Back to results
US 11,380,213 B2Granted
Customer care training with situational feedback generation
AssigneeInternational Business Machines Corporation
InventorsAnbang Xu, Vibha S. Sinha, Rama Kalyani T. Akkiraju, Jalal U. Mahmud
Life of this patent
Estimating the term…
Abstract
In an approach for training customer service agents using persona-based chatbots, a processor retrieves customer service interaction information. A processor analyzes, using natural language processing, the customer service interaction information, wherein the analyzing includes preprocessing and aggregating the customer service interaction information. A processor interacts with a user. A processor provides feedback to the user, based on the user's style and performance during training.
Claims14
A method comprising:
- analyzing, by one or more processors, using natural language processing, customer service interaction information retrieved from at least two distinct platforms, wherein the at least two distinct platforms include a call center and a social media server, and wherein the analyzing includes preprocessing and aggregating the retrieved customer service interaction information;
- generating, by one or more processors, a plurality of responses according to a target style, a tone, and a persona;
- updating, by one or more processors, a model to directly consider a style assessment and an expertise assessment of a user as additional constraints, wherein the model utilizes word embedding to learn the additional constraints;
- mapping, by one or more computer processors, based, at least in part, on the model, a plurality of styles of the user to a plurality of task scenarios and a plurality of customer personas to generate a transformation matrix for optimizing performance in subsequent customer service interactions;
- and
- creating, by one or more processors, a simulated environment for providing situational customer service feedback, wherein the simulated environment includes the call center server, the social media server, a computing device, an interactive customer chatbot subsystem and an interactive feedback generation subsystem interconnected over a network, wherein the interactive customer chatbot subsystem simulates a type of customer persona in a task scenario utilizing a bottom-up taxonomy derived from extracted tone and persona styles manifested in collected conversational data, wherein the interactive feedback generation subsystem receives user performance as an input when the user interacts with the chatbot subsystem, and wherein the interactive feedback generation subsystem outputs situational feedback to the user based on the task scenario and user progress relative to the type of customer persona in the task scenario.
3 more elements
A computer program product comprising:
- One or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the stored program instructions comprising:
- program instructions to analyze, using natural language processing, customer service interaction information retrieved from at least two distinct platforms, wherein the at least two distinct platforms include a call center and a social media server, and wherein the analyzing includes preprocessing and aggregating the retrieved customer service interaction information;
- program instructions to generate a plurality of responses according to a target style, a tone, and a persona;
- program instructions to update a model to directly consider a style assessment and an expertise assessment of the user as additional constraints, wherein the model utilizes word embedding to learn the additional constraints;
- program instructions to map based, at least in part, on the model, a plurality of styles of the user to a plurality of task scenarios and a plurality of customer personas to generate a transformation matrix for optimizing performance in subsequent customer service interactions;
- and
- program instructions to create a simulated environment for providing situational customer service feedback, wherein the simulated environment includes the call center server, the social media server, a computing device, an interactive customer chatbot subsystem and an interactive feedback generation subsystem interconnected over a network, wherein the interactive customer chatbot subsystem simulates a type of customer persona in a task scenario utilizing a bottom-up taxonomy derived from extracted tone and persona styles manifested in collected conversational data, wherein the interactive feedback generation subsystem receives user performance as an input when the user interacts with the chatbot subsystem, and wherein the interactive feedback generation subsystem outputs situational feedback to the user based on the task scenario and user progress relative to the type of customer persona in the task scenario.
4 more elements
A computer system comprising:
- One or more computer processors, one or more computer readable storage media, and program instructions stored on the one or more computer readable storage media for execution by at least one of the one or more computer processors, the stored program instructions comprising:
- program instructions to analyze, using natural language processing, customer service interaction information retrieved from at least two distinct platforms, wherein the at least two distinct platforms include a call center and a social media server, and wherein the analyzing includes preprocessing and aggregating the retrieved customer service interaction information;
- program instructions to generate a plurality of responses according to a target style, a tone, and a persona;
- program instructions to update a model to directly consider a style assessment and an expertise assessment of the user as additional constraints, wherein the model utilizes word embedding to learn the additional constraints;
- program instructions to map based, at least in part, on the model, a plurality of styles of the user to a plurality of task scenarios and a plurality of customer personas to generate a transformation matrix for optimizing performance in subsequent customer service interactions;
- and
- program instructions to create a simulated environment for providing situational customer service feedback, wherein the simulated environment includes the call center server, the social media server, a computing device, an interactive customer chatbot subsystem and an interactive feedback generation subsystem interconnected over a network, wherein the interactive customer chatbot subsystem simulates a type of customer persona in a task scenario utilizing a bottom-up taxonomy derived from extracted tone and persona styles manifested in collected conversational data, wherein the interactive feedback generation subsystem receives user performance as an input when the user interacts with the chatbot subsystem, and wherein the interactive feedback generation subsystem outputs situational feedback to the user based on the task scenario and user progress relative to the type of customer persona in the task scenario.
4 more elements
Dependencies are inferred from the claim text.