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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 04/30/2026 and 05/19/2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Applicant(s) Response to Office Action
The response on 04/30/2026 has been entered and made of record.
Claims 1,11 and 20 have been amended. No new claims have been added or removed.
Response to Arguments
Currently Claims 1-16 are pending in this application.
Applicant’s arguments filed on 4/30/2026 have been fully considered but are not persuasive.
Applicant on Page 10 states:
In the Office Action, Wen is cited because it describes access controls. However, Wen does not teach the features of claim 1, including generating a result message by, after receiving the result, processing the result to obfuscate the one or more data values contained therein based on the access level. Instead, Wen teaches a data governance framework for establishing secure datasets prior to any query. Wen's system "generates a data usage configuration from a document specifying requirements for a dataset" (Wen, Abstract) and uses this configuration for "controlling a data retrieval process" (Wen, [0019]). Wen's "data masking/obfuscation' ([0013]) is part of a preemptive framework for creating compliant datasets from "raw data" (Wen, FIG. 2); Wen is not a tool for post-processing live query results. Furthermore, Wen provides controls access to the source data, but not the final output message.
Regarding the argument above, the Examiner would like to state the following. The Examiner is unsure regarding the Applicant’s argument of Wen not teaching “including generating a result message by, after receiving the result, processing the result to obfuscate the one or more data values contained therein based on the access level”. In the office action, Wen was used to teach the limitation of “obtain an access level associated with the requesting entity;” The limitation “generate a result message using the result” is disclosed by Uttam in Col 4 lines 53-56. Uttam states “The query is then be outputted and/or executed on the structured database(s) and/or systems to return data as a response to the user’s original natural language question.
The limitation that has been added to in the amendment “after receiving the result, processing the result to obfuscate the one or more data values contained therein” is however disclosed by Wen in Paragraph [0013]. Wen discloses: The information filtering mechanism governs the data retrieval process through a content management system. It can provide multiple types of data masking/obfuscation operations based on user needs (e.g., replacing phone numbers by random strings, etc.) and based on the access level of the requester, ensuring the output data is compliant with regulation or other requirements. One of ordinary skill in the art can determine that the mechanism may obfuscate the output data in order to ensure it is complaint with regulations or other requirements. Therefore, the argument is not persuasive.
The system of claim 1, by contrast, operates in a different sequence and for a different purpose. In claim 1, the system receives the natural language question from a requesting entity; and obtains an access level associated with the requesting entity. It generates and then executes a query to receive a result, without filtering. Only after receiving the result does it apply obfuscation that is specific to the access level of the requesting entity. This is a dynamic, per-query, runtime modification of the result message itself, a concept absent from Wen's data governance architecture. A person of ordinary skill in the art would not find in Wen the teaching to build the system of claim 1.
Regarding the Applicant’s argument, the Examiner would like to state the following. Wen is used to strictly teach the limitation of “obtain an access level associated with the requesting entity;” which is disclosed in Paragraph [0067] “Field types is used to define multiple levels of sensitive data each with its own access group and permission).
The other limitation that is now cancelled: “wherein the one or more data values are obfuscated in the result message based on the access level”. Is disclosed in Paragraph [0019] “The content management system utilizes multiple types of data masking/obfuscation operation based on user needs and access levels.”
Therefore, the Examiner is using Wen in order to teach obfuscation and access levels, and the argument is not persuasive.
Furthermore, Applicant submits that there is no clear impetus in Uttam and Wen to combine the two references together. Any evidence that supports an impetus to combine elements from disparate references must suggest the desirability of the combination, not merely the feasibility, re Fulton, 73 USPQ2d 1141, 1145 (Fed. Cir. 2004). Any impetus to combine elements from disparate references must "clearly and particularly" lead one of ordinary skill in the art to make a combination. See Ruiz V. A.B. Chance Co., 234 F.3d 654, 660 (Fed. Cir. 2000). See also re Wada and Murphy, Appeal No. 2007- 3733, slip op. at 7 (BPAI 2008).
Regarding the Applicant’s argument above, the Examiner would like to state the following: The Applicant argues there is no clear motivation to combine the two references together. One of ordinary skill in the art would have been motivated to combine the references because Wen teaches a known technique for access control based on group role, permission etc. of systems such as that of Uttam, and the combination would have yielded predictable results. Therefore the argument is not persuasive.
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) 1-17 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Chakraborty (US12306828) herein after “Uttam” in view of Wen (US20250278502).
Regarding Claims 1,11 and 20, Uttam discloses a computing system for processing a natural language question, the computing system comprising: (Col 3 lines 33-37 Examiner Note (E.N.) A service provider provides a user questions repository (UQR), which is utilized for applications that respond to user questions in natural language that are queried and/or searched against a structured database.)
a memory, a communication interface, and a processor operatively coupled to the memory and the communication interface; (Col 19 lines 44-64)
a retrieval system (Col 5 lines 25-28 E.N. An improved data searching, storage, and retrieval system with better compatibility and more convenient and efficient searching is disclosed.)
and a structured query language (SQL) large language model (LLM) (Col 2 lines 4-8 E.N. The service provider is required to determine, for the task of asking the LLM to convert a natural language question to an SQL query.)
stored in the memory and executable by the processor; (Col 17 lines 38-42 and lines 48-52)
the processor configured to: receive the natural language question from a requesting entity; (Col 7 lines 21-23 E.N. A natural language question or other input is received, UQR us used with LLMs for data retrieval.)
generate a prompt that comprises the natural language question (Col 15 lines 20-22 E.N. A user question arrives in natural language from a user, the question is checked against UQR for matches.)
and a database schema corresponding to a database; (Col 14 lines 38-46 E.N. Operations performed by the IQG to generate interesting questions from an initial input of a set of database views and/or other schema definition for a set of structured data and/or structured database or other storage system.)
process, using the retrieval system, the prompt to identify one or more tables in the database, the one or more tables relevant to the natural language question; generate, using the retrieval system, an augmented prompt that comprises the natural language question, the database schema, and one or more identities of the one or more tables; (Col 11 lines 42-55 E.N. User devices interact with an application/service to submit questions, requests, and other inputs to be queried on structured data stored by a structured database or other structured data storage system. These inputs are provided in natural language format and the application/service corresponds to any such software application that is required to convert natural language to SQL or other structured data language for querying on structured databases (e.g. databases or other data storages systems storing structured data in data tables and views including columns and rows that are searchable using structured data queries in a specific format.)
generate, using the SQL LLM, a set of SQL code based on the augmented prompt; (Col 11 lines 59-62 E.N. The user question repository (UQR) is utilized by the application/service to provide data for converting natural language inputs to the corresponding format and syntax of SQL or other structured data language)
initiate executing the set of SQL code on the database and receiving a result that comprises one or more data values from the one or more tables; (Col 16 lines 38-43 E.N. The LLM is prompted using the question and corresponding identified metadata for the match, and a structured data query (SQL query) is generated by the LLM. This query is then used for structured data retrieval from a structured database system.)
generate a result message by, (Col 4 lines 53-56 E.N. The query is then be outputted and/or executed on the structured database(s) and/or systems to return data as a response to the user’s original natural language question.)
and provide the result message responsive to the natural language question. (Col 4 lines 53-56 E.N. The query is then be outputted and/or executed on the structured database(s) and/or systems to return data as a response to the user’s original natural language question.)
Uttam does not, but in related art, Wen discloses obtain an access level associated with the requesting entity; (Paragraph [0067] E.N. Field types is used to define multiple levels of sensitive data each with its own access group (role) and permission)
after receiving the result, processing the result to obfuscate the one or more data values contained therein (Paragraph [0013] E.N. The information filtering mechanism governs the data retrieval process through a content management system. It can provide multiple types of data masking/obfuscation operations based on user needs (e.g., replacing phone numbers by random strings, etc.) and based on the access level of the requester, ensuring the output data is compliant with regulation or other requirements. One of ordinary skill in the art can determine that the mechanism may obfuscate the output data in order to ensure it is complaint with regulations or other requirements.)
(Paragraph [0019] E.N. The content management system utilizes multiple types of data masking/obfuscation operations based on user needs and access levels.)
Therefore, it would be obvious to one of ordinary skill in the art, prior to the effective filing date of the claimed invention to have modified Uttam to incorporate the teachings of Wen because Uttam does not explicitly disclose access levels and obfuscating data values which is disclosed by Wen. Incorporating the teachings of Wen to Uttam allows for the LLM to take into account sensitive information and correctly allow or deny users access to said sensitive information during the query/requests.
Regarding Claim 2, Uttam in view of Wen discloses the computing system of Claim 1. Uttam further discloses wherein the result comprises a plurality of data values, and the processor is configured to aggregate the plurality of data values to generate one or more aggregated data values, the result message comprises the one or more aggregated data values. (Figure 5 E.N. The diagram discloses a matching algorithm that identifies pre-generated questions matching a user submitted questions to a certain accuracy or threshold requirement such that a confidence in the accuracy of the matching is used to retrieve metadata for structured query generation.)
Regarding Claim 3, Uttam in view of Wen discloses the computing system of Claim 1. Uttam does not, but in related art, Wen discloses wherein the result comprises a plurality of data values, and the plurality of data values comprise a plurality of personal identifiable information (PII) data values and a plurality of corresponding non-PII data values, and wherein the processor generates the result message without the plurality of PII data values. (Paragraph [0065] E.N. The field classes of the tables include PI with a corresponding access control (deny all all; allow read, write Owner; allow read Other) An access control includes an action (allow, deny, etc.) permissions (read, write, obfuscated-read, etc.) and role.)
Therefore, it would be obvious to one of ordinary skill in the art, prior to the effective filing date of the claimed invention to have modified Uttam to incorporate the teachings of Wen because Uttam does not explicitly disclose PII data values and obfuscating data values which is disclosed by Wen. Incorporating the teachings of Wen to Uttam allows for the LLM to take into account sensitive information and correctly allow or deny users access to said sensitive information during the query/requests.
Regarding Claims 4 and 14, Uttam in view of Wen discloses the computing system of Claim 1 and the method of Claim 11. Uttam further discloses and wherein the preliminary LLM generates, (Col 5 lines 10-20 E.N. A computing service and framework may be coded, deployed, and made available to users that automatically generates structured queries from natural language questions using LLMs, GPTs (e.g., GPT-4), or the like.)
the result message comprising a natural language response that is derived from the one or more data values (Col 4 lines 38-42 E.N. Using the metadata, embeddings, and/or the original natural language question, a structured query is generated by the LLM to provide the structed query in response to a prompt.)
Uttam does not, but in related art, Wen discloses further comprising a preliminary LLM that is configured to receive the result and the access level to generate the result message, (Paragraph [0013] The information filtering mechanisms governs the data retrieval process through a content management system. It provides multiple types of data masking/obfuscation operation based on user needs and based on the access level of the requester, ensuring the output data is compliant with regulations or other requirements.)
based on the access level, (Paragraph [0019] E.N. The content management system utilizes multiple types of data masking/obfuscation operation based on user needs and access level.)
and the result message excludes the one or more data values. (Paragraph [0013] The information filtering mechanisms governs the data retrieval process through a content management system. It provides multiple types of data masking/obfuscation operation based on user needs and based on the access level of the requester, ensuring the output data is compliant with regulations or other requirements.)
Therefore, it would be obvious to one of ordinary skill in the art, prior to the effective filing date of the claimed invention to have modified Uttam to incorporate the teachings of Wen because Uttam does not explicitly disclose access levels and obfuscating data values which is disclosed by Wen. Incorporating the teachings of Wen to Uttam allows for the LLM to take into account sensitive information and correctly allow or deny users access to said sensitive information during the query/requests.
Regarding Claim 5, Uttam in view of Wen discloses the computing system of Claim 1. Uttam further discloses wherein the result comprises a plurality of data values; and wherein the preliminary LLM generates, (Col 4 lines 38-42 E.N. Using the metadata, embeddings, and/or the original natural language question, a structured query is generated by the LLM to provide the structed query in response to a prompt.)
the result message comprising a natural language response that comprises a subset of the plurality of data values. (Col 4 lines 38-42 E.N. Using the metadata, embeddings, and/or the original natural language question, a structured query is generated by the LLM to provide the structed query in response to a prompt.)
Uttam does not, but in related art, Wen discloses further comprising a preliminary LLM that is configured to receive the result and the access level to generate the result message; (Paragraph [0019] E.N. The content management system utilizes multiple types of data masking/obfuscation operation based on user needs and access level.)
based on the access level, (Paragraph [0019] E.N. The content management system utilizes multiple types of data masking/obfuscation operation based on user needs and access level.)
Therefore, it would be obvious to one of ordinary skill in the art, prior to the effective filing date of the claimed invention to have modified Uttam to incorporate the teachings of Wen because Uttam does not explicitly disclose access levels and obfuscating data values which is disclosed by Wen. Incorporating the teachings of Wen to Uttam allows for the LLM to take into account sensitive information and correctly allow or deny users access to said sensitive information during the query/requests.
Regarding Claim 6, Uttam in view of Wen discloses the computing system of Claim 1. Uttam further discloses wherein the retrieval system comprises a retrieval LLM, and the retrieval LLM generates the augmented prompt. (Col 16 lines 38-41 E.N. The LLM is prompted using the question and corresponding identified metadata for the match, and a structured data query (SQL query) is generated by the LLM. This query is then used for structured data retrieval from a structured database system.)
Regarding Claims 7 and 15 Uttam in view of Wen discloses the computing system of Claim 1 and the method of Claim 11. Uttam further discloses a preliminary LLM in the memory, and the preliminary LLM generates the prompt that comprises the natural language question, the database schema and metadata of the database; (Col 11 lines 42-55 E.N. User devices interact with an application/service to submit questions, requests, and other inputs to be queried on structured data stored by a structured database or other structured data storage system. These inputs are provided in natural language format and the application/service corresponds to any such software application that is required to convert natural language to SQL or other structured data language for querying on structured databases (e.g. databases or other data storages systems storing structured data in data tables and views including columns and rows that are searchable using structured data queries in a specific format.)
wherein the retrieval system comprises a retrieval LLM, and the retrieval LLM processes the prompt to identify the one or more tables in the database and a subset of the metadata that corresponds to the one or more tables; and wherein the retrieval LLM generates the augmented prompt that further comprises the metadata and the subset of the metadata. (Col 16 lines 38-41 E.N. The LLM is prompted using the question and corresponding identified metadata for the match, and a structured data query (SQL query) is generated by the LLM. This query is then used for structured data retrieval from a structured database system.)
Regarding Claims 8 and 16, Uttam in view of Wen discloses the computing system of Claim 7 and the method of Claim 15. Uttam further discloses wherein the processor is further configured to at least: identify, using the retrieval system, one or more rows in the one or more tables that are relevant to the natural language question; (Figure 7 and Col 18 lines 31-38 E.N. The LLM is prompted for generation of a structured query to the structured database using a list of sub-questions that make up the natural language question with the tools and description.)
and establish one or more row indexes of the one or more rows as the subset of the metadata. (Col 11 lines 48-55 E.N. Software application that is required to convert natural language to SQL or other structured data language for querying on structured databases (e.g., databases or other data storage systems storing structured data in data tables and views including columns and rows that are searchable using structured data queries in a specific format.) One of ordinary skill in the art can determine that a structured database includes metadata that is searchable.)
Regarding Claims 9 and 17 Uttam in view of Wen discloses the computing system of Claim 7 and the method of Claim 15. Uttam further discloses wherein the processor is further configured to at least: identify, using the retrieval system, one or more columns in the one or more tables that are relevant to the natural language question; (Figure 7 and Col 18 lines 31-38 E.N. The LLM is prompted for generation of a structured query to the structured database using a list of sub-questions that make up the natural language question with the tools and description.)
and establish one or more column headings of the one or more columns as the subset of the metadata. (Col 11 lines 48-55 E.N. Software application that is required to convert natural language to SQL or other structured data language for querying on structured databases (e.g., databases or other data storage systems storing structured data in data tables and views including columns and rows that are searchable using structured data queries in a specific format.) One of ordinary skill in the art can determine that a structured database includes metadata that is searchable.)
Regarding Claims 10 and 19 Uttam in view of Wen discloses the computing system of Claim 1 and the method of Claim 11. Uttam further discloses wherein a chat user interface is stored in the memory; and the processor is further configured to: receive the natural language question via the chat user interface; generate the result message in a form of a natural language response that comprises the result; and provide the natural language response via the chat user interface. (Col 16 lines 44-50 E.N. A simplified diagram of application components for responding to user questions with structured data. An application user interface (UI) corresponds to a frontend component and interface to interact with users, where an application backend interacts with UQR for structured query generation from natural language questions. One of ordinary skill in the art can determine the UI allows the user to submit a query using natural language and receives a response in a similar fashion from the UI.)
Regarding Claim 12, Uttam in view of Wen discloses the method of Claim 11. Uttam further discloses by at least aggregating the plurality of data values to generate one or more aggregated data values, the result message comprising the one or more aggregated data values. (Figure 5 E.N. The diagram discloses a matching algorithm that identifies pre-generated questions matching a user submitted questions to a certain accuracy or threshold requirement such that a confidence in the accuracy of the matching is used to retrieve metadata for structured query generation.)
Uttam does not, but in related art, Wen discloses wherein the result comprises a plurality of data values, and the plurality of data values is obfuscated (Paragraph [0019] E.N. The content management system utilizes multiple types of data masking/obfuscation operation based on user needs and access level.)
Therefore, it would be obvious to one of ordinary skill in the art, prior to the effective filing date of the claimed invention to have modified Uttam to incorporate the teachings of Wen because Uttam does not explicitly disclose obfuscating data values which is disclosed by Wen. Incorporating the teachings of Wen to Uttam allows for the LLM to take into account sensitive information and correctly allow or deny users access to said sensitive information during the query/requests.
Regarding Claim 13, Uttam in view of Wen discloses the method of Claim 11. Uttam does not but in related art, Wen discloses wherein the result comprises a plurality of data values, and the plurality of data values comprise a plurality of personal identifiable information (PII) data values and a plurality of corresponding non-PII data values, and wherein the plurality of data values is obfuscated by at least generating the result message without the plurality of PII data values. (Paragraph [0065] E.N. The field classes of the tables include PI with a corresponding access control (deny all all; allow read, write Owner; allow read Other) An access control includes an action (allow, deny, etc.) permissions (read, write, obfuscated-read, etc.) and role.)
Therefore, it would be obvious to one of ordinary skill in the art, prior to the effective filing date of the claimed invention to have modified Uttam to incorporate the teachings of Wen because Uttam does not explicitly disclose PII data values and obfuscating data values which is disclosed by Wen. Incorporating the teachings of Wen to Uttam allows for the LLM to take into account sensitive information and correctly allow or deny users access to said sensitive information during the query/requests.
Claim(s) 18 rejected under 35 U.S.C. 103 as being unpatentable over Chakraborty (US12306828) herein after “Uttam” in view of Wen (US20250278502) and in further view of Vu (US20260037505).
Regarding Claim 18, Uttam in view of Wen discloses the method of Claim 11. Uttam further discloses generating a new set of SQL code, using the SQL LLM, based on the augmented prompt; initiating executing the new set of SQL code on the database; and receiving a new result comprising retrieved data from the database that is responsive to the new set of SQL code. (Figure 5 E.N. If the score is low, discard and ask for more context/refinement to the question)
Uttam and Wen do not, but in related art, Vu discloses wherein, when the result comprises an error message, the method further comprises: (Paragraph [0043] E.N. When the inferred result and the gold result are dissimilar, generate an error message corresponding to the dissimilarity and recording the natural language utterance, the gold form, the database schema information, the inferred logical form, and the error message as a semantic error example.)
Therefore, it would be obvious to one of ordinary skill in the art, prior to the effective filing date of the claimed invention to have modified Uttam in view of Wen to incorporate the teachings of Vu because Uttam and Wen do not explicitly disclose error messages which is taught by Vu. Incorporating the teachings of Vu to Uttam and Wen allows for the LLM to determine if there are any form of issues with the dataset by an error message and try to mitigate said messages.
Conclusion
THIS ACTION IS MADE FINAL. 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 AAYUSH ARYAL whose telephone number is (571)272-2838. The examiner can normally be reached 8:00 a.m. - 5:30 p.m..
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, Amir Mehrmanesh can be reached at (571) 270-3351. 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.
/AAYUSH ARYAL/Examiner, Art Unit 2435
/AMIR MEHRMANESH/Supervisory Patent Examiner, Art Unit 2435
Prosecution Insights