DETAILED ACTION
This non-final rejection is responsive to the Request for Continued Examination (RCE) filed June 29, 2026. Claims 1, 6-9, 11, 16-19 and 21-24 are currently amended. Claims 3-5, 10, 13-15, and 20 are cancelled. Claims 1, 2, 6-9, 11, 12, 16-19, and 21-24 are pending in this application.
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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on June 29, 2026 has been entered.
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, 2, 6-9, 11, 12, 16-19, and 21-24 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1 and 11 recite determining that the user query is ambiguous by: generating a first prompt with the user query asking a large language model (LLM) whether the user query is ambiguous; generating a second prompt comprising the user query and query content-based rules for returning disambiguated user queries, wherein the query content-based rules identify words that are not ambiguous; and generating Structured Query Language (SQL) for the selected disambiguated user query. The broadest reasonable interpretation of these steps is that the steps fall within the mental process groupings of abstract ideas because they cover concepts performed in the human mind, including observation, evaluation, judgment, and opinion. See MPEP 2106.04(a)(2), subsection III. For example, a user can mentally determine a query is ambiguous by generating a first prompt, and generate a SQL query for a disambiguated query.
This judicial exception is not integrated into a practical application. The limitations “receiving, by a computer program executed by a backend electronic device, a user query regarding an incident involving an affected system from a user interface computer program executed by a user electronic device”; “receiving, by the computer program and from the LLM, an indication of whether the user query is ambiguous”, “receiving, by the computer program and from the LLM, a plurality of disambiguated user queries for the user query and a rationale for the plurality of disambiguated user queries based on application of the query content-based rules”; “presenting, by the computer program, the plurality of disambiguated user queries to the user interface computer program”; “receiving, by the computer program, a selection of one of the disambiguated user queries from the user interface computer program”; and “returning, by the computer program, results of the execution of the SQL for the selected disambiguated user query on the database to the user interface computer program” are mere data gathering and output recited at a high level of generality, and thus are insignificant extra-solution activity. The limitations “submitting, by the computer program, the first prompt to the LLM”; “submitting, by the computer program, the second prompt to the LLM”; “executing, by the computer program, the SQL for the selected disambiguated user query on a database”; and “causing, by the computer program, a downstream system to take an action with the affected system in response to the results of the execution of the SQL for the selected disambiguated user query” amount to no more than mere instructions to apply the exception using a generic computer. Further, all of the steps are recited as being performed by a computer program/processors. The computer is recited at a high level of generality such that amounts to no more than mere instructions to apply the exception using a generic computer. Even when viewed in combination, these additional elements do not integrate the recited judicial exception into a practical application, and the claim is directed to the judicial exception.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above, the recitations of “receiving”, “presenting”, and “returning” are recited at a high level of generality. These elements amount to receiving or transmitting data over a network and presenting offers and are well-understood, routine, conventional activity. See MPEP 2106.05(d), subsection II. The “submitting”, “executing”, and “causing” limitations provide nothing more than mere instructions to apply the exception using a generic computer. As discussed above, the recitation of a computer program/processor to perform recited limitations amounts to no more than mere instructions to apply the exception using a generic computer component. Even when considered in combination, these additional elements represent mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept.
Dependent claims 2 and 12 recite wherein the user query is ambiguous when it is susceptible to a plurality of interpretations. This limitation falls within the mental process groupings of abstract ideas because it cover concepts performed in the human mind, including observation, evaluation, judgment, and opinion. A user can mentally determine that a query is ambiguous when it is susceptible to a plurality of interpretations. There are no additional elements. Therefore, this judicial exception is not integrated into a practical application and the claims do not recite additional elements that are sufficient to amount to significantly more than the judicial exception.
Dependent claims 6 and 16 recite wherein the second prompt further comprises rules to identify words or phrases in the user query that are not ambiguous. This limitation falls within the mental process groupings of abstract ideas because it covers concepts performed in the human mind, including observation, evaluation, judgment, and opinion. A user can mentally generate a second prompt having rules that identify words or phrases in the user query that are not ambiguous.
There are no additional elements. Therefore, the judicial exceptions are not integrated into a practical application and the claims do not recite additional elements that are sufficient to amount to significantly more than the judicial exception.
Dependent claims 7 and 17 recite wherein the second prompt further comprises rules that are derived from a plurality of past user queries statistically. This limitation falls within the mental process groupings of abstract ideas because it covers concepts performed in the human mind, including observation, evaluation, judgment, and opinion. A user can mentally generate a second prompt having rules that are derived from a plurality of past user queries statistically.
There are no additional elements. Therefore, the judicial exceptions are not integrated into a practical application and the claims do not recite additional elements that are sufficient to amount to significantly more than the judicial exception.
Dependent claims 8 and 18 recite wherein the second prompt further comprises rules that are based on a pattern identified in past user queries. This limitation falls within the mental process groupings of abstract ideas because it covers concepts performed in the human mind, including observation, evaluation, judgment, and opinion. A user can mentally generate a second prompt having rules that are based on a pattern identified in past user queries.
There are no additional elements. Therefore, the judicial exceptions are not integrated into a practical application and the claims do not recite additional elements that are sufficient to amount to significantly more than the judicial exception.
Dependent claims 9 and 19 recite the additional element “wherein the second prompt further comprises rules that are identified using machine learning.” This limitation is recited at a high level of generality such that it amounts to mere instructions to apply the abstract idea on a generic computer. Therefore, this judicial exception is not integrated into a practical application and the claims do not recite additional elements that are sufficient to amount to significantly more than the judicial exception.
Dependent claims 21 and 23 recite “isolating the affected system.” This limitation is not described in the specification. Therefore, a reasonable interpretation for this limitation may be identifying and examining data separately or causing a system/data to be separate. Under the first interpretation, this limitation may represent a mental process because identifying and examining data can be performed in the human mind. Alternatively, causing a system/data to be separate represents mere instructions to apply an abstract idea using a generic computer. This is the only limitation in the claim. As such, this judicial exception is not integrated into a practical application and the claims do not recite additional elements that are sufficient to amount to significantly more than the judicial exception.
Dependent claims 22 and 24 recite “adjusting network configurations for the affected system.” This limitation represents mere instructions to apply an abstract idea using a generic computer. As such, this judicial exception is not integrated into a practical application and the claims do not recite additional elements that are sufficient to amount to significantly more than the judicial exception.
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, 2, 6-9, 11, 12, 16-19, and 21-24 are rejected under 35 U.S.C. 103 as being unpatentable over Prakash et al. (US 2019/0272296 A1) (‘Prakash’) in view of Zhang et al. (US 12038918 B1) (‘Zhang’), further in view of Oakley et al. (US 2025/0321968 A1) (‘Oakley’), and further in view of Brown et al. (US 2025/0363345 A1) (‘Brown’).
With respect to claims 1 and 11, Prakash teaches:
receiving, by a computer program executed by a backend electronic device, a user query regarding an incident involving an affected system from a user interface computer program executed by a user electronic device (paragraphs 54 and 522);
determining, by the computer program, that the user query is ambiguous (paragraphs 507 and 522);
receiving, by the computer program, a plurality of disambiguated user queries for the user query (paragraphs 57, 507, and 522);
presenting, by the computer program, the plurality of disambiguated user queries to the user interface computer program (Fig. 14; paragraphs 57, 507, and 522);
receiving, by the computer program, a selection of one of the disambiguated user queries from the user interface computer program (paragraphs 59-60, 507 and 522);
generating, by the computer program, Structured Query Language (SQL) for the selected disambiguated user query (query or modified query may be in SQL format) (paragraphs 61 and 495-496);
executing, by the computer program, the SQL for the selected disambiguated user query on a database (paragraphs 61, 495-496, and 522);
returning, by the computer program, results of the execution of the SQL for the
selected disambiguated user query on the database to the user interface computer program (paragraphs 62 and 522); and
causing, by the computer program, a downstream system to take an action with the affected system in response to the results of the execution of the SQL for the selected disambiguated user query (Prakash, paragraphs 61-62, 109, 568, and 618).
Prakash does not explicitly teach wherein the step of determining, by the computer program, that the user query is ambiguous comprises: generating, by the computer program, a first prompt with the user query asking a large language model (LLM) whether the user query is ambiguous; submitting, by the computer program, the first prompt to the LLM; and receiving, by the computer program and from the LLM, an indication of whether the user query is ambiguous.
Zhang teaches wherein the step of determining, by the computer program, that the user query is ambiguous comprises:
generating, by the computer program, a first prompt with the user query asking a large language model (LLM) whether the user query is ambiguous (col. 3 line 65 – col. 4 line 4; col. 5 lines 48-63);
submitting, by the computer program, the first prompt to the LLM (col. 5 lines 64-67); and
receiving, by the computer program and from the LLM, an indication of whether the user query is ambiguous (col. 6 lines 31-40).
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the invention to have modified the determining of Prakash to be performed by using a LLM as taught by Zhang to enable detecting and potentially correcting ambiguous queries using LLM, which are designed to recognize text, summarize the text, and generate content using very large datasets (Zhang, abstract), thereby improving querying of large datasets by providing disambiguated queries. Further, Prakash teaches using machine learning and neural networks to disambiguate queries and thus combining this with the LLM of Zhang would yield predictable results.
Further regarding claims 1 and 11, although Zhang teaches generating, by the computer program, a second prompt to clarify the query to the LLM (Zhang, col. 8 lines 62-67), Prakash in view of Zhang does not explicitly teach generating, by the computer program, a second prompt comprising the user query and rules for returning the disambiguated queries, wherein the rules identify words that are not ambiguous; submitting, by the computer program, the second query to the LLM; and receiving, by the computer program and from the LLM, the plurality of disambiguated queries and a rationale for the plurality of disambiguated user queries based on application of the rules.
Oakley teaches generating, by the computer program, a second prompt comprising the user query and rules (Oakley, paragraphs 48 and 68 – prompt language asking to generate alternative queries based on the primary intent) for returning disambiguated queries, wherein the rules identify words that are not ambiguous (paragraphs 34, 48 and 55);
submitting, by the computer program, the second query to the LLM (paragraphs 34 and 55); and
receiving, by the computer program and from the LLM, a plurality of disambiguated queries (paragraphs 34 and 55) and a rationale for the plurality of disambiguated user queries based on application of the rules (535g and 540 in Fig. 5H; paragraph 60).
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the invention to have modified the providing of Prakash to be performed using a LLM as taught by Oakley to enable deep search functionality that enables refined and improved searching to provide the user with top relevant information (Oakley, abstract, paragraph 3). Further, Prakash teaches using machine learning and neural networks to disambiguate queries and thus combining this with the LLM of Oakley would yield predictable results.
Although Oakley teaches a second prompt having rules, Prakash in view of Zhang and Oakley does not explicitly teach query content-based rules that identify words that are not ambiguous.
Brown teaches generating a second prompt comprising the user query and query content-based rules for returning disambiguated queries, wherein the query content-based rules identify words that are not ambiguous (the example prompt 614 might include an additional instruction such as “If the query is classified as ambiguous, i.e. \” ambiguous_query\ “: true, then provide an explanation of what clarification is needed) (Fig. 5; paragraphs 101 and 128).
It would have been obvious to a person having ordinary skill in the art prior to the effective filing date of the invention to have further modified Prakash in view of Zhang and Oakley to generate a second prompt having query content-based rules as taught by Brown to provide a confidence value of ambiguity of the query that prevents waste of resources (Brown, paragraph 155).
With respect to claims 2 and 12, Prakash in view of Zhang, Oakley and Brown teaches wherein the user query is ambiguous when it is susceptible to a plurality of interpretations (Prakash, paragraphs 507-508).
With respect to claims 6 and 16, Prakash in view of Zhang, Oakley and Brown teaches wherein the second prompt further comprises rules to identify words or phrases in the user query that are not ambiguous (Oakley, paragraph 48 – selected intent; Zhang, col. 8 line 15 – col. 9 line 3 – less ambiguous term, not in ambiguous location; Brown, paragraph 128).
With respect to claims 7 and 17, Prakash in view of Zhang, Oakley and Brown teaches wherein the second prompt further comprises rules that are derived from a plurality of past user queries statistically (Oakley, paragraphs 33, 68 and 77; Prakash, paragraphs 515 and 609).
With respect to claims 8 and 18, Prakash in view of Zhang, Oakley and Brown teaches wherein the second prompt further comprises rules that are based on a pattern identified in past user queries (Prakash, paragraphs 46, 334, 430, 457; Oakley, paragraphs 33, 68, and 77).
With respect to claims 9 and 19, Prakash in view of Zhang, Oakley and Brown teaches wherein the second prompt further comprises rules that are identified using machine learning (Prakash, paragraphs 46, 109, 145, 485-486; Zhang, col. 5 line 64 – col. 6 line 11).
With respect to claims 21 and 23, Prakash in view of Zhang, Oakley and Brown teaches wherein the action comprises: isolating the affected system (isolating by filtering results suer doesn’t have permission to view - Prakash, paragraph 568; also filtering to remove or hide the older or previous version of results – Oakley, paragraph 54).
With respect to claims 22 and 24, Prakash in view of Zhang, Oakley and Brown teaches wherein the action comprises: adjusting network configuration for the affected system (adjust parameters, update the automatic database analysis system configuration data in response to an operative configuration event, such as a change in availability or performance for a physical or logical unit of the system, and/or updating data usage for token – Prakash, paragraphs 109, 586, 611 and 618; also continuously updating disambiguation result or selectable intent display field 535 in FIGS. 5B-5J as well as the continuously updating progress bar – Oakley, paragraph 59).
Response to Arguments
Applicant's arguments filed June 29, 2026 have been fully considered but they are not persuasive. Applicant argues that the claims are integrated into practical application under Step 2A, Prong Two because the computer program employs information to control another system. The examiner disagrees. Applicant argues that the steps of first disambiguating a user query, executing a SQL query based on a selected disambiguated query, and then using the results of that execution to cause a downstream system to take an action with the affected system provide a meaningful way of using the alleged judicial exception. However, the query disambiguation is a mental process, and that steps of executing a SQL query and causing a downstream system to take an action provide nothing more than mere instructions to apply the exception using a generic computer. Further, the claims do not recite or describe a particular action that is taken that amounts to more than generic computer processing. Therefore, there are no meaning limitations that employ information provided by the judicial exception.
Applicant’s other arguments with respect to claims 1, 2, 6-9, 11, 12, 16-19, and 21-24 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.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALICIA M WILLOUGHBY whose telephone number is (571)272-5599. The examiner can normally be reached 9-5:30, EST, M-F.
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, Ajay Bhatia can be reached at 571-272-3906. 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.
/ALICIA M WILLOUGHBY/Primary Examiner, Art Unit 2156 August 22, 2026
Prosecution Insights