International Business Machines Corporation

Arjun Jauhari

Jennifer A Mallette

Steven Ware Jones

Vivek Salve

A method, computer system, and a computer program product for customer representative matching is provided. The present invention may include receiving a chat transcript with one or more tagged triplets and one or more multi-dimensional success vectors. The present invention may include aggregating the one or more multi-dimensional success vectors. The present invention may include receiving at least one business priority. The present invention may include training a machine learning model to match a customer to at least one customer representative. The present invention may include querying the trained machine learning model to match the customer to the at least one customer representative. The present invention may include revealing a match.

Matching a customer and customer representative dynamically based on a customer representative's past performance

A method, computer system, and a computer program product for customer representative ratings is provided. The present invention may include receiving a chat transcript with one or more tagged triplets and one or more multi-dimensional success vectors. The present invention may include aggregating the one or more multi-dimensional success vectors. The present invention may include receiving at least one business priority. The present invention may include applying at least one filter to the one or more multi-dimensional success vectors. The present invention may include normalizing the one or more multi-dimensional success vectors based on the at least one applied filter. The present invention may include obtaining a rating.

Rating customer representatives based on past chat transcripts

A method, computer system, and a computer program product for response effectiveness is provided. The present invention may include receiving a chat transcript. The present invention may include separating the chat transcript into a set of triplets, the set including two or more triplets. The present invention may include tagging each triplet in the set of triplets with one or more tags, wherein the one or more tags includes an intent, an entity, and a sentiment. The present invention may include generating at least one multi-dimensional success vector. The present invention may include aggregating the generated multi-dimensional success vectors to determine an overall satisfaction.

Measuring the effectiveness of individual customer representative responses in historical chat transcripts

Using a personal entity analyzer, a personal entity difference between a natural language response to a natural language query and an edited version of the natural language response is scored, the natural language response selected from a set of natural language response recommendations. Using a product entity analyzer, a product entity difference between the natural language response and the edited version of the natural language response is scored. Using a sentence similarity analyzer, a sentence similarity between the natural language response and the edited version of the natural language response is scored. Based on the personal entity difference score, the product entity difference, score and the sentence similarity score, the set of natural language responses is updated. In a natural language interaction, a selected natural language response from the set of natural language responses is outputted.

Natural language response improvement in machine assisted agents

An interaction pace for a live natural language interaction is set. An acceptable response latency range is determined according to the interaction pace. By analyzing a live natural language query, a set of metadata tags corresponding to the query is determined. Using the set of metadata tags, a set of clusters of natural language query-response pairs is selected, a size of the set of clusters selected according to the acceptable response latency range. From the set of clusters, a query-response pairs is selected, wherein the query of the query-response pair has above a threshold relevance score with the first natural language query. From the selected query-response pair, a response recommendation is extracted, the response recommendation being a recommended response to the live natural language query, a latency between receipt of the live natural language query and extraction of the response recommendation being within the acceptable response latency range.

Growing community of inventors

Jersey City, NJ, United States of America

Arjun Jauhari