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 .
Continued Examination Under 37 CFR 1.114
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 5/26/2026 has been entered.
Claims 1, 3-12, 14-21 are pending.
Claims 2, 13 are cancelled.
Response to Arguments
Applicant’s arguments with respect to the rejections previously made and the amended claims filed on 5/26/2026 have been fully considered. In view of the amendment filed, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made.
Claim objections
In view of the amendment filed on 5/26/2026, the objections as set forth in the previous office action hereby withdrawn.
35 USC 103 Rejections
Applicant’s arguments on cited references of Zhang and Telling with respect to the amended claim 1-- and similar limitations are also recited in claims 11-12-- have been fully considered.
In response to the arguments, it is submitted that whether disclose Zhang discloses “ “receiving a selection of data relating to a previously performed task from the user” or not is irrelevant. Nowhere in claim 1 (or any of the pending claims) recite the limitation of “receiving, from the user, a selection of data relating to a previously performed task”, and hence it is not required to be taught by Zhang, or any prior art, nor required to be addressed.
The newly added limitation “wherein the analysis history represents a previously performed analysis task” merely describes that the analysis history is related to a previously performed analysis task by representing the previously performed analysis task, and such relationship does not impact any of the functionalities of the claimed steps. All the steps (i.e. receiving, determining, generating, inputting, executing, transmitting) would be performed the same regardless of whether the analysis history represents a previously performed analysis task or not. None of the claimed steps requires any usage of the previously performed analysis task.
Also, the limitation of “receiving, from a user terminal, a user input indicating a selection of an analysis history displayed on a user interface and comprises the natural language query requesting the data analysis” recited in claim 1 is different from “receiving, from the user, a selection of data relating to a previously performed task”. The claimed limitation of “receiving, from a user terminal, a user input indicating a selection of an analysis history displayed …the data analysis” merely requires an input that indicates a selection, and that indication may be data material that indicates a selection of an analysis history displayed. Such required indication is not limited to--nor required to-a selection of data relating to a previously performed task, or the a previously executed structured query language (SQL) statement, nor a result of the previously executed SQL statement.
Plus, nowhere in claim recite any limitation on “data regarding a previously performed analysis task can be selected through the GUI”, and hence it is not required to be taught by Zhang or any prior art, nor required to address.
In addition, nowhere in the claim recite any limitation on performing a current analysis task using a previously performed data analysis task or data related thereto”, and hence it is not required to be taught by Zhang or any prior art, nor required to be addressed.
Additionally, regarding the newly added limitations of “analysis history displayed on the
user interface includes a previously executed structured query language (SQL) statement and a result of the previously executed SQL statement” and "the analysis history represents a previously performed analysis task" as recited in claim 1, it is submitted that these limitations are directed to nonfunctional descriptive material and are not functionally involved in the steps recited. All the steps (i.e. receiving, determining, generating, inputting, executing, transmitting) would be performed the same regardless of (i) whether discloses the analysis history displayed on the user interface includes a previously executed structured query language (SQL) statement and a result of the previously executed SQL statement or not, and (ii) whether the analysis history represents a previously performed analysis task or not. None of the claimed steps requires any usage of the previously executed structured query language (SQL) statement, the result of previously executed SQL statement, or the previously performed analysis task. Thus, it would have been obvious to one skilled in the art before the effective filing date of the claimed invention to include any type of information in the analysis history, and have the analysis history represent any type of information because such data does not functionally relate to the steps in the claim, and also because the subjective interpretation of the data does not patentably distinguish the claimed invention.
Further it is submitted that all limitations in the amended claim 1 are properly addressed by the new ground of rejection; see rejection below for detail.
Furthermore, it is submitted that all limitations in claims--including those not specifically addressed in the Applicant’s remarks--are properly addressed. The reason is set forth in the rejections; see below for detail.
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.
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, 3-12, 14-21 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al (Pub No. US 2025/0190449 hereinafter Zhang) in view of Telling et al (Pub No. US 2025/0094439, hereinafter Telling), and further in view of Freschil et al (Pub No.US 2017/0039128, hereinafter Freschil).
Zhang and Telling are cited in the previous office action.
With respect to claim 1, Zhang discloses a method of performing data analysis according to a natural language query from a user (abstract), the method comprising:
receiving, from a user terminal, a user input indicating a selection of an analysis history displayed on a user interface and comprises the natural language query requesting the data analysis ([0004], [0031], Fig 1 & 12: receive a user input represented by a prompt—e.g. prompt 170-- indicates a selection of analysis history display on a graphical user interface 174. The user input includes but not limited to indication of user preference for an analysis history as further described in [0044], and a natural language query represented by a natural language question requesting the data analysis via question submission);
determining, based on the user input, at least one database among a plurality of databases as a target database ([0004], [0033-0035], [0049], [0071], Fig 2-4: determine at least one database represented by at least one structured data set as a target database/data set among multiple databases/datasets, as each data set is corresponded to a database);
generating a prompt based on the user input and the target database ([0004],[0008], [0035], [0038], [0049], [0071], Fig 5-7: generate a prompt represented by a modified prompt based on user input prompt and the target data set/database according to at least structure/field of data set analysis);
inputting the prompt into a code generation model to obtain an SQL statement ([0040], [0053], [0055], [0077-0078], Fig 7: input the prompt into a code generation model such as and not limited to a SQL agent to obtain a SQL statement as the SQL agent processes received modified prompt via performing text to SQL query);
executing the SQL statement to generate a result of the data analysis on the target database ([0078], [0090], [0093-0094], Fig 7 & 11-12: execute the SQL statement to generate result of the data analysis as the SQL performs SQL over the SQL database/dataset to obtain response correspond to the result); and
transmitting the result of the data analysis to the user terminal, wherein the result of the data analysis is displayed on a screen of the user terminal ([0005], [0045], [0090], [0093-0094] Fig 2 & 10 & 11-12: transmitting the result of the data analysis as the obtained response is being displayed to the user via screen of a GUI, and further allowing the user to provide feedback accordingly).
Zhang does not explicitly disclose that the user input is directed to a first user input and a second user input; the analysis history displayed on the user interface includes a previously executed structured query language (SQL) statement and a result of the previously executed SQL statement; the at least one database determination is based on the first user input and second user input; and the prompt is generated based on the first user input, second user input and the target database; and wherein the analysis history represents a previously performed analysis task as claimed.
However, Telling discloses receiving, from a user terminal, a first user input indicating a selection of an analysis history displayed on a user interface and a second user input that comprises the natural language query requesting the data analysis ([0095-0096], [0107], [0140], Fig 8: receive a first user input indicating a user selection of data set corresponding an analysis history displayed on a user interface since analysis is directed to a type of data, and receive a second input of a natural language query request data analysis via a LLM as further described in [0054] & [0058]);
determining, based on the first user input and the second user input, at least one database among a plurality of databases as a target database ([0096-0097], [0141-0142], Fig 8: determine at least a database represented by a dataset among the datasets as target database, which is correspond to the dataset, as further described in [0051], [0064]);
generating a prompt based on the first user input, the second user input, and the target database ([0096], [00140], Fig 8: generate a prompted based on the 1st & 2nd user inputs and the target database represented by at least the dataset via indication);
Since both Zhang and Telling are from the same field of because both directed to performing data analysis according to natural language query from a user, which is in the same field of endeavor as the claimed invention, it would have been obvious to one skilled in the art at the time of the invention to combine their teachings by incorporate the first input indicating a user selection and a second input comprises a user natural language query user and of Telling into Zhang for analysis result generation as claimed. The motivation to combine is to optimize user request processing with intelligently perform analytic tasks while minimize effort required by human users (Zhang, [0001]; Telling, [0005).
Neither Telling, nor the combination with Zhang, explicitly discloses the analysis history displayed on the user interface includes a previously executed structured query language (SQL) statement and a result of the previously executed SQL statement; and wherein the analysis history represents a previously performed analysis task as claimed.
However, these differences are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. All the steps (i.e. receiving, determining, generating, inputting, executing, transmitting) would be performed the same regardless of (i) whether discloses the analysis history displayed on the user interface includes a previously executed structured query language (SQL) statement and a result of the previously executed SQL statement or not, and (ii) whether the analysis history represents a previously performed analysis task or not. None of the claimed steps requires any usage of the previously executed structured query language (SQL) statement, the result of previously executed SQL statement, or the previously performed analysis task. Therefore, it would have been obvious to one skilled in the art before the effective filing date of the claimed invention to include any type of information in the analysis history, and have the analysis history represent any type of information because such data does not functionally relate to the steps in the claim, and also because the subjective interpretation of the data does not patentably distinguish the claimed invention.
Also, Freschil discloses the analysis history displayed on the user interface includes a previously executed structured query language (SQL) statement and a result of the previously executed SQL statement ([0090-0091], Fig 5 & 9: the analysis history represented by the displayed log includes previously executed SQL and a result of the SQL, including but not limited t the difference); and wherein the analysis history represents a previously performed analysis task ([0092], Fig 6-9: the log correspond to the analysis history represent represented a preciously preformed analysis task at least as set forth by the previously SQL):
Since Zhang, Telling and Freschi are from the same field of because all directed to performing data analysis according to user request, which is in the same field of endeavor as the claimed invention, it would have been obvious to one skilled in the art at the time of the invention to combine their teachings by incorporate the analysis history with different types of data information of Freschi into Zhang and Telling for analysis result generation as claimed. The motivation to combine is to optimize user request processing with intelligently perform analytic tasks while minimize effort required by human users and enhance database performance (Zhang, [0001]; Telling, [0005]; Freschi, [0005]).
With respect to claim 12, Zhang discloses an electronic device for performing data analysis according to a natural language query from a user (Abstract, Fig 1), the electronic device comprising:
memory storing one or more instructions ([0111], Fig 1); and
at least one processor operatively coupled to the memory, wherein the one or more instructions, when executed by the at least one processor ([0109-0111], Fig 1), cause the electronic device to:
receiving, from a user terminal, a user input indicating a selection of an analysis history displayed on a user interface and comprises the natural language query requesting the data analysis ([0004], [0031], Fig 1 & 12: receive a user input represented by a prompt—e.g. prompt 170-- indicates a selection of analysis history display on a graphical user interface 174. The user input includes but not limited to indication of user preference for an analysis history as further described in [0044], and a natural language query represented by a natural language question requesting the data analysis via question submission);
determining, based on the user input, at least one database among a plurality of databases as a target database ([0004], [0033-0035], [0049], [0071], Fig 2-4: determine at least one database represented by at least one structured data set as a target database/data set among multiple databases/datasets, as each data set is corresponded to a database);
generating a prompt based on the user input and the target database ([0004],[0008], [0035], [0038], [0049], [0071], Fig 5-7: generate a prompt represented by a modified prompt based on user input prompt and the target data set/database according to at least structure/field of data set analysis);
inputting the prompt into a code generation model to obtain an SQL statement ([0040], [0053], [0055], [0077-0078], Fig 7: input the prompt into a code generation model such as and not limited to a SQL agent to obtain a SQL statement as the SQL agent processes received modified prompt via performing text to SQL query);
executing the SQL statement to generate a result of the data analysis on the target database ([0078], [0090], [0093-0094], Fig 7 & 11-12: execute the SQL statement to generate result of the data analysis as the SQL performs SQL over the SQL database/dataset to obtain response correspond to the result); and
transmitting the result of the data analysis to the user terminal, wherein the result of the data analysis is displayed on a screen of the user terminal ([0005], [0045], [0090], [0093-0094] Fig 2 & 10 & 11-12: transmitting the result of the data analysis as the obtained response is being displayed to the user via screen of a GUI, and further allowing the user to provide feedback accordingly).
Zhang does not explicitly disclose that the user input is directed to a first user input and a second user input; the analysis history displayed on the user interface includes a previously executed structured query language (SQL) statement and a result of the previously executed SQL statement; the at least one database determination is based on the first user input and second user input; and the prompt is generated based on the first user input, second user input and the target database; and wherein the analysis history represents a previously performed analysis task as claimed.
However, Telling discloses receiving, from a user terminal, a first user input indicating a selection of an analysis history displayed on a user interface and a second user input that comprises the natural language query requesting the data analysis ([0095-0096], [0107], [0140], Fig 8: receive a first user input indicating a user selection of data set corresponding an analysis history displayed on a user interface since analysis is directed to a type of data, and receive a second input of a natural language query request data analysis via a LLM as further described in [0054] & [0058]);
determining, based on the first user input and the second user input, at least one database among a plurality of databases as a target database ([0096-0097], [0141-0142], Fig 8: determine at least a database represented by a dataset among the datasets as target database, which is correspond to the dataset, as further described in [0051], [0064]);
generating a prompt based on the first user input, the second user input, and the target database ([0096], [00140], Fig 8: generate a prompted based on the 1st & 2nd user inputs and the target database represented by at least the dataset via indication);
Since both Zhang and Telling are from the same field of because both directed to performing data analysis according to natural language query from a user, which is in the same field of endeavor as the claimed invention, it would have been obvious to one skilled in the art at the time of the invention to combine their teachings by incorporate the first input indicating a user selection and a second input comprises a user natural language query user and of Telling into Zhang for analysis result generation as claimed. The motivation to combine is to optimize user request processing with intelligently perform analytic tasks while minimize effort required by human users (Zhang, [0001]; Telling, [0005).
Neither Telling, nor the combination with Zhang, explicitly discloses the analysis history displayed on the user interface includes a previously executed structured query language (SQL) statement and a result of the previously executed SQL statement; and wherein the analysis history represents a previously performed analysis task as claimed.
However, these differences are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. All the steps (i.e. receiving, determining, generating, inputting, executing, transmitting) would be performed the same regardless of (i) whether discloses the analysis history displayed on the user interface includes a previously executed structured query language (SQL) statement and a result of the previously executed SQL statement or not, and (ii) whether the analysis history represents a previously performed analysis task or not. None of the claimed steps requires any usage of the previously executed structured query language (SQL) statement, the result of previously executed SQL statement, or the previously performed analysis task. Therefore, it would have been obvious to one skilled in the art before the effective filing date of the claimed invention to include any type of information in the analysis history, and have the analysis history represent any type of information because such data does not functionally relate to the steps in the claim, and also because the subjective interpretation of the data does not patentably distinguish the claimed invention.
Also, Freschil discloses the analysis history displayed on the user interface includes a previously executed structured query language (SQL) statement and a result of the previously executed SQL statement ([0090-0091], Fig 5 & 9: the analysis history represented by the displayed log includes previously executed SQL and a result of the SQL, including but not limited t the difference); and wherein the analysis history represents a previously performed analysis task ([0092], Fig 6-9: the log correspond to the analysis history represent represented a preciously preformed analysis task at least as set forth by the previously SQL):
Since Zhang, Telling and Freschi are from the same field of because all directed to performing data analysis according to user request, which is in the same field of endeavor as the claimed invention, it would have been obvious to one skilled in the art at the time of the invention to combine their teachings by incorporate the analysis history with different types of data information of Freschi into Zhang and Telling for analysis result generation as claimed. The motivation to combine is to optimize user request processing with intelligently perform analytic tasks while minimize effort required by human users and enhance database performance (Zhang, [0001]; Telling, [0005]; Freschi, [0005]).
With respect to claims 3 and 14, the combined teachings of Zhang, Telling and Freschi further discloses wherein the determining of the at least one database as the target database comprises:
determining, by using a similarity determination model, a degree of similarity between at least one natural language query related to the selected analysis history and the received natural language query and metadata of each of the plurality of databases (Zhang, [0034], [0039-0040], [0051], [0069-0070], [0080-0081]; Freschi, [0021], [0037-0038]: determine a degree of similarity between the natural language query related to selected history, receive and the data set attribute/metadata as the received prompt is being optimized and at least one agent with respect to historical information); and
determining, based on a result of the determining of the degree of similarity, at least one of the plurality of databases as the target database (Zhang, [0071-0073], [0081]; Freschi, [0021]: determine at least one data set as the target based on the result of similarity determination via AI agent that accesses the target data set via score with respect to the similarity).
With respect to claims 4 and 15, the combined teachings of Zhang, Telling and Freschi further discloses wherein the metadata comprises a table catalog and a table schema, the table catalog comprises a description of a table included in a database corresponding to the metadata and a description of each column in the table, and the table schema defines a structure and rules of the table included in the database corresponding to the metadata (the limitations are directed to non-functional descriptive materials that are not necessary being used to impact the functionalities of the claimed steps, and all claimed steps would be performed the same regardless; Zhang, [0035], [0041], [0049], [0059]; Telling, [0051-0052], [0071], [0090]; Freschi,[0037-0038]: the metadata comprises table catalog and table schema represented by the schema descriptions having fields of tables that define the structure of the table of the database with respect rules).
With respect to claims 5 and 16, the combined teachings of Zhang, Telling, Freschi further discloses wherein the prompt comprises an analysis history-related portion and a current natural language query-related portion (Zhang, [0004], [0035], [0038-0039], [0048-0049], [0056], [0071], Fig 5-7; Telling, [0082], [0096], [0140]; Freschi, [0047-0048], [0071], [0089-0092], Fig 5-9: the modified prompt comprises different types of data included history related and query relation), and
the generating of the prompt comprises:
generating the analysis history-related portion by using metadata of a database related to the selected analysis history, a natural language query related to the selected analysis history, and an SQL statement related to the selected analysis history (Zhang, [0004],[0008], [0035], [0038], [0041], [0049], [0071], Fig 5-7; Telling, [0067], [0095-0096], [0140]; Freschi, [0047-0048], [0071], [0089-0092], Fig 5-9: generate the history related portion by using data set schema description, and past queries, such as SQL with AI SQL agent, via prompt optimization) :; and
generating the current natural language query-related portion by using metadata of the target database and the received natural language query (Zhang, [0004], [0008], [0035], [0038], [0041], [0049], [0071], Fig 5-7: Telling, [0067], [0095-0096], [0140]; Freschi, [0047-0048], [0071], [0089-0092], Fig 5-9: generate the current natural language portion using metadata represented by the field of data set and receive query via prompt optimization and AI agent selection).
With respect to claims 6 and 17, the combined teachings of Zhang, Telling, and Freschi further discloses wherein the database related to the selected analysis history is a database used in performing at least one analysis task included in the selected analysis history (the limitation is directed to non-functional descriptive material that is not necessary being used to impact the functionalities of the claimed steps, and all claimed steps would be performed the same regardless; Zhang,[0034], [0039], [0051], [0069-0070], [0080-0081]; Telling, [0051-0053], [0095-0096]; Freschi, [0047-0048], [0071], [0089-0092], Fig 5-9: the dataset is related to the select analysis history via learning and similarity determination with respect to historical performance),
the natural language query related to the selected analysis history is a natural language query input in performing the at least one analysis task included in the selected analysis history (the limitation is directed to non-functional descriptive material that is not necessary being used to impact the functionalities of the claimed steps; every element in the system is related to others element in the same system/method either directly or indirectly, and all claimed steps would be performed the same regardless; Zhang,[0004],[0008], [0035], [0038], [0041], [0049], [0071], Fig 5- 7; Telling, [0095-0096], [0140]; Fig 8; Freschi, [0047-0048], [0071], [0089-0092], Fig 5-9: the natural query is a query input in performing the analysis via prompt optimization and/or AI agent assignment), and
the SQL statement related to the selected analysis history is an SQL statement generated by the code generation model in performing the at least one analysis task included in the selected analysis history (the limitation is directed to non-functional descriptive material that is not necessary being used to impact the functionalities of the claimed steps; every element in the system is related to others element in the same system/method either directly or indirectly, and all claimed steps would be performed the same regardless; Zhang, [0004],[0008], [0035], [0038], [0040-0041], [0049], [0053], [0055], [0071], [0077-0078], Fig 5- 7; Telling, [0051-0053], [0067], [0095-0096]; Freschi, [0047-0048], [0071], [0089-0092], Fig 5-9: the SQL is related to the analysis history and is a SQL generated by the code generated model represented by the selected AI SQL agent that is being selected with respect to history analysis).
With respect to claims 7 and 18, the combined teachings of Zhang, Telling and Freschi further discloses wherein each of the analysis history-related portion and the current natural language query-related portion comprises an instruction to generate an SQL statement corresponding to a natural language query by referring to metadata of at least one database from the plurality of databases (the limitation is directed to non-functional descriptive material that is not necessary being used to impact the functionalities of the claimed steps and all claimed steps would be performed the same regardless; Zhang, [0004],[0008], [0035], [0038], [0040-0041], [0049], [0053], [0055], [0071], [0077-0078], Fig 5- 7; Telling, [0051-0053], [0095-0096]; Freschi, [0047-0048], [0071], [0089-0092], Fig 5-9: the history related and the current query portion represented by the modified prompt include instruction to generate SQL statement as the modified prompt is being assigned to an AI SQL agent that access the dataset by referring to the metadata represented by the fields).
With respect to claims 8 and 19, the combined teachings of Zhang, Telling and Freschi further discloses wherein the analysis history comprises at least one analysis task previously performed on at least one database among the plurality of databases (the limitation is directed to non-functional descriptive material that is not necessary being used to impact the functionalities of the claimed steps and all claimed steps would be performed the same regardless; Zhang, [0004],[0008], [0035], [0038], [0040-0041], [0049], [0053], [0055], [0071], [0077-0078], Fig 5- 7; Telling, [0067], [0095-0096]; Freschi, [0089-0092], Fig 5-9 : the analysis history include analysis of past queries performance and/or performance of the dataset via prompt optimization and AI agent assignment with a learning process).
With respect to claims 9 and 20, the combined teachings of Zhang, Telling and Freschi further discloses wherein the outputting of the result of the data analysis comprises
generating a prompt for visualizing the result of the data analysis by using the received natural language query and the generated SQL statement (Zhang, [0043-0045], [0083], [0090], [0093-0094]; Telling, [0096], [0140], [0143], Fig 8; Freschi, [0047-0048], [0071], [0089-0092], Fig 5-9: generate a prompt represented by instructions for visualizing/presenting the result using the query obtained from the SQL statement execution via AI SQL agent);
obtaining a visualization code by inputting the prompt for visualizing the result of the data analysis to the code generation model (Zhang, [0043-0045], [0083], [0090], [0093-0094]; Telling, [0096], [0140], [0143], Fig 8; Freschi, [0047-0048], [0071], [0089-0092], Fig 5-9: input the prompt for visualization as the result and visualization are being processed via AI); and
visualizing and outputting the result of the data analysis as at least one of a graph or a chart by executing the visualization code (Zhang, [0043-0045], [0083], [0090], [0093-0094]; Telling, [0140], [0143], Fig 8: visualizing and outputting the result in a particular format by executing the code/instruction).
With respect to claim 10 the combined teachings of Zhang, Telling and Freschi further discloses wherein the prompt for visualizing the result of the data analysis comprises an instruction to generate the visualization code corresponding to the received natural language query by referring to the generated SQL statement (Zhang, [0043-0045], [0083], [0090], [0093-0094]; Telling, [0096], [0140], [0143], Fig 8; Freschi, [0047-0048], [0071], [0089-0092], Fig 5-9: configure to generate the visualization/outputting instruction/code via referring the SQL statement as the visualization agent generate a graph or other visualization output based on the SQL execution).
With respect to claim 11, Zhang discloses a non-transitory computer-readable storage medium having instructions stored therein, which when executed by a processor (abstract, [0109-0111], Fig 1), cause the processor to execute a method comprising:
receiving, from a user terminal, a user input indicating a selection of an analysis history displayed on a user interface and comprises the natural language query requesting the data analysis ([0004], [0031], Fig 1 & 12: receive a user input represented by a prompt—e.g. prompt 170-- indicates a selection of analysis history display on a graphical user interface 174. The user input includes but not limited to indication of user preference for an analysis history as further described in [0044], and a natural language query represented by a natural language question requesting the data analysis via question submission);
determining, based on the user input, at least one database among a plurality of databases as a target database ([0004], [0033-0035], [0049], [0071], Fig 2-4: determine at least one database represented by at least one structured data set as a target database/data set among multiple databases/datasets, as each data set is corresponded to a database);
generating a prompt based on the user input and the target database ([0004],[0008], [0035], [0038], [0049], [0071], Fig 5-7: generate a prompt represented by a modified prompt based on user input prompt and the target data set/database according to at least structure/field of data set analysis);
inputting the prompt into a code generation model to obtain an SQL statement ([0040], [0053], [0055], [0077-0078], Fig 7: input the prompt into a code generation model such as and not limited to a SQL agent to obtain a SQL statement as the SQL agent processes received modified prompt via performing text to SQL query);
executing the SQL statement to generate a result of the data analysis on the target database ([0078], [0090], [0093-0094], Fig 7 & 11-12: execute the SQL statement to generate result of the data analysis as the SQL performs SQL over the SQL database/dataset to obtain response correspond to the result); and
transmitting the result of the data analysis to the user terminal, wherein the result of the data analysis is displayed on a screen of the user terminal ([0005], [0045], [0090], [0093-0094] Fig 2 & 10 & 11-12: transmitting the result of the data analysis as the obtained response is being displayed to the user via screen of a GUI, and further allowing the user to provide feedback accordingly).
Zhang does not explicitly disclose that the user input is directed to a first user input and a second user input; the analysis history displayed on the user interface includes a previously executed structured query language (SQL) statement and a result of the previously executed SQL statement; the at least one database determination is based on the first user input and second user input; and the prompt is generated based on the first user input, second user input and the target database; and wherein the analysis history represents a previously performed analysis task as claimed.
However, Telling discloses receiving, from a user terminal, a first user input indicating a selection of an analysis history displayed on a user interface and a second user input that comprises the natural language query requesting the data analysis ([0095-0096], [0107], [0140], Fig 8: receive a first user input indicating a user selection of data set corresponding an analysis history displayed on a user interface since analysis is directed to a type of data, and receive a second input of a natural language query request data analysis via a LLM as further described in [0054] & [0058]);
determining, based on the first user input and the second user input, at least one database among a plurality of databases as a target database ([0096-0097], [0141-0142], Fig 8: determine at least a database represented by a dataset among the datasets as target database, which is correspond to the dataset, as further described in [0051], [0064]);
generating a prompt based on the first user input, the second user input, and the target database ([0096], [00140], Fig 8: generate a prompted based on the 1st & 2nd user inputs and the target database represented by at least the dataset via indication);
Since both Zhang and Telling are from the same field of because both directed to performing data analysis according to natural language query from a user, which is in the same field of endeavor as the claimed invention, it would have been obvious to one skilled in the art at the time of the invention to combine their teachings by incorporate the first input indicating a user selection and a second input comprises a user natural language query user and of Telling into Zhang for analysis result generation as claimed. The motivation to combine is to optimize user request processing with intelligently perform analytic tasks while minimize effort required by human users (Zhang, [0001]; Telling, [0005).
Neither Telling, nor the combination with Zhang, explicitly discloses the analysis history displayed on the user interface includes a previously executed structured query language (SQL) statement and a result of the previously executed SQL statement; and wherein the analysis history represents a previously performed analysis task as claimed.
However, these differences are only found in the nonfunctional descriptive material and are not functionally involved in the steps recited. All the steps (i.e. receiving, determining, generating, inputting, executing, transmitting) would be performed the same regardless of (i) whether discloses the analysis history displayed on the user interface includes a previously executed structured query language (SQL) statement and a result of the previously executed SQL statement or not, and (ii) whether the analysis history represents a previously performed analysis task or not. None of the claimed steps requires any usage of the previously executed structured query language (SQL) statement, the result of previously executed SQL statement, or the previously performed analysis task. Therefore, it would have been obvious to one skilled in the art before the effective filing date of the claimed invention to include any type of information in the analysis history, and have the analysis history represent any type of information because such data does not functionally relate to the steps in the claim, and also because the subjective interpretation of the data does not patentably distinguish the claimed invention.
Also, Freschil discloses the analysis history displayed on the user interface includes a previously executed structured query language (SQL) statement and a result of the previously executed SQL statement ([0090-0091], Fig 5 & 9: the analysis history represented by the displayed log includes previously executed SQL and a result of the SQL, including but not limited t the difference); and wherein the analysis history represents a previously performed analysis task ([0092], Fig 6-9: the log correspond to the analysis history represent represented a preciously preformed analysis task at least as set forth by the previously SQL):
Since Zhang, Telling and Freschi are from the same field of because all directed to performing data analysis according to user request, which is in the same field of endeavor as the claimed invention, it would have been obvious to one skilled in the art at the time of the invention to combine their teachings by incorporate the analysis history with different types of data information of Freschi into Zhang and Telling for analysis result generation as claimed. The motivation to combine is to optimize user request processing with intelligently perform analytic tasks while minimize effort required by human users and enhance database performance (Zhang, [0001]; Telling, [0005]; Freschi, [0005]).
With respect to claim 21, the combined teachings of Zhang, Telling and Freschi further discloses wherein the prompt includes the natural language query, data corresponding to the selected analysis history, and metadata of the target database (the limitation is directed to non-functional descriptive material that is not necessary being used to impact the functionalities of the claimed steps, and all claimed steps would be performed the same regardless; Zhang, [0004], [0035], [0038-0039], [0048-0049], [0056], [0071], Fig 5-7; Telling, [0096], [0140]; Freschi, [0047-0048], [0071], [0089-0092], Fig 5-9: the prompt includes different type of data that correspond to the query, data and metadata represented by the features).
Examiner Note
Examiner has cited particular columns/paragraph 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.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Michelle Owyang whose telephone number is (571)270-1254. The examiner can normally be reached Monday-Friday, 8am-6pm EST.
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, Charles Rones can be reached at (571)272-4085. 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.
/MICHELLE N OWYANG/Primary Examiner, Art Unit 2168
Prosecution Insights