International Business Machines Corporation

Globalfoundries Inc.

Steven Ware Jones

Jennifer A Mallette

Vivek Salve

Ruchi Asthana

Jacob Lewis

Arjun Jauhari

Jia Liu

Shuai Wang

Lisa Beth Lurie

Viorel C Ontalus

Abhishek Dube

Jophy Stephen Koshy

Desmond J Donegan, Jr

Nicholas Fong

A method, computer system, and a computer program product for automatically generated question suggestions is provided. The present invention may include generating an intent-entity sequence representative of a current chat conversation with a user. The present invention may also include predicting, using a trained intent-entity prediction model, a next intent-entity sequence based on the generated intent-entity sequence representative of the current chat conversation. The present invention may further include converting the predicted next intent-entity sequence into at least one likely question suggestion to return back to the user.

Automatically generated question suggestions

A computer assists in training a user to speak with a target accent by determining improvable aspects of diagnostic input of a user speaking diagnostic phrases with the target accent. The computer selects, a focus phrase characterized by at least one of said improvable aspects. The computer records performance input of the user attempting to say the focus phrase in the target accent. The computer converts the performance input into output having a baseline voice of the and the target accent applied. The computer presents the output and determines teachable aspects of revised performance input from the user replicating the output. The computer converts selected aspects of the revised performance input into augmented teaching output in the user's voice with the target accent applied. The computer presents the augmented teaching output to the user.

Computer assisted linguistic training including machine learning

Generating questions by receiving user utterance data, determining an intent confidence vector for the user utterance data, predicting, by a trained next user-intent prediction model, a next user-intent confidence vector using the intent confidence vector, and generating a next question using the next user-intent confidence vector.

Question generation by intent prediction

A method, system, and computer program product for routing queries to answer resources based on component parts and intents of a received query is provided. The method receives a query from a user. The query is analyzed to identify a set of entities associated with the query and generate an utterance representing the query. The method generates an intent classification for the utterance and a vector for the query. The vector is generated based on the set of entities, the utterance, and the intent classification. The method determines an answer resource for the query based on the vector and the intent classification of the query. In response to determining the answer resource, the method provides an answer interface based on the query, the vector, and the intent classification. The answer interface dynamically provides a response to the query.

Query routing for bot-based query response

A computer-implemented method, a computer system, and a computer program product for automatically generated conversation output is provided. The present invention may include training an answer-intent classifier to associate an intent expressed in an example question with an example answer that is responsive to the example question. The present invention may further include classifying, using the trained answer-intent classifier, a content transmitted to the trained answer-intent classifier with the intent expressed in the example question in response to determining, using the trained answer-intent classifier, that the content includes relevant information for generating the example answer that is responsive to the example question.

Automatically generated conversation output

A method can include obtaining notification data for a user, and obtaining a first set of images of the user from one or more cameras. The method can include identifying a first status of the user, and generating a set of notification options based on the first status. The method can include selecting a first notification option, and initiating a first notification by the first notification option. The method can include determining that the user does not acknowledge the first notification, and obtaining a second set of images from the one or more cameras. The method can include identifying a second status of the user, and selecting a second notification option of the set of notification options. The method can include initiating a second notification by the second notification option.

Notification escalation based on visual recognition

In an approach to customizing meeting notes, a computer receives audio input of a virtual meeting, converts the audio input to text, and displays the text to a plurality of meeting participants. A computer receives highlighted phrases of the text from the plurality of meeting participants and determines a highlighting frequency of each of the highlighted phrases. A computer determines phrases with a highlighting frequency greater than a pre-defined threshold. A computer orders the phrases based on a chronological order of the phrases in the audio input. A computer determines preferences of a first meeting participant associated with a meeting summary. A computer generates a customized summary of the virtual meeting for the first meeting participant of the plurality of meeting participants based on the ordered phrases with a high frequency of highlighting and on the preferences. A computer transmits the customized summary to the first meeting participant.

Customized meeting notes

In an approach for identifying when transferring a real-time conversation on a chatbot application to a customer support agent would be more valuable than outputting suggested queries, a processor classifies a query inputted into a real-time conversation as an intention. A processor predicts a set of next intentions of the user. A processor filters out one or more intentions from the set of next intentions of the user that do not further the real-time conversation. A processor generates a set of suggested queries the user can ask to further the real-time conversation from the subset of next intentions. A processor builds a suggestion evaluation contextual bandit model that determines whether the real-time conversation will be resolved successfully if transferred to a customer support agent. A processor trains the suggestion evaluation contextual bandit model against a set of annotated historical interactions. A processor outputs a response recommendation.

Question suggestion and agent transfer to advance a customer support conversation

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

When a chatbot application is in a mode of live chat conversation with a user, a trained intent classifier determines an intent that underlies a first live question received by the trained intent classifier from the user. A trained next predictor receives the intent from the intent classifier. The trained next intent predictor generates a set of predicted next intents responsive to receiving the intent. A trained re-ranker selects at least one of the predicted next intents responsive to receiving the set of predicted next intents. A question selection engine sends at least one suggested question to the user responsive to receiving the at least one predicted next intent. As a result of the above, the chatbot application provides to the user at least one suggested next question the user may wish to ask in response to the first question from the user.

Intent-based question suggestion engine to advance a transaction conducted via a chatbot

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

A method, system and computer program product for improving the understanding of chat transcript data. Chat transcripts are analyzed to classify the utterances into intents and identify products discussed in the chat transcripts. The data of the chat transcripts are divided into categories of utterances associated with products and intents by applying tags to the chat transcripts. The categories of utterances associated with products and intents are then clustered into clusters based on sentence similarity. Once the utterances are grouped, a representative utterance is extracted from a cluster, where the representative utterance is an utterance that has the highest semantic similarity to the utterances in the cluster. In this manner, users will be provided a more accurate guide as to the underlying meaning of the chat transcript data thereby improving the understanding of the chat transcript data more efficiently and accurately than current chat transcript analysis tools.

Analyzing chat transcript data by classifying utterances into products, intents and clusters

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

Astoria, NY, United States of America

Steven Ware Jones