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 .
Information Disclosure Statement
The information disclosure statements filed 7/21/2025 and 7/23/2025 have been considered by examiner.
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 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 –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-4, 9-12, 14, 15, 19, and 20 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Lee et al. in US Patent № 2020/0334233, hereinafter called Lee.
In regard to claim 1, Lee teaches a computing system comprising: a processing unit configured to execute computer-readable instructions to cause the system to:
receive, from a user device, contextual information containing a textual description of an optimization problem in natural language (“The example embodiments are directed to a system that can translate a natural language input into a structured query language (SQL) command, also referred to herein as text-to-SQL generation.” Paragraph 0015, wherein optimization is taught in at least paragraph 0021);
update a structured model summary data structure (i.e. SQL query) by retrieving, from a template database, one or more templates for one or more model components, each of the one or more templates being retrieved using a respective refined query generated from the contextual information, and updating the structured model summary data structure using metadata (i.e. descriptions; alternatively or additionally, metadata, paragraph 0029) associated with each of the retrieved one or more templates (“The candidate set includes a plurality of candidates (e.g., hundreds, thousands, etc.). Each candidate in the set includes an SQL template (SQL syntax with open slots) paired with a natural language text input that corresponds to the SQL template. Each pair may have a unique SQL template and a unique natural language text input paired therewith. The deep learning neural networks can identify similarities between a received natural language input and an SQL template by comparing the corresponding natural language text paired together with the SQL template to the received natural language input.” Paragraph 0017);
retrieve a base model template using the structured model summary data structure as a query to the template database (“For a given user input 302, the candidate search network 310 chooses the top-n most relevant items with respect to the user input 302 from the candidate set 312 to build the reduced set 322.” Paragraph 0044);
update a symbolic model associated with the base model template by retrieving, from the template database, one or more additional templates (i.e. variables) for one or more additional model components, each of the one or more templates being retrieved using a respective additional refined query (i.e. LTSM encoders used to determine token-to-variable mappings, as in paragraphs 0051-0054), and updating the symbolic model using symbolic content associated with each of the retrieved one or more templates (“For example, the determining may include filling-in one or more slots of the selected SQL template with one or more words from the natural language input. In some embodiments, the determining may include determining, via a third predictive network, a word from the natural language input which belongs in an empty slot of the selected SQL template.” Paragraph 0060);
and output the symbolic model as a generated optimization model (i.e. execution of SQL query in optimization form, paragraph 0021).
In regard to claim 14, it is substantially similar to claim 1 and accordingly is rejected under similar reasoning.
In regard to claim 2, Lee further teaches that updating the structured model summary data structure includes updating the contextual information using metadata associated with the retrieved one or more templates, and wherein the updated contextual information is outputted (“The architecture 100 may include metadata defining objects which are mapped to logical entities of data store 110. The metadata may be stored in data store 110 and/or a separate repository (not shown). The metadata may include information regarding dimension names ( e.g., country, year, product, etc.), dimension hierarchies (e.g., country, state, city, etc.), measure names (e.g., profit, units, sales, etc.) and any other suitable metadata. According to some embodiments, the metadata includes information associating users, queries, query patterns and visualizations. The information may be collected during operation of system and may be used to determine a visualization to present in response to a received query, and based on the query and the user from whom the query was received.” Paragraph 0029).
In regard to claim 15, it is substantially similar to claim 2 and accordingly is rejected under similar reasoning.
In regard to claim 3, Lee further teaches that updating the structured model summary data structure is performed iteratively, and wherein the structured model summary data structure is updated using metadata associated with one retrieved template for one model component in each iteration (“For example, the candidate search network may limit/reduce all possible SQL template candidates to a predefined subset (e.g., 3, 5, 7, etc.) of SQL templates and the matching network may select a most closely matching SQL template from the smaller subset.” Paragraph 0016; alternatively or additionally, cosine similarity performed in paragraph 0058 to populate a subset).
In regard to claim 4, Lee further teaches that updating the symbolic model is performed iteratively, and wherein the symbolic model is updated using symbolic content associated with one retrieved template for one model component in each iteration (i.e. choosing each of all possible classes in k-nearest neighbors, 0035).
In regard to claim 9, Lee further teaches that the at least one refined query is generated from an initial query received from the user device (“In the example embodiments, the pointer network is adapted to fill variables of the selected/predicted SQL template using tokens (e.g., words, text, etc.) from the natural language input sentence” paragraph 0036).
In regard to claim 10, Lee further teaches that the processing unit is further configured to execute computer-readable instructions to cause the system to: provide a user interface (UI) to the user device, wherein the contextual information is received as natural language input from the user device via the UI (“Thus, the applications 145 and/or service 135 may provide a natural language interface to the database and the data stored therein.” Paragraph 0023).
In regard to claim 11, Lee further teaches that the processing unit is further configured to execute computer-readable instructions to cause the system to implement a refined query generator comprising:
a first natural language processing (NLP) encoder trained to encode context segments, segmented from the contextual information, into respective context vectors and to encode an initial query into a query vector, wherein the context vectors and the query vector are encoded into a common vector space (“The deep learning networks may convert the natural language text and the natural language input into vectors, and perform a vector similarity comparison such as cosine similarity, etc. Each of the candidate search network and the matching network may use different functions to convert the text/input into vectors.” Paragraph 0017);
a first similarity module configured to select at least one selected context segment based on a similarity between the query vector and the context vector encoded from the at least one selected context segment (“Furthermore, the deep learning neural network compares the vectors 316 of the candidate set to the vectorized format of the user input 320, and chooses the top-n most relevant vectors 316.” Paragraph 0043);
anda first NLP generative model trained to generate at least one refined query based on the initial query and the at least one selected context segment (“Then, a cosine similarity is performed to compare the vectors 326 of the reduced set 322 to the vectorized user input 302. In the matching network 320, the neural network uses a different function to convert the candidates into vectors and chooses a closest vector using cosine similarity.” Paragraph 0047).
In regard to claim 19, it is substantially similar to claim 11 and accordingly is rejected under similar reasoning.
In regard to claim 12, Lee further teaches that the processing unit is further configured to execute computer-readable instructions to cause the system to implement a template retriever comprising:
a second NLP encoder trained to encode the at least one refined query into a refined query vector and to encode metadata associated with each one or more templates into respective one or more template vectors, wherein the one or more template vectors and the refined query vector are encoded into a common vector space (“Similar to the candidate search network 310, the matching network includes a deep learning neural network which converts the candidates in the reduced set 322 into vectors 326. In particular, the deep learning neural network converts the natural language text of the candidate set into vectors 326 using a vector function (f) 324. Furthermore, the user input 302 is also converted into a vector format using the vector function (f)” paragraph 0047);
and a second similarity module configured to select at least one selected template to be retrieved based on a similarity between the refined query vector and the template vector encoded from metadata associated with the at least one selected template (“Then, a cosine similarity is performed to compare the vectors 326 of the reduced set 322 to the vectorized user input 302. In the matching network 320, the neural network uses a different function to convert the candidates into vectors and chooses a closest vector using cosine similarity.” Paragraph 0047).
In regard to claim 20, it is substantially similar to claim 12 and accordingly is rejected under similar reasoning.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 5, 7, 13, 16, 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lee as applied to claim 1, 12, or 14 above, as applicable, and further in view of Cao et al. in US Patent Application Publication № 2022/0129450, hereinafter called Cao.
In regard to claim 5, Lee teaches the system of claim 1, as above. However, Lee fails to teach that updating the structured model summary data structure includes generating a context-grounded explanation for each retrieved one or more templates, and wherein the context-grounded explanation is presented via the user device.
Cao teaches that updating the structured model summary data structure includes generating a context-grounded explanation for each retrieved one or more templates, and wherein the context-grounded explanation is presented via the user device (“Given a SQL query, it is parsed under the grammar to obtain a derivation, which may then be followed to obtain the explanation text” paragraph 0133, wherein “This grammar is that each high-level SQL template can be associated with an English explanation template that reveals the high level logic and abstracts away from the details in the concrete queries.” Paragraph 0135)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant invention to modify the template-based SQL generation system (which includes templates of SQL queries with natural language explanations, Lee paragraph 0017) taught by Lee to include the explanation of the meaning of an SQL query (in a system which includes templates of SQL queries with natural language explanations, Cao paragraph 0135) as taught by Cao. One would have been motivated to do so in order to allow the user to easily interpret the differences, as taught by Cao in paragraph 0132.
In regard to claim 16, it is substantially similar to claim 5 and accordingly is rejected under similar reasoning.
In regard to claim 7, Lee teaches the system of claim 1, as above. However, Lee fails to teach that the processing unit is further configured to executing computer-readable instructions to cause the system to: after retrieving the base model template, present, via the user device, a generated explanation for the base model template, the generated explanation being generated from metadata associated with the base model template and the contextual information.
Cao teaches that the processing unit is further configured to executing computer-readable instructions to cause the system to: after retrieving the base model template, present, via the user device, a generated explanation for the base model template, the generated explanation being generated from metadata associated with the base model template and the contextual information (“Given a SQL query, it is parsed under the grammar to obtain a derivation, which may then be followed to obtain the explanation text” paragraph 0133, wherein “This grammar is that each high-level SQL template can be associated with an English explanation template that reveals the high level logic and abstracts away from the details in the concrete queries.” Paragraph 0135).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant invention to modify the template-based SQL generation system (which includes templates of SQL queries with natural language explanations, Lee paragraph 0017) taught by Lee to include the explanation of the meaning of an SQL query (in a system which includes templates of SQL queries with natural language explanations, Cao paragraph 0135) as taught by Cao. One would have been motivated to do so in order to allow the user to easily interpret the differences, as taught by Cao in paragraph 0132.
In regard to claim 17, it is substantially similar to claim 7 and accordingly is rejected under similar reasoning.
In regard to claim 13, Lee teaches the system of claim 12, as above. However, he failed to expressly teach that the processing unit is further configured to execute computer-readable instructions to cause the system to implement an explanation generator comprising: a second NLP generative model trained to generate a context-grounded explanation for the at least one selected template based on the metadata associated with the at least one selected template and the refined query.
Cao teaches an explanation generator comprising: a second NLP generative model trained to generate a context-grounded explanation for the at least one selected template based on the metadata associated with the at least one selected template and the refined query (“Given a SQL query, it is parsed under the grammar to obtain a derivation, which may then be followed to obtain the explanation text” paragraph 0133, wherein “This grammar is that each high-level SQL template can be associated with an English explanation template that reveals the high level logic and abstracts away from the details in the concrete queries.” Paragraph 0135, further, “Finally, whenever the final value in the query differs from original text span due to post-processing, a sentence in the explanation states the change explicitly for clarity. For example, "'Asian' in the question is matched to 'Asia' which appears in the column Continent." Paragraph 0136)
Claim(s) 6, 8, 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lee as applied to claim 1 or 14 above, as applicable, and further in view of Arroyo et al. in US Patent Application Publication № 2019/0213185, hereinafter called Arroyo.
In regard to claim 6, Lee teaches the system of claim 1, as above. However, he fails to expressly teach that updating the structured model summary data includes presenting, via the user device, at least one refined query, and receiving approval, via the user device, of the at least one refined query prior to using the at least one refined query to retrieve a respective at least one template.
Arroyo teaches updating the structured model summary data includes presenting, via the user device, at least one refined query (i.e. generated template from searches, paragraph 0137, wherein “This involves submitting proposals for predefined semantic query templates by users and their examination by reviewers. Approved semantic query template may then be added by an administrator, or the original submitter can be given the access right to add the proposed predefined semantic query.” Paragraph 0138), and receiving approval, via the user device, of the at least one refined query prior to using the at least one refined query to retrieve a respective at least one template (“Approved semantic query template may then be added by an administrator, or the original submitter can be given the access right to add the proposed predefined semantic query.” Paragraph 0138).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to modify the template-based SQL generation system (which includes templates of SQL queries with natural language explanations, Lee paragraph 0017) taught by Lee to include the approval of conversion of search queries into new templates, as taught by Arroyo (paragraph 0137). One would have been motivated to do so in order to ensure no inconsistencies are included in the templates, as taught by Arroyo in paragraph 0138.
In regard to claim 8, Lee teaches the system of claim 1, as above. However, he fails to expressly teach that updating the symbolic model includes presenting, via the user device, at least one additional refined query , and receiving approval, via the user device, of the at least one additional refined query prior to using the at least one additional refine query to retrieve a respective at least one template.
Arroyo teaches that updating the symbolic model includes presenting, via the user device, at least one additional refined query (i.e. generated template from searches, paragraph 0137, wherein “This involves submitting proposals for predefined semantic query templates by users and their examination by reviewers. Approved semantic query template may then be added by an administrator, or the original submitter can be given the access right to add the proposed predefined semantic query.” Paragraph 0138), and receiving approval, via the user device, of the at least one additional refined query prior to using the at least one additional refine query to retrieve a respective at least one template (“Approved semantic query template may then be added by an administrator, or the original submitter can be given the access right to add the proposed predefined semantic query.” Paragraph 0138).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to modify the template-based SQL generation system (which includes templates of SQL queries with natural language explanations, Lee paragraph 0017) taught by Lee to include the approval of conversion of search queries into new templates, as taught by Arroyo (paragraph 0137). One would have been motivated to do so in order to ensure no inconsistencies are included in the templates, as taught by Arroyo in paragraph 0138.
In regard to claim 18, it is substantially similar to claim 8 and accordingly is rejected under similar reasoning.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US Patent Application Publication № 2024/0012810 teaches a system which uses multiple passes and templates to convert natural language to SQL queries
US Patent Application Publication № 2024/0061833 teaches a system which iteratively generates new training data
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Lauren Z Ganger whose telephone number is (571)272-0270. The examiner can normally be reached 10:00 AM - 7:30 PM.
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.
/AJAY M BHATIA/Supervisory Patent Examiner, Art Unit 2156
Prosecution Insights