# US 12,222,938 B1 · Systems and methods for query optimization > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,222,938 B1 - Document ID: US12222938B1 - Status: Granted - Kind: B1 - Application number: 18/394,493 - Filed: 2023-12-22 - Granted: 2025-02-11 - Earliest claimed: 2023-12-22 - Assignees: Capital One Services, LLC - Applicants: Capital One Services, LLC - Inventors: Mohamed Seck; Pavlo Savchuk; Nikitha Kondapally; Chris Gallucci; Prerna Kandhari; Anand Annamalai - Web page: https://patentgrep.com/patent/US12222938B1 ## CPC - G06F 16/24534: {Query rewriting; Transformation} - G06F 11/3409: {for performance assessment} - G06F 16/243: {Natural language query formulation} - G06F 16/2453: Query optimisation - G06F 16/2455: Query execution - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A method for query optimization may include capturing a proposed database query input into a user interface. The method may further include providing the proposed database query to a machine-learning model. The machine-learning model may have been trained, using one or more gathered and/or simulated sets of query execution overhead data and one or more gathered and/or simulated sets of database queries, to determine a potential execution overhead of a database query and output a query execution score. The method may further include outputting, by the machine-learning model, the query execution score based on the proposed database query. The method may further include determining that the query execution score exceeds a query execution score threshold. The method may further include triggering a corrective action based on the query execution score exceeding the query execution score threshold. ## Claims ### Claim 1 A computer-implemented method comprising: capturing, by one or more processors, a proposed database query input into a user interface; providing, by the one or more processors, the proposed database query to a machine-learning model, wherein the machine-learning model has been trained, using one or more gathered and/or simulated sets of query execution overhead data and one or more gathered and/or simulated sets of database queries, to determine a potential execution overhead of a database query and output a query execution score; outputting, by the machine-learning model, the query execution score based on the proposed database query; determining, by the one or more processors, that the query execution score exceeds a query execution score threshold; and triggering, by the one or more processors, a corrective action based on the query execution score exceeding the query execution score threshold. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, further comprising: obtaining an execution overhead resulting from executing the proposed database query; and retraining the machine-learning model using the proposed database query and the execution overhead. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein the potential execution overhead comprises a predicted query workload placed upon a database system. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein triggering the corrective action comprises: blocking, by the one or more processors, the proposed database query from being executed. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein triggering the corrective action comprises: identifying, by a natural language processor, one or more of a database update command or a database information request of the proposed database query; and generating, by the natural language processor, an optimized database query including the one or more of the database update command and the database information request. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein triggering the corrective action comprises: determining, by the one or more processors, that a threshold number of query execution scores exceeding the query execution score threshold has been reached; and outputting, by the one or more processors, one or more sets of user training outputs to the user interface. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, further comprising: recording, by the one or more processors, data associated with a unique user that input the proposed database query into the user interface. ### Claim 8 A computer-implemented method comprising: providing, by one or more processors, a proposed database query to a machine-learning model, wherein the machine-learning model has been trained, using one or more gathered and/or simulated sets of query execution overhead data and one or more gathered and/or simulated sets of database queries, to determine a potential execution overhead of a database query and output a query execution score; outputting, by the machine-learning model, the query execution score based on the proposed database query; determining, by the one or more processors, that the query execution score exceeds a query execution score threshold; identifying, by a natural language processor, one or more of a database update command or a database information request of the proposed database query; and generating, by the natural language processor, an optimized database query including the one or more of the database update command and the database information request. ### Claim 9 (depends on 8) The computer-implemented method of claim 8, further comprising: obtaining an execution overhead resulting from executing the proposed database query; and retraining the machine-learning model using the proposed database query and the execution overhead. ### Claim 10 (depends on 8) The computer-implemented method of claim 8, wherein the potential execution overhead comprises a predicted query workload placed upon a database system. ### Claim 11 (depends on 8) The computer-implemented method of claim 8, further comprising: outputting the optimized database query to a user interface. ### Claim 12 (depends on 8) The computer-implemented method of claim 8, further comprising: determining, by the one or more processors, that a threshold number of query execution scores exceeding the query execution score threshold has been reached; and outputting, by the one or more processors, one or more sets of user training outputs to a user interface. ### Claim 13 A system comprising: a memory storing instructions and a machine-learning model that has been trained to find associations between one or more gathered and/or simulated sets of query execution overhead data and one or more gathered and/or simulated sets of database queries to determine a potential execution overhead of a database query and output a query execution score; and a processor operatively connected to the memory and configured to execute the instructions to perform operations including: capturing, by one or more processors, a proposed database query input into a user interface; providing, by the one or more processors, the proposed database query to the machine-learning model; outputting, by the machine-learning model, the query execution score based on the proposed database query; determining, by the one or more processors, that the query execution score exceeds a query execution score threshold; and triggering, by the one or more processors, a corrective action based on the query execution score exceeding the query execution score threshold. ### Claim 14 (depends on 13) The system of claim 13, the operations further comprising: obtaining an execution overhead resulting from executing the proposed database query; and retraining the machine-learning model using the proposed database query and the execution overhead. ### Claim 15 (depends on 13) The system of claim 13, wherein the potential execution overhead comprises a predicted query workload placed upon a database system. ### Claim 16 (depends on 13) The system of claim 13, wherein triggering the corrective action comprises: blocking, by the one or more processors, the proposed database query from being executed. ### Claim 17 (depends on 13) The system of claim 13, further comprising a natural language processor. ### Claim 18 (depends on 17) The system of claim 17, wherein triggering the corrective action comprises: identifying, by the natural language processor, one or more of a database update command or a database information request of the proposed database query; and generating, by the natural language processor, an optimized database query including the one or more of the database update command and the database information request. ### Claim 19 (depends on 13) The system of claim 13, wherein triggering the corrective action comprises: determining, by the processor, that a threshold number of query execution scores exceeding the query execution score threshold has been reached; and outputting, by the processor, one or more sets of user training outputs to the user interface. ### Claim 20 (depends on 13) The system of claim 13, the operations further comprising: recording, by the processor, data associated with a unique user that input the proposed database query into the user interface.