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 .
DETAILED ACTION
This responds to Applicant’s Arguments/Remarks filed 03/31/2026. Claims 1, 8-12 have been amended. Claims 2-7, 13-20 have been cancelled. Claims 21-25 have been newly added. Claims 1, 8-12, 21-25 are now pending in this Application
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy has been filed in parent Application No. 18/933,349, filed on 10/31/2024.
Claim Objections
Claims 1 and 5 are objected to because of the following informalities:
Claim scope is not limited by claim language that suggests or makes optional but does not require steps to be performed, or by claim language that does not limit a claim to a particular structure. However, examples of claim language, although not exhaustive, that may raise a question as to the limiting effect of the language in a claim are:
(A) "adapted to" or "adapted for" clauses;
(B) "wherein" clauses; and
(C) "whereby" clauses.
The determination of whether each of these clauses is a limitation in a claim depends on the specific facts of the case. In Hoffer V. Microsoft Corp., 405 F.3d 1326, 1329, 74 USPQ2d 1481, 1483 (Fed. Cir. 2005), the court held that when a "whereby' clause states a condition that is material to patentability, it cannot be ignored in order to change the substance of the invention." Id. However, the court noted (quoting Minton V. Nat 'I Ass 'n of Securities Dealers, Inc., 336 F.3d 1373, 1381, 67 USPQ2d 1614, 1620 (Fed. Cir. 2003)) that a "whereby clause in a method claim is not given weight when it simply expresses the intended result of a process step positively recited.
Response to Arguments
Applicant's arguments filed 3/31/2026 have been fully considered but they are not persuasive.
Applicant argues that Salim does not disclose “the query changing (e.g., searching a change query dictionary), the multi-intent processing (i.e., inducing and summarizing the original query and the change query to obtain a multi-intent query), the multi-intent based search (i.e., searching, according to the multi-intent query, a webpage library to obtain a reference result) and the structured prompts based results generation (i.e., generating according to an input prompt which is constructed based on the original query or the multi-intent query, the change query, the reference result and a target instruction).
In response to Applicant’s argument, the examiner submits that Salim discloses “the system can modify or expand a prompt based on the query to include additional information. This “additional information” can provide an additional “perspective” on or regarding the original query, by expanding or modifying on the original query entered by the user” (Par [0020]). Modifying query is a “query changing”
Salim discloses “…for example, the system can execute a chatbot application to solicit definitions, alternatives or synonym of one or more terms of a query and ca add to or replace any of those terms with the definitions, alternative or synonym to modify a perspective of the query, resulting the modified queries each having a different perspective driven by its distinct content. The system can execute large language model using each of the modified queries to generate a response for each of the queries. The system can compare each of the modified queries to identity one or more queries that include content that is substantially the same or that is substantially different, … (Par [0022]). Processing multi-intent search.
Therefore, Salim discloses these limitation.
Applicant’s arguments with respect to claim(s) 3/31/2026 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
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) 1-9, 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Salim et al (U.S. Pub No. 2025/0278574 A1), and in view of Jing et al (U.S. Pub No. 2025/0335520 A1).
As per claim 1, a result generation method, applied to a generation system comprising a query-understanding Large Language Model, a search engine and an organization-generative Large Language Model, wherein the method comprises:
acquiring, by the query-understanding Large Language Model, an input original query (Par [0004, 0069]);
searching, by the query-understanding Large Language Model, a change query dictionary for a change query corresponding to the original query; wherein the change query and the original query have a similar or same intention or semantics (par [0004-0006, 0032]);
inducing and summarizing, by the query-understanding Large Language Model, the original query and the change query, to obtain a multi-intent query; searching, by the search engine, according to the multi- intent query input (par [0032, 0059-0061]);
generating, by the organization-generative Large Language Model, according to an input prompt, an output result corresponding to the original query (Par [0031-0032]);
wherein the prompt comprises a task description area, an interactive information area, a search result area and an instruction area; wherein the task description area is used to describe a task that the organization-generative Large Language Model is required to execute, and constructed based on the original query or the multi-intent query; wherein the interactive information area is used to describe a potential requirement that the organization-generative Large Language Model is required to refer to when generating answers, and constructed based on the change query; wherein the search result area is constructed based on the reference result; and wherein the instruction area is constructed based on a target instruction instructing the organization-generative Large Language Model to comprehensively reference the original query, the change query and the reference result for answering (Par [0019-0022]).
Salim does not explicitly disclose a webpage library to obtain a reference result.
However, Jing discloses a webpage library to obtain a reference result (Par [0031-0032, 0039]).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention was made to incorporate the features as disclosed in Jing into the teaching of Salim in order to improve content and summarized content (Par [0006]).
As per claim 8, Salim discloses the method of claim 1, wherein searching, by the organization-generative Large Language Model, the change query dictionary for the change query corresponding to the original query comprises:
searching, organization-generative Large Language Model, the change query dictionary for a plurality change queries associated with the original query in a session; and cleaning, organization-generative Large Language Model, according to a search intention of the original query, the plurality of change queries associated with the original query in the session to obtain the change query (par [0004-0005, 0031]).
As per claim 9. The method of claim 8, wherein cleaning, organization-generative Large Language Model, according to the search intention of the original query the plurality of change queries associated with the original query in the session comprises at least one of:
obtaining, based on keyword matching, a plurality of first similarities between the original query and the pluralities of change queries in the session, , and retaining, according to the plurality of first similarities the change query has the search intention similar to the original query; or obtaining, based on semantic understanding for intention discrimination, a plurality of second similarities between the original query and the plurality of change queries in the session, and retaining, according to the plurality of second similarities, the change query has the search intention similar to the original query (Par [0056]).
As per claim 21, Salim discloses a generation system comprising a query-understanding Large Language Model, a search engine and an organization-generative Large Language Model, wherein:
The query-understanding Large Language Model is configured to: acquired an input original query (par [0004, 0069]);
search a change query dictionary for a change query corresponding to the original query; wherein the change query and the original query have a similar or same intention or semantics (par [0004-0006, 0032]); and
induce and summarize the original query and the change query, to obtain a multi-intent query; the search engine is configured to: search, according to the multi-intent query (par [0032, 0059-0061]),
the organization-generative Large Language Model is configured to: generate, according to an input prompt, an output result corresponding to the original query (Par [0031-0032]);
wherein the prompt comprises a task description area, an interactive information area, a search result area and an instruction area; wherein the task description area is used to describe a task that the organization- generative Large Language Model is required to execute, and constructed based on the original query or the multi-intent query; wherein the interactive information area is used to describe a potential requirement that the organization-generative Large Language Model is required to refer to when generating answers, and constructed based on the change query; wherein the search result area is constructed based on the reference result; and wherein the instruction area is constructed based on a target instruction instructing the organization-generative Large Language Model to comprehensively reference the original query, the change query and the reference result for answering (Par [0019-0022]).
Salim does not explicitly disclose a webpage library to obtain a reference result.
However, Jing discloses a webpage library to obtain a reference result (Par [0031-0032, 0039]).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention was made to incorporate the features as disclosed in Jing into the teaching of Salim in order to improve content and summarized content (Par [0006]).
As per claim 22, Salim discloses the generation system of claim 21, wherein the query-understanding Large Language Model is configured to perform searching the change query dictionary for the change query corresponding to the original query, by:
searching the change query dictionary for a plurality of change queries associated with the original query in a session; and cleaning, according to a search intention of the original query, the plurality of change queries associated with the original query in the session, to obtain the change query (par [0004-0005, 0031]).
As per claim 23, Salim discloses the generation system of claim 22, wherein the query-understanding Large Language Model is configured to perform cleaning the plurality of change queries associated with the original query in the session by at least one of:
obtaining, based on keyword matching, a plurality of first similarities between the original
query and the plurality of change queries in the session, and retaining, according to the plurality of first similarities, the change query has a search intention similar to the original query; or obtaining, based on semantic understanding for intention discrimination, a plurality of second similarities between the original query and the plurality of change queries in the session, and retaining, according to the plurality of second similarities, the change query has a search intention similar to the original query (Par [0056]).
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) 10, 24 is/are rejected under 35 U.S.C. 103 as being unpatentable over Salim et al (U.S. Pub No. 2025/0278574 A1), and in view of CUI et al (U.S. Pub No. 2025/0335773 A1).
As per claim 10, Salim discloses second prompts including one or more second data clarifying the first query. Salim does not explicitly disclose the method of claim 8, further comprising: ranking, the organization-generative Large Language Model, the plurality of change queries associated with the original query based on a key feature, wherein the key feature includes at least one of: a change query rate, a change query source or feedback information after change query; and selecting, the organization-generative Large Language Model, according to a ranking result the change query retained from the plurality of change queries associated with the original query.
However, CUI discloses further comprising: the method of claim 8, further comprising: ranking, the organization-generative Large Language Model, the plurality of change queries associated with the original query based on a key feature, wherein the key feature includes at least one of: a change query rate, a change query source or feedback information after change query; and selecting, the organization-generative Large Language Model, according to a ranking result the change query retained from the plurality of change queries associated with the original query (par [0075-0080]).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention was made to incorporate the features as disclosed in CUI into the teaching of Salim in order to generate a response to improve the prompt (Par [0075]).
As per claim 24, Salim does not explicitly disclose the generation system of claim 22, wherein the query-understanding Large Language Model is further configured to: rank the plurality of change queries associated with the original query based on a key feature, wherein the key feature includes at least one of: a change query rate, a change query source or feedback information after change query; and select, according to a ranking result, the change query retained from the plurality of change queries associated with the original query.
However, CUI discloses wherein the query-understanding Large Language Model is further configured to: rank the plurality of change queries associated with the original query based on a key feature, wherein the key feature includes at least one of: a change query rate, a change query source or feedback information after change query; and select, according to a ranking result, the change query retained from the plurality of change queries associated with the original query (par [0075-0080]).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention was made to incorporate the features as disclosed in CUI into the teaching of Salim in order to generate a response to improve the prompt (Par [0075]).
Claim(s) 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Salim et al (U.S. Pub No. 2025/0278574 A1), and in view of Smith et al (U.S. Pub No. 2025/0278633 A1).
As per claim 11, CUI discloses the method of claim 10, further comprising: aggregating, according to the search intention, based on the original query and the change query according to the search intention retained (Par [0075-0080]).
Salim and CUI do not explicitly disclose dynamic time window. However, Smith discloses dynamic time window (Par [0023] and fig 3).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention was made to incorporate the features as disclosed in Smith into the teaching of Salim as modified by CUI in order to improve the quality of responses to users’ prompt (Par [0022]).
As per claim 25, CUI discloses the generation system of claim 24, wherein the query-understanding Large Language Model is further configured to: aggregate, based on a dynamic time window, according to the search intention, the original query and the change query retained (Par [0075-0080]).
Salim and CUI do not explicitly disclose dynamic time window. However, Smith discloses dynamic time window (Par [0023] and fig 3).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention was made to incorporate the features as disclosed in Smith into the teaching of Salim as modified by CUI in order to improve the quality of responses to users’ prompt (Par [0022]).
Claim(s) 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over CUI et al (U.S. Pub No. 2025/0335773 A1), and in view of Salim et al (U.S. Pub No. 2025/0278574 A1).
As per claim 12, Salim discloses a generation model training method, applied to a generation system comprising a query-understanding Large Language Model, a search engine and an organization-generative Large Language Model, wherein the method comprises:
acquiring, by the query-understanding Large Language Model, an input original query (Par [0004, 0069]);
searching, by the query-understanding Large Language Model, a change query dictionary for a change query corresponding to the original query; wherein the change query and the original query have a similar or same intention or semantics (par [0004-0006, 0032]);
inducing and summarizing, by the query-understanding Large Language Model, the original query and the change query, to obtain a multi-intent query; searching, by the search engine, according to the multi- intent query input (par [0032, 0059-0061]);
generating, by the organization-generative Large Language Model, according to an input prompt, an output result corresponding to the original query (Par [0031-0032]);
wherein the prompt comprises a task description area, an interactive information area, a search result area and an instruction area; wherein the task description area is used to describe a task that the organization-generative Large Language Model is required to execute, and constructed based on the original query or the multi-intent query; wherein the interactive information area is used to describe a potential requirement that the organization-generative Large Language Model is required to refer to when generating answers, and constructed based on the change query; wherein the search result area is constructed based on the reference result; and wherein the instruction area is constructed based on a target instruction instructing the organization-generative Large Language Model to comprehensively reference the original query, the change query and the reference result for answering (Par [0019-0022]);
adjusting the organization-generative Large Language Model according to an expected answer for the prompt and the predicted answer (par [0022, 0030, 0047]).
Salim does not explicitly disclose a webpage library to obtain a reference result.
However, Jing discloses a webpage library to obtain a reference result (Par [0031-0032, 0039]).
It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention was made to incorporate the features as disclosed in Jing into the teaching of Salim in order to improve content and summarized content (Par [0006]).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to THU N NGUYEN whose telephone number is (571)270-1765. The examiner can normally be reached Monday to Friday from 9:30AM-6:00PM.
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, Boris Gorney can be reached at 571-272-5626. 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.
June 13, 2026
/THU N NGUYEN/Examiner, Art Unit 2154
Prosecution Insights