| CPC G10L 17/04 (2013.01) [G06F 40/216 (2020.01); G06F 40/295 (2020.01); G06F 40/30 (2020.01); G06F 40/35 (2020.01); G06Q 10/063118 (2013.01); G10L 17/02 (2013.01); G10L 17/06 (2013.01); G10L 17/22 (2013.01); G10L 15/26 (2013.01)] | 19 Claims |
|
1. A computer-implemented method comprising:
extracting, by an entity-relation extraction module, a set of designated entities and a set of relationships between designated entities from speech content of an audio feed of a plurality of participants of a current web conference, wherein the extracting uses a first machine learning model that is trained to classify parts of speech content;
generating, by a current listing module, a list of current action items based on the extracted set of designated entities and the set of relationships between designated entities;
identifying, by a list comparison module, a first current action item from the list of current action items that is an updated version of an ongoing action item on a progress list, wherein the progress list includes a set of ongoing action items from past web conferences prior to the current web conference;
identifying, by the list comparison module, a second current action item from the list of current action items that is unrelated to any of the set of ongoing action items on the progress list;
updating, by a progress list updating module, the progress list to an updated progress list by updating the first ongoing action item based on the first current action item and by adding the second current action item as a new ongoing action item on the progress list;
generating, by a summary reporting module, a progress report based on the updated progress list; and
partitioning, by a clustering module, the audio feed into clusters of audio feed data of the audio feed using a second machine learning model that forms a plurality of clusters based on prosodic features of the audio feed.
|