# US 12,007,869 B2 · Systems and methods for modeling computer resource metrics > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,007,869 B2 - Document ID: US12007869B2 - Status: Granted - Kind: B2 - Application number: 17/561,358 - Filed: 2021-12-23 - Published: 2022-04-14 - Granted: 2024-06-11 - Earliest claimed: 2015-06-17 - Assignees: Capital One Services, LLC - Applicants: Capital One Services, LLC - Inventors: Igor Trubin; Mark Schutt; Jeffery Robinson - Web page: https://patentgrep.com/patent/US12007869B2 ## CPC - G06F 11/3442: {for planning or managing the needed capacity} - G06F 11/3452: {Performance evaluation by statistical analysis} - G06Q 10/067: Enterprise or organisation modelling - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract In some embodiments, a plurality of devices may be respectively mapped to a plurality of interaction types. Statistical models may be generated, where the statistical models are indicative of relationships between aggregated interaction data related to the interaction types and aggregated resource utilization data related to the devices. With respect to each interaction type of the interaction types, the statistical models may be scored based on strength of one or more of the relationships. A subset of the statistical models may be selected based on the scoring for the interaction types. As an example, a first statistical model is included in the subset based on the scoring related to a first interaction type and a second statistical model is included in the subset based on the scoring related to a second interaction type different from the first interaction type. One or more of the devices may be remapped to one or more interaction types based on the selected subset of the statistical models. ## Claims ### Claim 1 A computer-implemented method comprising: generating statistical models indicative of correlations between aggregated interaction data for a plurality of interaction types and aggregated resource utilization data for a plurality of devices respectively mapped to the interaction types, the interaction types comprising a mobile-device interaction type and a non-mobile-device interaction type, the statistical models comprising a first model and a second model; for each model of the statistical models, scoring the model for one or more interaction types based on respective levels of the correlations (i) indicated by the model and (ii) related to resource type usages of the one or more interaction types; and remapping the devices and the interaction types based on the scoring of the statistical models by: (i) using the first model to remap one or more first devices having a first resource type to the mobile-device interaction type based on the first model indicating a high level of correlation between the mobile-device interaction type and the first resource type; and (ii) using the second model to remap one or more second devices having a second resource type to the non-mobile-device interaction type based on the second model indicating a high level of correlation between the non-mobile-device interaction type and the second resource type, the second resource type being different from the first resource type. ### Claim 2 (depends on 1) The method of claim 1, wherein the mobile-device interaction type is associated with a first service provided via a mobile user device, and the non-mobile-device interaction type is associated with a second service provided via a non-mobile user device. ### Claim 3 (depends on 1) The method of claim 1, wherein the devices include one or more servers of a financial institution providing a service related to at least one of the interaction types. ### Claim 4 (depends on 1) The method of claim 1, further comprising: performing load balancing based on the remapping of the devices and the interaction types. ### Claim 5 (depends on 4) The method of claim 4, wherein the statistical models comprise at least one of: a slope, an intercept, an R2 fit value, or a root-mean-squared-error. ### Claim 6 (depends on 1) The method of claim 1, wherein the generated statistical models are multivariate statistical models. ### Claim 7 (depends on 1) The method of claim 1, wherein the interaction types comprise at least one interaction type associated with at least one of: online banking, mobile banking, ATM operations, or mobile check cashing. ### Claim 8 A system, comprising: one or more hardware processors; and one or more memory units storing instructions executable by the one or more hardware processors to perform acts comprising: generating statistical models indicative of relationships between aggregated interaction data for a plurality of interaction types and aggregated resource utilization data for a plurality of devices respectively mapped to the interaction types, the interaction types comprising a first interaction type and a second interaction type different from the first interaction type, the statistical models comprising a first model and a second model; for each model of the statistical models, scoring the model for one or more interaction types based on respective levels of the relationships (i) indicated by the model and (ii) related to resource type usages of the one or more interaction types; causing, based on the selected subset of the statistical models and the scoring of the statistical models, remapping of the devices to the interaction types such that: (i) the first model is used to remap one or more first devices to the first interaction type based on the first model indicating a strong relationship between the first interaction type and a first resource type; and (ii) the second model is used to remap one or more second devices to the second interaction type based on the second model indicating a strong relationship between the first interaction type and a second resource type different from the first resource type. ### Claim 9 (depends on 8) The system of claim 8, wherein causing the remapping comprises: (i) using the first model to remap the one or more first devices to a mobile-device interaction type based on the first model indicating a strong relationship between the mobile-device interaction type and the first resource type; and (ii) using the second model to remap the one or more second devices to a non-mobile-device interaction type based on the second model indicating a strong relationship between the non-mobile-device interaction type and the second resource type. ### Claim 10 (depends on 8) The system of claim 8, wherein causing the remapping comprises: (i) using the first model to remap the one or more first devices to an automated teller machine (ATM) interaction type based on the first model indicating a strong relationship between the ATM interaction type and the first resource type; and (ii) using the second model to remap the one or more second devices to a non-ATM interaction type based on the second model indicating a strong relationship between the non-ATM interaction type and the second resource type. ### Claim 11 (depends on 8) The system of claim 8, wherein causing the remapping comprises: (i) using the first model to remap the one or more first devices to an automated teller machine (ATM) interaction type based on the first model indicating a strong relationship between the ATM interaction type and the first resource type; and (ii) using the second model to remap the one or more second devices to a mobile-device interaction type based on the second model indicating a strong relationship between the mobile-device interaction type and the second resource type. ### Claim 12 (depends on 11) The system of claim 11, wherein the statistical models comprise at least one of: a slope, an intercept, an R2 fit value, or a root-mean-squared-error. ### Claim 13 (depends on 8) The system of claim 8, wherein the generated statistical models are multivariate statistical models. ### Claim 14 (depends on 8) The system of claim 8, wherein the interaction types comprise at least one interaction type associated with at least one of: online banking, mobile banking, ATM operations, or mobile check cashing. ### Claim 15 One or more non-transitory computer-readable media storing instructions that, when executed by one or more hardware processors, perform operations comprising: generating statistical models indicative of relationships between aggregated interaction data for a plurality of interaction types and aggregated resource utilization data for a plurality of devices respectively mapped to the interaction types, the interaction types comprising a first interaction type and a second interaction type different from the first interaction type, the statistical models comprising a first model and a second model; for each model of the statistical models, scoring the model for one or more interaction types based on respective levels of the relationships (i) indicated by the model and (ii) related to resource type usages of the one or more interaction types; and causing, based on the scoring of the statistical models, remapping of one or more devices of the devices to one or more the interaction types such that: (i) the first model is used to remap one or more first devices to the first interaction type based on the first model indicating a strong relationship between the first interaction type and a first resource type; and (ii) the second model is used to remap one or more second devices to the second interaction type based on the second model indicating a strong relationship between the first interaction type and a second resource type different from the first resource type. ### Claim 16 (depends on 15) The one or more non-transitory computer-readable media of claim 15, wherein causing the remapping comprises: (i) using the first model to remap the one or more first devices to a mobile-device interaction type based on the first model indicating a strong relationship between the mobile-device interaction type and the first resource type; and (ii) using the second model to remap the one or more second devices to a non-mobile-device interaction type based on the second model indicating a strong relationship between the non-mobile-device interaction type and the second resource type. ### Claim 17 (depends on 15) The one or more non-transitory computer-readable media of claim 15, wherein causing the remapping comprises: (i) using the first model to remap the one or more first devices to an automated teller machine (ATM) interaction type based on the first model indicating a strong relationship between the ATM interaction type and the first resource type; and (ii) using the second model to remap the one or more second devices to a non-ATM interaction type based on the second model indicating a strong relationship between the non-ATM interaction type and the second resource type. ### Claim 18 (depends on 15) The one or more non-transitory computer-readable media of claim 15, wherein causing the remapping comprises: (i) using the first model to remap the one or more first devices to an automated teller machine (ATM) interaction type based on the first model indicating a strong relationship between the ATM interaction type and the first resource type; and (ii) using the second model to remap the one or more second devices to a mobile-device interaction type based on the second model indicating a strong relationship between the mobile-device interaction type and the second resource type. ### Claim 19 (depends on 18) The one or more non-transitory computer-readable media of claim 18, wherein the statistical models comprise at least one of: a slope, an intercept, an R2 fit value, or a root-mean-squared-error. ### Claim 20 (depends on 15) The one or more non-transitory computer-readable media of claim 15, wherein the interaction types comprise at least one interaction type associated with at least one of: online banking, mobile banking, ATM operations, or mobile check cashing.