DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
Claims 1-20 are pending in this application.
Response to Arguments
Regarding Rejection under 35 U.S.C. 101
Applicant’s arguments with respect to rejections have been fully considered but they are not persuasive.
The Applicant argues that the rejection under 35 U.S.C. 101 is improper because: 1) the amended claims recite a specific configuration of software components that produces a tangible technological improvement of database query system and 2) the amended Claim 1 explicitly recites the sequential steps and specialized components (the "prompt system," "retrieval system," "SQL LLM," and "personalization LLM") that execute this context-saving, latency-reducing data processing architecture (REMARKS, on page 8, 4th paragraph-13, 4th paragraph).
However, Examiner respectfully disagrees that the rejection under 35 U.S.C. 101 is improper because the newly amended claim 1 is still directed to abstract idea.
Applicant’s invention is not technological improvement of the existing but helping to achieve better human functionality in the field of language processing using a generic computer. The amended claim does not recite concrete operations that tie the claimed method to the disclosed improvement. Even though the disclosed invention is described in the background as improving computer technology, the claim provides no meaningful limitations such that this improvement is realized.
Therefore, claim 1 does not amount to significantly more than the abstract idea itself.
Furthermore, the pending claims are not similar to those at issue in Ex parte Desjardins, which notes the claims for improving the function of the machine learning model itself, citing reduced storage requirement, lowered system complexity, and the prevention of “catastrophic forgetting”- the claimed system changes the architecture itself – e.g., how information flows, not just what it does – that may satisfy eligibility.
With respect to independent claims 11 and 20, claims 11 and 20 are similar to claim 1.
With respect to dependent claims 2-10 and 12-19 are also directed to processes which manipulate data which are processes which can be performed by a human and implemented by a generic computer. Accordingly, the limitations of the Claims are not sufficient to add significantly more to improve technological functionality. As such, claims 1-20 are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
Thus, the rejection is maintained at this time. Please see the rejection below for the whole analysis.
Regarding Rejection under 35 U.S.C. 102
Applicant’s arguments with respect to rejections have been fully considered but are moot because the arguments do not apply to any of the references being used in the current rejection. The amended limitations raise new grounds for rejections and further that the Examiner is therefore applying a new reference.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 and are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 2A, Prong One: The independent claim 11 recites “responsive to receiving the natural language question from a requesting entity, obtaining user profile data associated with the requesting entity; automatically generating, using a prompt system, a prompt that comprises the natural language question and a database schema corresponding to a database, wherein the prompt system communicates with the database to obtain a file comprising the database schema; processing, using a retrieval system, the prompt generated by the prompt system to identify one or more tables in the database, the one or more tables relevant to the natural language question; generating, 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; generating, using the SQL large language model (LLM), a set of SQL code based on the augmented prompt generated by the retrieval system; initiating executing the set of SQL code, generated by the SQL LLM, on the database and receiving a result, wherein the SQL LLM communicates with the database; inputting the result and the user profile data into a personalization LLM to generate a personalized result message; and outputting the personalized result message responsive to the natural language question”.
Claims 1, 11 and 20 recite a workflow: receive a natural-language question, identify relevant database tables, generate SQL, execute it, and personalize the returned result using profile data. This relates to conceptually organizing data, translating a question into a query, performing retrieval, and formatting a personalized response.
Those tasks are similar to organizing information, lookup, routine data processing, and natural language conversion as abstract ideas when claimed at a high level. See Alice and Data Engine (abstract idea of storing, organizing, and retrieving information / manipulating data).
Accordingly, the claims are directed to the judicial exception of a mental process with a pen and paper.
Step 2A, Prong Two: This judicial exception is not integrated into a practical application. The computer is recited at a high-level of generality (i.e., as performing a generic computer function and being used as an applying) such that it amounts no more than mere instructions to apply the exception using a generic computer. Accordingly, there additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
Step 2B — Claims Do Not Recite an Inventive Concept That Transforms the Mental Process into Patent-Eligible Subject Matter
The claims add generic, well-understood computer components (memory and processor) and name LLMs (personalization LLM, SQL LLM) and a “retrieval system,” but does not explain how those components are specially configured, or how their interaction produces a technical improvement to the computer itself (e.g., reduced latency, improved correctness of generated SQL, new indexing/search data structures, memory savings, or improved security). Merely implementing an abstract idea on generic computer components or saying “use an LLM” is usually insufficient.
Because the claims lack limitations that tie the mental-process steps to a particular way of achieving a technological improvement (for example, a novel model architecture, specialized data representation, unique training regimen that yields demonstrable technical performance gains, a specialized streaming/decoding pipeline that reduces latency by a quantifiable amount, or hardware/software co-design), the additional elements do not transform the mental processes into significantly more.
Therefore, claims 1, 11 and 20 fail to recite an inventive concept sufficient to transform the judicial exception into patent-eligible subject matter.
With respect to dependent claims 2 and 12, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
With respect to dependent claims 3 and 13, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
With respect to dependent claims 4 and 14, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
With respect to dependent claims 5 and 15, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
With respect to dependent claims 6 and 16, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
With respect to dependent claims 7 and 17, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
With respect to dependent claim 8, the claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
With respect to dependent claims 9 and 18, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
With respect to dependent claims 10 and 19, the claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Conclusion — Rejection
Claims 1-20 are rejected under 35 U.S.C. § 101 as being directed to a judicial exception (mental processes) and failing to recite additional elements that amount to significantly more than the judicial exception.
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 for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 7, 8, 11, 17, and 20 are rejected under 35 U.S.C. 102(a)(2) as being unpatentable by Chakraborty (US Pat. 12,306,828) in view of Ojha et al., (US 12,511,282 B1).
Regarding claim 1, Chakraborty discloses a computing system for processing a natural language question, the computing system comprising:
a memory, a communication interface, and a processor operatively coupled to the memory and the communication interface (Figs. 6 and 8, memory, application UI and processor);
a prompt system, a personalization large language model (LLM), a retrieval system, and a structured query language (SQL) LLM stored in the memory and executable by the processor (Figs. 6 and 8, Col. 1, lines 40-67, LLM, retrieval system, utilizing LLMs to converse with and/or search structured data);
the processor configured to:
[responsive to receiving] the natural language question from a requesting entity, [obtain user profile data] associated with the requesting entity (Fig. 7, step 705, Col. 3, lines 33-59, Col. 17, lines 46-64, receiving a natural language question and utilizing a user questions repository, UQR, which is persona specific and provides relevant metadata for responding to users);
automatically generate, using the prompt system, a prompt that comprises the natural language question and a database schema corresponding to a database, Wherein the prompt system communicates with the database to obtain a file comprising the database schema (Fig. 7, steps 704 and 706, Col 17, line 64- Col. 18, line 30, determining sub-questions and pre-generated questions corresponding to the received question; matching embeddings for each sub-question to pre-generated embeddings and generating questions in a user questions repository which is indicative of a/the “database”);
process, using the retrieval system, the prompt generated by the prompt system to identify one or more tables in the database, the one or more tables relevant to the natural language question (Fig. 7, steps 706, Col 17, line 64- Col. 18, line 30, retrieving metadata from the UQR including names of tools and descriptions for each sub-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. 3, lines 49-59, generating questions using a retrieval augmented generation, RAG - based prompting);
generate, using the SQL LLM, a set of SQL code based on the augmented prompt generated by the retrieval system (Fig. 7, step 708, Col. 18, lines 31-48, generating a structured query to the structured database using a list of the sub-questions; Fig. 2, Col. 11, line 59- Col. 12, line 12, Col. 17, lines 19-20, utilizing UQR and LLM 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, generated by the SQL LLM, on the database and receiving a result, wherein the SQL LLM communicates with the database (Fig. 7, step 708, Col. 16, lines 38-43, Col. 18, lines 31-48, providing intelligent generation of structured queries based on syntax of SQL or other structured data language);
input the result and [the user profile data] into the personalization LLM to generate a personalized result message (Fig. 7, step 710, Col. 18, lines 49-62, querying the structured database using the structured query in order to receive a result; Col. 12, lines 10-16, integrating UQR and LLM); and
output [the personalized result message responsive] to the natural language question (Col. 4, lines 51-56, Col. 7, lines 21-45, returning data as a response to the user’s original natural language question based on user’s preferences and structured data system).
Chakraborty does not explicitly teach the bracketed limitation however Ojha does explicitly teach:
[responsive to receiving] the natural language question from a requesting entity, [obtain user profile data] associated with the requesting entity (Figs. 1, 8, 9, and 12, Col. 24, lines 61- 67, receiving a prompt from the logged user); and
input the result and the [user profile data] into the personalization LLM to generate a personalized result message; and output [the personalized result message responsive] to the natural language question (Figs. 1, 8, 9, and 12, Col. 9, lines 8-39, generating an interactive document using LLM which can personalize the style of interactions and types of results generated).
Therefore, it would have been obvious to one of ordinary skill before the effective filing date of the claimed invention to incorporate the method of the method of processing user’s query using a large language model as taught by Chakraborty with method of adopting user profile to LLM as taught by Ojha to improve the versatility of LLM to handle the wide range of user requests using a personalized knowledge base for individual users.
Regarding claim 7, Chakraborty discloses the computing system of claim 1, and Chakraborty further discloses:
wherein the retrieval system comprises a retrieval LLM, and the retrieval LLM generates the augmented prompt (Col. 3, lines 33-59, “prompting strategies may be used, such as a retrieval augmented generation (RAG)-based prompting and questioning process”).
Regarding claim 8, Chakraborty in view of Ojha discloses the computing system of claim 1, and Chakraborty further discloses:
wherein the prompt system comprises a preliminary LLM and the preliminary LLM generates the prompt that comprises the natural language question, the database schema and metadata of the database (Col. 11, lines 42-58, utilizing a UQR with an LLM and converting 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 14-44, prompting LLM using the question and corresponding identified metadata for the match, and generating a SQL query which is used for structured data retrieval from a structured database system).
Regarding claims 11 and 17, Claims 11 and 17 are the corresponding method claims to system claims 1 and 7. Therefore, claims 11 and 17 are rejected using the same rationale as applied to claims 1 and 7 above.
Regarding claim 20, Claim 20 is the corresponding medium claim to system claim 1. Therefore, claim 20 is rejected using the same rationale as applied to claim 1 above.
Claims 2-6, 10, 12-16 and 19 are rejected under pre-AIA 35 U.S.C. 103(a) as being unpatentable over Chakraborty (US Pat. 12,306,828) in view of Ojha et al., (US 12,511,282 B1) and further in view of Gruber et al, (US Pub. 2020/0327895).
Regarding claim 2, Chakraborty in view of Ojha discloses the computing system of claim 1. Chakraborty in view of Ojha does not explicitly teach however Gruber does explicitly teach:
wherein the processor is further configured to use the personalization LLM to derive personalization data from the natural language question to add to the user profile data (Gruber, Fig. 28, [0132]-[0141][0202]-[0210] using user-specific information and personal interaction history in the interpretation and execution of user requests such as that found in personal memory 1052 and 1054) .
Therefore, it would have been obvious to one of ordinary skill before the effective filing date of the claimed invention to incorporate the method of the method of processing user’s query using a large language model as taught by Chakraborty in view of Ojha with the method of engaging short and long term memory for personalizing user data as taught by Gruber so that user input can be interpreted in proper context given previous events and communications within a given session, as well as historical and profile information about the user (Gruber, [0011]).
Regarding claim 3, Chakraborty in view of Ojha discloses the computing system of claim 1. Chakraborty in view of Ojha does not explicitly teach however Gruber does explicitly teach:
wherein the processor is further configured to: receive a natural language response to the personalized result message; and use the personalization LLM to derive personalization data from the natural language response to add to the user profile data (Gruber, Fig. 28, [0132]-[0141][0202]-[0210] using user-specific information and personal interaction history in the interpretation and execution of user requests such as that found in short term and long term personal memory 1052 and 1054).
Regarding claim 4, Chakraborty in view of Ojha discloses the computing system of claim 1. Chakraborty in view of Ojha does not explicitly teach however Gruber does explicitly teach:
wherein the personalization LLM generates the personalized result message by incorporating a plurality of words from the user profile data (Gruber, [0132]-[0141] generating result using personal information and personal interaction history).
The previous motivation statement as in claim 2 is still applied.
Regarding claim 5, Chakraborty in view of Ojha discloses the computing system of claim 1. Chakraborty in view of Ojha does not explicitly teach however Gruber does explicitly teach:
wherein the personalization LLM generates one or more graphics using the user profile data and the result, and the personalized result message comprises the one or more graphics (Gruber, Fig. 27, [0151]-[0159][0389][0390] generating graphical result using data source based on identifier for saving to personal memory and personal notes and etc.).
The previous motivation statement as in claim 2 is still applied.
Regarding claim 6, Chakraborty in view of Ojha discloses the computing system of claim 1. Chakraborty in view of Ojha does not explicitly teach however Gruber does explicitly teach:
wherein the personalization LLM uses a digital voice associated with the user profile data to generate the personalized result message as audio speech data (Gruber, [0102][0151]-[0159] output synthesized speech from the assistant to the user in reply).
The previous motivation statement as in claim 2 is still applied.
Regarding claim 10, Chakraborty in view of Ojha discloses the computing system of claim 1.
wherein a chat user interface is stored in the memory, the chat user interface in communication with the personalization LLM and [a user profile database that stores the user profile]; and the processor is further configured to:
receive the natural language question via the chat user interface (Fig. 7, step 702, Col. 17, lines 46-64, receiving a natural language question);
generate the personalized 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 (Fig. 7, step 710, Col. 18, lines 49-62, querying the structured database using the structured query in order to receive a result; Col. 12, lines 10-16, integrating UQR and LLM; Col. 4, lines 51-56, Col. 7, lines 21-45, returning data as a response to the user’s original natural language question based on user’s preferences and structured data system).
Chakraborty in view of Ojha does not explicitly teach however Gruber does explicitly teach: [a user profile database that stores the user profile] (Gruber, Fig. 28, [0132]-[0141][0202]-[0210] using user-specific information and personal interaction history in the interpretation and execution of user requests such as that found in short term and long term personal memory 1052 and 1054).
The previous motivation statement as in claim 2 is still applied.
Regarding claims 12-16 and 19, Claims 12-16 and 19 are the corresponding method claims to system claims 2-6 and 10. Therefore, claims 12-16 and 19 are rejected using the same rationale as applied to claims 2-6 and 10 above.
Claims 9 and 18 are rejected under pre-AIA 35 U.S.C. 103(a) as being unpatentable over Chakraborty (US Pat. 12,306,828) in view of Ojha et al., (US 12,511,282 B1) and further in view of Vu et al., (US Pub. 2026/0037505).
Regarding claim 9, Chakraborty in view of Ojha discloses the computing system of claim 1, and Chakraborty in view of Ojha further discloses:
wherein, [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 (Col. 17, lines 1-26, when user questions are not found in UQR 206, e.g., a very low matching score, an automated pipeline may generate variations of low scoring questions that are served on structured data and additional automated actions may be taken based on the results).
Chakraborty in view of Ojha does not explicitly teach the bracketed limitation however Vu does explicitly teach the bracketed limitation:
when the result comprises an error message ([0041]-[0043] generating an error message corresponding to the dissimilarity between the inferred result and the gold result).
Therefore, it would have been obvious to one of ordinary skill before the effective filing date of the claimed invention to incorporate the method of the method of processing user’s query using a large language model as taught by Chakraborty in view of Ojha with the method of providing error messages as taught by Vu to allow 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.
Regarding claim 18, Claim 18 is the corresponding method claim to system claim 9. Therefore, claim 18 is rejected using the same rationale as applied to claim 9 above.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Please see attached form PTO-892.
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 SEONG-AH A. SHIN whose telephone number is (571)272-5933. The examiner can normally be reached 9 AM-3PM.
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, Pierre-Louis Desir can be reached at 571-272-7799. 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.
Seong-ah A. Shin
Primary Examiner
Art Unit 2659
/SEONG-AH A SHIN/ Primary Examiner, Art Unit 2659
Prosecution Insights