International Business Machines Corporation

Collin James Murray

John Michael Boyer

David Deidou Taieb

Muhtar B Akbulut

David Amid

Kshitij P Fadnis

Dan O'Connor

David P George

Justin A Ziniel

Ashley Golen Johnston

Nina Shahriaree

Anna Guri

Catherine Leavenworth Fincun

Adam Benvie

Jose Francisco Martinez-Rivera

A computer product and methodology is contemplated for adaptively serving hold content during an automated communication session. This includes training a machine learning model with a set of training data that includes a feature of hold duration times during historical automated communication sessions. In response to encountering a computer transaction request during a new automated communication session, a hold time duration is predicted for executing the computer transaction request based on obtaining an inference from the machine learning model. Whether to serve hold content in response to the computer transaction request is determined, based on a comparison of the predicted hold time duration to a predetermined threshold time interval.

Adaptively serving hold content during an automated communication session

A mechanism is provided to implement a chatbot application for providing contextual help recommendations based on conversational context and interaction patterns. The chatbot application receives a query from a user and applies natural language processing (NLP) to the query to determine an objective of the query and a confidence of the objective. Responsive to determining the confidence of the objective is below a predetermined threshold, the chatbot application automatically generates a first set of recommendations to the user based on the conversation context and activates a contextual help recommendation button to indicate to the user that the first set of recommendations are available to be viewed.

Contextual help recommendations for conversational interfaces based on interaction patterns

A mechanism is provided in a data processing system comprising at least one processor and at least one memory, the at least one memory comprising instructions which are executed by the at least one processor and configure the processor to implement a conversation scope system, comprising a conversation scope controller and a conversation scope extractor, for progressively extending conversation scope in a multi-user messaging platform. The conversation scope controller captures an utterance input by a user into a chat platform. The conversation scope extractor determines a conversation scope for the utterance based on at least one entity extracted from the entity. The conversation scope controller directs the utterance to a messaging chat room based on the determined conversation scope.

Progressively extending conversation scope in multi-user messaging platform

A mechanism is provided in a data processing system comprising at least one processor and a memory comprising instructions which, when executed by the at least one processor, causes the at least one processor to train a similar passage cognitive system. The mechanism receives a question and answer key for a question answering cognitive system, the question and answer key comprising a list of question and answer specification pairs. Each question is a text string and each answer specification references one or more text passages from a corpus of information. The mechanism uses the question and answer key to generate a similar passage map for the similar passage cognitive system, the similar passage map comprising a list of text relation pairs. Each text relation pair comprises a sample input text component and a list comprising one or more sample output text components. The mechanism trains a similar passage machine learning model of the similar passage cognitive system using the similar passage map.

Training a similar passage cognitive system using ground truth from a question answering cognitive system

Growing community of inventors

LITTLETON, MA, United States of America

Collin James Murray