System and method for automated agent assistance within a cloud-based contact center
AssigneeTalkdesk, Inc.
InventorsJafar Adibi, Tiago Paiva, Charanya Kannan, Bruno Antunes, Joao Carmo, Marco Costa
Life of this patent
Estimating the term…
Abstract
Methods to reduce agent effort and improve customer experience quality through artificial intelligence. The Agent Assist tool provides contact centers with an innovative tool designed to reduce agent effort, improve quality and reduce costs by minimizing search and data entry tasks The Agent Assist tool is natively built and fully unified within the agent interface while keeping all data internally protected from third-party sharing.
Claims16
A method of analyzing a call center communication between an agent and a customer to determine compliance with communication policies, the method comprising:
- receiving a current communication voice between a customer and an agent;
- parsing the current voice communication using a natural language processing module;
- bifurcating the current voice communication into a voice of the agent and a voice of the customer;
- and
- applying rules to the voice of the agent to determine if the agent articulates at least one of prohibited words, competitors of the call center user, talks at an undesired speed, discusses other products, promoted violence and/or discusses personal issues.
A method for enhancing a database in a call center to group communication records into relevant groups and thereby provide agents of the call center with information relevant to a current communication, the method comprising:
- receiving multiple communications, each communication being between a customer and an agent;
- bifurcating the current voice communication into a voice of the agent and a voice of the customer;
- for each of the communications,
- determining a time of the communication,
- determining a duration,
- determining a topic of the communication,
- determining a frequency of at least one keyword used in the communication by the agent;
- determining a frequency of at least one keyword used in the communication by the agent;
- and
- creating a vector of the communication based on the results of each of the determining steps;
- and
- clustering the communications in the database based on the vector of each communication.
A system for analyzing a call center communication between an agent and a customer to determine compliance with communication policies, the system comprising:
- a processor;
- and
- a memory device operatively coupled to the processor and storing instructions which, when executed by the processor, cause the processor to:
- receive a current communication voice between a customer and an agent;
- parse the current voice communication using a natural language processing module;
- bifurcate the current voice communication into a voice of the agent and a voice of the customer;
- and
- apply rules to the voice of the agent to determine if the agent articulates at least one of prohibited words, competitors of the call center user, talks at an undesired speed, discusses other products, promoted violence and/or discusses personal issues.
A system for enhancing a database in a call center to group communication records into relevant groups and thereby provide agents of the call center with information relevant to a current communication, the method comprising:
- a processor;
- and
- a memory device operatively coupled to the processor and storing instructions which, when executed by the processor, cause the processor to:
- receive multiple communications, each communication being between a customer and an agent;
- bifurcate the current voice communication into a voice of the agent and a voice of the customer;
- for each of the communications,
- determine a time of the communication,
- determine a duration,
- determine a topic of the communication,
- determine a frequency of at least one keyword used in the communication by the agent;
- determine a frequency of at least one keyword used in the communication by the agent;
- and
- create a vector of the communication based on the results of each of the determining steps;
- and
- cluster the communications in the database based on the vector of each communication.
Dependencies are inferred from the claim text.