# US 2021/0344800 A1 · Artificial-intelligence powered skill management systems and methods > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0344800 A1 - Document ID: US20210344800A1 - Status: Published application - Kind: A1 - Application number: 16/864,376 - Filed: 2020-05-01 - Published: 2021-11-04 - Earliest claimed: 2020-05-01 - Assignees: Nice Ltd. - Applicants: Nice Ltd. - Inventors: Ifat SHWARTZ; Tal RASKIN; Michael SEGAL; Natan KATZ - Web page: https://patentgrep.com/patent/US20210344800A1 ## CPC - H04M 3/5175: {Call or contact centers supervision arrangements} - G06N 3/006: based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/092: Reinforcement learning - G06Q 10/063112: {Skill-based matching of a person or a group to a task} - G06Q 10/06393: {Score-carding, benchmarking or key performance indicator [KPI] analysis} - G06Q 10/06398: {Performance of employee with respect to a job function} - G06Q 30/016: After-sales - H04M 3/5233: {Operator skill based call distribution} - G06N 3/045: Combinations of networks - G06N 20/00: Machine learning - H04M 2203/401: Performance feedback - 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) - 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 Methods for routing customers to an agent include receiving a customer communication; representing the customer communication as an array of one or more agent skills desired to handle the customer communication in one hot coding format or as a vector with an induced metric using an embedding algorithm; routing the represented customer communication to an agent having the one or more agent skills; measuring performance of the agent in relation to the one or more agent skills during or after the customer communication; updating, in real-time, one or more performance scores of the agent in a skill profile, wherein the one or more performance scores are related to the one or more agent skills; and routing subsequent customer communications based on the updated one or more performance scores. ## Claims ### Claim 1 An agent skill management system comprising: a processor and a computer readable medium operably coupled thereto, the computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform operations which comprise: receiving a customer communication; representing the customer communication as an array or a vector of one or more agent skills desired to handle the customer communication; routing the represented customer communication to an agent having the one or more agent skills; measuring performance of the agent in relation to the one or more agent skills during or after the customer communication based on data analysis using reinforcement learning; updating, in real-time, one or more performance scores of the agent in a skill profile based on data analysis using reinforcement learning, wherein the one or more performance scores are related to the one or more agent skills; and routing subsequent customer communications based on the updated one or more performance scores. ### Claim 2 (depends on 1) The agent skill management system of claim 1, wherein measuring performance of the agent comprises: defining a key performance indicator (KPI) in relation to each of the one or more agent skills; and measuring each KPI during or after the customer communication. ### Claim 3 (depends on 2) The agent skill management system of claim 2, wherein the KPI comprises one or more of a call length, a satisfaction survey score, or a customer desire for another agent. ### Claim 4 (depends on 2) The agent skill management system of claim 2, wherein the operations further comprise: defining a threshold score for each KPI; and comparing the threshold score for each KPI to each updated performance score. ### Claim 5 (depends on 4) The agent skill management system of claim 4, wherein the operations further comprise providing an alert to an agent supervisor when an updated performance score is above or below the threshold score for a respective KPI. ### Claim 6 (depends on 5) The agent skill management system of claim 5, wherein the operations further comprise recommending training of the agent or removal of an agent skill from the skill profile when the updated performance score is below the threshold score for the respective KPI. ### Claim 7 (depends on 1) The agent skill management system of claim 1, wherein the operations further comprise: routing a plurality of additional customer communications to the agent based on the skill profile of the agent; continuously measuring performance of the agent in relation to a skill in the skill profile during or after each additional customer communication; continuously updating, in real-time, a performance score of the agent in the skill profile, wherein the performance score is related to the skill in the skill profile; and routing a plurality of future customer communications based on the updated performance score. ### Claim 8 (canceled) ### Claim 9 A method, which comprises: receiving, by a processor, a customer communication; representing, by a processor, the customer communication as an array or a vector of one or more agent skills desired to handle the customer communication; routing the represented customer communication to an agent having the one or more agent skills; measuring, by a processor, performance of the agent in relation to the one or more agent skills during or after the customer communication based on data analysis using reinforcement learning; updating, by a processor in real-time, one or more performance scores of the agent in a skill profile based on data analysis using reinforcement learning, wherein the one or more performance scores are related to the one or more agent skills; and routing subsequent customer communications based on the updated one or more performance scores. ### Claim 10 (depends on 9) The method of claim 9, wherein measuring performance of the agent comprises: defining, by a processor, a key performance indicator (KPI) in relation to each of the one or more agent skills; and measuring, by a processor, each KPI during or after the customer communication. ### Claim 11 (depends on 10) The method of claim 10, further comprising: defining a threshold score for each KPI; and comparing the threshold score for each KPI to each updated performance score. ### Claim 12 (depends on 11) The method of claim 11, further comprising providing an alert to an agent supervisor when an updated performance score is above or below the threshold score for a respective KPI. ### Claim 13 (depends on 9) The method of claim 9, wherein further comprising: routing a plurality of additional customer communications to the agent based on the skill profile of the agent; continuously measuring, by a processor, performance of the agent in relation to a skill in the skill profile during or after each additional customer communication; continuously updating, by a processor in real-time, a performance score of the agent in the skill profile, wherein the performance score is related to the skill in the skill profile; and routing a plurality of future customer communications based on the updated performance score. ### Claim 14 (canceled) ### Claim 15 A non-transitory computer-readable medium having stored thereon computer-readable instructions executable by a processor to perform operations which comprise: receiving a customer communication; representing the customer communication as an array or as a vector of one or more agent skills desired to handle the customer communication; routing the represented customer communication to an agent having the one or more agent skills; measuring performance of the agent in relation to the one or more agent skills during or after the customer communication based on data analysis using reinforcement learning; updating, in real-time, one or more performance scores of the agent in a skill profile, wherein the one or more performance scores are related to the one or more agent skills based on data analysis using reinforcement learning; and routing subsequent customer communications based on the updated one or more performance scores. ### Claim 16 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein measuring performance of the agent comprises: defining, by a processor, a key performance indicator (KPI) in relation to each of the one or more agent skills; and measuring, by a processor, each KPI during or after the customer communication. ### Claim 17 (depends on 16) The non-transitory computer-readable medium of claim 16, wherein the operations further comprise: defining a threshold score for each KPI; and comparing the threshold score for each KPI to each updated performance score ### Claim 18 (depends on 17) The non-transitory computer-readable medium of claim 17, wherein the operations further comprise providing an alert to an agent supervisor when an updated performance score is above or below the threshold score for a respective KPI. ### Claim 19 (depends on 15) The non-transitory computer-readable medium of claim 15, wherein the operations further comprise: routing a plurality of additional customer communications to the agent based on the skill profile of the agent; continuously measuring performance of the agent in relation to a skill in the skill profile during or after each additional customer communication; continuously updating, in real-time, a performance score of the agent in the skill profile, wherein the performance score is related to the skill in the skill profile; and routing a plurality of future customer communications based on the updated performance score. ### Claim 20 (canceled) ### Claim 21 (depends on 1) The agent skill management system of claim 1, wherein the customer communication is represented as an array of one or more agent skills desired to handle the customer communication in one hot coding format. ### Claim 22 (depends on 1) The agent skill management system of claim 1, wherein the customer communication is represented as a vector of one or more agent skills, the vector having an induced metric. ### Claim 23 (depends on 22) The agent skill management system of claim 22, wherein an auto encoder is used to convert the one or more agent skills to the vector with an induced metric.