Detecting and assigning action items to conversation participants in real-time and detecting completion thereof
Described herein is a system for automatically detecting and assigning action items in a real-time conversation and determining whether such action items have been completed. The system detects, during a meeting, a plurality of action items and an utterance that corresponds to a completed action item. Responsive to detecting the utterance, the system generates a similarity score with respect to a first action item of the plurality of action items. The system compares the similarity score to a first threshold. Responsive to determining that the similarity score does not exceed the first threshold, the system generates a second similarity score with respect to a second action item of the plurality of action items. The system compares the second similarity score to a second threshold, which exceeds the first threshold. Responsive to determining that the second similarity score exceeds the second threshold, the system marks the second action item as completed.
1. A non-transitory computer readable storage medium comprising stored instructions, the instructions when executed by one or more processors cause the one or more processors to:
detect, during a meeting, a plurality of action items;
detect, during the meeting, that an utterance corresponds to a completed action item;
for each respective action item of the plurality of action items, generate a respective similarity score;
identify a matching action item of the plurality of action items based on its respective similarity score exceeding a threshold; and
mark, in response to a determination that its respective similarity score exceeds the threshold, the matching action item completed.
2. The non-transitory computer readable storage medium of claim 1 , wherein a first similarity score is generated for a first action item, and wherein a second similarity score is generated for a second action item responsive to determining that the first similarity score does not exceed the threshold.
3. The non-transitory computer readable storage medium of claim 2 , wherein the second action item is selected to be a part of the plurality of action items based on it being next in a group of candidate action items for having a next most recent timestamp from the meeting relative to the first action item.
4. The non-transitory computer readable storage medium of claim 1 , wherein the instructions to detect, during a meeting, the plurality of action items, further cause the one or more processors to detect each of the plurality of action items within a threshold amount of time from a current time.
5. The non-transitory computer readable storage medium of claim 1 , wherein the instructions further cause the one or more processors to:
receive, from an administrator, a threshold number and threshold amount of time;
determine a subset of the plurality of action items, wherein the subset includes fewer than the threshold number of action items and each action item of the subset occurred within a threshold amount of time from a time that the utterance was detected; and
generate similarity scores for action items in the subset based on recency of the action items.
6. The non-transitory computer readable storage medium of claim 1 , wherein the instructions further cause the one or more processors to:
transmit a notification, via a user interface at a client device, to an owner of the matching action item that the action item has been completed.
7. The non-transitory computer readable storage medium of claim 1 , wherein each similarity score is generated using a machine learning model, the machine learning model trained on a plurality of pairings of action items and utterances, wherein each pairing is labeled with a similarity score.
8. The non-transitory computer readable storage medium of claim 1 , wherein each similarity score is generated using fuzzy logic.
9. A method for closing completed action items during a meeting, the method comprising:
detecting, during a meeting, a plurality of action items;
detecting, during the meeting, that an utterance corresponds to a completed action item;
for each respective action item of the plurality of action items, generating a respective similarity score;
identifying a matching action item of the plurality of action items based on its respective similarity score exceeding a threshold; and
marking, in response to a determination that its respective similarity score exceeds the threshold, the matching action item completed.
10. The method of claim 9 , wherein a first similarity score is generated for a first action item, and wherein a second similarity score is generated for a second action item responsive to determining that the first similarity score does not exceed the threshold.
11. The method of claim 10 , wherein the second action item is selected to be a part of the plurality of action items based on it being next in a group of candidate action items for having a next most recent timestamp from the meeting relative to the first action item.
12. The method of claim 9 , wherein detecting, during the meeting, the plurality of action items, further comprises detecting each of the plurality of action items within a threshold amount of time from a current time.
13. The method of claim 9 , further comprising:
receiving, from an administrator, a threshold number and threshold amount of time;
determining a subset of the plurality of action items, wherein the subset includes fewer than the threshold number of action items and each action item of the subset occurred within a threshold amount of time from a time that the utterance was detected; and
generating similarity scores for action items in the subset based on recency of the action items.
14. The method of claim 9 , further comprising transmitting a notification, via a user interface at a client device, to an owner of the matching action item that the action item has been completed.
15. The method of claim 9 , wherein each similarity score is generated using a machine learning model, the machine learning model trained on a plurality of pairings of action items and utterances, wherein each pairing is labeled with a similarity score.
16. The method of claim 9 , wherein each similarity score is generated using fuzzy logic.
17. A system for closing completed action items during a meeting, the system comprising:
memory with instructions encoded thereon; and
one or more processors that, when executing the instructions, are caused to perform operations comprising:
detecting, during a meeting, a plurality of action items;
detecting, during the meeting, that an utterance corresponds to a completed action item;
for each respective action item of the plurality of action items, generating a respective similarity score;
identifying a matching action item of the plurality of action items based on its respective similarity score exceeding a threshold; and
marking, in response to a determination that its respective similarity score exceeds the threshold, the matching action item completed.
18. The system of claim 17 , wherein a first similarity score is generated for a first action item, and wherein a second similarity score is generated for a second action item responsive to determining that the first similarity score does not exceed the threshold.
19. The system of claim 18 , wherein the second action item is selected to be a part of the plurality of action items based on it being next in a group of candidate action items for having a next most recent timestamp from the meeting relative to the first action item.
20. The system of claim 17 , wherein detecting, during the meeting, the plurality of action items, further comprises detecting each of the plurality of action items within a threshold amount of time from a current time.