# US 11,907,840 B2 · Method and system for generating a dynamic sequence of actions > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,907,840 B2 - Document ID: US11907840B2 - Status: Granted - Kind: B2 - Application number: 18/061,189 - Filed: 2022-12-02 - Published: 2023-03-30 - Granted: 2024-02-20 - Earliest claimed: 2019-11-25 - Assignees: Verizon Patent and Licensing Inc. - Applicants: Verizon Patent and Licensing Inc. - Inventors: Sumit Singh; Balagangadhara Thilak Adiboina; Adithya Umakanth; Ganesh Narasimman; Sambasiva R Bhatta; Anurag Pant - Web page: https://patentgrep.com/patent/US11907840B2 ## CPC - G06N 3/08: Learning methods - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/045: Combinations of networks - G06N 3/09: Supervised learning - G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound - G06N 5/022: Knowledge engineering; Knowledge acquisition - G06N 20/20: Ensemble learning - G06Q 30/016: After-sales - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - 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 A device may receive historical data and real-time data associated with a troubleshooting service, identify, using a machine learning model, an optimal resolution based on the historical data and the real-time data, and identify, using a graph analytics model, an optimal path of actions based on the optimal resolution. The machine learning model may be trained to identify one of the set of historical issues associated with the unresolved issue, and identify the optimal resolution based on one of the set of historical resolutions associated with the one of the set of historical issues. The graph analytics model may be trained to generate a set of paths of actions based on the historical data, and identify the optimal path based on respective numbers of actions associated with the set of paths. The device may identify optimal action based on the optimal path and the prior action. ## Claims ### Claim 1 A method, comprising: identifying, by a device and based on a model, an optimal resolution, based on historical data and real-time data, associated with an unresolved issue; identifying, by the device and based on a graph analytics model, an optimal action to be performed based on the unresolved issue and the optimal resolution, wherein the graph analytics model is trained to generate a set of paths of actions between the unresolved issue and the optimal resolution, identify an optimal path of actions based on respective numbers of actions associated with the set of paths, and identify the optimal action based on the optimal path of actions, and wherein edges of an analytical graph, associated with the set of paths, are assigned respective weights to determine path lengths of the set of paths, wherein the analytical graph comprises a set of nodes, corresponding to historical actions between the unresolved issue and the optimal resolution, interconnected by the edges, and wherein identifying the optimal path of actions comprises selecting a subset of nodes, of the set of nodes that connect the unresolved issue and the optimal resolution based on the respective numbers of actions associated with the set of paths; and causing, by the device, the optimal action to be performed. ### Claim 2 (depends on 1) The method of claim 1, wherein the model comprises a random forest machine learning model. ### Claim 3 (depends on 1) The method of claim 1, wherein identifying the optimal resolution comprises: identifying a historical issue from the historical data that is similar to the unresolved issue, and identifying the optimal resolution based on a historical resolution used to resolve the historical issue. ### Claim 4 (depends on 1) The method of claim 1, wherein the real-time data includes information identifying one or more of: a prior action that was performed, a performance metric, an alarm, a notification, or a response. ### Claim 5 (depends on 1) The method of claim 1, wherein the analytical graph comprises nodes corresponding to historical issues, historical actions, or historical resolutions from the historical data. ### Claim 6 (depends on 1) The method of claim 1, wherein the edges correspond to historical paths of actions from the historical data. ### Claim 7 (depends on 1) The method of claim 1, wherein a weight, of the respective weights, is determined based on one or more of: a conditional probability associated with the historical data or the real-time data, or an efficacy associated with resolving a historical issue of the historical data. ### Claim 8 A device, comprising: one or more processors configured to: identify, based on a model, an optimal resolution, based on historical data and real-time data, associated with an unresolved issue; identify, based on a graph analytics model, an optimal action to be performed based on the unresolved issue and the optimal resolution, wherein the graph analytics model is trained to generate a set of paths of actions between the unresolved issue and the optimal resolution, identify an optimal path of actions based on respective numbers of actions associated with the set of paths, and identify the optimal action based on the optimal path of actions, and wherein edges of an analytical graph, associated with the set of paths, are assigned respective weights to determine path lengths of the set of paths, wherein the analytical graph comprises a set of nodes, corresponding to historical actions between the unresolved issue and the optimal resolution, interconnected by the edges, and wherein identifying the optimal path of actions comprises selecting a subset of nodes, of the set of nodes that connect the unresolved issue and the optimal resolution based on the respective numbers of actions associated with the set of paths; and cause the optimal action to be performed. ### Claim 9 (depends on 8) The device of claim 8, wherein the model comprises a random forest machine learning model. ### Claim 10 (depends on 8) The device of claim 8, wherein the one or more processors, to identify the optimal resolution, are configured to: identify a historical issue from the historical data that is similar to the unresolved issue, and identify the optimal resolution based on a historical resolution used to resolve the historical issue. ### Claim 11 (depends on 8) The device of claim 8, wherein the real-time data includes information identifying one or more of: a prior action that was performed, a performance metric, an alarm, a notification, or a response. ### Claim 12 (depends on 8) The device of claim 8, wherein the analytical graph comprises nodes corresponding to historical issues, historical actions, or historical resolutions from the historical data. ### Claim 13 (depends on 8) The device of claim 8, wherein the edges correspond to historical paths of actions from the historical data. ### Claim 14 (depends on 8) The device of claim 8, wherein a weight, of the respective weights, is determined based on one or more of: a conditional probability associated with the historical data or the real-time data, or an efficacy associated with resolving a historical issue of the historical data. ### Claim 15 A non-transitory computer-readable medium storing a set of instructions, the set of instructions comprising: one or more instructions that, when executed by one or more processors of a device, cause the device to: identify, based on a model, an optimal resolution, based on historical data and real-time data, associated with an unresolved issue; identify, based on a graph analytics model, an optimal action to be performed based on the unresolved issue and the optimal resolution, wherein the graph analytics model is trained to generate a set of paths of actions between the unresolved issue and the optimal resolution, identify an optimal path of actions based on respective numbers of actions associated with the set of paths, and identify the optimal action based on the optimal path of actions, and wherein edges of an analytical graph, associated with the set of paths, are assigned respective weights to determine path lengths of the set of paths, wherein the analytical graph comprises a set of nodes, corresponding to historical actions between the unresolved issue and the optimal resolution, interconnected by the edges, and wherein identifying the optimal path of actions comprises selecting a subset of nodes, of the set of nodes that connect the unresolved issue and the optimal resolution based on the respective numbers of actions associated with the set of paths; and cause the optimal action to be performed. ### Claim 16 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the one or more instructions, that cause the device to identify the optimal resolution, cause the device to: identify a historical issue from the historical data that is similar to the unresolved issue, and identify the optimal resolution based on a historical resolution used to resolve the historical issue. ### Claim 17 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the real-time data includes information identifying one or more of: a prior action that was performed, a performance metric, an alarm, a notification, or a response. ### Claim 18 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the analytical graph comprises nodes corresponding to historical issues, historical actions, or historical resolutions from the historical data. ### Claim 19 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the edges correspond to historical paths of actions from the historical data. ### Claim 20 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein a weight, of the respective weights, is determined based on one or more of: a conditional probability associated with the historical data or the real-time data, or an efficacy associated with resolving a historical issue of the historical data.