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 .
This communication is in response to Application filed on April 28, 2025. Claims 1-11 are pending.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 4/28/2025 is being considered by the examiner.
Priority
Acknowledgment is made of applicant's claim for foreign priority based on an application filed in Japan on 6/7/2024. It is noted, however, that applicant has not filed a certified copy of the JP2024-093266 application as required by 37 CFR 1.55.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-11 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 1 and 11 recite the limitation "the candidate pattern in the prompt" in line 21 of the respective claims. There is insufficient antecedent basis for this limitation in the claims. For purposes of examination, Examiner will assume that the limitation reads ‘a candidate pattern in the prompt’.
Claims 2-10 are also rejected under 101 by virtue of their dependencies.
Due to the 35 USC 112 rejections, the claims have been examined as best understood by the Examiner.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: ‘data registration unit’, ‘query generation unit’, ‘query execution unit’, query history accumulation unit’, ‘additional instruction update unit’ in claim 11.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
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 1-11 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1 and 11 recite:
data registration processing of pre-registering a query generation instruction, a schema of a search target database, and a candidate pattern for the additional instruction for creating the prompt;
query generation processing of generating the query by inputting the prompt to the language model;
query execution processing of executing the query with respect to the search target database to acquire a query execution result and an error log;
query history accumulation processing of acquiring feedback for the query execution result, and accumulating a query history in which the prompt, the query, the query execution result, the error log, and the feedback are associated with each other by identification information; and
additional instruction update processing of updating the additional instruction by determining whether to describe the candidate pattern in the prompt using the query history.
Step 1: The claims as a whole fall within one or more statutory categories.
Step 2A prong 1: At least claims 1 and 11 recite limitations that are abstract ideas.
The limitation “query generation processing of generating the query” is a mental step. One can mentally determine what data to search for based on a criteria. Thus, the claimed limitation can be performed by the human mind.
Furthermore, the limitation “additional instruction update processing of updating the additional instruction by determining whether to describe the candidate pattern in the prompt using the query history” is also a mental step. One can mentally make a determination as to whether certain criteria applies to a pattern of data. Thus, the claimed limitation can be performed by the human mind.
Step 2A prong 2:
Claims 1 and 11 recite the limitations “query execution processing of executing the query with respect to the search target database to acquire a query execution result and an error log” and “query history accumulation processing of acquiring feedback for the query execution result”. These limitations are additional elements and are insignificant extra-solution activity as retrieval/receiving of data (i.e. mere data gathering) such as 'obtaining information' as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
In addition, the limitations, “data registration processing of pre-registering a query generation instruction, a schema of a search target database, and a candidate pattern for the additional instruction for creating the prompt” and “accumulating a query history in which the prompt, the query, the query execution result, the error log, and the feedback are associated with each other by identification information” are also additional elements and are using of a computer or other machinery in its ordinary capacity for tasks such as storing or simply adding computer components after the fact to an abstract idea (mental process) does not integrate a judicial exception into a practical application or provide significantly more.
Furthermore, Claims 1 and 11 recite the following additional elements “system”, “data registration unit”, “query generation unit”, “query execution unit”, “query history accumulation unit”, “additional instruction update unit” and “language model”, note that these recited additional elements are a high-level recitation of generic computer hardware and software components to perform the mental process and applied on a computer as in MPEP 2106.05(f), which does not provide integration into a practical application.
Step 2B: the conclusions for the additional elements representing mere implementation using a computer are carried over and do not provide significantly more.
With respect to the “executing” and "acquiring” limitations identified as insignificant extra-solution activity above when re-evaluated these elements are well-understood, routine, and conventional as evidenced by the court cases in MPEP 2106.05(d)(II), "i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); … OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network);" and thus remains insignificant extra-solution activity that does not provide significantly more.
Furthermore, the “pre-registering” and “accumulating” limitations identified as insignificant extra-solution activity above when re-evaluated these elements are well-understood, routine, and conventional as evidenced by the court cases in MPEP 2106.05(d)(II), “iv. Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015); OIP Techs., 788 F.3d at 1363, 115 USPQ2d at 1092-93” and thus remains insignificant extra-solution activity that does not provide significantly more.
Therefore, the claims as a whole do not change this conclusion and the claims are ineligible.
Claims 2 and 5 depend from claim 1 and thus include all the limitations of claim 1, therefore claims 2 and 5 recite the same abstract ideas of "mental processes".
Claims 2 and 5 furthermore recite:
[Claim 2] wherein the search target database is expressed by a knowledge graph, the query is a query for the knowledge graph, and the prompt includes information about a structure and a grammar specific to the knowledge graph;
[Claim 5] the error log during the execution of the query includes any of a log corresponding to an execution failure due to a grammatical error in the generated query, a log corresponding to an execution failure due to a query timeout, and a log corresponding to an execution failure due to a mismatch between a schema stored in the search target database and a schema specified by the query.
Step 1: Claims 2 and 5 as a whole fall within one or more statutory categories.
Step 2A prong 1: Claims 2 and 5 recite limitations that are abstract ideas because they depend from claim 1 which recites mental steps.
Claim 2 recites the limitation “the query is a query for the knowledge graph, and the prompt includes information about a structure and a grammar specific to the knowledge graph”, which further defines the query and the prompt in the ‘generating the query’ limitation step in claim 1, which was considered a mental step. As such, this limitation is also a mental step.
Step 2A prong 2:
Claim 2 recites the limitation “wherein the search target database is expressed by a knowledge graph” which further defines the search target database in the ‘preregistering’ step in claim 1, which is an additional element and is using of a computer or other machinery in its ordinary capacity for tasks such as storing or simply adding computer components after the fact to an abstract idea (mental process) does not integrate a judicial exception into a practical application or provide significantly more.
Claim 5 recites the limitation “the error log during the execution of the query includes any of a log corresponding to an execution failure due to a grammatical error in the generated query, a log corresponding to an execution failure due to a query timeout, and a log corresponding to an execution failure due to a mismatch between a schema stored in the search target database and a schema specified by the query” which further defines the ‘executing the query’ step in claim 1 and is an additional element, is insignificant extra-solution activity as retrieval/receiving of data (i.e. mere data gathering) such as 'obtaining information' as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
Step 2B:
With respect to the “executing” and "acquiring” limitations identified as insignificant extra-solution activity above when re-evaluated these elements are well-understood, routine, and conventional as evidenced by the court cases in MPEP 2106.05(d)(II), "i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); … OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network);" and thus remains insignificant extra-solution activity that does not provide significantly more.
Therefore, claims 2 and 5 as a whole do not change this conclusion and the claims are ineligible.
Claims 3 and 4 depend from claim 1 and thus include all the limitations of claim 1, therefore claims 3 and 4 recite the same abstract ideas of "mental processes".
Claims 3 and 4 furthermore recite:
[Claim 3] processing of describing ontology of the knowledge graph in the prompt, with a file defining the ontology of the knowledge graph as an input;
[Claim 4] processing of describing an instance of the knowledge graph in the prompt, with a file describing the instance of the knowledge graph as an input.
Step 1: Claims 3 and 4 as a whole fall within one or more statutory categories.
Step 2A prong 1: Claims 3 and 4 recite limitations that are abstract ideas because they depend from claim 1 which recites mental steps.
Step 2A prong 2:
Claims 3 and 4 recite the limitations “processing of describing ontology of the knowledge graph in the prompt, with a file defining the ontology of the knowledge graph as an input” and “processing of describing an instance of the knowledge graph in the prompt, with a file describing the instance of the knowledge graph as an input”. These are additional elements and are mere output recited at a high level of generality in response to an input file and is considered insignificant extra-solution activity as ‘selecting information for output as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
Step 2B:
With respect to the “describing” limitations identified as insignificant extra-solution activity above when re-evaluated this element is well-understood, routine, and conventional as evidenced by the court cases in MPEP 2106.05(d)(II), "i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); … OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network);" and thus remains insignificant extra-solution activity that does not provide significantly more.
Therefore, claims 3 and 4 as a whole do not change this conclusion and the claims are ineligible.
Claims 6-8 depend from claim 1 and thus include all the limitations of claim 1, therefore claims 6-8 recite the same abstract ideas of "mental processes".
Claims 6-8 furthermore recite:
[Claim 6] wherein the feedback includes any of feedback indicating that the query execution result is entirely correct, feedback indicating that the query execution result is partially or entirely erroneous, and feedback indicating that the query execution result is partially or entirely empty;
[Claim 7] wherein a button corresponding to the feedback indicating that the query execution result is entirely correct, the feedback indicating that the query execution result is partially or entirely erroneous, and the feedback indicating that the query execution result is partially or entirely empty is displayed on a screen, so that a user is allowed to input the feedback by performing a selection operation on the button;
[Claim 8] wherein in addition to the button, a text input box is displayed on the screen so that the user is allowed to input the feedback by writing a free-form statement in the text input box.
Step 1: Claims 6-8 as a whole fall within one or more statutory categories.
Step 2A prong 1: Claims 6-8 recite limitations that are abstract ideas because they depend from claim 1 which recites mental steps.
Step 2A prong 2:
Claims 6-8 recite the limitations “wherein the feedback includes any of feedback indicating that the query execution result is entirely correct, feedback indicating that the query execution result is partially or entirely erroneous, and feedback indicating that the query execution result is partially or entirely empty”, “wherein a button corresponding to the feedback indicating that the query execution result is entirely correct, the feedback indicating that the query execution result is partially or entirely erroneous, and the feedback indicating that the query execution result is partially or entirely empty is displayed on a screen, so that a user is allowed to input the feedback by performing a selection operation on the button”, and “wherein in addition to the button, a text input box is displayed on the screen so that the user is allowed to input the feedback by writing a free-form statement in the text input box”. These limitations further define the feedback in the ‘acquiring feedback’ step in claim 1. As such, these limitations are additional elements and are insignificant extra-solution activity as retrieval/receiving of data (i.e. mere data gathering) such as 'obtaining information' as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
Step 2B:
With respect to the “acquiring feedback” limitation identified as insignificant extra-solution activity above when re-evaluated these elements are well-understood, routine, and conventional as evidenced by the court cases in MPEP 2106.05(d)(II), "i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); … OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network);" and thus remains insignificant extra-solution activity that does not provide significantly more.
Therefore, claims 6-8 as a whole do not change this conclusion and the claims are ineligible.
Claims 9 and 10 depend from claim 1 and thus include all the limitations of claim 1, therefore claims 9 and 10 recite the same abstract ideas of "mental processes".
Claims 9 and 10 furthermore recite:
[Claim 9] wherein when updating the additional instruction, a file defining the candidate pattern for the additional instruction is input, and a quantitative evaluation as to whether to employ the candidate pattern for the additional instruction is determined by a program implementing a certain algorithm;
[Claim 10] wherein when updating the additional instruction, a file defining the candidate pattern for the additional instruction is input, and a quantitative evaluation as to whether to employ the candidate pattern for the additional instruction is determined based on a quantitative evaluation returned by the language model.
Step 1: Claims 9 and 10 as a whole fall within one or more statutory categories.
Step 2A prong 1: Claims 9 and 10 recite limitations that are abstract ideas because they depend from claim 1 which recites mental steps.
Step 2A prong 2:
Claims 9 and 10 recite the limitations “wherein when updating the additional instruction, a file defining the candidate pattern for the additional instruction is input, and a quantitative evaluation as to whether to employ the candidate pattern for the additional instruction is determined by a program implementing a certain algorithm” and “wherein when updating the additional instruction, a file defining the candidate pattern for the additional instruction is input, and a quantitative evaluation as to whether to employ the candidate pattern for the additional instruction is determined based on a quantitative evaluation returned by the language model”. These are additional elements and are mere output recited at a high level of generality in response to input instructions and is considered insignificant extra-solution activity as ‘selecting information for output as identified in MPEP 2106.05(g) and does not provide integration into a practical application.
Step 2B:
With respect to the “determined” limitations identified as insignificant extra-solution activity above when re-evaluated this element is well-understood, routine, and conventional as evidenced by the court cases in MPEP 2106.05(d)(II), "i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); … OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network);" and thus remains insignificant extra-solution activity that does not provide significantly more.
Therefore, claims 9 and 10 as a whole do not change this conclusion and the claims are ineligible.
To expedite a complete examination of the instant application, the claims rejected under 35 U.S.C. 101 (nonstatutory} above are further rejected as set forth below in anticipation of applicant amending these claims to place them within the four statutory categories of the invention.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-4 and 6-11 are rejected under 35 U.S.C. 103 as being unpatentable over in US 2021/0064932 by Wang et al (hereafter Wang), as disclosed by Applicant in IDS dated 4/28/2025, and further in view of US 2025/0298952 by Berg et al (hereafter Berg).
Referring to claim 1, Wang discloses a method for updating an additional instruction described in a query using a chatbot [query paths generated from an input query using a chatbot and used to return a query result, Abstract; para 8; Fig 6], the method comprising:
data registration processing of pre-registering a schema of a search target database [knowledge graph is a knowledgebase integrated (i.e. stored within) with a graph database, para 3], a query generation instruction [query paths generated in knowledge graph, para 70; Fig 6, element 610] and a candidate pattern for the additional instruction for creating the query [chatbots retrieve replies to an input dialog and retrieve a reply having the most similar word patterns from a database, para 4];
query generation processing of generating the query by inputting the query to the chatbot [natural language query received from client is sent to AI chatbot and executed by the chatbot, see Fig 6, elements 602-616];
query execution processing of executing the query with respect to the search target database to acquire a query execution result [query results Fig 3, element 310; query result generated by AI chatbot based on validated query paths, para 71, Fig 6, element 616];
query history accumulation processing of accumulating a query history, in which the query and the query execution result are associated with each other [query history of same or similar query submitted previously, para 70]; and
additional instruction update processing of updating the additional instruction by determining whether to describe the candidate pattern in the query using the query history [selection of a query path (i.e. updating the initial query) is based on validation of the query paths based on a calculated score with respect to multiple dimensions including whether the query is included in a query history as a same or similar query submitted previously, para 70; Fig 6, element 612].
Referring to claim 1, while Wang discloses all of the above claimed subject matter and also discloses updating query path (instructions) for an input query using an AI chatbot [Wang, para 8], it remains silent as to: generating the query through a prompt to a natural language model; acquiring an error log; acquiring feedback for the query execution result; and wherein the prompt, error log, and the feedback are stored associated with each other by identification information.
Berg teaches generating a query through a prompt to a natural language model [generative AI tool constructs a prompt to LLM 250 and produces functional code satisfying the natural language query, para 30]; acquiring an error log [error messages from log files, para 30]; acquiring feedback for the query execution result [user accepted response to the LLM responses/generated code, para 71, 73, Fig 4]; and wherein the prompt, error log, and the feedback are stored associated with each other by identification information [para 30; see Fig 2, element 207; indexed data, para 61-70].
Wang and Berg are analogous art because they are directed to the same field of endeavor- query analysis. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the query input to the AI chatbot in Wang to send it via a generated prompt to the LLM, in Berg because it would achieve predicable results.
The ordinary skilled artisan would have been motivated to make this modification because the prompt to the generative AI tool using an LLM would further enhance the chatbot functionality of Wang.
Referring to claim 11, the limitations of the claim are similar to those of claim 1 in the form of a system [Wang, computer system 101, Fig 1], comprising a data registration unit, a query generation unit, a query execution unit, a query history accumulation unit, and an additional instruction update unit [Wang, processors, para 21, Fig 1]. As such, claim 11 is rejected for the same reasons as claim 1.
Referring to claim 2, Wang/Berg discloses wherein the search target database is expressed by a knowledge graph, the query is a query for the knowledge graph [query characteristics are mapped to knowledge graph, para 8, 35], and the prompt includes information about a structure and a grammar specific to the knowledge graph [Wang, query is mapped to base elements 224 within the knowledge graph, para 36, 39, 70, Fig 6, element 608; Berg, prompts to AI LLM system, para 21].
Referring to claim 3, Wang/Berg discloses processing of describing ontology of the knowledge graph in the prompt, with a file defining the ontology of the knowledge graph as an input [Wang, base elements of knowledge graph are defined by the input query, para 59, Fig 3, element 304; para 69, Fig 6, element 604; Berg, prompts to AI LLM system, para 21].
Referring to claim 4, Wang/Berg discloses processing of describing an instance of the knowledge graph in the prompt, with a file describing the instance of the knowledge graph as an input [Wang, query paths contain base elements of knowledge graph including anchor element ‘China’ and jump element “Capital”, and jump element “famous places”, para 59, see Fig 3, elements 304, 306; Berg, prompts to AI LLM system 250 are constructed by extracting parameter names and default values, para 21,30; Fig 2, element 207].
Referring to claim 6, Wang/Berg discloses wherein the feedback includes any of feedback indicating that the query execution result is entirely correct, feedback indicating that the query execution result is partially or entirely erroneous, and feedback indicating that the query execution result is partially or entirely empty [Berg, user accepts generated code, para 34, 56, Fig 4].
Referring to claim 7, Wang/Berg discloses wherein a button corresponding to the feedback indicating that the query execution result is entirely correct, the feedback indicating that the query execution result is partially or entirely erroneous, and the feedback indicating that the query execution result is partially or entirely empty is displayed on a screen, so that a user is allowed to input the feedback by performing a selection operation on the button [Berg, user accepts generated code through ‘Accept’ button, para 34, 56, Fig 4].
Referring to claim 8, Wang/Berg discloses wherein in addition to the button, a text input box is displayed on the screen so that the user is allowed to input the feedback by writing a free-form statement in the text input box [Berg, ‘Generated code section’ is editable, so users can modify the code as they wish before accepting it, para 56, Fig 4].
Referring to claim 9, Wang/Berg discloses wherein when updating the additional instruction, a file defining the candidate pattern for the additional instruction is input, and a quantitative evaluation as to whether to employ the candidate pattern for the additional instruction is determined by a program implementing a certain algorithm [Wang, query paths are scored 242 by AI chatbot before being considered in being used as the query, para 40, 61, 67, Fig 3,5; Berg, LLM 107/250, Fig 1, 2].
Referring to claim 10, Wang/Berg discloses wherein when updating the additional instruction, a file defining the candidate pattern for the additional instruction is input, and a quantitative evaluation as to whether to employ the candidate pattern for the additional instruction is determined based on a quantitative evaluation returned by the language model [Wang, query paths are scored 242 by AI chatbot before being considered in being used as the query, para 40, 61, 67, Fig 3,5; Berg, LLM 107/250, Fig 1, 2].
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Wang, in view of Berg, as applied to claim 1 above, and further in view of US 2008/0183704 by Miller et al (hereafter Miller).
Referring to claim 5, while Wang/Berg discloses all of the above claimed subject matter and also discloses receiving error messages in log files [Berg, para 30], and that a user provides feedback on retrieved entries retrieved from the index 1006 that were used as part of the prompt for the LLM to create the generated code, wherein the feedback includes removing poor quality entries [Berg, para 34] and accepting correct or satisfactory responses [Berg, para 68]. It remains silent as to the feedback pertaining the recognition of poor quality responses being an execution failure due to a grammatical error in the generated query, an execution failure due to a query timeout, or an execution failure due to a mismatch between a schema stored in the search target database and a schema specified by the query.
Miller discloses a stopping criterion to interrupt an iterative pattern matching process due to a timeout [para 34-37].
Wang/Berg and Miller are analogous art because they are directed to the same field of endeavor- query analysis. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the error messages in log files and user feedback of Berg to be based on the stopping criterion in Miller because it would achieve predicable results.
The ordinary skilled artisan would have been motivated to make this modification because the timeout stopping criterion of Miller refines the type of error messages recorded in logs of Berg and the reason for a user to not accept the generated code results in Berg.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Verma (US 20180349377) directed to: converting natural language input to structured queries and restructuring queries based on knowledge graph ontology, user feedback [para 55-57, 63-64 Fig 6 and related portions of specification];
Li (US 20230177363) directed to: generation of query templates for knowledge graph based question answering system [Abstract; Fig 4, 5, 8 and related portions of specification];
Anthony (US 20250004450) directed to: prompt engineering for AI assisted industrial automation device troubleshooting including using feedback to regenerate prompt [para 22-25, 67, 72, Fig 2, 3, 5 and related portions of specification];
Acharya (US 20250045148) directed to: detecting and repairing reliability issues in operating systems using a generative AI system that analyzes error information associated with a detected issue to identify a prompt to a language model [entire document].
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHERYL M SHECHTMAN whose telephone number is (571)272-4018. The examiner can normally be reached on Mon-Fri: 8am-4pm.
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, Amy Ng can be reached on 571-270-1698. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
CHERYL M SHECHTMANPatent Examiner
Art Unit 2164
/C.M.S/
/AMY NG/Supervisory Patent Examiner, Art Unit 2164
Prosecution Insights