# US 10,375,241 B2 · System and method for automatic quality management in a contact center environment > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,375,241 B2 - Document ID: US10375241B2 - Status: Granted - Kind: B2 - Application number: 15/713,342 - Filed: 2017-09-22 - Published: 2018-03-29 - Granted: 2019-08-06 - Earliest claimed: 2016-09-23 - Applicants: Genesys Telecommunications Laboratories, Inc. - Inventors: Derek M. Miller; Taylor Brennan - Web page: https://patentgrep.com/patent/US10375241B2 ## CPC - H04M 3/5175: {Call or contact centers supervision arrangements} - G06F 7/02: Comparing digital values (G06F7/06, {G06F7/22,} G06F7/38 take precedence) - G06N 5/04: Inference or reasoning models - G06Q 10/06398: {Performance of employee with respect to a job function} - G06Q 50/2057: {Career enhancement or continuing education service} - H04M 3/2281: {Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls} - H04M 3/42221: {Conversation recording systems (at the subscriber's set H04M1/656)} - G06N 20/00: Machine learning - H04M 2201/18: Comparators - H04M 2203/402: Agent or workforce management - H04M 2203/403: Agent or workforce training - H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - 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 method for automatically managing a recorded interaction between a customer and an agent of a contact center includes: extracting, by a processor, features from the recorded interaction; computing, by the processor, a score of the recorded interaction by supplying the features to a prediction model; detecting, by the processor, a condition based on the score; matching, by the processor, the condition with an action; and controlling, by the processor, a workforce management server to assign a training session to the agent of the contact center. ## Claims ### Claim 1 A method for automatically managing a recorded interaction between a customer and an agent of a contact center, the method comprising: extracting, by a processor, features from the recorded interaction; computing, by the processor, a score of the recorded interaction by supplying the features to a prediction model, wherein the prediction model is configured to predict, automatically, the score that would be assigned in a manual evaluation of the recorded interaction, the prediction model being trained based on: a plurality of historical interactions; a plurality of features extracted from the historical interactions; and a plurality of manually generated scores corresponding to the historical interactions; detecting, by the processor, a condition based on the score; matching, by the processor, the condition with an action; and controlling, by the processor, a workforce management server to assign a training session to the agent of the contact center. ### Claim 2 (depends on 1) The method of claim 1, wherein the condition comprises comparing the score to a threshold corresponding to a failure to comply with agent performance standards. ### Claim 3 (depends on 2) The method of claim 2, wherein the threshold corresponds to a predicted performance based on historical performance of the agent. ### Claim 4 (depends on 2) The method of claim 2, wherein the threshold is based on a Gaussian distribution of agents of the contact center and the score is computed as a z-score being below the threshold. ### Claim 5 (depends on 2) The method of claim 2, wherein the score is an aggregate of a plurality of automatically computed scores of a plurality of recorded interactions, the plurality of recorded interactions occurring during a time window. ### Claim 6 (depends on 5) The method of claim 5, wherein the aggregate corresponds to a percentage of the recorded interactions during the time window that satisfy an individual interaction threshold condition, and wherein the threshold corresponds to a percentage of recorded interactions satisfying the individual interaction threshold condition. ### Claim 7 (depends on 1) The method of claim 1, wherein the training session is selected from a plurality of training topics in accordance with the condition detected based on the score. ### Claim 8 (depends on 7) The method of claim 7, wherein the score is associated with script compliance and the training session relates to script compliance. ### Claim 9 (depends on 7) The method of claim 7, wherein the score is associated with knowledge of a product line and the training session relates to information regarding the product line. ### Claim 10 A system for automatically managing a recorded interaction between a customer and an agent of a contact center comprises: a processor; and a memory storing instructions that, when executed by the processor, cause the processor to: extract features from the recorded interaction; compute a score of the recorded interaction by supplying the features to a prediction model, wherein the prediction model is configured to predict, automatically, the score that would be assigned in a manual evaluation of the recorded interaction, the prediction model being trained based on: a plurality of historical interactions; a plurality of features extracted from the historical interactions; and a plurality of manually generated scores corresponding to the historical interactions; detect a condition based on the score; match the condition with an action; and control a workforce management server to assign a training session to the agent of the contact center. ### Claim 11 (depends on 10) The system of claim 10, wherein the condition comprises comparing the score to a threshold corresponding to a failure to comply with agent performance standards. ### Claim 12 (depends on 11) The system of claim 11, wherein the threshold corresponds to a predicted performance based on historical performance of the agent. ### Claim 13 (depends on 11) The system of claim 11, wherein the threshold is based on a Gaussian distribution of agents of the contact center and the score is computed as a z-score being below the threshold. ### Claim 14 (depends on 11) The system of claim 11, wherein the score is an aggregate of a plurality of automatically computed scores of a plurality of recorded interactions, the plurality of recorded interactions occurring during a time window. ### Claim 15 (depends on 14) The system of claim 14, wherein the aggregate corresponds to a percentage of the recorded interactions during the time window that satisfy an individual interaction threshold condition, and wherein the threshold corresponds to a percentage of recorded interactions satisfying the individual interaction threshold condition. ### Claim 16 (depends on 10) The system of claim 10, wherein the training session is selected from a plurality of training topics in accordance with the condition detected based on the score. ### Claim 17 (depends on 16) The system of claim 16, wherein the score is associated with script compliance and the training session relates to script compliance. ### Claim 18 (depends on 16) The system of claim 16, wherein the score is associated with knowledge of a product line and the training session relates to information regarding the product line. ### Claim 19 A system for automatically managing a recorded interaction between a customer and an agent of a contact center comprising: means for extracting features from the recorded interaction; means for computing a score of the recorded interaction by supplying the features to a prediction model, wherein the prediction model is configured to predict, automatically, the score that would be assigned in a manual evaluation of the recorded interaction, the prediction model being trained based on: a plurality of historical interactions; a plurality of features extracted from the historical interactions; and a plurality of manually generated scores corresponding to the historical interactions; means for detecting a condition based on the score; means for matching the condition with an action; and means for controlling a workforce management server to assign a training session to the agent of the contact center. ### Claim 20 (depends on 19) The system of claim 19, wherein the condition comprises comparing the score to a threshold corresponding to a failure to comply with agent performance standards.