International Business Machines Corporation

Christian Muise

Elizabeth Daly

Adi Ionel Botea

Oznur Alkan

Shubham Agarwal

Luis Alfonso Lastras-Montano

Akihiro Kishimoto

Radu Marinescu

Matthew Scott Davis

Marco Patricio Crasso

Yasaman Khazaeni

Pablo Pedemonte

Joseph Kim

Zhongshen Zeng

Miroslav Vodolán

Ondrej Bajgar

Embodiments are provided that relate to a computer system, a computer program product, and a machine-implemented method for improving performance of a dialog system employing an automated virtual agent. Embodiments involve clustering traces of dialog conversation logs into sets, and searching the traces for one or more contrastive temporal patterns between the sets.

Searching conversation logs of a virtual agent dialog system for contrastive temporal patterns

A computer-implemented method includes determining a current state and a current context of an environment in which an automated agent runs to execute a contingent plan. The state indicates that one or more fluents of a plurality of fluents are true, and the plurality of fluents are associated with a contingent problem solved by the contingent plan. The context describes values corresponding to the one or more fluents. An action is performed with respect to at least a subset of the context. A nondeterministic effect of the action on the environment is evaluated, using a computer processor. The state is updated based on the nondeterministic effect. The context is updated based on the nondeterministic effect.

Real-world execution of contingent plans

Embodiments for intelligent career planning actions in a computing environment by a processor. A career planning model may be created for a user according to a career goal, a user profile, and one or more alternative user profiles and historical data of alternative users having achieved the career goal. A career plan may be generated for the user according to the career planning model.

Intelligent career planning in a computing environment

In one or more embodiments described herein, device, computer-implemented methods, and/or computer program products that facilitate enhancing test coverage of dialogue models. According to an embodiment, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise a conversation processing component that receives and processes a first conversation. The computer executable components can further comprise a node marking component that tags a first node of a node map as an accessed node if the first node was accessed during processing of the first conversation. The computer executable components can further comprise a reporting component that generates a report comprising a list of nodes, wherein the list of nodes comprises one or more second nodes that were not accessed during processing of the first conversation.

Enhancing test coverage of dialogue models

Various embodiments are provided for understanding user sentiment in a dialog system in a computing environment by a processor. A sentiment of a user may be detected according to a sentiment analysis and user feedback during a dialog with the user. One or more reasons for the sentiment of the user may be identified. Behavior of the dialog system may be adjusted according to the one or more reasons.

Understanding user sentiment using implicit user feedback in adaptive dialog systems

Growing community of inventors

Somerville, MA, United States of America

Christian Muise