| 摘要 |
An example method is provided and includes receiving recorded meeting information, selecting a meeting participant from the recorded meeting information, determining at least one of meeting participant emotion information, meeting participant speaker role information, or meeting participant engagement information based, at least in part, on the meeting information, and determining an interaction map associated with the meeting participant based, at least in part, on at least one of the meeting participant emotion information, the meeting participant speaker role information, or the meeting participant engagement information. |
| 主权项 |
1. A method comprising:
receiving, by a multimedia conference server, recorded meeting information, the recorded meeting information comprising audio data, video data, and a list of meeting participants, and the recorded meeting information corresponding to a meeting that has ended; executing, by the multimedia conference server, a video feature extraction algorithm to generate scale-invariant feature transform (SIFT) data based on the video data; executing, by the multimedia conference server, an audio feature extraction algorithm to generate mel-frequency cepstrum (MFC) data based on the audio data; selecting, by the multimedia conference server, a meeting participant from the list of meeting participants; generating, by the multimedia conference server, at least one label identifying the meeting participant in a segment of the recorded meeting information, wherein the generating comprises:
generating the at least one label when it is determined, based on the SIFT data, that a face of the meeting participant is present in the video data, andgenerating the at least one label when it is determined, based on the MFC data, that a voice print of the meeting participant is present in the audio data; determining, by the multimedia conference server, at least one of meeting participant emotion information, meeting participant speaker role information, or meeting participant engagement information based, at least in part, on the SIFT data and the MFC data; generating, by the multimedia conference server, an interaction map associated with the meeting participant based, at least in part, on at least one of the meeting participant emotion information, the meeting participant speaker role information, or the meeting participant engagement information; merging the interaction map into an organizational interaction map that comprises information indicative of a plurality of interaction maps, wherein the organizational interaction map corresponds to an organization; generating a behavioral report for the meeting participant from the organizational interaction map, wherein the meeting participant is an employee of the organization and the behavioral report includes sociometric data for the meeting participant over a plurality of past meetings; and transmitting the behavioral report to an endpoint associated with a manager within the organization. |
