# US 2024/0205336 A1 · Systems and methods for relative gain in predictive routing > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2024/0205336 A1 - Document ID: US20240205336A1 - Status: Published application - Kind: A1 - Application number: 18/365,577 - Filed: 2023-08-04 - Published: 2024-06-20 - Earliest claimed: 2022-12-19 - Assignees: Genesys Cloud Services, Inc. - Applicants: Genesys Cloud Services, Inc. - Inventors: Emir Muñoz; Apostolos Galanpoulos; Greg Toth; David Farrell; Maciej Dabrowski - Web page: https://patentgrep.com/patent/US20240205336A1 ## CPC - H04M 3/5233: {Operator skill based call distribution} - H04M 3/5175: {Call or contact centers supervision arrangements} - H04M 3/5238: {with waiting time or load prediction arrangements} - H04M 2203/402: Agent or workforce management - H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08) ## Abstract A method of routing interactions to contact center agents according to an embodiment includes identifying an interaction to be routed to a contact center agent, determining a predictive routing score for each prospective contact center agent to which the interaction can be routed based on a historical performance of each prospective agent, determining a relative gain for each prospective agent based on an interaction class of the interaction, an agent class performance of the prospective agent, and an agent value of the prospective agent, wherein the relative gain of a respective agent is indicative of a relative optimization improvement of routing the interaction to the respective agent relative to another of the prospective agents, ranking the prospective agents based on the associated predictive routing score and the associated relative gain for each prospective agent, and routing the interaction to an agent selected based on the ranking of the prospective agents. ## Claims ### Claim 1 A method of leveraging relative gain in predictive routing of interactions to contact center agents, the method comprising: identifying an interaction to be routed to a contact center agent; determining a predictive routing score for each prospective contact center agent of a plurality of prospective contact center agents to which the interaction can be routed based on a historical performance of each prospective contact center agent; determining a relative gain for each prospective contact center agent based on an interaction class of the interaction, an agent class performance of the prospective contact center agent, and an agent value of the prospective contact center agent, wherein the relative gain of a respective contact center agent is indicative of a relative optimization improvement of routing the interaction to the respective contact center agent relative to another of the prospective contact center agents; ranking the prospective contact center agents based on the associated predictive routing score and the associated relative gain for each prospective contact center agent; selecting the contact center agent of the prospective contact center agents based on the ranking of the prospective contact center agents; and routing the interaction to the selected contact center agent. ### Claim 2 (depends on 1) The method of claim 1, wherein the historical performance of each prospective contact center agent is associated with a historical performance of the respective prospective contact center agent with handling interactions of the interaction class. ### Claim 3 (depends on 1) The method of claim 1, further comprising ranking the prospective contact center agents based on the associated predictive routing score for each prospective contact center agent to determine a first agent ranking; wherein ranking the prospective contact center agents based on the associated predictive routing score and the associated relative gain for each prospective contact center agent comprises re-ranking the first agent ranking based on the associated relative gain for each prospective contact center agent to determine a second agent ranking; and wherein selecting the contact center agent of the prospective contact center agents based on the ranking comprises selecting the contact center agent of the prospective contact center agents based on the second agent ranking. ### Claim 4 (depends on 1) The method of claim 1, wherein determining the relative gain for each prospective contact center agent based on the interaction class of the interaction comprises determining the relative gain for each prospective contact center agent based on a class value associated with the interaction class. ### Claim 5 (depends on 1) The method of claim 1, further comprising determining the interaction class of the interaction in response to identifying the interaction to be routed to the contact center agent. ### Claim 6 (depends on 5) The method of claim 5, wherein the interaction class is selected from a plurality of interaction classes predefined by an administrator. ### Claim 7 (depends on 5) The method of claim 5, wherein the plurality of interaction classes is defined by machine learning. ### Claim 8 (depends on 5) The method of claim 5, further comprising: identifying a prospective interaction class; determining an average handle time and an agent performance rank of each contact center agent for the identified prospective interaction class based on historical performance data of each contact center agent; determining whether relative gain criteria are satisfied based on the average handle time and the agent performance rank of each contact center agent for the identified prospective interaction class; and defining the prospective interaction class as an interaction class for relative gain analysis in response to determining that the relative gain criteria are satisfied. ### Claim 9 (depends on 8) The method of claim 8, wherein determining whether the relative gain criteria are satisfied comprises: determining an agent performance rank variance metric from the agent performance rank of each contact center agent for the identified prospective interaction class; and determining an average handle time variance metric from the average handle time of each contact center agent for the identified prospective interaction class. ### Claim 10 (depends on 9) The method of claim 9, wherein the relative gain criteria are satisfied in response to a determination that the agent performance rank variance metric exceeds a first threshold and the average handle time variance metric is less than a second threshold. ### Claim 11 (depends on 9) The method of claim 9, wherein each of the agent performance variance metric and the average handle time variance metric is a coefficient of variation. ### Claim 12 A system for leveraging relative gain in predictive routing of interactions to contact center agents, the system comprising: at least one processor; and at least one memory comprising a plurality of instructions stored therein that, in response to execution by the at least one processor, causes the system to: identify an interaction to be routed to a contact center agent; determine a predictive routing score for each prospective contact center agent of a plurality of prospective contact center agents to which the interaction can be routed based on a historical performance of each prospective contact center agent; determine a relative gain for each prospective contact center agent based on an interaction class of the interaction, an agent class performance of the prospective contact center agent, and an agent value of the prospective contact center agent, wherein the relative gain of a respective contact center agent is indicative of a relative optimization improvement of routing the interaction to the respective contact center agent relative to another of the prospective contact center agents; rank the prospective contact center agents based on the associated predictive routing score and the associated relative gain for each prospective contact center agent; select the contact center agent of the prospective contact center agents based on the ranking of the prospective contact center agents; and route the interaction to the selected contact center agent. ### Claim 13 (depends on 12) The system of claim 12, wherein the historical performance of each prospective contact center agent is associated with a historical performance of the respective prospective contact center agent with handling interactions of the interaction class. ### Claim 14 (depends on 12) The system of claim 12, wherein the plurality of instructions further causes the system to rank the prospective contact center agents based on the associated predictive routing score for each prospective contact center agent to determine a first agent ranking; wherein to rank the prospective contact center agents based on the associated predictive routing score and the associated relative gain for each prospective contact center agent comprises to re-rank the first agent ranking based on the associated relative gain for each prospective contact center agent to determine a second agent ranking; and wherein to select the contact center agent of the prospective contact center agents based on the ranking comprises to select the contact center agent of the prospective contact center agents based on the second agent ranking. ### Claim 15 (depends on 12) The system of claim 12, wherein to determine the relative gain for each prospective contact center agent based on the interaction class of the interaction comprises to determine the relative gain for each prospective contact center agent based on a class value associated with the interaction class. ### Claim 16 (depends on 12) The system of claim 12, wherein the plurality of instructions further causes the system to determine the interaction class of the interaction in response to identifying the interaction to be routed to the contact center agent. ### Claim 17 (depends on 16) The system of claim 16, wherein the interaction class is selected from a plurality of interaction classes predefined by an administrator. ### Claim 18 (depends on 16) The system of claim 16, wherein the plurality of instructions further causes the system to: identify a prospective interaction class; determine an average handle time and an agent performance rank of each contact center agent for the identified prospective interaction class based on historical performance data of each contact center agent; determine whether relative gain criteria are satisfied based on the average handle time and the agent performance rank of each contact center agent for the identified prospective interaction class; and define the prospective interaction class as an interaction class for relative gain analysis in response to determining that the relative gain criteria are satisfied. ### Claim 19 (depends on 18) The system of claim 18, wherein to determine whether the relative gain criteria are satisfied comprises to: determine an agent performance rank variance metric from the agent performance rank of each contact center agent for the identified prospective interaction class; and determine an average handle time variance metric from the average handle time of each contact center agent for the identified prospective interaction class. ### Claim 20 (depends on 19) The system of claim 19, wherein the relative gain criteria are satisfied in response to a determination that the agent performance rank variance metric exceeds a first threshold and the average handle time variance metric is less than a second threshold.