# US 12,184,509 B2 · Machine learning monitoring of wireless network infrastructure application servers > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,184,509 B2 - Document ID: US12184509B2 - Status: Granted - Kind: B2 - Application number: 17/745,277 - Filed: 2022-05-16 - Published: 2023-11-16 - Granted: 2024-12-31 - Earliest claimed: 2022-05-16 - Assignees: T-Mobile USA, Inc. - Applicants: T-Mobile USA, Inc. - Inventors: Sakshi Shori; Vijay Veggalam - Web page: https://patentgrep.com/patent/US12184509B2 ## CPC - H04L 41/16: using machine learning or artificial intelligence - H04L 41/0631: using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis - H04L 41/0661: {by reconfiguring faulty entities} - H04L 41/147: for predicting network behaviour - H04L 41/5009: Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF] - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract Machine learning systems and techniques are described herein for monitoring application servers within the computing infrastructure of a wireless network. A machine learning system may train and execute models based on performance metrics, error data, and failures from application servers configured to perform various functions relating to communication session authorization, monitoring, and charging for voice, data, and messaging communication services over the wireless network. Machine learning models may be configured to predict service degradations, detect performance anomalies, and determine root causes, and various models may output particular application servers, components, and/or predicted times of certain events. Based on the outputs of the machine learning models, the machine learning system may perform various actions for the wireless network infrastructure, including data outputting and/or executing processes on the application servers to analyze, restart, and/or repair particular components. ## Claims ### Claim 1 A computer-implemented method, comprising: receiving, by a computer system, a first server performance metric associated with a first charging system node of a wireless communication network, wherein the first server performance metric is associated with a plurality of network service requests processed by the wireless communication network; receiving, by the computer system, a second server performance metric associated with a second charging system node of the wireless communication network, wherein the second server performance metric is associated with the plurality of network service requests; providing, by the computer system, the first server performance metric and the second server performance metric as input to a machine learning model; determining, by the computer system, a third charging system node of the wireless communication network, based at least in part on an output of the machine learning model; and initiating, by the computer system, a network operations process associated with the third charging system node, wherein the third charging system node is configured to perform at least one of: authorizing network service requests within the wireless communication network; or maintaining subscriber device data and associated network usage data within the wireless communication network. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the plurality of network service requests includes: at least one voice communication session request provided by a voice service of the wireless communication network; at least one data session request provided by a data service of the wireless communication network; and at least one message request provided by a messaging service of the wireless communication network. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein the first server performance metric and the second server performance metric each include at least one of: a number of server errors over a time duration; a server error rate over the time duration; or a server request success ratio over the time duration. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein the output of the machine learning model includes data indicating a performance anomaly and a wireless communication service type associated with the performance anomaly. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the output of the machine learning model includes data indicating a time of a predicted further future failure associated with the third charging system node. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein initiating the network operations process comprises: initiating execution of a diagnostic process on the third charging system node; and determining, based at least in part on the diagnostic process, a server repair process for the third charging system node. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, further comprising: determining, based at least in part on the output of the machine learning model, a performance degradation associated with the wireless communication network, wherein the performance degradation includes at least one of: a current operational performance degradation of the wireless communication network; or a predicted future operational performance degradation of the wireless communication network. ### Claim 8 (depends on 1) The computer-implemented method of claim 1, wherein the first charging system node is configured to: receive a first application service request associated with a first network service request received by the wireless communication network; transmit, based at least in part on the first application service request, a second application service request to the third charging system node; receive, from the third charging system node, a response to the second application service request; and transmit a response to the first application service request, based at least in part on the response to the second application service request. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, wherein at least one of the first charging system node, the second charging system node, or the third charging system node is an account information and refill (AIR) system node, a charging control node (CCN), a service data point (SDP) node, a multi mediation (MM) node, an online charging control (OCC) node, or a charging traffic aggregator (CTA)/charging service aggregator (CSA). ### Claim 10 A system comprising: one or more processors; and one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising: receiving a first server performance metric associated with a first application server of a wireless communication network, wherein the first server performance metric is associated with a plurality of network service requests processed by the wireless communication network; receiving a second server performance metric associated with a second application server of the wireless communication network, wherein the second server performance metric is associated with the plurality of network service requests; providing the first server performance metric and the second server performance metric as input to a first machine learning model associated with service degradation and to a second machine learning model associated with anomaly detection or prediction; determining a third application server of the wireless communication network, based at least in part on an output of the first machine learning model or the second machine learning model; and initiating a network operations process associated with the third application server. ### Claim 11 (depends on 10) The system of claim 10, wherein the plurality of network service requests includes: at least one voice communication session request provided by a voice service of the wireless communication network; at least one data session request provided by a data service of the wireless communication network; and at least one message request provided by a messaging service of the wireless communication network. ### Claim 12 (depends on 10) The system of claim 10, wherein the first server performance metric and the second server performance metric each include at least one of: a number of server errors over a time duration; a server error rate over the time duration; or a server request success ratio over the time duration. ### Claim 13 (depends on 10) The system of claim 10, wherein the output of the second machine learning model includes data indicating a performance anomaly and a wireless communication service type associated with the performance anomaly. ### Claim 14 (depends on 10) The system of claim 10, wherein the output of the first machine learning model or the second machine learning model includes data indicating a time of a predicted further future failure associated with the third application server. ### Claim 15 (depends on 10) The system of claim 10, wherein initiating the network operations process comprises: initiating execution of a diagnostic process on the third application server; and determining, based at least in part on the diagnostic process, a server repair process for the third application server. ### Claim 16 (depends on 10) The system of claim 10, the operations further comprising: determining, based at least in part on the output of the first machine learning model, a performance degradation associated with the wireless communication network, wherein the performance degradation includes at least one of: a current operational performance degradation of the wireless communication network; or a predicted future operational performance degradation of the wireless communication network. ### Claim 17 (depends on 10) The system of claim 10, wherein the first application server is configured to: receive a first application service request associated with a first network service request received by the wireless communication network; transmit, based at least in part on the first application service request, a second application service request to the third application server; receive, from the third application server, a response to the second application service request; and transmit a response to the first application service request, based at least in part on the response to the second application service request. ### Claim 18 (depends on 10) The system of claim 10, wherein the third application server is configured to perform at least one of: authorizing network service requests within the wireless communication network; monitoring network communication sessions within the wireless communication network; or maintaining subscriber device data and associated network usage data within the wireless communication network. ### Claim 19 One or more non-transitory computer-readable media storing instructions executable by a processor, wherein the instructions, when executed, cause the processor to perform operations comprising: receiving a first server performance metric associated with a first charging system node of a wireless communication network, wherein the first server performance metric is associated with a plurality of network service requests processed by the wireless communication network; receiving a second server performance metric associated with a second charging system node of the wireless communication network, wherein the second server performance metric is associated with the plurality of network service requests; providing the first server performance metric and the second server performance metric as input to a first machine learning model associated with service degradation and to a second machine learning model associated with anomaly detection or prediction; determining a third charging system node of the wireless communication network, based at least in part on an output of the first machine learning model or the second machine learning model; and initiating a network operations process associated with the third charging system node. ### Claim 20 (depends on 19) The one or more non-transitory computer-readable media of claim 19, wherein initiating the network operations process comprises: initiating execution of a diagnostic process on the third charging system node; and determining, based at least in part on the diagnostic process, a server repair process for the third charging system node.