Social analysis in multi-participant meetings
AssigneeInternational Business Machines Corporation
InventorsGal Ashour, Zak Mandel
Life of this patent
Estimating the term…
Abstract
Methods and systems for social analysis in multi-participant meetings provide for receiving a data stream of a multi-participant meeting, wherein multiple topics are discussed. The data stream is analyzed to detect topics and to define topical sub-activities that are performed by at least a portion of the participants. Contributions to a topic by two of the participants in the topical sub-activities are identified and evaluated. A connection weight between the two participants is calculated based on the evaluation of their respective contributions.
Claims21
1-24. (canceled)
A method for social analysis in multi-participant meetings, comprising:
- receiving a data stream of a multi-participant meeting having participants, wherein multiple topics are discussed;
- analyzing the data stream to detect one of the topics and to define topical sub-activities of the one topic, the topical sub-activities being performed by at least a portion of the participants;
- identifying respective contributions to the one topic by two of the participants in the topical sub-activities associated therewith;
- making an evaluation of the respective contributions to selected ones of the topical sub-activities;
- and
- calculating a connection weight between the two participants based on the evaluation of the respective contributions,
- wherein said receiving, analyzing, identifying, making and calculating steps are implemented in either computer hardware, or computer software embodied in a non-transitory, tangible, computer-readable storage medium.
A computer software product, including a non-transitory computer-readable storage medium in which computer program instructions are stored, which instructions, when executed by a computer, cause the computer to perform the steps of:
- receiving a data stream of a multi-participant meeting having participants, wherein multiple topics are discussed;
- analyzing the data stream to detect one of the topics and to define topical sub-activities of the one topic, the topical sub-activities being performed by at least a portion of the participants;
- identifying respective contributions to the one topic by two of the participants in the topical sub-activities associated therewith;
- making an evaluation of the respective contributions to selected ones of the topical sub-activities;
- calculating a connection weight between the two participants based on the evaluation of the respective contributions;
- and
- reporting the connection weight, wherein said receiving, analyzing, identifying, making and calculating steps are implemented in either computer hardware, or computer software embodied in a non-transitory, tangible, computer-readable storage medium.
A data processing system, comprising:
- a processor comprising:
- a receiver for raw activity data, the data comprising an audio stream;
- an automatic speech recognition component for processing the audio stream;
- a topic detector;
- a sub-activity detection component;
- and
- a connection strength calculating component, wherein the processor is operative to perform the steps of:
- with the receiver receiving a data stream of a multi-participant meeting having participants, wherein multiple topics are discussed;
- using the topic detector and the sub-activity detection component, analyzing the data stream to detect one of the topics and to define topical sub-activities of the one topic, the topical sub-activities being performed by at least a portion of the participants;
- identifying respective contributions to the one topic by two of the participants in the topical sub-activities associated therewith;
- making an evaluation of the respective contributions to selected ones of the topical sub-activities;
- and
- using the connection strength calculating component for calculating a connection weight between the two participants based on the evaluation of the respective contributions.
Dependencies are inferred from the claim text.