DETAILED ACTION
Applicant has amended claims 1, 3-4, 7, 9, 13, 15 in the filed amendment on 10/18/2025.
Claims 1-18 are pending in this office action.
Response to Arguments
Applicant’s arguments with respect to claim(s) 1-18 have been considered but are moot in new ground of rejection.
For 101 rejection:
Applicant argued that claims 1, 7, 13 have been amended; thus, 101 rejection should be withdrawn.
Examiner respectfully disagrees.
At step 2A Prong One:
Claims 1, 7, 13 recite abstract limitations
generate a query plan in natural language format;
generate a large language model ("LLM") input based on the natural language format of the query plan;
execute an LLM on the LLM input;
generate, in response to execution of the LLM, a plurality of recommended actions to perform to improve the query plan;
alter the query plan in accordance with the at least one of the plurality of recommended actions) are directed to judicial exception of mental processes. One can mentally select an application and as drafted, is a process or system or medium that, under its broadest reasonable interpretation, covers performance of the limitations in the mind but for the recitation of generic computer components. 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” grouping of abstract ideas. The human mind can perform step of generating, generating, executing, generating and altering. Accordingly, the claims recite an abstract idea.
At step 2A Prong Two:
The claims do not include additional elements that integrate the judicial exception into a practical application because additional elements of a storage device, a plurality of processing nodes, at least one of the processing nodes (in claim 1); a processor, a storage device (in claim 7) and a storage device, instructions (in claim 13) that are recited at a high-level of generality such that it amounts no more than mere instructions to apply the exception using a generic computer component for obtaining that are well understood routine and conventional activities;
the additional limitation of (wherein the natural language format of the query plan comprises a system-generated natural language description of the query plan) that just define definition of the natural language format of the query plan including description of the query plan; and
the additional limitations of (store a plurality of data; receive a query on at least a portion of the data; receive input to execute at least one of the plurality of recommended actions) in claim 1; and (receiving a query on at least a portion of data stored in a storage device; receiving input to execute at least one of the plurality of recommended actions) in claims 7, 13 are insignificant extra solution activities which are well understood routine and conventional activities, see (Presenting offers and gathering statistics, OIP Techs and Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec) and See (MPEP 2106.05(g) or 2106.05(d) for Receiving or transmitting data over a network, e.g. see Intellectual Ventures v. Symantec; Storing and retrieving information in memory: Versata; Analyzing data: Genetic Techs; Determining: OIP Techs; Electronic recordkeeping: Alice Corp).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
At step 2B:
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because additional elements of a storage device, a plurality of processing nodes, at least one of the processing nodes (in claim 1); a processor, a storage device (in claim 7) and a storage device, instructions (in claim 13) that are recited at a high-level of generality such that it amounts no more than mere instructions to apply the exception using a generic computer component for obtaining that are well understood routine and conventional activities;
the additional limitation of (wherein the natural language format of the query plan comprises a system-generated natural language description of the query plan) that just define definition of the natural language format of the query plan including description of the query plan; and
the additional limitations of (store a plurality of data; receive a query on at least a portion of the data; receive input to execute at least one of the plurality of recommended actions) in claim 1; and (receiving a query on at least a portion of data stored in a storage device; receiving input to execute at least one of the plurality of recommended actions) in claims 7, 13 are insignificant extra solution activities which are well understood routine and conventional activities, see (Presenting offers and gathering statistics, OIP Techs and Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec) and See (MPEP 2106.05(g) or 2106.05(d) for Receiving or transmitting data over a network, e.g. see Intellectual Ventures v. Symantec; Storing and retrieving information in memory: Versata; Analyzing data: Genetic Techs; Determining: OIP Techs; Electronic recordkeeping: Alice Corp).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. The claims are not patent eligible.
As discussed above, claims 1-18 directed to an abstract idea; thus 101 rejection for claims is still maintained in this office action.
For 103 rejection:
Applicant argued that none of the prior arts of the record teach “wherein the natural language format of the query plan comprises a system-generated natural language description of the query plan”.
In response to Applicant’s argument, claims are rejected in new ground of rejection.
In addition, Ba teaches limitations
“receive a query on at least a portion of the data” as receive a query (abstract, paragraphs 48, 70, 169-170), the query is executed on one or more data resources 134 to retrieve facet values from the one or more data sources (paragraph 61), the facet values of one or more data resources is represented as a portion of data;
“generate a query plan……” as generate a query plan in (abstract, paragraph 54, fig. 1A) a set of functions, the set of functions are executable using a set of data resources to create a modified version of the initial query (paragraph 25);
“generate a large language model ("LLM") input based on……” as configure as generate a input classification prompt for larger language model (LLM) (paragraphs 48, 127) based on generator 112 (paragraphs 50-51) or resources (paragraph 102). An input classification prompt for larger language model (LLM) is represented as a large language model ("LLM") input.
In particular, the input classification prompt generator 112 configures the input classification prompt as a zero-shot prompt (paragraph 50);
“execute an LLM on the LLM input” as process as execute a large language model on the input classification prompt as the LLM input (paragraphs 100-102) or applying the LLM on the prompt as the LLM input (fig. 7A, paragraphs 172-173).
For instance, when the large language model processes the input classification prompt 226, the large language model 116 only processes the selected instructions 222, e.g., only those instructions that are applicable to the possible intents 214 (paragraph 90).
For instance, when the large language model processes the plan generation prompt 338, the large language model 116 only reads data pertaining to the possible resources, e.g., only those data resources that are applicable to the possible functions 312, instead of the entire resource library 326 (paragraph 102);
“generate, in response to execution of the LLM,……” as obtain as generate, in response to applying the LLM at step 708 as in response to execution of the LLM, intent (fig. 7A, paragraphs 172-173);
“receive input to execute ……” as receive input to perform an operation using input (paragraph 142).
Bossman teaches limitations
a plurality of recommended actions to perform to improve the query plan (as generate optimization hints as a plurality of recommended actions to produce modified access plan having improved performance over the base access plan: paragraphs 14, 42).
In particularly, the analysis of the determined performance problems resulting from the second analysis and the generated recommendations are processed to generate optimization hints, wherein the optimization hints indicate modifications to the base access plan to produce a modified access plan having improved performance over the base access plan. A user interface providing a visualization of the optimization hints is generated (paragraph 14);
“at least one of the plurality of recommended actions” as receive input (paragraph 30, 37) or user selected hint(s) entered through visual plan hint component 60 to valid the selected hint of the hints as at least one of the plurality of recommended actions (paragraph 41).
In particularly, the base access plan 34 adjusted with user selected hints entered through the visual plan hint component 60 may then be subject to validation by the estimates validator 56 to ensure that the optimization hint produces a modified plan that is accurate and complete. The estimates validator 56 may produce error feedback on the modification suggested by the hint, and provide suggestions for further modification for the user to review. The user may then invoke the visual plan hint 60 to make further changes until the desired access path is achieved (paragraph 41)
“alter the query plan in accordance with the at least one of the plurality of recommended actions” as adjust or tune as alter a plan for query (abstract) with a selected hint of hints (paragraphs 31, 41) that is used to modify the plan (paragraph 35) is represented as one of the plurality of recommended actions.
For instance, to develop meaningful optimization hints to modify a base access plan, the administrator would have to know the plan table structure, optimization hint constraints, and available access path choices, such as join methods, indexes to use (paragraph 35).
The visual plan hint 60 receives as input the plan table of the base access plan 34, and may provide a visualization in a GUI of the access plan. Further, the visual plan hint 60 may display in the GUI 66 optimization hints and other suggested modifications based on output from the estimates validator 56 and query advisor 58. Further the visual plan hint 60 can also receive administrator input. The visual plan hint 60 includes heuristics to determine optimization hints from the information from the estimates validator 56 and query advisor 58 to modify the base access plan 34. Further, the visual plan hint 60 may generate a user interface to allow the administrator to graphically modify the base access plan 34 (paragraph 37).
Bossman further teaches limitations
“receive a query on at least a portion of the data” as receive a search request on attributes in dimension tables to locate records in a fact table (paragraph 26);
generate a plurality of recommended actions to perform to improve the query plan (as generate optimization hints as a plurality of recommended actions to produce modified access plan having improved performance over the base access plan: paragraphs 14, 42);
“receive input to execute at least one of the plurality of recommended actions” as receive input (paragraph 30, 37) or user selected hint(s) entered through visual plan hint component 60 to valid the selected hint of the hints as recommended actions (paragraph 41).
In particularly, the base access plan 34 adjusted with user selected hints entered through the visual plan hint component 60 may then be subject to validation by the estimates validator 56 to ensure that the optimization hint produces a modified plan that is accurate and complete. The estimates validator 56 may produce error feedback on the modification suggested by the hint, and provide suggestions for further modification for the user to review. The user may then invoke the visual plan hint 60 to make further changes until the desired access path is achieved (paragraph 41).
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-18 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
The limitation “wherein the natural language format of the query plan comprises a system-generated natural language description of the query plan” in claims 1, 7, 13 was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed.
Remark: According to paragraph 6 of the publication of the instant application “generating, with the processor, a query plan in natural language format. The method may further include generating, with the processor, a large language model (“LLM”) input based on the natural language format of the query plan. The method may further include executing, with the processor, an LLM on the LLM input. The method may further include generating, with the processor, in response to execution of the LLM, a plurality of recommended actions to perform to improve the query plan”, a query plan in natural language format is generated, but the format the natural language format of the query plan does not comprises “a system-generated natural language description of the query plan”.
Dependent claims 2-6, 8-12, 14-18 of claims 1, 7, 13 are rejected under the same reason as discussed in claims 1, 7, 13.
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 1-18 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claim 1 recites limitations
a storage device configured to store a plurality of data; a plurality of processing nodes in communication with the storage device, wherein at least one of the processing nodes is configured to: receive a query on at least a portion of the data;
generate a query plan in natural language format;
generate a large language model ("LLM") input based on the natural language format of the query plan, wherein the natural language format of the query plan comprises a system-generated natural language description of the query plan;
execute an LLM on the LLM input;
generate, in response to execution of the LLM, a plurality of recommended actions to perform to improve the query plan;
receive input to execute at least one of the plurality of recommended actions; and
alter the query plan in accordance with the at least one of the plurality of recommended actions.
Claim 7 recites limitations
receiving, with a processor, a query on at least a portion of data stored in a storage device, wherein the storage device is in communication with the processor;
generating, with the processor, a query plan in natural language format;
generating, with the processor, a large language model ("LLM") input based on the natural language format of the query plan, wherein the natural language format of the query plan comprises a system-generated natural language description of the query plan;
executing, with the processor, an LLM on the LLM input;
generating, with the processor, in response to execution of the LLM, a plurality of recommended actions to perform to improve the query plan;
receiving, with the processor, input to execute at least one of the plurality of recommended actions; and
altering, with the processor, the query plan in accordance with the at least one of the plurality of recommended actions.
Claim 13 recites limitations
instructions to receive a query on at least a portion of data stored in a storage device; instructions to generate a query plan in natural language format;
instructions to generate a large language model ("LLM") input based on the natural language format of the query plan, wherein the natural language format of the query plan comprises a system-generated natural language description of the query plan;
instructions to execute an LLM on the LLM input;
instructions to generate, in response to execution of the LLM, a plurality of recommended actions to perform to improve the query plan;
instructions to receive input to execute at least one of the plurality of recommended actions; and
instructions to alter the query plan in accordance with the at least one of the plurality of recommended actions.
a) In analyzing under step 2A Prong One, Does the claim recite an abstract idea law of nature or natural phenomenon? Yes.
Claims 1, 7, 13 recite abstract limitations
generate a query plan in natural language format;
generate a large language model ("LLM") input based on the natural language format of the query plan;
execute an LLM on the LLM input;
generate, in response to execution of the LLM, a plurality of recommended actions to perform to improve the query plan;
alter the query plan in accordance with the at least one of the plurality of recommended actions) are directed to judicial exception of mental processes. One can mentally select an application and as drafted, is a process or system or medium that, under its broadest reasonable interpretation, covers performance of the limitations in the mind but for the recitation of generic computer components. 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” grouping of abstract ideas. The human mind can perform step of generating, generating, executing, generating and altering. Accordingly, the claims recite an abstract idea.
b) In analyzing under step 2A Prong Two, Does the claim recite additional elements that integrate the judicial exception into a practical application? NO.
The claims do not include additional elements that integrate the judicial exception into a practical application because additional elements of a storage device, a plurality of processing nodes, at least one of the processing nodes (in claim 1); a processor, a storage device (in claim 7) and a storage device, instructions (in claim 13) that are recited at a high-level of generality such that it amounts no more than mere instructions to apply the exception using a generic computer component for obtaining that are well understood routine and conventional activities;
the additional limitation of (wherein the natural language format of the query plan comprises a system-generated natural language description of the query plan) that just define definition of the natural language format of the query plan including description of the query plan; and
the additional limitations of (store a plurality of data; receive a query on at least a portion of the data; receive input to execute at least one of the plurality of recommended actions) in claim 1; and (receiving a query on at least a portion of data stored in a storage device; receiving input to execute at least one of the plurality of recommended actions) in claims 7, 13 are insignificant extra solution activities which are well understood routine and conventional activities, see (Presenting offers and gathering statistics, OIP Techs and Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec) and See (MPEP 2106.05(g) or 2106.05(d) for Receiving or transmitting data over a network, e.g. see Intellectual Ventures v. Symantec; Storing and retrieving information in memory: Versata; Analyzing data: Genetic Techs; Determining: OIP Techs; Electronic recordkeeping: Alice Corp).
Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
c) In analyzing under step 2B, does the claim recite additional elements that amount to significantly more than the judicial exception? NO
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because additional elements of a storage device, a plurality of processing nodes, at least one of the processing nodes (in claim 1); a processor, a storage device (in claim 7) and a storage device, instructions (in claim 13) that are recited at a high-level of generality such that it amounts no more than mere instructions to apply the exception using a generic computer component for obtaining that are well understood routine and conventional activities;
the additional limitation of (wherein the natural language format of the query plan comprises a system-generated natural language description of the query plan) that just define definition of the natural language format of the query plan including description of the query plan; and
the additional limitations of (store a plurality of data; receive a query on at least a portion of the data; receive input to execute at least one of the plurality of recommended actions) in claim 1; and (receiving a query on at least a portion of data stored in a storage device; receiving input to execute at least one of the plurality of recommended actions) in claims 7, 13 are insignificant extra solution activities which are well understood routine and conventional activities, see (Presenting offers and gathering statistics, OIP Techs and Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec) and See (MPEP 2106.05(g) or 2106.05(d) for Receiving or transmitting data over a network, e.g. see Intellectual Ventures v. Symantec; Storing and retrieving information in memory: Versata; Analyzing data: Genetic Techs; Determining: OIP Techs; Electronic recordkeeping: Alice Corp).
Accordingly, these additional elements do not amount to significantly more than the judicial exception. The claims are not patent eligible.
Dependent claims 2-6, 8-12, 14-18 include all the limitations of claims 1, 7, 13. Therefore, claims 2-6, 8-12, 14-18 recite the same abstract idea practically being performed in the mind, and the analysis must therefore proceed to Step 2A Prong Two.
In particularly:
Claims 2, 8, 14 similarly recite limitation (wherein the LLM input is a prompt template) that just indicates definition of input as template.
Claims 3, 9, 15 similarly recite limitation (wherein the prompt template comprises output of a SQL EXPLAIN statement on the query plan) that just indicates template including output of explain statement on plan.
Claims 4, 10, 16 similarly recite limitation (receive input that comprises at least one inquiry on one or more of the recommended actions; provide the input to the LLM; and provide a response generated by the LLM) that represent well-understood, routine, conventional activity (See MPEP 2106.05(g) or 2106.05(d) for Receiving or transmitting data over a network, e.g. see Intellectual Ventures v. Symantec; Storing and retrieving information in memory: Versata; Analyzing data: Genetic Techs; Determining: OIP Techs; Electronic recordkeeping: Alice Corp; and Presenting offers and gathering statistics, OIP Techs).
Claims 5, 11, 17 similarly recite limitation (wherein the LLM is trained on at least one of: benchmark data; workload information data; product information data; blog content data; support incident data; and forum discussion data) that just indicate model trained by data.
Claims 6, 12, 18 similarly recite limitation (wherein the query comprises a plurality of queries associated with a common workload) that just indicates definition of query.
Accordingly, these additional elements of dependent claims 2-6, 8-12, 14-18 do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea and do not amount to significantly more than the judicial exception The claims are directed to an 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.
Claims 1-2, 5, 7-8, 11,13-14, 17 are rejected under 35 U.S.C. 103 as being unpatentable over Baldua et al (or hereinafter “Ba”) (US 20250110957) in view of Bossman et al (US 20030182276) and SHARMA et al (US 20250111164).
As to claim 1, Ba teaches a system comprising:
“a storage device configured to store a plurality of data” as a storage device including a data storage system 660 (fig. 6, paragraph 160) configured to store one or more data resources as a plurality of data (paragraphs 61, 86, 95);
“a plurality of processing nodes in communication with the storage device, wherein at least one of the processing nodes is configured to” as computing devices e.g., user systems 610, query planning system 680 as a plurality of processing nodes in communication with the storage device (fig. 6, paragraphs 134-136, 160), a processing device e.g., dynamic query planning system 680 of computing devices is configured to (fig. 6, paragraphs 160, 168-171):
“receive a query on at least a portion of the data” as receive a query (abstract, paragraphs 48, 70, 169-170), the query is executed on one or more data resources 134 to retrieve facet values from the one or more data sources (paragraph 61), the facet values of one or more data resources is represented as a portion of data;
“generate a query plan……” as generate a query plan in (abstract, paragraph 54, fig. 1A) a set of functions, the set of functions are executable using a set of data resources to create a modified version of the initial query (paragraph 25);
“generate a large language model ("LLM") input based on……” as configure as generate a input classification prompt for larger language model (LLM) (paragraphs 48, 127) based on generator 112 (paragraphs 50-51) or resources (paragraph 102). An input classification prompt for larger language model (LLM) is represented as a large language model ("LLM") input.
In particular, the input classification prompt generator 112 configures the input classification prompt as a zero-shot prompt (paragraph 50);
“execute an LLM on the LLM input” as process as execute a large language model on the input classification prompt as the LLM input (paragraphs 100-102) or applying the LLM on the prompt as the LLM input (fig. 7A, paragraphs 172-173).
For instance, when the large language model processes the input classification prompt 226, the large language model 116 only processes the selected instructions 222, e.g., only those instructions that are applicable to the possible intents 214 (paragraph 90).
For instance, when the large language model processes the plan generation prompt 338, the large language model 116 only reads data pertaining to the possible resources, e.g., only those data resources that are applicable to the possible functions 312, instead of the entire resource library 326 (paragraph 102);
“generate, in response to execution of the LLM,……” as obtain as generate, in response to applying the LLM at step 708 as in response to execution of the LLM, intent (fig. 7A, paragraphs 172-173);
“receive input to execute ……” as receive input to perform an operation using input (paragraph 142).
Ba does not explicitly teach limitations
a plurality of recommended actions to perform to improve the query plan;
at least one of the plurality of recommended actions;
alter the query plan in accordance with the at least one of the plurality of recommended actions;
in natural language format; the natural language format of the query plan;
wherein the natural language format of the query plan comprises a system-generated natural language description of the query plan.
Bossman teaches limitations
a plurality of recommended actions to perform to improve the query plan (as generate optimization hints as a plurality of recommended actions to produce modified access plan having improved performance over the base access plan: paragraphs 14, 42).
In particularly, the analysis of the determined performance problems resulting from the second analysis and the generated recommendations are processed to generate optimization hints, wherein the optimization hints indicate modifications to the base access plan to produce a modified access plan having improved performance over the base access plan. A user interface providing a visualization of the optimization hints is generated (paragraph 14);
“at least one of the plurality of recommended actions” as receive input (paragraph 30, 37) or user selected hint(s) entered through visual plan hint component 60 to valid the selected hint of the hints as at least one of the plurality of recommended actions (paragraph 41).
In particularly, the base access plan 34 adjusted with user selected hints entered through the visual plan hint component 60 may then be subject to validation by the estimates validator 56 to ensure that the optimization hint produces a modified plan that is accurate and complete. The estimates validator 56 may produce error feedback on the modification suggested by the hint, and provide suggestions for further modification for the user to review. The user may then invoke the visual plan hint 60 to make further changes until the desired access path is achieved (paragraph 41)
“alter the query plan in accordance with the at least one of the plurality of recommended actions” as adjust or tune as alter a plan for query (abstract) with a selected hint of hints (paragraphs 31, 41) that is used to modify the plan (paragraph 35) is represented as one of the plurality of recommended actions.
For instance, to develop meaningful optimization hints to modify a base access plan, the administrator would have to know the plan table structure, optimization hint constraints, and available access path choices, such as join methods, indexes to use (paragraph 35).
The visual plan hint 60 receives as input the plan table of the base access plan 34, and may provide a visualization in a GUI of the access plan. Further, the visual plan hint 60 may display in the GUI 66 optimization hints and other suggested modifications based on output from the estimates validator 56 and query advisor 58. Further the visual plan hint 60 can also receive administrator input. The visual plan hint 60 includes heuristics to determine optimization hints from the information from the estimates validator 56 and query advisor 58 to modify the base access plan 34. Further, the visual plan hint 60 may generate a user interface to allow the administrator to graphically modify the base access plan 34 (paragraph 37).
Bossman further teaches limitations
“receive a query on at least a portion of the data” as receive a search request on attributes in dimension tables to locate records in a fact table (paragraph 26);
generate a plurality of recommended actions to perform to improve the query plan (as generate optimization hints as a plurality of recommended actions to produce modified access plan having improved performance over the base access plan: paragraphs 14, 42);
“receive input to execute at least one of the plurality of recommended actions” as receive input (paragraph 30, 37) or user selected hint(s) entered through visual plan hint component 60 to valid the selected hint of the hints as recommended actions (paragraph 41).
In particularly, the base access plan 34 adjusted with user selected hints entered through the visual plan hint component 60 may then be subject to validation by the estimates validator 56 to ensure that the optimization hint produces a modified plan that is accurate and complete. The estimates validator 56 may produce error feedback on the modification suggested by the hint, and provide suggestions for further modification for the user to review. The user may then invoke the visual plan hint 60 to make further changes until the desired access path is achieved (paragraph 41).
Bossman and Ba disclose a method of generating plan for executing a query. Theses references are in the same field with application field. Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention Bossman’s teaching to Ba’s system in order to reduce time executing a query based on an access plan and further to provide a user recommendations for tuning plan to improve performance of a query.
Sharma teaches limitations
“in natural language format” as a plan e.g., plan 106 that is generated for a user request is represented as query plan (fig. 1, paragraph 27) in natural language tool 110 as natural language format (figs. 2, 6-7, paragraphs 31, 35-36);
“the natural language format of the query plan” as the natural language tool 110 as the natural language format of the plan 106 that is generated for a user request is represented as query plan (figs. 1-2, 6-7, paragraphs 27, 31, 35-36);
“wherein the natural language format of the query plan comprises a system-generated natural language description of the query plan” as the natural language tool 110 as the natural language format of the plan of request as the query plan (fig. 1, paragraph 27) comprises natural language description e.g. natural language description 126 of tool 102A of the request plan 106 as the query plan (figs. 1-2, paragraphs 26-27).
In particularly:
Natural language description 126 of tool 120A may be used by planning engine 104 when selecting tools for execution in response to user request 102. An example description 126 is “Generate molecules that can potentially bind to the target protein” (paragraph 26).
Plan 106 may be constructed to invoke selected tools 112, which is an ordered subset of tools 120 that was selected based on user request 102. For example, plan 106 may include tool invocation codes 130 which describe how to programmatically invoke corresponding tools 120 of selected tools 112. Plan 106 may also describe one or more orders in which tool invocation code 130 should be executed, e.g., tool 120A followed by tool 120D and then tool 120W. Plan 106 may also describe input variables supplied to each of the selected tools 112, output variables obtained from each of the selected tools 112, and how to forward the output of one tool as input to another tool. As illustrated, input 152 is provided to tool 120A, which generates output 154. Output 154 is then provided as input to tool 120W. Plan 106 may also indicate how to modify, transform, or otherwise alter values before they are provided as parameters to a tool or after they are returned by a tool (paragraph 27).
Sharma further teaches limitation
“generate a query plan in natural language format” as generate a query plan in natural language tool as natural language format (paragraphs 26-27, 31, figs. 1-2).
Sharma and Ba disclose a method of generating plan for executing a query or request. Theses references are in the same field with application field. Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention Sharma’s teaching to Ba’s system in order to enable users to quickly and conveniently perform complex operations satisfy user request to increase productivity and further to allow the users to interact with a natural language-based system in a natural, conversational manner.
As to claims 2, 8, 14, Ba, Bossman and Sharma teach limitation
“wherein the LLM input is a prompt template” as a input classification prompt is zero-shot prompt as a prompt template (Ba: paragraphs 50-510) or text prompt as a prompt template (Sharma: paragraph 35, fig. 3) or graph as a prompt template (Bossman: paragraph 38).
As to claims 5, 11, 17, Ba, Bossman and Sharma teach limitation
“wherein the LLM is trained on at least one of: benchmark data; workload information data; product information data; blog content data; support incident data; and forum discussion data” as the LLM is trained on size and composition of datasets as benchmark data (Ba: paragraphs 68-69) or statistics (Bo: paragraph 49, fig. 3).
Claim 7 has the same limitation as discussed in claim 1; thus claim 7 is rejected under the same reason as discussed in claim 1. In addition, Ba further teaches a method comprising:
“receiving, with a processor, a query on at least a portion of data stored in a storage device, wherein the storage device is in communication with the processor” as receive, by a processor (paragraphs 205, 217, 230), a query (abstract, paragraphs 48, 70, 169), the query is executed on one or more data resources 134 to retrieve facet values of the one data sources as at least a portion of data (paragraph 61) stored in data storage system (fig. 6, paragraph 95), the data storage system resides in storage device (paragraph 160), the storage device communicates with a processor of user system or application system or dynamic query planning system (figs. 6, 8, paragraphs 136-137, 206-207);
“generating, with the processor, a query plan ……” as generate, by the processor (paragraphs 206-207), a query plan in (abstract, paragraph 54, fig. 1A) a set of functions, the set of functions are executable using a set of data resources to create a modified version of the initial query (paragraph 25);
“generating, with the processor, a large language model ("LLM") input based on……” as configure as generate, by the processor (paragraphs 206-207), a input classification prompt for larger language model (LLM) (paragraphs 48, 127) based on generator 112 (paragraphs 50-51) or resources (paragraph 102). An input classification prompt for larger language model (LLM) is represented as a large language model ("LLM") input.
In particular, the input classification prompt generator 112 configures the input classification prompt as a zero-shot prompt (paragraph 50);
“executing, with the processor, an LLM on the LLM input” as processing, by the processor (paragraphs 206-207), a large language model on input classification prompt for larger language model (LLM) that is represented as the LLM input (paragraphs 100-102) or applying the LLM on the prompt as the LLM input (fig. 7A, paragraphs 172-173)
For instance, when the large language model processes the input classification prompt 226, the large language model 116 only processes the selected instructions 222, e.g., only those instructions that are applicable to the possible intents 214 (paragraph 90). For instance, when the large language model processes the plan generation prompt 338, the large language model 116 only reads data pertaining to the possible resources, e.g., only those data resources that are applicable to the possible functions 312, instead of the entire resource library 326 (paragraph 102);
“generating, with the processor, in response to execution of the LLM, ……” as obtain as generate, by the processor (paragraphs 206-207) in response to applying the LLM at step 708 as in response to execution of the LLM, intent (fig. 7A, paragraphs 172-173);
“receiving, with the processor, input to execute ……” as receive, by the processor (paragraphs 206-207), input to perform an operation using input (paragraph 142).
Ba does not explicitly teach limitations
altering, with the processor, the query plan in accordance with the at least one of the plurality of recommended actions.
Bossman teaches limitations
“altering, with the processor, the query plan in accordance with the at least one of the plurality of recommended actions” as adjust or tune as alter, by a processor (paragraph 40), a plan for query (abstract) with a selected hint of hints (paragraphs 31, 41) that is used to modify the plan (paragraph 35) is represented as one of the plurality of recommended actions.
For instance, to develop meaningful optimization hints to modify a base access plan, the administrator would have to know the plan table structure, optimization hint constraints, and available access path choices, such as join methods, indexes to use (paragraph 35).
The visual plan hint 60 receives as input the plan table of the base access plan 34, and may provide a visualization in a GUI of the access plan. Further, the visual plan hint 60 may display in the GUI 66 optimization hints and other suggested modifications based on output from the estimates validator 56 and query advisor 58. Further the visual plan hint 60 can also receive administrator input. The visual plan hint 60 includes heuristics to determine optimization hints from the information from the estimates validator 56 and query advisor 58 to modify the base access plan 34. Further, the visual plan hint 60 may generate a user interface to allow the administrator to graphically modify the base access plan 34 (paragraph 37).
Bossman further teaches limitations
“receiving, with a processor, a query on at least a portion of the data” as receive, by a processor (paragraph 40), a search request on attributes in dimension tables to locate records in a fact table (paragraph 26);
generating, with the processor, a plurality of recommended actions to perform to improve the query plan (as generate, by the processor (paragraphs 40, 55), optimization hints as a plurality of recommended actions to produce modified access plan having improved performance over the base access plan: paragraphs 14, 42);
“receiving, with the processor, input to execute at least one of the plurality of recommended actions” as receive, by the processor (paragraph 40), input (paragraph 30, 37) or user selected hint(s) entered through visual plan hint component 60 to valid the selected hint of the hints as recommended actions (paragraph 41).
In particularly, the base access plan 34 adjusted with user selected hints entered through the visual plan hint component 60 may then be subject to validation by the estimates validator 56 to ensure that the optimization hint produces a modified plan that is accurate and complete. The estimates validator 56 may produce error feedback on the modification suggested by the hint, and provide suggestions for further modification for the user to review. The user may then invoke the visual plan hint 60 to make further changes until the desired access path is achieved (paragraph 41).
Bossman and Ba disclose a method of generating plan for executing a query. Theses references are in the same field with application field. Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention Bossman’s teaching to Ba’s system in order to reduce time executing a query based on an access plan and further to provide a user recommendations for tuning plan to improve performance of a query.
Claim 13 has the same limitation as discussed in claim 1; thus claim 13 is rejected under the same reason as discussed in claim 1. In addition, Ba teaches a non-transitory computer-readable medium encoded with a plurality of instructions executable by a processor, the plurality of instructions comprising: (paragraphs 206-207):
“instructions to receive a query on at least a portion of data stored in a storage device” as instructions (paragraphs 206-207) to receive a query (abstract, paragraphs 48, 70, 169), the query is executed on one or more data resources 134 to retrieve facet values of the one or more data sources as at least a portion of data (paragraph 61) stored in data storage system (fig. 6, paragraph 95), the data storage system resides in storage device (paragraph 160);
“instructions to generate a query plan ……” as instructions (paragraphs 206-207) to generate a query plan in (abstract, paragraph 54, fig. 1A) a set of functions, the set of functions are executable using a set of data resources to create a modified version of the initial query (paragraph 25);
“instructions to generate a large language model ("LLM") input based on……” as instructions (paragraphs 206-207) to configure as generate a input classification prompt for larger language model (LLM) (paragraphs 48, 127) based on generator 112 (paragraphs 50-51) or resources (paragraph 102). An input classification prompt for larger language model (LLM) is represented as a large language model ("LLM") input.
In particular, the input classification prompt generator 112 configures the input classification prompt as a zero-shot prompt (paragraph 50);
“instructions to execute an LLM on the LLM input” as instructions (paragraphs 206-207) to processing a large language model on input classification prompt for larger language model (LLM) that is represented as the LLM input (paragraphs 100-102) or applying the LLM on the prompt as the LLM input (fig. 7A, paragraphs 172-173)
For instance, when the large language model processes the input classification prompt 226, the large language model 116 only processes the selected instructions 222, e.g., only those instructions that are applicable to the possible intents 214 (paragraph 90). For instance, when the large language model processes the plan generation prompt 338, the large language model 116 only reads data pertaining to the possible resources, e.g., only those data resources that are applicable to the possible functions 312, instead of the entire resource library 326 (paragraph 102);
“instructions to generate, in response to execution of the LLM, ……” as instructions (paragraphs 206-207) to obtain as generate, in response to applying the LLM at step 708 as in response to execution of the LLM, intent (fig. 7A, paragraphs 172-173);
“ instructions to receive input to execute……” as instructions (paragraphs 206-207) to receive input to perform an operation using input (paragraph 142);
“instructions to…...” as instructions (paragraphs 206-207) to receive input ((paragraph 142).
Claims 3, 9, 15 are rejected under 35 U.S.C. 103 as being unpatentable over Ba in view of Bossman and Sharma and further in view of Gelle et al (US 20220114188)
As to claims 3, 9, 15, Ba, Bossman and Sharma teach limitation
“wherein the prompt template comprises ……on the query plan” as an input classification prompt is zero-shot prompt as a prompt template (Ba: paragraphs 50-510) or a prompt as prompt template (Sharma: paragraph 5) comprises output of the query analyzer on (Bossman: paragraphs 28-29) request plan as query plan (Sharma: paragraphs 26-27).
Ba, Bossman and Sharma do not explicitly teach limitation
output of SQL EXPLAIN statement.
Gelle teaches limitation
“output of SQL EXPLAIN statement” as output of EXPLAIN statement (paragraphs 24, 60) for PostgreSQL (abstract).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention Gelle’s teaching to Ba’s system in order to minimize resources used by the query and further to allow allocation of resources available in the remote system, in order to accommodate the load being transferred
Claims 4, 10, 16 are rejected under 35 U.S.C. 103 as being unpatentable over Ba in view of Bossman and Sharma and further in view of Phillipps et al (or hereinafter “Phi”) (US 20140358828).
As to claims 4, 10, 16, Ba, Bossman and Sharma teach limitation
“wherein the at least one processing node is further configured to:” as the processing device is configured to: (Ba: paragraphs 169-171) or “the plurality of instructions further comprising” as instructions comprising (Ba: paragraphs 205, 217, 230):
receive input that comprises……; or receiving, with the processor, input that comprises……; or instructions to receive input that comprises…… (as