Notice of Pre-AIA or AIA Status
The present applicati7410on 18/940,529, filed on 11/7/2024 (or after March 16, 2013), is being examined under the first inventor to file provisions of the AIA (First Inventor to File).
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.
DETAILED ACTION
Response to RCE
Claims 1-20 are pending in this application.
Examiner acknowledges applicant’s amendment filed on 10/16/2026
A request for continued examination under 37 CFR 1.114, including the fee set
forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this
application is eligible for continued examination under 37 CFR 1.114, and the fee set
forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action
has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on
10/16/2026 has been entered
Drawings
The Drawings filed on 11/7/2024 are acceptable for examination purpose.
Response to Arguments
Applicant's arguments filed 10/16/2026 with respect to claims 1-20 have been fully considered but they are not persuasive, for examiner’s response, see discussion below:
35 USC § 101
a)At page 9-12, claim 1, applicant argues
The claims are directed to generating follow up queries to a user query in text-to-database query conversion services based on context provided by a database query representation of the user query. This cannot accurately be characterized as a mere observation, evaluation, judgement, or opinion that can practically be performed in the human mind. Examples of such claims identified as mental processes include claims directed to "collecting information, analyzing it,…………….claims 1,13,17 recite a specific technique for generating follow up queries. There are other ways to generate follow up queries that do not involve extracting an entity name(s) corresponding to an entity type(s)………..
Examiners response:
Examiner submits that the pending claims (as amended 6/22/2026) should pass the test set forth in the 2019 Revised Patent Subject Matter Eligibility Guidance published on January 7, 2019 (84 Fed. Reg. 50), as updated October 2019, referred to herein as the PEG 2019. Applicant will focus on Prong Two of Step 2A, in evaluating the pending claims using this section of the test set forth in the PEG 2019
To determine whether a claim recites an abstract idea, (1) identify the claim’s specific limitations that recite an abstract idea, and (2) determine whether the identified limitations fall within certain subject matter groupings, namely (a) mathematical concepts; (b) certain method of organizing human activity; or (c) mental processes. Mental processes are “concepts performed in the human mind that including an observation, evaluation, judgement or opinion. See MPEP 2106.04(a), 2106.04(a)(2)(III)
“generating one or more follow up queries ………….., wherein
generating the one or more follow up queries based on the context provided by the
first database query comprises,
extracting one or more entity names ………. first database query against the target database;
transforming each of the one or more entity names ………….. one of the one or more entity types; and
populating each of the one or more user query templates ………one or more follow up queries, wherein each of the one or more entity names has been transformed into a natural language representation”, examiner finds that the “generating”, “extracting”, “transforming”, “populating” steps recite mental processes because it merely data gathering including populating query template(s) and thus are mental process[es], accomplishable in the human mind or on paper
Also, claim 1 recites that the “generating”, “extracting”,”transforming”,”populating” steps discussed above are performed by the processor and/or generic computer using the query process and does not integrate the judicial exception (i.e., the mental processes recited above), further above steps of the claim use “generic computer components (processor unit, query process, etc.,) and amount to “insignificant extra-solution activity” as mere “generating”,”extracting”…..”populating” steps together do not amount to an “improvement in a technology or the function of a computer”(Step 2A, Prong Two)
With respect to Step 2B: Examiner finds that the additional elements of claim 1 do not amount to significantly more than the judicial exception itself (mental processes), because claim 1 steps “generating”, “extracting”, “transforming”, “populating” mere data collection, routine and conventional activities using generic computer components.
Examiner applies above arguments to claims 2-12,14-16,18-20 depend from claim 1,13,17
b)At page 14-15, claim 1, applicant argues:
Lee fails to disclose the natural language input in Lee is an input translated to a SQL command, the natural language input is not a natural language representation of one or more entity names …….as amended in claim 1
Chang fails to cure the deficiencies of Lee. Chang discloses filling templates with data/information from a result generated in response to a query and data/information filled into a template in Chang is never transformed to a natural language representation…………In Chang, templates are simply populated with data/information…………Chang merely mentions that follow-up queries, but does not disclose populating a template in any manner…….Incorporating Chang into Lee thus fails to cure the deficiencies of Lee, and Lee/Chang fails to disclose all elements of claim 1 (p 17-18)
Examiners response:
As to the above argument (b), the prior art of Lee is directed to receiving natural language input and an SQL template, database software for example performs natural language processing based on text-SQL model (Lee: fig 1, 0018-0019) that including defining templates as detailed in fig 3A, 3B temp1…..temp N, fig 3C, while receiving natural language input from the user(s) as detailed in fig 2 . The prior art of Lee teaches SQL template of user query from subsets selecting and populating based on the natural language input and text values. The prior art of Lee teaches SQL template element 332 for the user input element 302 ie., candidate sets (entities) including tables with plurality of rows corresponding to a columns for SQL templates and text values as natural language inputs to the respective SQL template, query templates corresponds to Lee’s fig 3C-3D SQL template element 332.
The prior art of Chang is directed to summarization for question-answering system particularly processing initial natural language queries and creating relevant follow-up queries and performing relevant summary of the performed analysis (Chang: Abstract). The prior art of Chang query template(s) associated with natural language module in processing queries (see fig 4). The prior art of Chang teaches entity name, entity types for example in the defined template as detailed in fig 5, 0069 and the follow-up queries generated from for example query processing module as detailed in fig 2, element 200
The combination of Lee, Chang is obvious because both Lee, Chang supports natural language queries (Lee: Abstract, fig 2; Chang: Abstract, 0030,0039), and both Lee, Chang supports natural language template (Lee: fig 3, Chang: fig 6), and they both Lee, Chang are from the same field of endeavor, and would have been obvious to combine to achieve the predictable interesting patterns, and/or insightful information including statistical analysis to suggest the relevant information (Chang: 0003) thus improves overall quality and reliability of the follow-up queries. The exemplary rationales that may support prima facie conclusion of obviousness includes (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention- -KSR, 550 US at 398.
It is however, noted that Lee, Chang do not teach “transforming each of the one or more entity names into a natural language representation based at least partly on a corresponding one of the one or more entity types”, “wherein each of the one or more entity names has been transformed into a natural language representation”, although prior art of Lee teaches “text-to-SQL (Lee: Abstract, fig 2) and prior art of Chang teaches natural language query processing including follow-up queries (Chang: Abstract, fig 2-3). On the other hand, Song disclosed “transforming each of the one or more entity names into a natural language representation based at least partly on a corresponding one of the one or more entity types”, “wherein each of the one or more entity names has been transformed into a natural language representation” (Song: Abstract, fig 4-fig 6, 0067-0075 – Song teaches both text-to-SQL and SQL-to text model particularly using machine learning technique processing the SQL-to-text model, further Song teaches database schema defining entity name, entity type for example “airlines” entity type, and “airline name” is “entity name” (see para 0074). The prior art of Song teaches generating “SQL-to-text model to converse with a text to SQL model, also supports pre-trained SQL-to-text model as detailed in fig 7
PNG
media_image1.png
184
230
media_image1.png
Greyscale
PNG
media_image2.png
161
204
media_image2.png
Greyscale
PNG
media_image3.png
199
230
media_image3.png
Greyscale
It would have been obvious to a person of ordinary skill in the art at the time of filing the claimed invention generating SQL-text model to converse with a text-to-SQL mode, pre-training the SQL-to-text on training data, sampling SQL query of Song into natural language embellishment generation and summarization for question-answer system particularly follow-up queries of Chang et al., one shot learning for text-sql particularly using SQL template based on natural language input of Lee et al., because all the references supports natural language queries (Lee: Abstract, fig 2; Chang: Abstract, 0030,0039 and Song: Abstract) and they are all from same field of endeavor. Because all the prior art references teaches database queries, natural language queries, and template(s) it would have been obvious to one skill ed in the art to substitute and/or modify one method for the other particularly using SQL-to-text and text-to-SQL model while pre training SQL queries to achieve the predictable interaction and goal query, while SQL templates using SQL queries in the input training data transforming respective data query in natural language (Song: 0004-0006), thus improves overall quality and reliability of the SQL-to-text and vise versa. The exemplary rationales that may support prima facie conclusion of obviousness includes (F) Known work in one field of endeavor may prompt variations of it for use in either the same field or a different one based on design incentives or other market forces if the variations are predictable to one of ordinary skill in the art-KSR, 550 US at 398.
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 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The judicial exception is not integrated into a practical application.
Claim 1-20 is/are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The judicial exception is not integrated into a practical application. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The eligibility analysis in support of these findings is provided below, in accordance with the 2019 Revised Patent Subject Matter Eligibility Guidance, Federal Register (84 FR 50) on January 7, 2019 hereinafter 2019 PEG
Step 1. In accordance with Step 1 of the eligibility inquiry (as explained in MPEP 2106), it is noted that the method of claim 1,13,17, directed to one of the eligible categories of subject matter and therefore satisfy Step 1.
Step 2A. In accordance with Step 2A prong one of the 2019 PEG, the limitations reciting the abstract idea are highlighted, and the limitations directed to additional elements are highlighted, as set forth in exemplary claim 1
obtaining a first user query comprising natural language and a first database query representing the first user query, wherein the first database query corresponds to a target database;
based on extracting one or more entity types from the first database query, retrieving one or more user query templates from a plurality of user query templates, wherein each of the one or more user query templates comprises one or more parameters corresponding to the one or more entity types;
generating one or more follow up queries to the first user query, based on context provided by the first database query, wherein each of the one or more follow up queries is a follow up to the first user query in natural language, wherein generating the one or more follow up queries based on the context provided by the first database query comprises,
extracting one or more entity names corresponding to the one or more entity types from at least one of the first database query and a result of executing the first database query against the target database; and
transforming each of the one or more entity names into a natural language representation based at least partly on a corresponding one of the one or more entity types”,
populating each of the one or more user query templates based on the one or more entity names to generate a corresponding one of the one or more follow up queries, wherein each of the one or more entity names has been transformed into a natural language representation
responding to the first user query with a first response comprising the one or more follow up queries”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, extracting entity types, retrieving query templates, generating queries, extracting entity names, populating templates in the context of this claim encompasses the user thinking mere data gathering
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” i.e., concepts performed in the human mind including an observation, evaluation, judgment, opinion and/or using paper pencil, grouping of abstract ideas set forth in the 2019 PEG. Accordingly, the claim recites an abstract idea.
With respect to Step 2A prong two of the 2019 PEG, the judicial exception is not integrated into a practical application. The additional elements are directed to method steps, however, these elements fail to integrate the abstract idea into a practical application because they fail to provide an improvement to the functioning of a computer or to any other technology or technical field, fail to apply the exception with a particular machine, fail to apply the judicial exception to effect a particular data structure of populating template, extracting entity names and like to effect a transformation of a particular article to a different state or thing, and fail to apply/use the abstract idea in a meaningful way beyond generally linking the use of the judicial exception to a particular technological environment.
Furthermore, although these elements have been fully considered, they are directed to the use of generic computing elements (para: 0071-0076, fig 8 of the instant specification make it clear that the disclosed functionality is implemented on well-known computing systems and general purpose computing devices) to perform the abstract idea, which is not sufficient to amount to a practical application (as noted in the 2019 PEG) and is amount to simply saying "apply it" using a general purpose computer, which merely serves to tie the abstract idea to a particular technological environment computer based operating environment) by using the computer as a tool to perform the abstract idea.
Since the analysis of Step 2A prong one and prong two results in the conclusion that the claims are directed to an abstract idea, additional analysis under Step 2B of the eligibility inquiry must be conducted in order to determine whether any claim element or combination of elements amount to significantly more than the judicial exception.
Step 2B. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The additional method limitations are directed to a generic computer, at a very high level of generality and without imposing meaningful limitations on the scope of the claim. In addition para: 0071-0076, fig 8 of the instant specification describe generic off-the-shelf computer-based elements for implementing the claimed invention which does not amount to significantly more than the abstract idea and is not enough to transform an abstract idea into eligible subject matter. Such generic, high-level, and nominal involvement of a computer or computer-based elements for carrying out the invention merely serves to tie the abstract idea to a particular technological environment, which is not enough to render the claims patent-eligible, as noted at pg. 74624 of Federal Register/Vol. 79, No. 241, citing Alice, which in turn cites Mayo. Further, See, e.g., Alice Corp. Pty. Ltd. v. CLS Bank Int'l, 134 S. Ct. 2347, 2359-60, 110 USPQ2d 1976, 1984 (2014). See also OIP Techs. v. Amazon.com, 788 F.3d 1359, 1364, 115 USPQ2d 1090, 1093-94 (Fed. Cir. 2015) ("Just as Diehr could not save the claims in Alice, which were directed to 'implement[ing] the abstract idea of intermediated settlement on a generic computer', it cannot save O/P's claims directed to implementing the abstract idea of price optimization on a generic computer.") (citations omitted). See also, Affinity Labs of Texas LLC v. DirecTV LLC, 838 F.3d 1253, 1257-1258 (Fed. Cir. 2016) (mere recitation of a GUI does not make a claim patent-eligible); Intellectual Ventures I LLC v. Capital One Bank, 792 F.3d 1363, 1370 (Fed. Cir. 2015) ("the interactive interface limitation is a generic computer element".)
he additional elements are broadly applied to the abstract idea at a high level of generality ("similar to how the recitation of the computer in the claims in Alice amounted to mere instructions to apply the abstract idea of intermediated settlement on a generic computer,") as explained in MPEP § 2106.05(f)) and they operate in a well-understood, routine, and conventional manner.
MPEP § 2106.05 (d)(II) sets forth the following:
The courts have recognized the following computer functions as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g. at a high level of generality) as insignificant extra-solution activity.
Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec...; TLI Communications LLC v. AV Auto. LLC...; OIP Techs., Inc., v. Amazon.com, Inc... ; buySAFE, Inc. v. Google, Inc...;
Performing repetitive calculations, Flook ... ; Bancorp Services v. Sun Life...;
Electronic recordkeeping, Alice Corp...; Ultramercial... ;
Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc...;
Electronically scanning or extracting data from a physical document, Content Extraction and Transmission, LLC v. Wells Fargo Bank...; and
A web browser's back and forward button functionality, Internet Patent Corp. v. Active Network, Inc...
Courts have held computer-implemented processes not to be significantly more than an abstract idea (and thus ineligible) where the claim as a whole amounts to nothing more than generic computer functions merely used to implement an abstract idea, such as an idea that could be done by a human analog (i.e., by hand or by merely thinking).
Claim 2,14,18 The method of claim 1, further elaborates
“wherein retrieving the one or more user query templates further comprises retrieving a corresponding one or more database query templates,
and
wherein generating the one or more follow up queries further comprises populating parameters of each of the one or more database query templates with the one or more entity names extracted from at least one of the first database query and the result of executing the first database query”, which have been determined to be extra-solution activity that does not impose any meaningful limits on practicing the abstract idea. See MPEP 2106.05(b)(I). Even in combination, the additional details recited in these claims do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea..
Claim 3. The method of claim 1, further elaborates “wherein extracting the one or more entity types from the first database query comprises extracting the one or more entity types from at least one of a first statement in the first database query for selecting data from the target database and a second statement in the first database query for filtering the result obtained from executing the first database query”, which have been determined to be extra-solution activity that does not impose any meaningful limits on practicing the abstract idea. See MPEP 2106.05(b)(I). Even in combination, the additional details recited in these claims do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea..
Claim 4. The method of claim 3, further elaborates “wherein extracting the one or more entity names corresponding to the one or more entity types from at least one of the first database query and the result of executing the first database query against the target database comprises ,
for each of the one or more entity types extracted from the first statement in the first database query, extracting corresponding ones of the one or more entity names from the result obtained from executing the first database query; and
for each of the one or more entity types extracted from the second statement in the first database query, extracting corresponding ones of the one or more entity names from the second statement”, which have been determined to be extra-solution activity that does not impose any meaningful limits on practicing the abstract idea. See MPEP 2106.05(b)(I). Even in combination, the additional details recited in these claims do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea..
Claim 5,15,19 The method of claim 3, further elaborates “wherein the first database query comprises a Structured Query Language (SQL) query, wherein extracting the one or more entity types from at least one of the first statement in the statement in the database query for selecting data from the target database and the second statement in the database query for filtering the result obtained from executing the database query comprises extracting the one or more entity types from at least one of a SELECT statement in the SQL query and a WHERE statement in the SQL query”, which have been determined to be extra-solution activity that does not impose any meaningful limits on practicing the abstract idea. See MPEP 2106.05(b)(I). Even in combination, the additional details recited in these claims do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea..
Claim 6. The method of claim 1, further elaborates “generating a weighted one-hot vector based on the one or more entity types, wherein a vector database maintains a plurality of vectors generated based on the plurality of user query templates, wherein retrieving the one or more query templates comprises querying the vector database with the weighted one-hot vector for one or more of the plurality of vectors most similar to the weighted one-hot vector”, which have been determined to be extra-solution activity that does not impose any meaningful limits on practicing the abstract idea. See MPEP 2106.05(b)(I). Even in combination, the additional details recited in these claims do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea..
Claim 7. The method of claim 1, further elaborates “generating the plurality of user query templates based on a plurality of user queries and a corresponding plurality of database queries, wherein generating the plurality of user query templates comprises, for each user query of the plurality of user queries and corresponding database query from the plurality of database queries,
extracting one or more entity types and names from the database query; and
for each entity type and name of the one or more entity types and names extracted from the database query, determining one or more substrings of the user query to which the entity type and name corresponds and replacing the one or more substrings in the user query with a parameter corresponding to the type of the entity to generate a corresponding one of the plurality of user query templates”, which have been determined to be extra-solution activity that does not impose any meaningful limits on practicing the abstract idea. See MPEP 2106.05(b)(I). Even in combination, the additional details recited in these claims do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea..
claim 8. The method of claim 7, further elaborates “wherein determining the one or more substrings of the user query comprises determining the one or more substrings based on at least one of identifying an exact match between the entity type and name and the one or more substrings, based on fuzzy matching of the entity and the one or more substrings, and based on generating a vector representation of the entity type and name and vector representations of substrings of the user query and determining a most similar one of the vector representations of the substrings of the user query to the vector representation of the entity type and name”, which have been determined to be extra-solution activity that does not impose any meaningful limits on practicing the abstract idea. See MPEP 2106.05(b)(I). Even in combination, the additional details recited in these claims do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea..
claim 9. The method of claim 1, further elaborates “wherein extracting the one or more entity types and extracting the one or more entity names comprises extracting the one or more entity types and the one or more entity names from the first database query based on determining that the result of executing the first database query comprises an empty results set or a value or zero”, which have been determined to be extra-solution activity that does not impose any meaningful limits on practicing the abstract idea. See MPEP 2106.05(b)(I). Even in combination, the additional details recited in these claims do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea..
claim 10. The method of claim 1, further elaborates “based on determining that no entity types and names can be extracted from the first database query, retrieving one or more predefined follow up questions and responding to the first user query with a second response comprising the one or more predefined follow up questions”, which have been determined to be extra-solution activity that does not impose any meaningful limits on practicing the abstract idea. See MPEP 2106.05(b)(I). Even in combination, the additional details recited in these claims do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea..
claim 11. The method of claim 1, further elaborates “wherein the first database query representing the first user query was generated by a first language model based on the first user query, and wherein responding to the first user query comprises prompting a second language model to rephrase each of the one or more follow up queries and responding to the first user query with the rephrased one or more follow up queries”, which have been determined to be extra-solution activity that does not impose any meaningful limits on practicing the abstract idea. See MPEP 2106.05(b)(I). Even in combination, the additional details recited in these claims do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea..
claim 12. The method of claim 1, further elaborates “wherein the first database query indicates a first table of the target database, and wherein each of the one or more user query templates corresponds to the first table of the target database”, which have been determined to be extra-solution activity that does not impose any meaningful limits on practicing the abstract idea. See MPEP 2106.05(b)(I). Even in combination, the additional details recited in these claims do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea..
Claim 16,20. The non-transitory machine-readable media of claim 13, further elaborates
“wherein the instructions to extract the one or more entity types from the database query comprise instructions to extract the one or more entity types from a SQL WHERE statement of the database query,
and wherein the instructions to extract the one or more entity names corresponding to the one or more entity types from the result of executing the database query comprise instructions to extract the one or more entity names from the result of executing the database query”, which have been determined to be extra-solution activity that does not impose any meaningful limits on practicing the abstract idea. See MPEP 2106.05(b)(I). Even in combination, the additional details recited in these claims do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Lee et al., (hereafter Lee), US Pub. No. 2023/0097443 published Mar, 2023 Chang et al., (hereafter Chang), US Pub. No. 2017/0177660 published Jun, 2017 in view of Song, US Pub. No. 2024/0078230 filed Aug, 2022
As to Claim 1,13,17. Lee teaches a sys method comprising: (Lee: Abstract)
“obtaining a first user query comprising natural language and a first database query representing the first user query, wherein the first database query corresponds to a database” (Lee: fig 1-2, - Lee teaches text-to-SQL model particularly natural language interface to database; natural language corresponds to fig 2, element 210,220,230 and query language corresponds to element 212,222,232 respectively as detailed in fig 2)
PNG
media_image4.png
247
175
media_image4.png
Greyscale
“based on extracting one or more entity types from the first database query, retrieving one or more user query templates from a plurality of user query templates, wherein each of the one or more user query templates comprises one or more parameters corresponding to the one or more entity types” (Lee: 0029 – Lee teaches data items for example data records, data entries stored in the database element 100 and the database architecture element 100 including metadata defining objects to logical entities and entity types for example country, year, product, state, city, profit, units, sales and like as detailed in 0029; The prior art of Lee teaches query language (SQL) templates paired with respective text values in the predictive network environment (Lee: Abstract), Lee specifically teaches select[ing] SQL template with tokens from the natural language input, in completing the translation of the SQL query (0016, page 2, col 1,0039, fig 3B)
PNG
media_image5.png
221
330
media_image5.png
Greyscale
“generating one or more follow up queries for the first user query, wherein generating the one or more follow up queries comprises” (Lee: fig 2, 0032-Lee teaches generating multiple natural language queries of equivalent respective SQL) ,
PNG
media_image6.png
219
183
media_image6.png
Greyscale
“extracting one or more entity names corresponding to the one or more entity types from at least one of the first database query and a result of executing the first database query against the target database” (Lee: 0032-0033 – Lee teaches retrieving and/or extracting entity names such as “POPULATION”, ‘STATE”; “RIVER”, “Texas”, “Colorado” and like from the natural language input including nested queries and other SQL syntax and in response, the database element 202) and
“populating each of the one or more user query templates based on the one or more entity names”(Lee: Abstract, fig 3C-3D, fig 4, 0048-0049,0056 – Lee teaches SQL template of user query from subsets selecting and populating based on the natural language input and text values. The prior art of Lee teaches SQL template element 332 for the user input element 302 ie., candidate sets (entities) including tables with plurality of rows corresponding to a columns for SQL templates and text values as natural language inputs to the respective SQL template, query templates corresponds to Lee’s fig 3C-3D SQL template element 332)
PNG
media_image7.png
398
241
media_image7.png
Greyscale
; and
“responding to the first user query with a first response comprising the one or more follow up queries” (Lee: fig 2-3, Abstract, 0041 – Lee teaches text-to-SQL generation defining template based model architecture that generates trained templates of SQL with user query response along with training template queries as follow up queries) .
PNG
media_image6.png
219
183
media_image6.png
Greyscale
PNG
media_image5.png
221
330
media_image5.png
Greyscale
It is however, noted that Lee does not teach “first database query corresponds to a target database, “wherein each of the one or more follow up queries is a follow up to the first user query in natural language”, one or more entity names to generate a corresponding one of the one or more follow up queries, although Lee teaches text-to-SQL model particularly natural language interface to database (Lee: Abstract, fig 1-2). On the other hand, Chang disclosed “first database query corresponds to a target database” (Chang: Abstract, fig 1,0032,0036 – Chang teaches initial query processing from the client device through network to the server(s) within the distributed environment, further initial query being processed using query processing module and processing query results based on queries via user interface); “wherein each of the one or more follow up queries is a follow up to the first user query in natural language” (Chang: fig 2, 0041 – Cheng teaches query processing module processes the contextually guided question and answer conversation with the user and generates query results particularly relevance to the user based on the initial query including follow-up queries and/or questions.
PNG
media_image8.png
254
279
media_image8.png
Greyscale
The prior art of Chang teaches natural language module to provide first relevant follow-up query from a set of follow-up queries as detailed in fig 9, element 930
PNG
media_image9.png
217
245
media_image9.png
Greyscale
“one or more entity names to generate a corresponding one of the one or more follow up queries” (Chang: fig 3, fig 5, 0069-0071 – Chang teaches in response to the initial query, the response to the follow-up questions associated with the analytics session provided for output to the user using NLG templates associated with analytics session and selected template is filled with specific data i.e, set of data fields element 510, set of data values element 520 corresponds to entities
PNG
media_image10.png
257
372
media_image10.png
Greyscale
It would have been obvious to a person of ordinary skill in the art at the time of filing the claimed invention natural language embellishment generation and summarization for question-answer system particularly follow-up queries of Chang et al., into one shot learning for text-sql particularly using SQL template based on natural language input of Lee et al., because both Lee, Chang supports natural language queries (Lee: Abstract, fig 2; Chang: Abstract, 0030,0039), and both Lee, Chang supports natural language template (Lee: fig 3, Chang: fig 6), and they both Lee, Chang are from the same field of endeavor. Because both Lee, Chang teaches natural language queries, and template(s), it would have been obvious to one skill ed in the art to substitute and/or modify one method for the other particularly natural language follow-up queries, while maintaining respective template(s) to achieve the predictable interesting patterns, and/or insightful information including statistical analysis to suggest the relevant information (Chang: 0003) thus improves overall quality and reliability of the follow-up queries.
It is however, noted that Lee, Chang do not teach “transforming each of the one or more entity names into a natural language representation based at least partly on a corresponding one of the one or more entity types”, “wherein each of the one or more entity names has been transformed into a natural language representation”, although prior art of Lee teaches “text-to-SQL (Lee: Abstract, fig 2) and prior art of Chang teaches natural language query processing including follow-up queries (Chang: Abstract, fig 2-3). On the other hand, Song disclosed “transforming each of the one or more entity names into a natural language representation based at least partly on a corresponding one of the one or more entity types”, “wherein each of the one or more entity names has been transformed into a natural language representation” (Song: Abstract, fig 4-fig 6, 0067-0075 – Song teaches both text-to-SQL and SQL-to text model particularly using machine learning technique processing the SQL-to-text model, further Song teaches database schema defining entity name, entity type for example “airlines” entity type, and “airline name” is “entity name” (see para 0074). The prior art of Song teaches generating “SQL-to-text model to converse with a text to SQL model, also supports pre-trained SQL-to-text model as detailed in fig 7
PNG
media_image1.png
184
230
media_image1.png
Greyscale
PNG
media_image2.png
161
204
media_image2.png
Greyscale
PNG
media_image3.png
199
230
media_image3.png
Greyscale
It would have been obvious to a person of ordinary skill in the art at the time of filing the claimed invention generating SQL-text model to converse with a text-to-SQL mode, pre-training the SQL-to-text on training data, sampling SQL query of Song into natural language embellishment generation and summarization for question-answer system particularly follow-up queries of Chang et al., one shot learning for text-sql particularly using SQL template based on natural language input of Lee et al., because all the references supports natural language queries (Lee: Abstract, fig 2; Chang: Abstract, 0030,0039 and Song: Abstract) and they are all from same field of endeavor. Because all the prior art references teaches database queries, natural language queries, and template(s) it would have been obvious to one skill ed in the art to substitute and/or modify one method for the other particularly using SQL-to-text and text-to-SQL model while pre training SQL queries to achieve the predictable interaction and goal query, while SQL templates using SQL queries in the input training data transforming respective data query in natural language (Song: 0004-0006), thus improves overall quality and reliability of the SQL-to-text and vise versa.
As to Claim 2,14,18 , the combination of Lee, Chang, Song disclosed:
“wherein retrieving the one or more user query templates further comprises retrieving a corresponding one or more database query templates” (Lee: fig 3C-3D, 0047)
PNG
media_image11.png
136
218
media_image11.png
Greyscale
PNG
media_image12.png
87
227
media_image12.png
Greyscale
“wherein generating the one or more follow up queries further comprises populating parameters of each of the one or more database query templates with the one or more entity names extracted from at least one of the first database query and the result of executing the first database query” (Lee: fig 3C-3D, 0034,0047-0048,0056).
As to Claim 3, the combination of Lee, Chang, Song disclosed ”wherein extracting the one or more entity types from the first database query comprises extracting the one or more entity types from at least one of a first statement in the first database query for selecting data from the database and a second statement in the first database query for filtering the result obtained from executing the first database query” (Lee: fig 2, 0029,0032-0033 - Lee teaches database query including various entity types, also teaches SQL queries in selecting data from the database i.e., database 202 determine a SQL command/query to access data. On the other hand, Chang disclosed “database query for selecting data from the target database” (Chang: 0043, fig 1)
As to Claim 4, the combination of Lee, Chang, Song disclosed “wherein extracting the one or more entity names corresponding to the one or more entity types from at least one of the first database query and the result of executing the first database query against the target database comprises” (Lee: fig 2 – Lee teaches not only entity types, but also SQL query statement) ,
“for each of the one or more entity types extracted from the first statement in the first database query, extracting corresponding ones of the one or more entity names from the result obtained from executing the first database query” (Lee: fig 2, fig 3C – Lee teaches SQL query statement); and
“for each of the one or more entity types extracted from the second statement in the first database query, extracting corresponding ones of the one or more entity names from the second statement” (Lee: fig 2, fig 3C-3D, 0047-0049).
As to Claim 5,15,19, the combination of Lee, Chang, Song disclosed “wherein the first database query comprises a Structured Query Language (SQL) query, (Lee: fig 2 – Lee teaches SQL statement(s)) wherein extracting the one or more entity types from at least one of the first statement in the statement in the database query for selecting data from the target database and the second statement in the database query for filtering the result obtained from executing the database query comprises extracting the one or more entity types from at least one of a SELECT statement in the SQL query and a WHERE statement in the SQL query( Lee: fig 3C-3D, 0047-0049 – Lee teaches SELECT statement in the query corresponds to Lees fig 3D, element 332,340).
As to claim 6, the combination of Lee, Chang, Song disclosed “further comprising generating a weighted one-hot vector based on the one or more entity types, wherein a vector database maintains a plurality of vectors generated based on the plurality of user query templates, (Lee: fig 3B, 0039-0040)wherein retrieving the one or more query templates comprises querying the vector database with the weighted one-hot vector for one or more of the plurality of vectors most similar to the weighted one-hot vector” (Lee: fig 3B, 0039-0040,0043-0044) .
PNG
media_image13.png
164
248
media_image13.png
Greyscale
As to claim 7, the combination of Lee, Chang, Song disclosed “further comprising generating the plurality of user query templates based on a plurality of user queries and a corresponding plurality of database queries, wherein generating the plurality of user query templates comprises, for each user query of the plurality of user queries and corresponding database query from the plurality of database queries” (Lee: fig 3C-3D, 0047)
PNG
media_image11.png
136
218
media_image11.png
Greyscale
PNG
media_image12.png
87
227
media_image12.png
Greyscale
“extracting one or more entity types and names from the database query” (Lee: fig 2, 0029,0032-0033; and
“for each entity type and name of the one or more entity types and names extracted from the database query, determining one or more substrings of the user query to which the entity type and name corresponds (Lee: fig 2-3,0032-0033) and replacing the one or more substrings in the user query with a parameter corresponding to the type of the entity to generate a corresponding one of the plurality of user query templates” (Lee: fig 3C-3D)
PNG
media_image12.png
87
227
media_image12.png
Greyscale
PNG
media_image14.png
46
91
media_image14.png
Greyscale
As to claim 8, the combination of Lee, Chang, Song disclosed “wherein determining the one or more substrings of the user query comprises determining the one or more substrings based on at least one of identifying an exact match between the entity type and name and the one or more substrings, based on fuzzy matching of the entity and the one or more substrings, (Lee: 0015,0039) and based on generating a vector representation of the entity type and name and vector representations of substrings of the user query and determining a most similar one of the vector representations of the substrings of the user query to the vector representation of the entity type and name” (Lee: fig 3C, 0047-0048).
As to claim 9, the combination of Lee, Chang, Song disclosed “wherein extracting the one or more entity types and extracting the one or more entity names comprises extracting the one or more entity types and the one or more entity names from the first database query based on determining that the result of executing the first database query comprises an empty results set or a value or zero” (Lee: 0039-0040, fig 3B).
As to claim 10, the combination of Lee, Chang, Song disclosed “further comprising, based on determining that no entity types and names can be extracted from the first database query, retrieving one or more predefined follow up questions and responding to the first user query with a second response comprising the one or more predefined follow up questions “ (Lee: fig 2 natural language chat(s); Chang : fig 2, 4, 0045,0048-0049)
As to claim 10, the combination of Lee, Chang, Song disclosed “further comprising, based on determining that no entity types and names can be extracted from the first database query, retrieving one or more predefined follow up questions and responding to the first user query with a second response comprising the one or more predefined follow up questions.“ (Lee: fig 2 natural language chat(s); Chang: fig 8, 0082-0084)
As to claim 11, the combination of Lee, Chang, Song disclosed “wherein the first database query representing the first user query was generated by a first language model based on the first user query, and wherein responding to the first user query comprises prompting a second language model to rephrase each of the one or more follow up queries and responding to the first user query with the rephrased one or more follow up queries” (Chang: 0055,0058,0060,0066, fig 2, 0075,0078).
As to claim 12, the combination of Lee, Chang, Song disclosed “wherein the first database query indicates a first table of the database, and wherein each of the one or more user query templates corresponds to the first table of the database” (Lee: fig 2-3C-3D). On the other hand, Chang disclosed “target database” (Chang: Abstract, fig 1,0032,0036)
As to Claim 16,20, the combination of Lee, Chang, Song disclosed
“wherein the instructions to extract the one or more entity types from the database query comprise instructions to extract the one or more entity types from a SQL WHERE statement of the database query” (Lee: fig 2, element 212,222, 232)
PNG
media_image6.png
219
183
media_image6.png
Greyscale
“and wherein the instructions to extract the one or more entity names corresponding to the one or more entity types from the result of executing the database query comprise instructions to extract the one or more entity names from the result of executing the database query” (Lee: fig 2 – Lee teaches not only entity types, but also SQL query statement).
Conclusion
The prior art made of record
a. US Pub. No. 2023/0097443
b. US Pub. No. 2017/0177660
c. US Pub. No 2024/0078230
Examiner's Note: Examiner has cited particular columns and line numbers in the references applied to the claims above for the convenience of the applicant. Although the specified citations are representative of the teachings of the art and are applied to specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant in preparing responses, to fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the Examiner.
SEE MPEP 2141.02 [R-5] VI. PRIOR ART MUST BE CONSIDERED IN ITS ENTIRETY, INCLUDING DISCLOSURES THAT TEACH AWAY FROM THE CLAIMS: A prior art reference must be considered in its entirety, i.e., as a whole, including portions that would lead away from the claimed invention. W.L. Gore & Associates, Inc. v. Garlock, Inc., 721 F.2d 1540, 220 USPQ 303 (Fed. Cir. 1983), cert. denied, 469 U.S. 851 (1984) In re Fulton, 391 F.3d 1195, 1201,73 USPQ2d 1141, 1146 (Fed. Cir. 2004). >See also MPEP §2123.
In the case of amending the Claimed invention, Applicant is respectfully requested to indicate the portion(s) of the specification which dictate(s) the structure relied on for proper interpretation and also to verify and ascertain the metes and bounds of the claimed invention.
The prior art made of record, listed on form PTO-892, and not relied upon, if any, is considered pertinent to applicant's disclosure
Authorization for Internet Communications
The examiner encourages Applicant to submit an authorization to communicate with the examiner via the Internet by making the following statement (from MPEP 502.03):
“Recognizing that Internet communications are not secure, I hereby authorize the USPTO to communicate with the undersigned and practitioners in accordance with 37 CFR 1.33 and 37 CFR 1.34 concerning any subject matter of this application by video conferencing, instant messaging, or electronic mail. I understand that a copy of these communications will be made of record in the application file.”
Please note that the above statement can only be submitted via Central Fax (not Examiner's Fax), Regular postal mail, or EFS Web using PTO/SB/439
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Srirama Channavajjala whose telephone number is 571-272-4108. The examiner can normally be reached on Monday-Friday from 8:00 AM to 5:30 PM Eastern Time.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Gorney, Boris, can be reached on (571) 270- 5626. The fax phone numbers for the organization where the application or proceeding is assigned is 571-273-8300 Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free)
/Srirama Channavajjala/Primary Examiner, Art Unit 2154