Generating a synopsis of a meeting
The systems and techniques disclosed here feature a device including an audio analyzer connected to microphone(s) monitoring a conversation between one or more individuals. The audio analyzer can identify auditory expressions from audio captured by the microphone, where the auditory expressions can include linguistic expressions and nonlinguistic expressions. The audio analyzer can analyze the linguistic expressions to identify a topic and a time period when the topic was discussed. A video analyzer can be connected to camera(s) monitoring the conversation. The video analyzer can identify non-auditory expressions by the individuals from video captured by the camera. A sentiment analyzer can analyze auditory expressions during the time period when the topic was discussed and non-auditory expressions during the time period when the topic was discussed to determine sentiments to the topic. A processor can analyze the determined sentiments to the topic to determine a group sentiment to the topic.
1. A method for operating a system for determining an overall sentiment to a conversation, comprising:
identifying auditory expressions from audio captured by at least one microphone monitoring a conversation involving a plurality of individuals, the auditory expressions including linguistic expressions and nonlinguistic expressions;
analyzing the linguistic expressions to identify a topic and a time period when the topic was discussed;
identifying non-auditory expressions by the plurality of individuals from video captured by at least one camera monitoring the conversation;
analyzing at least one of auditory expressions during the time period when the topic was discussed and non-auditory expressions during the time period when the topic was discussed to determine sentiments to the topic; and
analyzing the determined sentiments to the topic to determine a group sentiment to the topic.
2. The method of claim 1 , further comprising analyzing group sentiments to multiple topics to determine an overall sentiment to the conversation.
3. The method of claim 1 , wherein analyzing the determined sentiments to the topic comprises:
generating a numeric score for each of the determined sentiments, wherein a numeric score above zero indicates a first sentiment and a numeric score below zero indicates a second sentiment; and
generating a sum of the numeric scores, wherein a sum above zero indicates a first group sentiment and a sum below zero indicates a second group sentiment.
4. The method of claim 3 , wherein a higher numeric score indicates a greater first sentiment and a lower numeric score indicates a greater second sentiment.
5. The method of claim 1 , wherein:
the plurality of individuals includes individuals in a first group and individuals in a second group, and
analyzing the determined sentiments to the topic comprises:
generating a numeric score for each determined sentiment that was expressed by the individuals in the first group, wherein a numeric score above zero indicates a first sentiment and a numeric score below zero indicates a second sentiment; and
generating a sum of the numeric scores, the sum only including numeric scores for sentiments expressed by the individuals in the first group, wherein a sum above zero indicates a first first group sentiment and a sum below zero indicates a second first group sentiment.
6. The method of claim 1 , wherein:
the plurality of individuals includes individuals in a first group and individuals in a second group, and
analyzing the determined sentiments to the topic comprises:
generating a first numeric score for each of the determined sentiments expressed by the individuals in the first group, wherein a first numeric score above zero indicates a first sentiment and a first numeric score below zero indicates a second sentiment;
generating a second numeric score for each of the determined sentiments expressed by the individuals in the second group, wherein a second numeric score above zero indicates a first sentiment and a second numeric score below zero indicates a second sentiment;
multiplying each of the first numeric scores by a first group factor to generate third numeric scores; and
generating a sum of the second numeric scores and the third numeric scores, wherein a sum above zero indicates a first group sentiment and a sum below zero indicates a second group sentiment.
7. The method of claim 6 , further comprising generating at least one of a follow-up meeting suggestion and a follow-up task list when the second group sentiment is determined.
8. The method of claim 1 , wherein analyzing the at least one of auditory expressions during the time period when the topic was discussed and the non-auditory expressions during the time period when the topic was discussed comprises:
analyzing at least one of the auditory expressions and the non-auditory expressions to determine sentiments expressed by the plurality of individuals;
determining when each of the sentiments was expressed during the conversation;
determining a topic discussed when each of the sentiments was expressed; and
mapping each of the sentiments to the topic discussed during the conversation.
9. A non-transitory computer-readable medium comprising instructions that, when executed by a processor, cause the processor to control a system for determining a group sentiment to perform:
identifying auditory expressions from audio captured by at least one microphone monitoring a conversation involving a plurality of individuals, the auditory expressions including linguistic expressions and nonlinguistic expressions;
analyzing the linguistic expressions to identify a topic and a time period when the topic was discussed;
identifying non-auditory expressions by the plurality of individuals from video captured by at least one camera monitoring the conversation;
analyzing at least one of auditory expressions during the time period when the topic was discussed and non-auditory expressions during the time period when the topic was discussed to determine sentiments to the topic; and
analyzing determined sentiments to the topic to determine a group sentiment to the topic.
10. The non-transitory computer-readable medium of claim 9 , wherein the instructions, when executed by the processor, further cause the processor to control the system to perform analyzing group sentiments to multiple topics to determine an overall sentiment to the conversation.
11. The non-transitory computer-readable medium of claim 9 , wherein, for analyzing the determined sentiments to the topic to determine the group sentiment to the topic, the instructions, when executed by the processor, further cause the processor to control the system to perform:
generating a numeric score for each of the determined sentiments, wherein a numeric score above zero indicates a first sentiment and a numeric score below zero indicates a second sentiment; and
generating a sum of the numeric scores, wherein a sum above zero indicates a first group sentiment and a sum below zero indicates a second group sentiment.
12. The non-transitory computer-readable medium of claim 9 , wherein:
the plurality of individuals includes individuals in a first group and individuals in a second group, and
for analyzing the determined sentiments to the topic to determine the group sentiment to the topic, the instructions, when executed by the processor, further cause the processor to control the system to perform:
generating a numeric score for each determined sentiment that was expressed by the individuals in the first group participating in the conversation, wherein a numeric score above zero indicates a first sentiment and a numeric score below zero indicates a second sentiment; and
generating a sum of the numeric scores, the sum only including numeric scores for sentiments expressed by the individuals in the first group, wherein a sum above zero indicates a first first group sentiment and a sum below zero indicates a second second group sentiment.
13. A system for determining an overall sentiment to a conversation, comprising:
a processor; and
a computer-readable medium comprising instructions that, when executed by the processor, cause the processor to control the system to perform:
identifying auditory expressions from audio captured by at least one microphone monitoring a conversation involving a plurality of individuals, the auditory expressions including linguistic expressions and nonlinguistic expressions;
analyzing the linguistic expressions to identify a topic and a time period when the topic was discussed;
identifying non-auditory expressions by the plurality of individuals from video captured by at least one camera monitoring the conversation;
analyzing at least one of auditory expressions during the time period when the topic was discussed and non-auditory expressions during the time period when the topic was discussed to determine sentiments to the topic; and
analyzing the determined sentiments to the topic to determine a group sentiment to the topic.
14. The system of claim 13 , wherein the instructions, when executed by the processor, further cause the processor to control the system to perform analyzing group sentiments to multiple topics to determine an overall sentiment to the conversation.
15. The system of claim 13 , wherein, for analyzing of the determined sentiments to the topic, the instructions, when executed by the processor, further cause the processor to control the system to perform:
generating a numeric score for each of the determined sentiments, wherein a numeric score above zero indicates a first sentiment and a numeric score below zero indicates a second sentiment; and
generating a sum of the numeric scores, wherein a sum above zero indicates a first group sentiment and a sum below zero indicates a second group sentiment.
16. The system of claim 15 , wherein a higher numeric score indicates a greater first sentiment, and a lower numeric score indicates a greater second sentiment.
17. The system of claim 13 , wherein:
the plurality of individuals includes individuals in a first group and individuals in a second group, and
for analyzing the determined sentiments to the topic, the instructions, when executed by the processor, further cause the processor to control the system to perform:
generating a numeric score for each determined sentiment that was expressed by the individuals in the first group, wherein a numeric score above zero indicates a first sentiment and a numeric score below zero indicates a second sentiment; and
generating a sum of the numeric scores, the sum only including numeric scores for sentiments expressed by the individuals in the first group, wherein a sum above zero indicates a first first group sentiment and a sum below zero indicates a second first group sentiment.
18. The system of claim 13 , wherein:
the plurality of individuals includes individuals in a first group and individuals in a second group, and
for analyzing the determined sentiments to the topic, the instructions, when executed by the processor, further cause the processor to control the system to perform:
generating a first numeric score for each of the determined sentiments expressed by the individuals in the first group, wherein a first numeric score above zero indicates a first sentiment and a first numeric score below zero indicates a second sentiment;
generating a second numeric score for each of the determined sentiments expressed by the individuals in the second group, wherein a second numeric score above zero indicates a first sentiment and a second numeric score below zero indicates a second sentiment;
multiplying each of the first numeric scores by a first group factor to generate third numeric scores; and
generating a sum of the second numeric scores and the third numeric scores, wherein a sum above zero indicates a first group sentiment and a sum below zero indicates a second group sentiment.
19. The system of claim 18 , wherein the instructions, when executed by the processor, further cause the processor to control the system to perform generating at least one of a follow-up meeting suggestion and a follow-up task list when the second group sentiment is determined.
20. The system of claim 13 , wherein, for analyzing the at least one of auditory expressions during the time period when the topic was discussed and the non-auditory expressions during the time period when the topic was discussed, the instructions, when executed by the processor, further cause the processor to control the system to perform:
analyzing at least one of the auditory expressions and the non-auditory expressions to determine sentiments expressed by the plurality of individuals;
determining when each of the sentiments was expressed during the conversation;
determining a topic discussed when each of the sentiments was expressed; and
mapping each of the sentiments to the topic discussed during the conversation.