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 .
Claim Status
Claims 1-20 are pending. Claims 7-8, 15-16 and 20 are objected to. Claims 1-6, 9-14 and 17-19 are rejected.
Allowable Subject Matter
Claim 7-8, 15-16 and 20 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
7. The method of claim 1 wherein:
the AI/ML pipeline comprises a dataspace agent, a class agent, a property agent, a query
agent, and a self-healing agent;
the dataspace agent identifies one of multiple dataspaces associated with the user query;
the class agent identifies at least one of multiple classes associated with the selected
dataspace, the at least one selected class mapped to the data topology;
the property agent identifies at least one of multiple properties within the at least one
selected class; and
the query agent generates each data access query based on at least one of: the at least
one selected class and the at least one selected property.
8. The method of Claim 7, wherein the self-healing agent determines, for each data
access query, whether: a syntax of the data access query has one or more errors;
at least one property in the data access query exists;
one or more values in the data access query are proper; and
a data type of a value in the data access query matches an expected data type.
15. The apparatus of Claim 10, wherein:
the AI/ML pipeline comprises a dataspace agent, a class agent, a property agent, a query
agent, and a self-healing agent;
the dataspace agent is configured to identify one of multiple dataspaces associated with
the user query;
the class agent is configured to identify at least one of multiple classes associated with
the selected dataspace, the at least one selected class mapped to the data topology;
the property agent is configured to identify at least one of multiple properties within the
at least one selected class; and
the query agent is configured to generate each data access query based on at least one
of: the at least one selected class and the at least one selected property.
16. The apparatus of Claim 15, wherein the self-healing agent is configured to
determine, for each data access query, whether:
a syntax of the data access query has one or more errors;
at least one property in the data access query exists;
one or more values in the data access query are proper; and
a data type of a value in the data access query matches an expected data type.
20. The non-transitory computer readable medium of Claim 17, wherein:
the AI/ML pipeline comprises a dataspace agent, a class agent, a property agent, a query
agent, and a self-healing agent;
the dataspace agent is configured to identify one of multiple dataspaces associated with
the user query;
the class agent is configured to identify at least one of multiple classes associated with
the selected dataspace, the at least one selected class mapped to the data topology;
the property agent is configured to identify at least one of multiple properties within the
at least one selected class; and
the query agent is configured to generate each data access query based on at least one
of: the at least one selected class and the at least one selected property.
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.
Claim(s) 1 is/are rejected under 35 U.S.C. 103 as being unpatentable over Townsend-Last (2025/0321944) in view of Li (US 11,561,979) in view of Truong (US 2024/0330279).
Examiner Note: Hereafter, above references will be entered as reference combination A.
Regarding claim 1, Townsend-Last discloses:
providing a user query to a self-healing multi-agent artificial intelligence/machine
learning (AI/ML) pipeline, the user query requesting a response based on data stored in a data
topology, the data topology modeled using a semantic data model;
Townsend-Last [0108] FIG. 5A is a flowchart showing an example method 500 of operation of the AI/ML based query generator 123c for the Q&A assistant 123a of FIG. 1, according to some arrangements. As a general overview, the AI/ML based query generator 123c can automatically generate block queries based on natural-language, unstructured user prompts. Automatically generating block queries based on natural-language prompts enables a host of technical advantages, including improving the user's ability to interact with the block-based schema, automating repetitive coding tasks, error reduction in automatically-generated queries via obviating the need to type parameters, such as date ranges, and optimization of AI-generated queries.
generating an initial data access query for retrieving the data from the data topology
using the AI/ML pipeline and the semantic data model;
Townsend-Last [0108] FIG. 5A is a flowchart showing an example method 500 of operation of the AI/ML based query generator 123c for the Q&A assistant 123a of FIG. 1, according to some arrangements. As a general overview, the AI/ML based query generator 123c can automatically generate block queries based on natural-language, unstructured user prompts. Automatically generating block queries based on natural-language prompts enables a host of technical advantages, including improving the user's ability to interact with the block-based schema, automating repetitive coding tasks, error reduction in automatically-generated queries via obviating the need to type parameters, such as date ranges, and optimization of AI-generated queries.
determining that the initial data access query includes a hallucination or error;
Townsend-Last discloses elements of the claimed invention as noted but does not disclose above limitation. However, Li discloses:
Li abstract A computer-implemented method dynamically detects and corrects an error in a query. The method includes identifying an error in a first query. The method further includes generating a set of alternate execution structures for the first query. The method includes running each of the alternate execution structures, including generating a set of results corresponding to each set of alternate execution structure, comparing each of the set of results against each other of the set of results, and storing each of the set of alternate execution structures to include a result of the set of results, for each alternate structure. The method further includes selecting, from the set of alternate execution structures, a first alternate execution structure based on a predetermined criteria, and implementing the first alternate structure in place of the first query.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Townsend-Last to obtain above limitation based on the teachings of Li for the purpose of dynamically detecting and correcting errors in queries [title].
One of ordinary skill in the art would have been motivated to look to Li’s analogous art from the same field of endeavor as the claimed invention. Based on the above, there is a reasonable expectation of success in combining Townsend-Last and Li to meet limitations of the claimed invention.
performing an automatic loop one or more times, wherein the automatic loop includes:
generating an updated data access query for retrieving the data from the data
topology using the AI/ML pipeline and the semantic data model;
Li abstract Li abstract A computer-implemented method dynamically detects and corrects an error in a query. The method includes identifying an error in a first query. The method further includes generating a set of alternate execution structures for the first query.
determining whether the updated data access query includes a hallucination or
error; and
Li abstract, The method further includes selecting, from the set of alternate execution structures, a first alternate execution structure based on a predetermined criteria, and implementing the first alternate structure in place of the first query.
if the updated data access query includes a hallucination or error, repeating the automatic loop; and
Li col 1 lines 50-60 The program instructions are further configured to cause the process to generate, for the second query, a set of alternate execution structures. The program instructions are also configured to cause the process to run each alternate execution structure in the set of alternate execution structures. The program instructions are further configured to cause the process to select a second alternate execution structure from the set of alternate execution structures. The program instructions are further configured to cause the process to replace an execution structure of the first query with the second alternate execution structure.
using a final data access query with no hallucination or error to retrieve the data from
the data topology in order to generate the response.
Townsend-Last discloses elements of the claimed invention as noted but does not disclose above limitation. However, Truong discloses:
Truong [0046] On the other hand, if request processing module 202 determines at step 414 that the maximum number of attempts has been reached, then method 300 continues to step 418, where request processing module 202 displays the generated query and the execution error(s) to a user, receives a corrected query from the user, and executes the corrected query against database 114.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Townsend-Last to obtain above limitation based on the teachings of Truong for the purpose of generating and correcting database queries using language models [title].
One of ordinary skill in the art would have been motivated to look to Truong’s analogous art from the same field of endeavor as the claimed invention. Based on the above, there is a reasonable expectation of success in combining Townsend-Last and Truong to meet limitations of the claimed invention.
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over reference combination A in view of nonfunctional descriptive material.
Claim 2 recites the semantic data model represents the data topology and identifies dataspaces, classes, and properties associated with the data topology;
agents of the AI/ML pipeline use the semantic data model to identify a specific
dataspace, one or more specific classes, and one or more specific properties associated with the
user query; and each data access query is generated based on the specific dataspace, the one or more specific classes, and the one or more specific properties.
The above printed material, particularly identifying dataspaces, classes, and properties associated with the data topology, is not functionally related to the claimed invention as a whole, i.e., a self-healing multi-agent artificial intelligence/machine learning model.
Claim 3, is/are rejected under 35 U.S.C. 103 as being unpatentable over reference combination A in view of nonfunctional descriptive material.
Claim 3 recites a model provides context to the agents of the AI/ML pipeline; the agents comprise one or more AI/ML models that generate responses when prompted
by the agents; and the responses from the one or more AI/ML models identify the specific dataspace, the one or more specific classes, the one or more specific properties, and the data access queries.
The above printed material, particularly models identify the specific dataspace, the one or more specific classes, the one or more specific properties, and the data access queries is not functionally related to the claimed invention as a whole, i.e., a self-healing multi-agent artificial intelligence/machine learning model.
Claim 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over reference combination A in view of Jain (US 2025/0258819)
Regarding claim 4, reference combination A discloses elements of the claimed invention as noted but does not disclose the data topology includes tabular data; and the semantic data model allows the AI/ML pipeline to understand columns of data in the tabular data. However, Jain discloses:
Jain [0067], For example, the database query may include “select ai from skills where region=‘North America’;” to indicate that the value of the “ai” column of the “skills” table should be selected for all rows where the region column is equal to “North America.”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify reference combination A to obtain above limitation based on the teachings of Jain such as if the database query processing service cannot determine whether the natural language processing service is intended to be invoked or not, the database query processing service may provide an error message in response to the query, indicating that the query is not properly formatted to invoke the natural language processing service but is also not properly formatted for execution against existing database structures. For example, such error message may be triggered when the database query contains “select ai from” as the prefix, unless the structure referenced after “from” is an existing database structure with an existing column name matching the “ai” or target portion of the marker [0068].
Claim 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over reference combination A in view of Xu (US 11,971,985).
Regarding claim 5, reference combination A discloses elements if the claimed invention as noted but does not disclose wherein the semantic data model models the data
topology using multiple classes and associated properties that are semantically aligned with
natural language on which the AI/ML pipeline is trained. However, Xu discloses:
Xu claim 1, A system, comprising: a processor configured to: receive an indication that an existing natural language processing model, trained to classify textual content, should be retrained; generate a set comprising a plurality of training samples, wherein the set includes at least one synthetic training sample constructed using one or more linguistic hints,
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify reference combination A to obtain above limitation based on the teachings of Xu for the purpose of allowing the threat detection platform to support several possible queries, including: The ability to filter emails by topic or combination of topics; The ability to count the number of emails associated with a given topic; and The ability to modify the topics associated with an email, as well as create labels for those topics, col 15, lines 60-65.
Claim 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over reference combination A in view of Xu in view of Speiser (US 2020/0380315).
Regarding claim 6, reference combination A in view of Xu discloses elements of the claimed invention as noted but does not disclose wherein at least some of the classes are associated with multiple associations in the semantic data model. However, Speiser discloses:
Speiser [0027] Alternatively, if the classes are not mutually exclusive, multiple associations can be formed for each of the probabilities that are over a given threshold. For example, a “frozen food” micromodel and a “chicken” micromodel could both provide outputs of above a 90% threshold indicating that the image included an item belonging to both classes (i.e., frozen chicken). A set of networks can have associated classes that have both mutually exclusive subgroups and potentially overlapping subgroups.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify reference combination A in view of Xu to obtain above limitation based on the teachings of Speiser for the purpose of using a micromodel to identify items from a specific class can be referred to as being “associated” with that class. In specific embodiments of the invention, an encoding of an image of an item can be applied to a set of networks in parallel and each network in the set of networks can generate an inference therefrom in the form of a probability that an item in the image belongs to the class associated with the network [0004]
Claim 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over reference combination A in view of Velipasaoglu (US 2012/0191745).
Regarding claim 9, reference combination A discloses elements of the claimed invention as noted but does not disclose wherein at least one of the data access queries is based on one or more of:
filtering of at least one of classes and properties defined in the semantic data model
based on the user query; and
joining of at least one of classes and properties defined at multiple levels in the semantic
data model based on the user query. However, Velipasaoglu discloses:
Velipasaoglu [0022] Then in operation 204, the data-mining software scores each candidate query on (a) its well-formedness (e.g., using statistical language models derived from query logs and web documents and a class-based language model), (b) relevance to the user query as determined by similarity measures (e.g., click-vector similarity, context-vector similarity, web-based-aboutness vector similarity, and web-result category similarity), and (c) utility.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify reference combination A to obtain above limitation based on the teachings of Velipasaoglu for the purpose of providing data-mining software to generate one or more candidate queries by adding terms to the unit. The added terms result from a hybrid method that utilizes query sessions and a web corpus. The data-mining software also scores each candidate query on well-formedness of the candidate query, utility, and relevance to the user query. Then the data-mining software stores the scored candidate queries in a database for subsequent display in a graphical user interface for a search engine, see abstract.
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Townsend-Last (2025/0321944) in view of Li (US 11,561,979) in view of Truong (US 2024/0330279).
Examiner Note: Hereafter, above references will be entered as reference combination A.
Regarding claim 10, Townsend-Last discloses:
at least one processing device configured to:
Townsend-Last [0081]
provide a user query to a self-healing multi-agent artificial intelligence/machine
learning (AI/ML) pipeline, the user query requesting a response based on data stored in a data
topology, the data topology modeled using a semantic data model;
Townsend-Last [0108] FIG. 5A is a flowchart showing an example method 500 of operation of the AI/ML based query generator 123c for the Q&A assistant 123a of FIG. 1, according to some arrangements. As a general overview, the AI/ML based query generator 123c can automatically generate block queries based on natural-language, unstructured user prompts. Automatically generating block queries based on natural-language prompts enables a host of technical advantages, including improving the user's ability to interact with the block-based schema, automating repetitive coding tasks, error reduction in automatically-generated queries via obviating the need to type parameters, such as date ranges, and optimization of AI-generated queries.
generate an initial data access query for retrieving the data from the data topology
using the AI/ML pipeline and the semantic data model;
Townsend-Last [0108] FIG. 5A is a flowchart showing an example method 500 of operation of the AI/ML based query generator 123c for the Q&A assistant 123a of FIG. 1, according to some arrangements. As a general overview, the AI/ML based query generator 123c can automatically generate block queries based on natural-language, unstructured user prompts. Automatically generating block queries based on natural-language prompts enables a host of technical advantages, including improving the user's ability to interact with the block-based schema, automating repetitive coding tasks, error reduction in automatically-generated queries via obviating the need to type parameters, such as date ranges, and optimization of AI-generated queries.
determine that the initial data access query includes a hallucination or error;
Townsend-Last discloses elements of the claimed invention as noted but does not disclose above limitation. However, Li discloses:
Li abstract A computer-implemented method dynamically detects and corrects an error in a query. The method includes identifying an error in a first query. The method further includes generating a set of alternate execution structures for the first query. The method includes running each of the alternate execution structures, including generating a set of results corresponding to each set of alternate execution structure, comparing each of the set of results against each other of the set of results, and storing each of the set of alternate execution structures to include a result of the set of results, for each alternate structure. The method further includes selecting, from the set of alternate execution structures, a first alternate execution structure based on a predetermined criteria, and implementing the first alternate structure in place of the first query.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Townsend-Last to obtain above limitation based on the teachings of Li for the purpose of dynamically detecting and correcting errors in queries [title].
One of ordinary skill in the art would have been motivated to look to Li’s analogous art from the same field of endeavor as the claimed invention. Based on the above, there is a reasonable expectation of success in combining Townsend-Last and Li to meet limitations of the claimed invention.
perform an automatic loop one or more times, wherein the automatic loop includes:
generate an updated data access query for retrieving the data from the data
topology using the AI/ML pipeline and the semantic data model;
Li abstract Li abstract A computer-implemented method dynamically detects and corrects an error in a query. The method includes identifying an error in a first query. The method further includes generating a set of alternate execution structures for the first query.
determine whether the updated data access query includes a hallucination or
error; and
Li abstract, The method further includes selecting, from the set of alternate execution structures, a first alternate execution structure based on a predetermined criteria, and implementing the first alternate structure in place of the first query.
if the updated data access query includes a hallucination or error, repeating the automatic loop; and
Li col 1 lines 50-60 The program instructions are further configured to cause the process to generate, for the second query, a set of alternate execution structures. The program instructions are also configured to cause the process to run each alternate execution structure in the set of alternate execution structures. The program instructions are further configured to cause the process to select a second alternate execution structure from the set of alternate execution structures. The program instructions are further configured to cause the process to replace an execution structure of the first query with the second alternate execution structure.
use a final data access query with no hallucination or error to retrieve the data from
the data topology in order to generate the response.
Townsend-Last discloses elements of the claimed invention as noted but does not disclose above limitation. However, Truong discloses:
Truong [0046] On the other hand, if request processing module 202 determines at step 414 that the maximum number of attempts has been reached, then method 300 continues to step 418, where request processing module 202 displays the generated query and the execution error(s) to a user, receives a corrected query from the user, and executes the corrected query against database 114.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Townsend-Last to obtain above limitation based on the teachings of Truong for the purpose of generating and correcting database queries using language models [title].
One of ordinary skill in the art would have been motivated to look to Truong’s analogous art from the same field of endeavor as the claimed invention. Based on the above, there is a reasonable expectation of success in combining Townsend-Last and Truong to meet limitations of the claimed invention.
Claim(s) 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over reference combination A in view of nonfunctional descriptive material.
Claim 11 recites
the semantic data model represents the data topology and identifies dataspaces, classes, and properties associated with the data topology;
agents of the AI/ML pipeline use the semantic data model to identify a specific
dataspace, one or more specific classes, and one or more specific properties associated with the
user query; and
the AI/ML pipeline is configured to generate each data access query is generated based on the specific dataspace, the one or more specific classes, and the one or more specific properties.
The above printed material, particularly identifying dataspaces, classes, and properties associated with the data topology, is not functionally related to the claimed invention as a whole, i.e., a self-healing multi-agent artificial intelligence/machine learning model.
Claim 12, is/are rejected under 35 U.S.C. 103 as being unpatentable over reference combination A in view of nonfunctional descriptive material.
Claim 12 recites a model provides context to the agents of the AI/ML pipeline; the agents comprise one or more AI/ML models that generate responses when prompted
by the agents; and the responses from the one or more AI/ML models identify the specific dataspace, the one or more specific classes, the one or more specific properties, and the data access queries.
The above printed material, particularly models identify the specific dataspace, the one or more specific classes, the one or more specific properties, and the data access queries is not functionally related to the claimed invention as a whole, i.e., a self-healing multi-agent artificial intelligence/machine learning model.
Claim 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over reference combination A in view of Xu (US 11,971,985).
Regarding claim 13, reference combination A discloses elements if the claimed invention as noted but does not disclose wherein the semantic data model models the data
topology using multiple classes and associated properties that are semantically aligned with
natural language on which the AI/ML pipeline is trained. However, Xu discloses:
Xu claim 1, A system, comprising: a processor configured to: receive an indication that an existing natural language processing model, trained to classify textual content, should be retrained; generate a set comprising a plurality of training samples, wherein the set includes at least one synthetic training sample constructed using one or more linguistic hints,
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify reference combination A to obtain above limitation based on the teachings of Xu for the purpose of allowing the threat detection platform to support several possible queries, including: The ability to filter emails by topic or combination of topics; The ability to count the number of emails associated with a given topic; and The ability to modify the topics associated with an email, as well as create labels for those topics, col 15, lines 60-65.
Claim 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over reference combination A in view of Xu in view of Speiser (US 2020/0380315).
Regarding claim 14, reference combination A in view of Xu discloses elements of the claimed invention as noted but does not disclose wherein at least some of the classes are associated with multiple associations in the semantic data model. However, Speiser discloses:
Speiser [0027] Alternatively, if the classes are not mutually exclusive, multiple associations can be formed for each of the probabilities that are over a given threshold. For example, a “frozen food” micromodel and a “chicken” micromodel could both provide outputs of above a 90% threshold indicating that the image included an item belonging to both classes (i.e., frozen chicken). A set of networks can have associated classes that have both mutually exclusive subgroups and potentially overlapping subgroups.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify reference combination A in view of Xu to obtain above limitation based on the teachings of Speiser for the purpose of using a micromodel to identify items from a specific class can be referred to as being “associated” with that class. In specific embodiments of the invention, an encoding of an image of an item can be applied to a set of networks in parallel and each network in the set of networks can generate an inference therefrom in the form of a probability that an item in the image belongs to the class associated with the network [0004]
Claim(s) 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Townsend-Last (2025/0321944) in view of Li (US 11,561,979) in view of Truong (US 2024/0330279).
Examiner Note: Hereafter, above references will be entered as reference combination A.
Regarding claim 17, Townsend-Last discloses:
provide a user query to a self-healing multi-agent artificial intelligence/machine
learning (AI/ML) pipeline, the user query requesting a response based on data stored in a data
topology, the data topology modeled using a semantic data model;
Townsend-Last [0108] FIG. 5A is a flowchart showing an example method 500 of operation of the AI/ML based query generator 123c for the Q&A assistant 123a of FIG. 1, according to some arrangements. As a general overview, the AI/ML based query generator 123c can automatically generate block queries based on natural-language, unstructured user prompts. Automatically generating block queries based on natural-language prompts enables a host of technical advantages, including improving the user's ability to interact with the block-based schema, automating repetitive coding tasks, error reduction in automatically-generated queries via obviating the need to type parameters, such as date ranges, and optimization of AI-generated queries.
generate an initial data access query for retrieving the data from the data topology
using the AI/ML pipeline and the semantic data model;
Townsend-Last [0108] FIG. 5A is a flowchart showing an example method 500 of operation of the AI/ML based query generator 123c for the Q&A assistant 123a of FIG. 1, according to some arrangements. As a general overview, the AI/ML based query generator 123c can automatically generate block queries based on natural-language, unstructured user prompts. Automatically generating block queries based on natural-language prompts enables a host of technical advantages, including improving the user's ability to interact with the block-based schema, automating repetitive coding tasks, error reduction in automatically-generated queries via obviating the need to type parameters, such as date ranges, and optimization of AI-generated queries.
determine that the initial data access query includes a hallucination or error;
Townsend-Last discloses elements of the claimed invention as noted but does not disclose above limitation. However, Li discloses:
Li abstract A computer-implemented method dynamically detects and corrects an error in a query. The method includes identifying an error in a first query. The method further includes generating a set of alternate execution structures for the first query. The method includes running each of the alternate execution structures, including generating a set of results corresponding to each set of alternate execution structure, comparing each of the set of results against each other of the set of results, and storing each of the set of alternate execution structures to include a result of the set of results, for each alternate structure. The method further includes selecting, from the set of alternate execution structures, a first alternate execution structure based on a predetermined criteria, and implementing the first alternate structure in place of the first query.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Townsend-Last to obtain above limitation based on the teachings of Li for the purpose of dynamically detecting and correcting errors in queries [title].
One of ordinary skill in the art would have been motivated to look to Li’s analogous art from the same field of endeavor as the claimed invention. Based on the above, there is a reasonable expectation of success in combining Townsend-Last and Li to meet limitations of the claimed invention.
perform an automatic loop one or more times, wherein the automatic loop includes:
generate an updated data access query for retrieving the data from the data
topology using the AI/ML pipeline and the semantic data model;
Li abstract Li abstract A computer-implemented method dynamically detects and corrects an error in a query. The method includes identifying an error in a first query. The method further includes generating a set of alternate execution structures for the first query.
determine whether the updated data access query includes a hallucination or
error; and
Li abstract, The method further includes selecting, from the set of alternate execution structures, a first alternate execution structure based on a predetermined criteria, and implementing the first alternate structure in place of the first query.
if the updated data access query includes a hallucination or error, repeating the automatic loop; and
Li col 1 lines 50-60 The program instructions are further configured to cause the process to generate, for the second query, a set of alternate execution structures. The program instructions are also configured to cause the process to run each alternate execution structure in the set of alternate execution structures. The program instructions are further configured to cause the process to select a second alternate execution structure from the set of alternate execution structures. The program instructions are further configured to cause the process to replace an execution structure of the first query with the second alternate execution structure.
use a final data access query with no hallucination or error to retrieve the data from
the data topology in order to generate the response.
Townsend-Last discloses elements of the claimed invention as noted but does not disclose above limitation. However, Truong discloses:
Truong [0046] On the other hand, if request processing module 202 determines at step 414 that the maximum number of attempts has been reached, then method 300 continues to step 418, where request processing module 202 displays the generated query and the execution error(s) to a user, receives a corrected query from the user, and executes the corrected query against database 114.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Townsend-Last to obtain above limitation based on the teachings of Truong for the purpose of generating and correcting database queries using language models [title].
One of ordinary skill in the art would have been motivated to look to Truong’s analogous art from the same field of endeavor as the claimed invention. Based on the above, there is a reasonable expectation of success in combining Townsend-Last and Truong to meet limitations of the claimed invention.
Claim(s) 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over reference combination A in view of nonfunctional descriptive material.
Claim 18 recites
the semantic data model represents the data topology and identifies dataspaces, classes, and properties associated with the data topology;
agents of the AI/ML pipeline use the semantic data model to identify a specific
dataspace, one or more specific classes, and one or more specific properties associated with the
user query; and
the AI/ML pipeline is configured to generate each data access query is generated based on the specific dataspace, the one or more specific classes, and the one or more specific properties.
The above printed material, particularly identifying dataspaces, classes, and properties associated with the data topology, is not functionally related to the claimed invention as a whole, i.e., a self-healing multi-agent artificial intelligence/machine learning model.
Claim 12, is/are rejected under 35 U.S.C. 103 as being unpatentable over reference combination A in view of nonfunctional descriptive material.
Claim 12 recites a model provides context to the agents of the AI/ML pipeline; the agents comprise one or more AI/ML models that generate responses when prompted
by the agents; and the responses from the one or more AI/ML models identify the specific dataspace, the one or more specific classes, the one or more specific properties, and the data access queries.
The above printed material, particularly models identify the specific dataspace, the one or more specific classes, the one or more specific properties, and the data access queries is not functionally related to the claimed invention as a whole, i.e., a self-healing multi-agent artificial intelligence/machine learning model.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ETIENNE PIERRE LEROUX whose telephone number is (571)272-4022. The examiner can normally be reached M-F 8:00 am to 4:30 pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Apu Mofiz can be reached at 571 272 4080. 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.
/ETIENNE P LEROUX/Primary Examiner of Art Unit 2161