines 7-17).
As per claim 16, Heller further teaches wherein the model output comprises a plurality of query expansion terms (col. 31, lines 41-67).
As per claim 17, Heller further teaches wherein the model output comprises an answer to the query (col. 34, lines 23-30).
As per claim 18, Heller further teaches wherein the model output comprises an answer to the query that follows a rationale supporting the answer (col. 37, lines 43-67).
As per claim 19, Heller further teaches wherein the information retrieval system is configured for sparse retrieval (col. 36, lines 15-32).
As per claim 20, Heller further teaches retrieving one or more documents; and providing the one or more documents in the model input (col. 36, lines 43-60).
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.
Claims 1-10 are rejected under 35 U.S.C. 103 as being unpatentable over Heller et al. (US Patent No. 12,067,366) in view of Mackie et al (“Generative Relevance Feedback with Large Language Models” (April 25, 2023) (IDS cited).
As per claim 1, Heller discloses a computer-implemented method for information retrieval, the method comprising:
obtaining, by a computing system comprising one or more computing devices, a query (Fig. 13, col. 29, line 11, as a query request is received at 1302);
generating, by the computing system, a model input comprising a combination of the query and a model prompt (Fig. 13, col. 29, lines 20-21, as a query expansion prompt is created at 1304 based on the query request and a query expansion prompt template).
Heller does not explicitly teach, but Mackie teaches wherein the model prompt comprises a chain of thought prompt that instructs a machine-learned language model to provide a rationale for its output (page 1, section “INTRODUCTION: as LLM to generate diverse types of query-specific text, chain of though (“COT”) reasoning);
processing, by the computing system, the model input with the machine-learned language model to generate, as an output of the machine-learned language model, a model output (page 3, col. 2, para. 3, as Table 1 shows the effectiveness of generative feedback with varying units of text (Keywords-News) and our full hybrid method that uses text from all subtasks. We test for significant improvements againstBM25 with RM3 expansion, to ascertain whether our zero-shot generative feedback methods improve over RM3 expansion. Generation subtasks that target short text span or lists (Key-words, Entities, Keywords-COT, Entities-COT, and Queries);
generating, by the computing system, an expanded query based on the query and the model output (page 2, col. 1, 3rd para, as Quer Expansion; LLM Query Augmentation The emergence of LLMs has shown progress across many different aspects of information retrieval [ 48].This includes using LLMs to change the query representation, such as query generation and rewriting [ 15 , 24 , 34 , 39, 44 , 50 ], context generation [12 , 23 ], and query-specific reasoning [ 10 , 36 ]. For ex-ample, Nogueira et al . [34] fine-tune a T5 model to generate queries for document expansion for passage retrieval. More recent work by Bonifacio et al . [3] shows that GPT3 can be effectively leveraged for few-short query generation for dataset generation. Furthermore, LLMs have been used for conversational query re-writing [ 44] and generating clarifying questions); and
providing, by the computing system, the expanded query as an input to an information retrieval system to receive a set of results as an output of the information retrieval system (pg. 3, para. 4, section 4.1.2, as We assess the system runs to a run depth of 1,000. With GRF being an initial retrieval model, recall-oriented evaluation is important, such as Recall@1000 and MAP to identify relevant documents. We also analyse NDCG@10 to show precision in the top ranks. We use ir-measures for all our evaluations [ 25 ]and a 95% confidence paired-t-test for significance).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention was made to modify the teachings of Heller to implement the above steps of Mackie because it would improve on document retrieval system, as suggested by Mackie (pg.1 col. 1, section: “ABSTRACT”).
As per claim 2, Mackie further teaches wherein the machine-learned language model comprises a general-purpose model that has not been fine-tuned on a query expansion task (pg. 3, col. 1, para. 5).
As per claim 3, Mackie further teaches wherein the model input further comprises one or more pseudo-relevance feedback documents that have been retrieved based on the query (pg. 1, col. 1, section: “INTRODUCTION”, 2nd para.).
As per claim 4, Mackie further teaches wherein generating, by the computing system, the expanded query based on the query and the model output comprises concatenating, by the computing system, the query and the model output to generate the expanded query (pg. 1, col.2, Fig. 1).
As per claim 5, Heller discloses a computing system for information retrieval, the computing system comprising:
one or more processors; and one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors (Fig. 7), cause the computing system to perform operations, the operations comprising:
obtaining, by the computing system, a query (Fig. 13, col. 29, line 11, as a query request is received at 1302);
generating, by the computing system, a model input comprising a combination of the query and a model prompt (Fig. 13, col. 29, lines 20-21, as a query expansion prompt is created at 1304 based on the query request and a query expansion prompt template).
Heller does not explicitly teach, but Mackie teaches wherein the model prompt comprises a zero-shot model prompt that specifies a task to be performed without providing any additional training data or examples (pg. 1, ABSTRACT: zero-shot generative subtasks; pg 2, #3, Generative Relevance Feedback (GRF) tackles query-document lex-ical mismatch using text generation for zero-shot query expansion; In essence, we show that LLMs can effectively generate zero-shot text context close to the target relevant documents.);
processing, by the computing system, the model input with a machine-learned language model to generate, as an output of the machine-learned language model, a model output (page 3, col. 2, para. 3, as Table 1 shows the effectiveness of generative feedback with varying units of text (Keywords-News) and our full hybrid method that uses text from all subtasks. We test for significant improvements againstBM25 with RM3 expansion, to ascertain whether our zero-shot generative feedback methods improve over RM3 expansion. Generation subtasks that target short text span or lists (Key-words, Entities, Keywords-COT, Entities-COT, and Queries);
generating, by the computing system, an expanded query based on the query and the model output (page 2, col. 1, 3rd para, as Quer Expansion; LLM Query Augmentation The emergence of LLMs has shown progress across many different aspects of information retrieval [ 48].This includes using LLMs to change the query representation, such as query generation and rewriting [ 15 , 24 , 34 , 39, 44 , 50 ], context generation [12 , 23 ], and query-specific reasoning [ 10 , 36 ]. For ex-ample, Nogueira et al . [34] fine-tune a T5 model to generate queries for document expansion for passage retrieval. More recent work by Bonifacio et al . [3] shows that GPT3 can be effectively leveraged for few-short query generation for dataset generation. Furthermore, LLMs have been used for conversational query re-writing [ 44] and generating clarifying questions); and
providing, by the computing system, the expanded query as an input to an information retrieval system to receive a set of results as an output of the information retrieval system (pg. 3, para. 4, section 4.1.2, as We assess the system runs to a run depth of 1,000. With GRF being an initial retrieval model, recall-oriented evaluation is important, such as Recall@1000 and MAP to identify relevant documents. We also analyse NDCG@10 to show precision in the top ranks. We use ir-measures for all our evaluations [ 25 ]and a 95% confidence paired-t-test for significance).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention was made to modify the teachings of Heller to implement the above steps of Mackie because it would improve on document retrieval system, as suggested by Mackie (pg.1 col. 1, section: “ABSTRACT”).
As per claims 6-8 have similar limitations as recited in claims 2-4; therefore, they are rejected under the same subject matter.
As per claim 9, Mackie further teaches wherein the model prompt instructs the machine-learned language model to generate a list of keywords for the query (pg. 1, col. 2, as query expansion models, types of generated text: keywords.
As per claim 10, Heller further teaches wherein the model prompt instructs the machine-learned language model to generate a passage that responds to the query (col. 29, lines 20-67).
Claim 15 are rejected under 35 U.S.C. 103 as being unpatentable over Heller et al. (US Patent No. 12,067,366) as applied to claim 1 above, and further in view of Mackie et al (“Generative Relevance Feedback with Large Language Models” (April 25, 2023) (IDS cited).
As per claim 15, Heller does not explicitly teach, but Mackie teaches wherein the model prompt comprises a zero-shot model prompt that specifies a task to be performed without providing any additional training data or examples (pg. 1, ABSTRACT: zero-shot generative subtasks; pg 2, #3, Generative Relevance Feedback (GRF) tackles query-document lex-ical mismatch using text generation for zero-shot query expansion; In essence, we show that LLMs can effectively generate zero-shot text context close to the target relevant documents.). Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention was made to modify the teachings of Heller to implement the above steps of Mackie because it would improve on document retrieval system, as suggested by Mackie (pg.1 col. 1, section: “ABSTRACT”).
Conclusion
The prior art made of record, listed on form PTO-892, and not relied upon, if any, is considered pertinent to applicant's disclosure.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DEBBIE M LE whose telephone number is (571)272-4111. The examiner can normally be reached 9:00-5:00.
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, Charles Rones can be reached at 571-272-4085. 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.
/DEBBIE M LE/Primary Examiner, Art Unit 2168 September 11, 2026
