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 upending
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 Tan (US 2025/0217351) in view of Clark (US 8,938,644).
Examiner Note: Hereafter, above references will be entered as combination A.
Tan discloses:
providing a user query to a self-healing multi-agent 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;
generating an initial data access query for retrieving the data from the data topology using the (AI/ML pipeline and the semantic model;
determining that the initial data access query includes a hallucination or error
Tan [abstract] A method for using a compiler to modify prompts for MLMs used to generate database queries includes receiving, at a query compiler, a first query of a database. The first query is at least in part generated by an MLM. The method includes determining, by the query compiler, whether the first query comprises an uncorrectable error. The method includes, responsive to determining that the first query comprises an uncorrectable error, generating a prompt element that describes the uncorrectable error and that is structured for inclusion in a prompt requesting the MLM to generate a modified first query that corrects the uncorrectable error. The method may include generating the prompt for the MLM, providing the prompt to the MLM, and responsive to providing the prompt, receiving, at the database query compiler, the modified first query that corrects the uncorrectable error.
INTERPRETATION:
pipeline = prompts for MLMs used to generate database queries
Tan [0022] Aspects of the disclosure address the above-mentioned and other challenges by providing a system capable of one or more of (1) generating an MLM prompt that requests the LLM to generate a database query; (2) analyzing the database query generated by the MLM to determine if the query contains any uncorrectable errors; and (3) generating a second prompt (e.g., a modified prompt in natural language) that requests the LLM to correct the errors in the database query. In some embodiments, the system may be configured to generate an MLM prompt. A prompt can refer to an input (e.g., a specific input) or instruction provided to a MLM to generate a response. The prompt may be written, at least in part, in natural language (e.g., natural language prompt). In some embodiments, the MLM prompt may include a request for the MLM to generate a database query. The prompt may also include context data that may assist the MLM in generating the database query. The system may provide the database query generated by the MLM to a query compiler. The query compiler may parse the database query and determine whether the database query has any errors. If the query has one or more errors, the query compiler may attempt to correct the errors. If the query compiler is not able to correct an error, the query compiler may provide the database query (with the correctable errors corrected) to a prompt generator. The prompt generator may generate a prompt (e.g., natural language prompt) for the MLM that includes one or more of (1) the database query, (2) data that provides information describing the uncorrectable error(s) (e.g., natural language description of the errors and instructions on how to correct the error(s)), and (3) context data that may help the MLM in correcting the error(s). The prompt generator may submit the prompt to the MLM so the MLM can generate a modified database query that corrects the error(s) remaining in the original database query. The MLM may then provide a response with a modified database query that corrects the error(s) that the query compiler was not able to correct. The system may then submit the modified query to the query compiler, which may then submit the database query to a database management system to execute the query.
generating an updated data access query for retrieving the data from the data topology using the AI/ML pipeline and the semantic model;
Interpretation:
Semantic = The prompt may also include context data that may assist the MLM in generating the database query
Tan discloses elements of the claimed invention as noted but does not disclose generating an updated data access query for retrieving the data from the data topology using the AI/ML pipeline and the semantic model;
determining whether the updated access query includes a hallucination or error and
if the updated access query includes a hallucination or error, repeating the automatic loop and using a final data access query with no hallucinations or error, as generated by the automatic loop to retrieve data from the topology in order to generate the response
However, Clark discloses:
Clark col 7 lines 45-62, As can be seen in FIG. 6, the system provides a plurality of feedback loops. A first feedback loop includes the PSF 625 and the exception monitor 615. In this first feedback loop, the system monitors, on a short-term basis, the execution of requests to detect deviations greater than a short-term threshold from the defined service level for the workload group to which the requests were defined. If such deviations are detected, the DBS 100 is adjusted, e.g., by adjusting the assignment of system resources to workload groups.
A second feedback loop includes the workload query (delay) manager 610, the PSF 625 and the exception monitor 615. In this second feedback loop, the DBS 100 monitors, on a long-term basis, to detect deviations from the expected level of service greater than a long-term threshold. If it does, the DBS 100 adjusts the execution of requests, e.g., by delaying, swapping out or aborting requests, to better provide the expected level of service.
It would have been obvious to one of ordinary skill on the art before the effective filing date of the claimed invention to modify Tan to obtain above limitation based on the teachings of Clark for the purpose of performing an automatic error recovery in a database system, see abstract.
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A in view of Mehta (US 2024/0364814).
Combination A discloses elements of the claimed invention as noted but does not disclose
wherein 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.
However, Mehta discloses:
Mehta claim 27, The computer-implemented method of claim 21, wherein executing the client self-service workflow based on receiving the indication of the user interaction with the personalized escalation digital text reply option comprises: executing a query corresponding to the predicted client-agent escalation class to identify a query response; and providing, for display, via the client device, a digital text reply comprising the query response.
It would have been obvious to one of ordinary skill on the art before the effective filing date of the claimed invention to modify combination A to obtain above limitation based on the teachings of Mehta for the purpose of providing machine learning models to generate personalized digital text reply options based on predicted client intent classifications and/or predicted client-agent escalation classes, see [0006].
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A in view of Mehta
Combination A in view of Mehta discloses the semantic data 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.
Tan [0022] Aspects of the disclosure address the above-mentioned and other challenges by providing a system capable of one or more of (1) generating an MLM prompt that requests the LLM to generate a database query; (2) analyzing the database query generated by the MLM to determine if the query contains any uncorrectable errors; and (3) generating a second prompt (e.g., a modified prompt in natural language) that requests the LLM to correct the errors in the database query. In some embodiments, the system may be configured to generate an MLM prompt. A prompt can refer to an input (e.g., a specific input) or instruction provided to a MLM to generate a response. The prompt may be written, at least in part, in natural language (e.g., natural language prompt). In some embodiments, the MLM prompt may include a request for the MLM to generate a database query. The prompt may also include context data that may assist the MLM in generating the database query. The system may provide the database query generated by the MLM to a query compiler. The query compiler may parse the database query and determine whether the database query has any errors. If the query has one or more errors, the query compiler may attempt to correct the errors. If the query compiler is not able to correct an error, the query compiler may provide the database query (with the correctable errors corrected) to a prompt generator. The prompt generator may generate a prompt (e.g., natural language prompt) for the MLM that includes one or more of (1) the database query, (2) data that provides information describing the uncorrectable error(s) (e.g., natural language description of the errors and instructions on how to correct the error(s)), and (3) context data that may help the MLM in correcting the error(s). The prompt generator may submit the prompt to the MLM so the MLM can generate a modified database query that corrects the error(s) remaining in the original database query. The MLM may then provide a response with a modified database query that corrects the error(s) that the query compiler was not able to correct. The system may then submit the modified query to the query compiler, which may then submit the database query to a database management system to execute the query.
generating an updated data access query for retrieving the data from the data topology using the AI/ML pipeline and the semantic model;
Interpretation:
Semantic = The prompt may also include context data that may assist the MLM in generating the database query
Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A in view of Mehta in view of Sprott (US 2024/0160856)
Combination A in view of Mehta 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, Sprott discloses:
Sprott [0104] This approach may be shown to teach the user the real predictors of success so that the user can understand why the AI system chose those columns.
It would have been obvious to one of ordinary skill on the art before the effective filing date of the claimed invention to modify combination A in view of Mehta to obtain above limitation based on the teachings of Mehta for the purpose of providing an automatic theorem solver to answer a query.
Claim(s) 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A in view of Mehta
Combination A in view of Mehta discloses: 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.
Mehta claim 27, The computer-implemented method of claim 21, wherein executing the client self-service workflow based on receiving the indication of the user interaction with the personalized escalation digital text reply option comprises: executing a query corresponding to the predicted client-agent escalation class to identify a query response; and providing, for display, via the client device, a digital text reply comprising the query response.
Claim(s) 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A in view of Mehta
Combination A in view of Mehta discloses wherein at least some of the classes are associated with multiple associations in the semantic data model.
Mehta claim 27, The computer-implemented method of claim 21, wherein executing the client self-service workflow based on receiving the indication of the user interaction with the personalized escalation digital text reply option comprises: executing a query corresponding to the predicted client-agent escalation class to identify a query response; and providing, for display, via the client device, a digital text reply comprising the query response.
Claim(s) 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A
Combination A discloses:
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.
Tan discloses:
providing a user query to a self-healing multi-agent 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;
generating an initial data access query for retrieving the data from the data topology using the (AI/ML pipeline and the semantic model;
determining that the initial data access query includes a hallucination or error
Tan [abstract] A method for using a compiler to modify prompts for MLMs used to generate database queries includes receiving, at a query compiler, a first query of a database. The first query is at least in part generated by an MLM. The method includes determining, by the query compiler, whether the first query comprises an uncorrectable error. The method includes, responsive to determining that the first query comprises an uncorrectable error, generating a prompt element that describes the uncorrectable error and that is structured for inclusion in a prompt requesting the MLM to generate a modified first query that corrects the uncorrectable error. The method may include generating the prompt for the MLM, providing the prompt to the MLM, and responsive to providing the prompt, receiving, at the database query compiler, the modified first query that corrects the uncorrectable error.
INTERPRETATION:
pipeline = prompts for MLMs used to generate database queries
Tan [0022] Aspects of the disclosure address the above-mentioned and other challenges by providing a system capable of one or more of (1) generating an MLM prompt that requests the LLM to generate a database query; (2) analyzing the database query generated by the MLM to determine if the query contains any uncorrectable errors; and (3) generating a second prompt (e.g., a modified prompt in natural language) that requests the LLM to correct the errors in the database query. In some embodiments, the system may be configured to generate an MLM prompt. A prompt can refer to an input (e.g., a specific input) or instruction provided to a MLM to generate a response. The prompt may be written, at least in part, in natural language (e.g., natural language prompt). In some embodiments, the MLM prompt may include a request for the MLM to generate a database query. The prompt may also include context data that may assist the MLM in generating the database query. The system may provide the database query generated by the MLM to a query compiler. The query compiler may parse the database query and determine whether the database query has any errors. If the query has one or more errors, the query compiler may attempt to correct the errors. If the query compiler is not able to correct an error, the query compiler may provide the database query (with the correctable errors corrected) to a prompt generator. The prompt generator may generate a prompt (e.g., natural language prompt) for the MLM that includes one or more of (1) the database query, (2) data that provides information describing the uncorrectable error(s) (e.g., natural language description of the errors and instructions on how to correct the error(s)), and (3) context data that may help the MLM in correcting the error(s). The prompt generator may submit the prompt to the MLM so the MLM can generate a modified database query that corrects the error(s) remaining in the original database query. The MLM may then provide a response with a modified database query that corrects the error(s) that the query compiler was not able to correct. The system may then submit the modified query to the query compiler, which may then submit the database query to a database management system to execute the query.
generating an updated data access query for retrieving the data from the data topology using the AI/ML pipeline and the semantic model;
Interpretation:
Semantic = The prompt may also include context data that may assist the MLM in generating the database query
Clark col 7 lines 45-62, As can be seen in FIG. 6, the system provides a plurality of feedback loops. A first feedback loop includes the PSF 625 and the exception monitor 615. In this first feedback loop, the system monitors, on a short-term basis, the execution of requests to detect deviations greater than a short-term threshold from the defined service level for the workload group to which the requests were defined. If such deviations are detected, the DBS 100 is adjusted, e.g., by adjusting the assignment of system resources to workload groups.
A second feedback loop includes the workload query (delay) manager 610, the PSF 625 and the exception monitor 615. In this second feedback loop, the DBS 100 monitors, on a long-term basis, to detect deviations from the expected level of service greater than a long-term threshold. If it does, the DBS 100 adjusts the execution of requests, e.g., by delaying, swapping out or aborting requests, to better provide the expected level of service.
It would have been obvious to one of ordinary skill on the art before the effective filing date of the claimed invention to modify Tan to obtain above limitation based on the teachings of Clark for the purpose of performing an automatic error recovery in a database system, see abstract.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A in view of Xu (2026/0119476).
Combination A discloses elements of the claimed invention as noted but does not disclose 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. However, Xu discloses:
Xu [0033] Corrective action can then be taken to address any conflicting aliases and/or the language model interface 105 can re-prompt the language model 113 to attempt to obtain a correct, executable database query.
Xu claim 3, based on determining that the syntax of the database query indicates one or more fields of the first table and that the alias corresponds to the first table, creating one or more edges between the first node and one or more of the second plurality of nodes that correspond to the one or more fields.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify combination A to obtain above limitation based on the teachings of Xu for the purpose of taking corrective to address any conflicting aliases and/or the language model interface can re-prompt the language model to attempt to obtain a correct, executable database query.
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A in view of Mehta
Combination A in view of Mehta discloses:
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.
Mehta claim 27, The computer-implemented method of claim 21, wherein executing the client self-service workflow based on receiving the indication of the user interaction with the personalized escalation digital text reply option comprises: executing a query corresponding to the predicted client-agent escalation class to identify a query response; and providing, for display, via the client device, a digital text reply comprising the query response.
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Tan in view of Clark..
Examiner Note: Hereafter, above references will be entered as combination A.
Tan discloses:
provide a user query to a self-healing multi-agent 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;
generate an initial data access query for retrieving the data from the data topology using the (AI/ML pipeline and the semantic model;
determine that the initial data access query includes a hallucination or error
Tan [abstract] A method for using a compiler to modify prompts for MLMs used to generate database queries includes receiving, at a query compiler, a first query of a database. The first query is at least in part generated by an MLM. The method includes determining, by the query compiler, whether the first query comprises an uncorrectable error. The method includes, responsive to determining that the first query comprises an uncorrectable error, generating a prompt element that describes the uncorrectable error and that is structured for inclusion in a prompt requesting the MLM to generate a modified first query that corrects the uncorrectable error. The method may include generating the prompt for the MLM, providing the prompt to the MLM, and responsive to providing the prompt, receiving, at the database query compiler, the modified first query that corrects the uncorrectable error.
INTERPRETATION:
pipeline = prompts for MLMs used to generate database queries
Tan [0022] Aspects of the disclosure address the above-mentioned and other challenges by providing a system capable of one or more of (1) generating an MLM prompt that requests the LLM to generate a database query; (2) analyzing the database query generated by the MLM to determine if the query contains any uncorrectable errors; and (3) generating a second prompt (e.g., a modified prompt in natural language) that requests the LLM to correct the errors in the database query. In some embodiments, the system may be configured to generate an MLM prompt. A prompt can refer to an input (e.g., a specific input) or instruction provided to a MLM to generate a response. The prompt may be written, at least in part, in natural language (e.g., natural language prompt). In some embodiments, the MLM prompt may include a request for the MLM to generate a database query. The prompt may also include context data that may assist the MLM in generating the database query. The system may provide the database query generated by the MLM to a query compiler. The query compiler may parse the database query and determine whether the database query has any errors. If the query has one or more errors, the query compiler may attempt to correct the errors. If the query compiler is not able to correct an error, the query compiler may provide the database query (with the correctable errors corrected) to a prompt generator. The prompt generator may generate a prompt (e.g., natural language prompt) for the MLM that includes one or more of (1) the database query, (2) data that provides information describing the uncorrectable error(s) (e.g., natural language description of the errors and instructions on how to correct the error(s)), and (3) context data that may help the MLM in correcting the error(s). The prompt generator may submit the prompt to the MLM so the MLM can generate a modified database query that corrects the error(s) remaining in the original database query. The MLM may then provide a response with a modified database query that corrects the error(s) that the query compiler was not able to correct. The system may then submit the modified query to the query compiler, which may then submit the database query to a database management system to execute the query.
generating an updated data access query for retrieving the data from the data topology using the AI/ML pipeline and the semantic model;
Interpretation:
Semantic = The prompt may also include context data that may assist the MLM in generating the database query
Tan discloses elements of the claimed invention as noted but does not disclose generate an updated data access query for retrieving the data from the data topology using the AI/ML pipeline and the semantic model;
determine whether the updated access query includes a hallucination or error and
if the updated access query includes a hallucination or error, repeating the automatic loop and using a final data access query with no hallucinations or error, as generated by the automatic loop to retrieve data from the topology in order to generate the response
However, Clark discloses:
Clark col 7 lines 45-62, As can be seen in FIG. 6, the system provides a plurality of feedback loops. A first feedback loop includes the PSF 625 and the exception monitor 615. In this first feedback loop, the system monitors, on a short-term basis, the execution of requests to detect deviations greater than a short-term threshold from the defined service level for the workload group to which the requests were defined. If such deviations are detected, the DBS 100 is adjusted, e.g., by adjusting the assignment of system resources to workload groups.
A second feedback loop includes the workload query (delay) manager 610, the PSF 625 and the exception monitor 615. In this second feedback loop, the DBS 100 monitors, on a long-term basis, to detect deviations from the expected level of service greater than a long-term threshold. If it does, the DBS 100 adjusts the execution of requests, e.g., by delaying, swapping out or aborting requests, to better provide the expected level of service.
It would have been obvious to one of ordinary skill on the art before the effective filing date of the claimed invention to modify Tan to obtain above limitation based on the teachings of Clark for the purpose of performing an automatic error recovery in a database system, see abstract.
Claim(s) 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A in view of Mehta (US 2024/0364814).
Combination A discloses elements of the claimed invention as noted but does not disclose
wherein 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.
However, Mehta discloses:
Mehta claim 27, The computer-implemented method of claim 21, wherein executing the client self-service workflow based on receiving the indication of the user interaction with the personalized escalation digital text reply option comprises: executing a query corresponding to the predicted client-agent escalation class to identify a query response; and providing, for display, via the client device, a digital text reply comprising the query response.
It would have been obvious to one of ordinary skill on the art before the effective filing date of the claimed invention to modify combination A to obtain above limitation based on the teachings of Mehta for the purpose of providing machine learning models to generate personalized digital text reply options based on predicted client intent classifications and/or predicted client-agent escalation classes, see [0006].
Claim(s 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A in view of Mehta
Combination A in view of Mehta discloses the semantic data 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.
Tan [0022] Aspects of the disclosure address the above-mentioned and other challenges by providing a system capable of one or more of (1) generating an MLM prompt that requests the LLM to generate a database query; (2) analyzing the database query generated by the MLM to determine if the query contains any uncorrectable errors; and (3) generating a second prompt (e.g., a modified prompt in natural language) that requests the LLM to correct the errors in the database query. In some embodiments, the system may be configured to generate an MLM prompt. A prompt can refer to an input (e.g., a specific input) or instruction provided to a MLM to generate a response. The prompt may be written, at least in part, in natural language (e.g., natural language prompt). In some embodiments, the MLM prompt may include a request for the MLM to generate a database query. The prompt may also include context data that may assist the MLM in generating the database query. The system may provide the database query generated by the MLM to a query compiler. The query compiler may parse the database query and determine whether the database query has any errors. If the query has one or more errors, the query compiler may attempt to correct the errors. If the query compiler is not able to correct an error, the query compiler may provide the database query (with the correctable errors corrected) to a prompt generator. The prompt generator may generate a prompt (e.g., natural language prompt) for the MLM that includes one or more of (1) the database query, (2) data that provides information describing the uncorrectable error(s) (e.g., natural language description of the errors and instructions on how to correct the error(s)), and (3) context data that may help the MLM in correcting the error(s). The prompt generator may submit the prompt to the MLM so the MLM can generate a modified database query that corrects the error(s) remaining in the original database query. The MLM may then provide a response with a modified database query that corrects the error(s) that the query compiler was not able to correct. The system may then submit the modified query to the query compiler, which may then submit the database query to a database management system to execute the query.
generating an updated data access query for retrieving the data from the data topology using the AI/ML pipeline and the semantic model;
Interpretation:
Semantic = The prompt may also include context data that may assist the MLM in generating the database query
Claim(s) 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A in view of Mehta
Combination A in view of Mehta discloses: 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.
Mehta claim 27, The computer-implemented method of claim 21, wherein executing the client self-service workflow based on receiving the indication of the user interaction with the personalized escalation digital text reply option comprises: executing a query corresponding to the predicted client-agent escalation class to identify a query response; and providing, for display, via the client device, a digital text reply comprising the query response.
Claim(s) 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A in view of Mehta
Combination A in view of Mehta discloses wherein at least some of the classes are associated with multiple associations in the semantic data model.
Mehta claim 27, The computer-implemented method of claim 21, wherein executing the client self-service workflow based on receiving the indication of the user interaction with the personalized escalation digital text reply option comprises: executing a query corresponding to the predicted client-agent escalation class to identify a query response; and providing, for display, via the client device, a digital text reply comprising the query response.
Claim(s) 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A
Combination A discloses:
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.
Tan discloses:
providing a user query to a self-healing multi-agent 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;
generating an initial data access query for retrieving the data from the data topology using the (AI/ML pipeline and the semantic model;
determining that the initial data access query includes a hallucination or error
Tan [abstract] A method for using a compiler to modify prompts for MLMs used to generate database queries includes receiving, at a query compiler, a first query of a database. The first query is at least in part generated by an MLM. The method includes determining, by the query compiler, whether the first query comprises an uncorrectable error. The method includes, responsive to determining that the first query comprises an uncorrectable error, generating a prompt element that describes the uncorrectable error and that is structured for inclusion in a prompt requesting the MLM to generate a modified first query that corrects the uncorrectable error. The method may include generating the prompt for the MLM, providing the prompt to the MLM, and responsive to providing the prompt, receiving, at the database query compiler, the modified first query that corrects the uncorrectable error.
INTERPRETATION:
pipeline = prompts for MLMs used to generate database queries
Tan [0022] Aspects of the disclosure address the above-mentioned and other challenges by providing a system capable of one or more of (1) generating an MLM prompt that requests the LLM to generate a database query; (2) analyzing the database query generated by the MLM to determine if the query contains any uncorrectable errors; and (3) generating a second prompt (e.g., a modified prompt in natural language) that requests the LLM to correct the errors in the database query. In some embodiments, the system may be configured to generate an MLM prompt. A prompt can refer to an input (e.g., a specific input) or instruction provided to a MLM to generate a response. The prompt may be written, at least in part, in natural language (e.g., natural language prompt). In some embodiments, the MLM prompt may include a request for the MLM to generate a database query. The prompt may also include context data that may assist the MLM in generating the database query. The system may provide the database query generated by the MLM to a query compiler. The query compiler may parse the database query and determine whether the database query has any errors. If the query has one or more errors, the query compiler may attempt to correct the errors. If the query compiler is not able to correct an error, the query compiler may provide the database query (with the correctable errors corrected) to a prompt generator. The prompt generator may generate a prompt (e.g., natural language prompt) for the MLM that includes one or more of (1) the database query, (2) data that provides information describing the uncorrectable error(s) (e.g., natural language description of the errors and instructions on how to correct the error(s)), and (3) context data that may help the MLM in correcting the error(s). The prompt generator may submit the prompt to the MLM so the MLM can generate a modified database query that corrects the error(s) remaining in the original database query. The MLM may then provide a response with a modified database query that corrects the error(s) that the query compiler was not able to correct. The system may then submit the modified query to the query compiler, which may then submit the database query to a database management system to execute the query.
generating an updated data access query for retrieving the data from the data topology using the AI/ML pipeline and the semantic model;
Interpretation:
Semantic = The prompt may also include context data that may assist the MLM in generating the database query
Clark col 7 lines 45-62, As can be seen in FIG. 6, the system provides a plurality of feedback loops. A first feedback loop includes the PSF 625 and the exception monitor 615. In this first feedback loop, the system monitors, on a short-term basis, the execution of requests to detect deviations greater than a short-term threshold from the defined service level for the workload group to which the requests were defined. If such deviations are detected, the DBS 100 is adjusted, e.g., by adjusting the assignment of system resources to workload groups.
A second feedback loop includes the workload query (delay) manager 610, the PSF 625 and the exception monitor 615. In this second feedback loop, the DBS 100 monitors, on a long-term basis, to detect deviations from the expected level of service greater than a long-term threshold. If it does, the DBS 100 adjusts the execution of requests, e.g., by delaying, swapping out or aborting requests, to better provide the expected level of service.
It would have been obvious to one of ordinary skill on the art before the effective filing date of the claimed invention to modify Tan to obtain above limitation based on the teachings of Clark for the purpose of performing an automatic error recovery in a database system, see abstract.
Claim(s) 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A in view of Xu (2026/0119476).
Combination A discloses elements of the claimed invention as noted but does not disclose 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. However, Xu discloses:
Xu [0033] Corrective action can then be taken to address any conflicting aliases and/or the language model interface 105 can re-prompt the language model 113 to attempt to obtain a correct, executable database query.
Xu claim 3, based on determining that the syntax of the database query indicates one or more fields of the first table and that the alias corresponds to the first table, creating one or more edges between the first node and one or more of the second plurality of nodes that correspond to the one or more fields.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify combination A to obtain above limitation based on the teachings of Xu for the purpose of taking corrective to address any conflicting aliases and/or the language model interface can re-prompt the language model to attempt to obtain a correct, executable database query.
Claim(s) 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Tan in view of Clark..
Examiner Note: Hereafter, above references will be entered as combination A.
Tan discloses:
provide a user query to a self-healing multi-agent 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;
generate an initial data access query for retrieving the data from the data topology using the (AI/ML pipeline and the semantic model;
determine that the initial data access query includes a hallucination or error
Tan [abstract] A method for using a compiler to modify prompts for MLMs used to generate database queries includes receiving, at a query compiler, a first query of a database. The first query is at least in part generated by an MLM. The method includes determining, by the query compiler, whether the first query comprises an uncorrectable error. The method includes, responsive to determining that the first query comprises an uncorrectable error, generating a prompt element that describes the uncorrectable error and that is structured for inclusion in a prompt requesting the MLM to generate a modified first query that corrects the uncorrectable error. The method may include generating the prompt for the MLM, providing the prompt to the MLM, and responsive to providing the prompt, receiving, at the database query compiler, the modified first query that corrects the uncorrectable error.
INTERPRETATION:
pipeline = prompts for MLMs used to generate database queries
Tan [0022] Aspects of the disclosure address the above-mentioned and other challenges by providing a system capable of one or more of (1) generating an MLM prompt that requests the LLM to generate a database query; (2) analyzing the database query generated by the MLM to determine if the query contains any uncorrectable errors; and (3) generating a second prompt (e.g., a modified prompt in natural language) that requests the LLM to correct the errors in the database query. In some embodiments, the system may be configured to generate an MLM prompt. A prompt can refer to an input (e.g., a specific input) or instruction provided to a MLM to generate a response. The prompt may be written, at least in part, in natural language (e.g., natural language prompt). In some embodiments, the MLM prompt may include a request for the MLM to generate a database query. The prompt may also include context data that may assist the MLM in generating the database query. The system may provide the database query generated by the MLM to a query compiler. The query compiler may parse the database query and determine whether the database query has any errors. If the query has one or more errors, the query compiler may attempt to correct the errors. If the query compiler is not able to correct an error, the query compiler may provide the database query (with the correctable errors corrected) to a prompt generator. The prompt generator may generate a prompt (e.g., natural language prompt) for the MLM that includes one or more of (1) the database query, (2) data that provides information describing the uncorrectable error(s) (e.g., natural language description of the errors and instructions on how to correct the error(s)), and (3) context data that may help the MLM in correcting the error(s). The prompt generator may submit the prompt to the MLM so the MLM can generate a modified database query that corrects the error(s) remaining in the original database query. The MLM may then provide a response with a modified database query that corrects the error(s) that the query compiler was not able to correct. The system may then submit the modified query to the query compiler, which may then submit the database query to a database management system to execute the query.
generating an updated data access query for retrieving the data from the data topology using the AI/ML pipeline and the semantic model;
Interpretation:
Semantic = The prompt may also include context data that may assist the MLM in generating the database query
Tan discloses elements of the claimed invention as noted but does not disclose generate an updated data access query for retrieving the data from the data topology using the AI/ML pipeline and the semantic model;
determine whether the updated access query includes a hallucination or error and
if the updated access query includes a hallucination or error, repeating the automatic loop and using a final data access query with no hallucinations or error, as generated by the automatic loop to retrieve data from the topology in order to generate the response
However, Clark discloses:
Clark col 7 lines 45-62, As can be seen in FIG. 6, the system provides a plurality of feedback loops. A first feedback loop includes the PSF 625 and the exception monitor 615. In this first feedback loop, the system monitors, on a short-term basis, the execution of requests to detect deviations greater than a short-term threshold from the defined service level for the workload group to which the requests were defined. If such deviations are detected, the DBS 100 is adjusted, e.g., by adjusting the assignment of system resources to workload groups.
A second feedback loop includes the workload query (delay) manager 610, the PSF 625 and the exception monitor 615. In this second feedback loop, the DBS 100 monitors, on a long-term basis, to detect deviations from the expected level of service greater than a long-term threshold. If it does, the DBS 100 adjusts the execution of requests, e.g., by delaying, swapping out or aborting requests, to better provide the expected level of service.
It would have been obvious to one of ordinary skill on the art before the effective filing date of the claimed invention to modify Tan to obtain above limitation based on the teachings of Clark for the purpose of performing an automatic error recovery in a database system, see abstract.
Claim(s) 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A in view of Mehta (US 2024/0364814).
Combination A discloses elements of the claimed invention as noted but does not disclose
wherein 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.
However, Mehta discloses:
Mehta claim 27, The computer-implemented method of claim 21, wherein executing the client self-service workflow based on receiving the indication of the user interaction with the personalized escalation digital text reply option comprises: executing a query corresponding to the predicted client-agent escalation class to identify a query response; and providing, for display, via the client device, a digital text reply comprising the query response.
It would have been obvious to one of ordinary skill on the art before the effective filing date of the claimed invention to modify combination A to obtain above limitation based on the teachings of Mehta for the purpose of providing machine learning models to generate personalized digital text reply options based on predicted client intent classifications and/or predicted client-agent escalation classes, see [0006].
Claim(s 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A in view of Mehta
Combination A in view of Mehta discloses the semantic data 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.
Tan [0022] Aspects of the disclosure address the above-mentioned and other challenges by providing a system capable of one or more of (1) generating an MLM prompt that requests the LLM to generate a database query; (2) analyzing the database query generated by the MLM to determine if the query contains any uncorrectable errors; and (3) generating a second prompt (e.g., a modified prompt in natural language) that requests the LLM to correct the errors in the database query. In some embodiments, the system may be configured to generate an MLM prompt. A prompt can refer to an input (e.g., a specific input) or instruction provided to a MLM to generate a response. The prompt may be written, at least in part, in natural language (e.g., natural language prompt). In some embodiments, the MLM prompt may include a request for the MLM to generate a database query. The prompt may also include context data that may assist the MLM in generating the database query. The system may provide the database query generated by the MLM to a query compiler. The query compiler may parse the database query and determine whether the database query has any errors. If the query has one or more errors, the query compiler may attempt to correct the errors. If the query compiler is not able to correct an error, the query compiler may provide the database query (with the correctable errors corrected) to a prompt generator. The prompt generator may generate a prompt (e.g., natural language prompt) for the MLM that includes one or more of (1) the database query, (2) data that provides information describing the uncorrectable error(s) (e.g., natural language description of the errors and instructions on how to correct the error(s)), and (3) context data that may help the MLM in correcting the error(s). The prompt generator may submit the prompt to the MLM so the MLM can generate a modified database query that corrects the error(s) remaining in the original database query. The MLM may then provide a response with a modified database query that corrects the error(s) that the query compiler was not able to correct. The system may then submit the modified query to the query compiler, which may then submit the database query to a database management system to execute the query.
generating an updated data access query for retrieving the data from the data topology using the AI/ML pipeline and the semantic model;
Interpretation:
Semantic = The prompt may also include context data that may assist the MLM in generating the database query
Claim(s) 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over combination A
Combination A discloses:
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.
Tan discloses:
providing a user query to a self-healing multi-agent 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;
generating an initial data access query for retrieving the data from the data topology using the (AI/ML pipeline and the semantic model;
determining that the initial data access query includes a hallucination or error
Tan [abstract] A method for using a compiler to modify prompts for MLMs used to generate database queries includes receiving, at a query compiler, a first query of a database. The first query is at least in part generated by an MLM. The method includes determining, by the query compiler, whether the first query comprises an uncorrectable error. The method includes, responsive to determining that the first query comprises an uncorrectable error, generating a prompt element that describes the uncorrectable error and that is structured for inclusion in a prompt requesting the MLM to generate a modified first query that corrects the uncorrectable error. The method may include generating the prompt for the MLM, providing the prompt to the MLM, and responsive to providing the prompt, receiving, at the database query compiler, the modified first query that corrects the uncorrectable error.
INTERPRETATION:
pipeline = prompts for MLMs used to generate database queries
Tan [0022] Aspects of the disclosure address the above-mentioned and other challenges by providing a system capable of one or more of (1) generating an MLM prompt that requests the LLM to generate a database query; (2) analyzing the database query generated by the MLM to determine if the query contains any uncorrectable errors; and (3) generating a second prompt (e.g., a modified prompt in natural language) that requests the LLM to correct the errors in the database query. In some embodiments, the system may be configured to generate an MLM prompt. A prompt can refer to an input (e.g., a specific input) or instruction provided to a MLM to generate a response. The prompt may be written, at least in part, in natural language (e.g., natural language prompt). In some embodiments, the MLM prompt may include a request for the MLM to generate a database query. The prompt may also include context data that may assist the MLM in generating the database query. The system may provide the database query generated by the MLM to a query compiler. The query compiler may parse the database query and determine whether the database query has any errors. If the query has one or more errors, the query compiler may attempt to correct the errors. If the query compiler is not able to correct an error, the query compiler may provide the database query (with the correctable errors corrected) to a prompt generator. The prompt generator may generate a prompt (e.g., natural language prompt) for the MLM that includes one or more of (1) the database query, (2) data that provides information describing the uncorrectable error(s) (e.g., natural language description of the errors and instructions on how to correct the error(s)), and (3) context data that may help the MLM in correcting the error(s). The prompt generator may submit the prompt to the MLM so the MLM can generate a modified database query that corrects the error(s) remaining in the original database query. The MLM may then provide a response with a modified database query that corrects the error(s) that the query compiler was not able to correct. The system may then submit the modified query to the query compiler, which may then submit the database query to a database management system to execute the query.
generating an updated data access query for retrieving the data from the data topology using the AI/ML pipeline and the semantic model;
Interpretation:
Semantic = The prompt may also include context data that may assist the MLM in generating the database query
Clark col 7 lines 45-62, As can be seen in FIG. 6, the system provides a plurality of feedback loops. A first feedback loop includes the PSF 625 and the exception monitor 615. In this first feedback loop, the system monitors, on a short-term basis, the execution of requests to detect deviations greater than a short-term threshold from the defined service level for the workload group to which the requests were defined. If such deviations are detected, the DBS 100 is adjusted, e.g., by adjusting the assignment of system resources to workload groups.
A second feedback loop includes the workload query (delay) manager 610, the PSF 625 and the exception monitor 615. In this second feedback loop, the DBS 100 monitors, on a long-term basis, to detect deviations from the expected level of service greater than a long-term threshold. If it does, the DBS 100 adjusts the execution of requests, e.g., by delaying, swapping out or aborting requests, to better provide the expected level of service.
It would have been obvious to one of ordinary skill on the art before the effective filing date of the claimed invention to modify Tan to obtain above limitation based on the teachings of Clark for the purpose of performing
Response to Arguments
Applicant’s arguments with respect to claim(s) 1-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant argues:
The Office Action concedes that Townsend-Last fails to disclose using a final data
access query with no hallucination or error to retrieve data from a data topology in order to
generate a response. To remedy this conceded deficiency in Townsend-Last, the Office
Action relies on paragraph [0046] of Truong. Office Action, pages 7-8.
Paragraph [0046] of Truong merely describes receiving a corrected query from a user
and executing the corrected query against a database. Truong expressly states that the
corrected query comes from a user, not an automatic loop as recited in Claim 1. Truong does
not disclose or suggest using a final data access query with no hallucination or error, as
generated by an automatic loop, to retrieve data from a data topology in order to generate a
response.
Moreover, the Office Action does not explain why one of ordinary skill in the art
would modify the AI assistant of Townsend-Last with the error correction mechanism of Li
and the user queries of Truong to arrive at the claimed self-healing pipeline. The Office
Action asserts that this combination would bc obvious "for the purpose of dynamically
detecting and correcting errors in queries" and "generating and correcting database queries
using language models." Office Action, pages 6-8. However, this combination differs
fundamentally from the self-healing multi-agent AI/ML features recited in Claim 1. Truong
uses a corrected query from a user, which is not generated by an automatic loop. Even
assuming these references could be combined, one of ordinary skill in the art would not and
For at least these reasons, Claim 1 and its dependent claims are allowable. For similar
reasons, Claims 10 and 17 and their respective dependent claims are allowable.
Examiner Responds:
Applicant’s arguments with respect to claim(s) 1 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant Argues:
With respect to Claims 2, 3, 11, 12, 18, and 19, the Office Action's assertions
regarding alleged "nonfunctional descriptive material" are incorrect. These claims do not
merely recite "printed material" or other nonfunctional descriptive material. Instead, these
claims recite specific elements that are functionally related to operations performed by an
AI/ML pipeline. As such, pursuant to MPEP § 2112.01, these elements cannot be ignored.s an example, Claim 2 recites that:
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 first paragraph of Claim 2 indicates that the semantic data model identifies dataspaces,
classes, and properties associated with the data topology. The next two paragraphs of Claim 2
clearly tie the semantic data model to the AI/ML pipeline - 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. Each data access query is
generated based on the specific dataspace, the one or more specific classes, and the one or
more specific properties. Thus, the contents of the semantic data model are clearly tied to the
operations of the AI/ML pipeline, and the operations of the AI/ML pipeline are expressly
recited in Claim 2. As a result, the Office is not permitted to ignore these elements as
somehow being nonfunctional.
Examiner Responds:
Applicant’s arguments with respect to claim(s) Claims 2, 3, 11, 12, 18, and 19 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant Argues:
As another example, Claim 3 recites that:
the semantic data 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 first paragraph of Claim 3 indicates that the semantic data model provides context to the
agents of the AI/ML pipeline. The next two paragraphs of Claim 3 recite operations that
involve the agents of the AI/ML pipeline. Again, these are all functional aspects, and the
Office is not permitted to ignore these elements as somehow being nonfunctional.
Examiner Responds:
Applicant’s arguments with respect to claim(s) Claims 2, 3, 11, 12, 18, and 19 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant Argues:
Claims 2, 3, 11, 12, 18, and 19 all recite features having functional relationships to
other elements recited in those claims and in their parent claims. These elements are therefore
not merely "nonfunctional descriptive material."
Examiner Responds:
Applicant’s arguments with respect to claim(s) Claims 2, 3, 11, 12, 18, and 19 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant Argues:
The Applicant therefore respectfully requests that the § 103 rejections be withdrawn.
Examiner Responds:
Applicant’s arguments with respect to claim(s) Claims 1-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
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
Prosecution Insights