CTNF 18/799,506 CTNF 101937 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Specification 07-29 AIA The disclosure is objected to because of the following informalities: Paragraph 0053 recites "SQL LLM 18". The associated figure lists SQL LLM as part 138 . Appropriate correction is required. Examiner’s Notes Claims of co-pending applications 18/799,168, 18/799,411, 18/799,235 and 18/799,327 are similar to the current claims, but are non-obvious at this time. However, if the claims become obvious due to amendments, a double patenting rejection will be reconsidered. While claim elements do recite abstract ideas (receiving questions, generating prompts in natural language, identification of relevant tables, sending), the claims when viewed as a whole are directed to an improvement to the functioning of a technology. Specifically, the claims are directed an improvement to the text-to SQL workflow. In light of Ex Parte Desjardins, a 35 USC § 101 rejection will not be made at this time. However, if future amendments alter the scope of the claims, a 35 USC § 101 rejection will be reconsidered. Claim Objections 07-29-01 AIA Claim 18 is objected to because of the following informalities: Claim preamble recites ”The method claim 11” and should instead recite ”The method of claim 11” . Appropriate correction is required. Claim Rejections - 35 USC § 102 07-07-aia AIA 07-07 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 – 07-12-aia AIA (a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention. 07-15-03-aia AIA Claim s 1-2, 4, 7-8, 10-12, 14, 17-18, 20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Yakovlev(US PGPub 20250284688) . Regarding Claim 1, Yakovlev teaches a computing system for processing a natural language command, the computing system comprising: a memory, a communication interface, and a processor operatively coupled to the memory and the communication interface (Figure 5, 506, 518, 504, 502) ; a retrieval system and a structured query language (SQL) large language model (LLM) (NL2SQL generative model is configured to generate one or more SQL queries for searching the relational database based on the linguistic prompt[0066]) stored in the memory and executable by the processor; the processor configured to: receive the natural language command (receives a natural language query from a user (block 201)[0064]) ; generate a prompt that comprises the natural language command and a database schema corresponding to a database (the database system may generate the linguistic prompt by selecting a subset of database tables based at least in part on the metadata and add schema descriptions for the subset of database tables to the linguistic prompt[0067]) ; 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 command (These ML models 154, referred to herein as insight models, help the vector store agent decide which tables and columns are relevant to (i.e., implicated by) the user's question[0060]) ; generate, using the retrieval system, an augmented prompt that comprises the natural language command, the database schema, and one or more identities of the one or more tables (prompt engineering component 155 can dynamically generate or augment a linguistic prompt to combine a user's question with schema, table, and column information[0054]) ; generate, using the SQL LLM, a set of SQL code based on the augmented prompt ( the generative AI model comprises a natural language to structured query language (NL2SQL) generative model, and the NL2SQL generative model is configured to generate one or more SQL queries for searching the relational database based on the linguistic prompt.[0066]) ; initiate executing the set of SQL code on the database and receiving a result (the database system can execute the SQL queries and generate query results. In one embodiment, the database system can return the query results to the user[0089]) ; initiate an executable action using the result ( the database system then generates a prompt for an LLM including the user's query and the query results as context[0089]) ; receive a feedback that the executable action was completed (The LLM generates a natural language response explaining the query results as an answer to the user's query[0089], Interpretation: the natural language response from the LLM is feedback that the action was completed) ; and transmit a result message responsive to the natural language command (The LLM generates a natural language response explaining the query results as an answer to the user's query[0089]) . Claim 11 is directed to a method claim with similar limitations to that of Claim 1 and is rejected under the same rationale. Claim 20 is directed to a computer readable memory claim with similar limitations to that of Claim 1 and is rejected under the same rationale. Regarding Claim 2, Yakovlev teaches the executable action comprises the result (the database system then generates a prompt for an LLM including the user's query and the query results as context[0089]). Claim 12 is directed to a method claim with similar limitations to that of Claim 2 and is rejected under the same rationale. Regarding Claim 4, Yakovlev teaches initiating the executable action comprises transmitting the result (the database system can execute the SQL queries and generate query results[0089]) to an action system (the database system then generates a prompt for an LLM including the user's query and the query results as context[0089]) and the action system executes the executable action (The LLM generates a natural language response explaining the query results as an answer to the user's query[0089]) . Claim 14 is directed to a method claim with similar limitations to that of Claim 4 and is rejected under the same rationale. Regarding Claim 7, Yakovlev teaches the retrieval system comprises a retrieval LLM (The linguistic prompt can further be augmented using ML inference[0022]) , and the retrieval LLM generates the augmented prompt (The embodiment uses information from ML automation to dynamically engineer a linguistic prompt to combine a user's question with schema, table, and column information[0021]). Claim 17 is directed to a method claim with similar limitations to that of Claim 7 and is rejected under the same rationale. Regarding Claim 8, Yakovlev teaches a preliminary LLM in the memory (database system further includes generative artificial intelligence (AI) components that provide integrated and automated generative AI with in-database large language models (LLMs)[0019]) , and the preliminary LLM generates the prompt that comprises the natural language command, the database schema and metadata of the database (the database system may generate the linguistic prompt by selecting a subset of database tables based at least in part on the metadata and add schema descriptions for the subset of database tables to the linguistic prompt[0067]) ; 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 (These ML models 154, referred to herein as insight models, help the vector store agent decide which tables and columns are relevant to (i.e., implicated by) the user's question[0060]) and a subset of the metadata that corresponds to the one or more tables; and wherein the retrieval LLM generates the augmented prompt (The linguistic prompt can further be augmented using ML inference[0022]) that further comprises the metadata and the subset of the metadata (The embodiment uses information from ML automation to dynamically engineer a linguistic prompt to combine a user's question with schema, table, and column information[0021]) . Claim 18 is directed to a method claim with similar limitations to that of Claim 8 and is rejected under the same rationale. Regarding Claim 10, Yakovlev teaches a chat user interface (Software system 600 includes a graphical user interface (GUI) 615, for receiving user commands and data in a graphical (e.g., “point-and-click” or “touch gesture”) fashion. These inputs, in turn, may be acted upon by system 600 in accordance with instructions from operating system 610 and/or application(s) 602. The GUI 615 also serves to display the results of operation from the OS 610 and application(s) 602, whereupon the user may supply additional inputs[0129]]) is stored in the memory; and the processor is further configured to: receive the natural language command via the chat user interface (Users can ask questions in natural language via applications[0019]) ; generate the result message in a form of a natural language response that comprises the result (the database system can execute the SQL queries and generate query results. In one embodiment, the database system can return the query results to the user[0089]) ; and provide the natural language response via the chat user interface (The GUI 615 also serves to display the results of operation[0129]) . Claim Rejections - 35 USC § 103 07-20-aia AIA 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. 07-21-aia AIA Claim (s) 3, 13 are rejected under 35 U.S.C. 103 as being unpatentable over Yakovlev (US PGPub 20250284688) in view of Hariharan (US PGPub 20160019281) . Regarding Claim 3, Yakovlev teaches the result comprises one or more data values from the database (the database system can execute the SQL queries and generate query results. In one embodiment, the database system can return the query results to the user[0089]) . Yakovlev does not teach the executable action comprises: creating new data in the database using the one or more data values; or modifying the one or more data values in the database; or deleting the one or more data values in the database; or a combination thereof. However, Hariharan(US PGPub 20160019281) does teach the executable action comprises: creating new data in the database using the one or more data values; or modifying the one or more data values in the database; or deleting the one or more data values in the database; or a combination thereof (relational database server system 130 to perform queries on stored data, add data, delete data, and/or modify data) . It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the database actions of Hariharan with the system disclosed in Yakovlev because accessing the data for simulating changes to such data and/or modifying such data may be useful to a user(Hariharan). Claim 13 is directed to a method claim with similar limitations to that of Claim 3 and is rejected under the same rationale . 07-21-aia AIA Claim (s) 5, 15 are rejected under 35 U.S.C. 103 as being unpatentable over Yakovlev (US PGPub 20250284688) in view of Kersh (A Guide To Using SQL For Email Marketing) . Regarding Claim 5, Yakovlev does not teach the result (the database system can execute the SQL queries and generate query results[0089]) comprises contact information of one or more entities, and the executable action comprises sending one or more messages using the contact information to the one or more entities. However, Kersh(A Guide To Using SQL For Email Marketing) does teach the result comprises contact information of one or more entities, PNG media_image1.png 692 1215 media_image1.png Greyscale and the executable action comprises sending one or more messages using the contact information to the one or more entities (Once you’ve run a valid query and are happy with the results, the results of that query are loaded as the list of recipients to send the newsletter to[How To Use SQL With Email Marketing]) . It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the contact system of Kersh with the system disclosed in Yakovlev because it would make it simple to run queries and narrow down an audience(Kersh). Claim 15 is directed to a method claim with similar limitations to that of Claim 5 and is rejected under the same rationale . 07-21-aia AIA Claim (s) 6, 16 are rejected under 35 U.S.C. 103 as being unpatentable over Yakovlev (US PGPub 20250284688) in view of Socher (US PGPub 20240020538) . Regarding Claim 6, Yakovlev teaches the action system comprises an action LLM and the action LLM uses the result ((the database system then generates a prompt for an LLM(Interpretation: this LLM is the action LLM) including the user's query and the query results(Interpretation: query results are the results from the N2SQL model) as context[0089]) . Yakovlev does not teach the processor is further configured to, using the retrieval system, obtain and transmit an identity of an additional data platform to the action system; and, the action LLM uses the result and the identity of the additional data platform to generate one or more commands executable by the additional data platform. However, Socher does teach the processor is further configured to, using the retrieval system, obtain and transmit an identity of an additional data platform to the action system (The search submodule 232 may determine one or more data sources for the search, e.g., based on user configuration of preferences, user past behavior indicating a preference, the search query(Interpretation: prompt given to retrieval system), a source type, and/or the like[0056]) ; and, the action LLM uses the result and the identity of the additional data platform to generate one or more commands executable by the additional data platform (The search submodule 232 may further generate customized queries according to each data sources, and transmits the customized queries to the corresponding APIs (e.g., 112a-n in FIGS. 1A and 1B) and receives search results from the APIs.[0056]) . It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the external data source calling system of Socher with the system disclosed in Yakovlev because it would allow the user to verify information and to perform further research(Socher). Claim 16 is directed to a method claim with similar limitations to that of Claim 6 and is rejected under the same rationale . 07-21-aia AIA Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Yakovlev (US PGPub 20250284688 in view of Sanjeeb (Build a robust text-to-SQL solution generating complex queries, self-correcting, and querying diverse data sources Cited in IDS ) . Regarding Claim 9, Yakovlev does not teach that when the result comprises an error message, the processor is configured to: generate a new set of SQL code, using the SQL LLM, based on the augmented prompt; initiate executing the new set of SQL code on the database; and receive a new result comprising retrieved data from the database that is responsive to the new set of SQL code. However, Sanjeeb teaches when the result comprises an error message( If Athena provides an error message that mentions the syntax is incorrect, the model uses the error text from Athena’s response [Solution overview Step 7] ), the processor is configured to: generate a new set of SQL code, using the SQL LLM, based on the augmented prompt; initiate executing the new set of SQL code on the database( The model creates the corrected SQL and continues the process. This iteration can be performed multiple times[Solution overview Step 9] ); and receive a new result comprising retrieved data from the database that is responsive to the new set of SQL code( Finally, we run the SQL using Athena and generate output. Here, the output is presented to the user[Solution overview Step 10] ). It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to incorporate the error handling of Sanjeeb with the system disclosed in Yakovlev because it would allow for more accurate and effective corrections in the generated SQL(Sanjeeb). Claim 19 is directed to a method claim with similar limitations to that of Claim 9 and is rejected under the same rationale. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to ARJUN R SWAMY whose telephone number is (571)272-9763. The examiner can normally be reached Mon-Fri 8-5. 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, Hai Phan can be reached at (571) 272-6338. 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. /ARJUN SWAMY/Examiner, Art Unit 2654 /HAI PHAN/Supervisory Patent Examiner, Art Unit 2654 Application/Control Number: 18/799,506 Page 2 Art Unit: 2654 Application/Control Number: 18/799,506 Page 3 Art Unit: 2654 Application/Control Number: 18/799,506 Page 4 Art Unit: 2654 Application/Control Number: 18/799,506 Page 5 Art Unit: 2654 Application/Control Number: 18/799,506 Page 6 Art Unit: 2654 Application/Control Number: 18/799,506 Page 7 Art Unit: 2654 Application/Control Number: 18/799,506 Page 8 Art Unit: 2654 Application/Control Number: 18/799,506 Page 9 Art Unit: 2654 Application/Control Number: 18/799,506 Page 10 Art Unit: 2654 Application/Control Number: 18/799,506 Page 11 Art Unit: 2654 Application/Control Number: 18/799,506 Page 12 Art Unit: 2654 Application/Control Number: 18/799,506 Page 13 Art Unit: 2654
Prosecution Insights