# US 12,602,254 B2 · Job negotiation for workflow automation tasks > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,602,254 B2 - Document ID: US12602254B2 - Status: Granted - Kind: B2 - Application number: 18/152,754 - Filed: 2023-01-10 - Published: 2024-07-11 - Granted: 2026-04-14 - Earliest claimed: 2023-01-10 - Assignees: AT&T Intellectual Property I, L.P. - Applicants: AT&T Intellectual Property I, L.P. - Inventors: Eric Zavesky; Louis Alexander; Aritra Guha; Wen-Ling Hsu; Tan Xu; Jean-Francois Paiement - Web page: https://patentgrep.com/patent/US12602254B2 ## CPC - G06F 9/5038: {considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration (scheduling strategies G06F9/4881 and subgroups)} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Devices, non-transitory computer-readable media, and methods for job negotiation for workflow automation tasks are disclosed. An example method includes receiving a delegation of a task from a controller, wherein the task is one of a plurality of tasks that collectively forms a workflow, assessing an ability of the processing system to perform the task as defined in the delegation, suggesting a modification to the task as defined in the delegation, determining whether the modification was accepted by the controller, and declining the task when the modification is not accepted by the controller, and performing the task including the modification when the modification is accepted by the controller. ## Claims ### Claim 1 A method comprising: receiving, by a processing system including at least one processor, a delegation of a task from a controller, wherein the task is one of a plurality of tasks that collectively forms a workflow; assessing, by the processing system, an ability of the processing system to perform the task as defined in the delegation; suggesting, by the processing system, a modification to the task as defined in the delegation, wherein the modification comprises a redelegation of the task to another processing system or machine; determining, by the processing system, whether the modification was accepted by the controller; declining, by the processing system, the task when the modification is not accepted by the controller; and performing, by the processing system, the modification when the modification is accepted by the controller. ### Claim 2 (depends on 1) The method of claim 1, wherein the workflow is a partially automated workflow. ### Claim 3 (depends on 1) The method of claim 1, wherein the workflow is a fully automated workflow. ### Claim 4 (depends on 1) The method of claim 1, wherein the assessing comprises determining whether the processing system has access to at least one of: hardware necessary to perform the task as defined in the delegation and software necessary to perform the task as defined in the delegation. ### Claim 5 (depends on 1) The method of claim 1, wherein the assessing comprises determining whether the processing system is able to perform the task as defined in the delegation, including satisfying a condition imposed on a performance of the task. ### Claim 6 (depends on 5) The method of claim 5, wherein the condition relates to a timeframe within which the task must be performed. ### Claim 7 (depends on 5) The method of claim 5, wherein the modification further comprises a modification to the condition. ### Claim 8 (depends on 1) The method of claim 1, wherein the assessing comprises determine whether a status of the processing system will allow the processing system to perform the task as defined. ### Claim 9 (depends on 1) The method of claim 1, wherein the assessing comprises determine whether an environment of the processing system will allow the processing system to perform the task as defined. ### Claim 10 (depends on 1) The method of claim 1, wherein the assessing is performed using a machine learning model that is trained to take as an input the task as defined and to generate as an output a likelihood that the processing system is able to perform the task as defined, and wherein the machine learning model is trained using data about past tasks performed by the processing system. ### Claim 11 (depends on 1) The method of claim 1, wherein the assessing is performed in accordance with a risk/reward function. ### Claim 12 (depends on 1) The method of claim 1, wherein the processing system is part of a pool of machines available to the controller for performing the plurality of tasks. ### Claim 13 (depends on 1) The method of claim 1, further comprising: storing, by the processing system, a result of performing the task or the modification. ### Claim 14 (depends on 13) The method of claim 13, wherein the result is used by the processing system to assess an ability of the processing system to perform a subsequent task defined in a subsequent delegation by the controller. ### Claim 15 (depends on 14) The method of claim 14, wherein the result is used to generate a simulation that shows a probable outcome of performing the subsequent task. ### Claim 16 (depends on 1) The method of claim 1, wherein the assessing considers a limitation on the processing system that has been pre-programmed by a manufacturer of the processing system, and wherein the limitation causes the processing system to decline tasks of a specified type. ### Claim 17 (depends on 1) The method of claim 1, wherein the assessing considers a dependency associated with the task as defined in the delegation. ### Claim 18 (depends on 12) The method of claim 12, wherein each processing system in pool of machines is associated with a profile that specifies at least one capability of the each processing system. ### Claim 19 A non-transitory computer-readable medium storing instructions which, when executed by a processing system including at least one processor, cause the processing system to perform operations, the operations comprising: receiving a delegation of a task from a controller, wherein the task is one of a plurality of tasks that collectively forms a workflow; assessing an ability of the processing system to perform the task as defined in the delegation; suggesting a modification to the task as defined in the delegation, wherein the modification comprises a redelegation of the task to another processing system or machine; determining whether the modification was accepted by the controller; declining the task when the modification is not accepted by the controller; and performing the modification when the modification is accepted by the controller. ### Claim 20 A device comprising: a processing system including at least one processor; and a non-transitory computer-readable medium storing instructions which, when executed by the processing system, cause the processing system to perform operations, the operations comprising: receiving a delegation of a task from a controller, wherein the task is one of a plurality of tasks that collectively forms a workflow; assessing an ability of the processing system to perform the task as defined in the delegation; suggesting a modification to the task as defined in the delegation, wherein the modification comprises a redelegation of the task to another processing system or machine; determining whether the modification was accepted by the controller; declining the task when the modification is not accepted by the controller; and performing the modification when the modification is accepted by the controller.