Communication Session Processing

• US 20180295334A1
• Filed: 06/15/2018
• Published: 10/11/2018
• Est. Priority Date: 09/18/2015
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Furesjo, Fredrik, Nilsson, Mattias Dan, Nitsche, Daniel, Turbell, Henrik Valdemar, Lindblom, Jonas Nils Rune
• Granted Patent: US 10,681,324 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 3/0485 Scrolling or panning
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 21/055 for synchronising with other signals, e.g. video signals
• CPC Class Codes: G11B 27/34 Indicating arrangements indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D
• CPC Class Codes: H04M 2203/301 Management of recordings
• CPC Class Codes: H04M 2203/305 Recording playback features, e.g. increased speed
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04N 7/152 Multipoint control units therefor
• CPC Class Codes: H04N 9/8715 involving the mixing of the reproduced video signal with a non-recorded signal, e.g. a text signal

Abstract

Techniques for processing content for communication sessions are described. Implementations, for example, enable various ways of detecting and storing events that occur during communication sessions.

Claims

1. A method comprising:

analyzing communication data of a communication session to determine a first event and a second event that occurred during the communication session, said analyzing including executing different sets of code instructions that are each configured to detect different content types to analyze the communication data and identify the first event and the second event based on respective content types for the first event and the second event;

generating a first visual representation and a first relevance value for the first event, and a second visual representation and a second relevance value for the second event, the first relevance value and the second relevance value being generated by executing an algorithm to;

compare respective content of the first event and the second event to content attribute data that identifies one or more pre-defined content attributes; and

assign the first relevance value and the second relevance value based on whether the respective content of the first event and the second event matches the one or more content attributes such that the first relevance value is higher than the second relevance value based on content of the first event more closely corresponding to the one or more content attributes than content of the second event;

storing the first visual representation, the first relevance value, the second visual representation, and the second relevance value as further data associated with the communication data; and

generating user interface data that is executable to display content of the communication session based at least in part on the further data such that the first visual representation and the second visual representation are differently displayable in a user interface based on the first relevance value and the second relevance value, respectively.

2. A computer-implemented method as recited in claim 1, wherein the first event includes a timestamp, and wherein the method further comprises:

synchronizing the communication data with the first visual representation based on the timestamp; and

generating a media file from the synchronized communication data such that the first visual representation is displayed when the media file is played back.

3. A computer-implemented method as recited in claim 1, wherein:

the second event occurs within a pre-defined period of time after the first event; and

said assigning the first relevance value and the second relevance value is further based on whether the first event and second event occur within a pre-defined period of time such that a relevance value is relatively increased if a subsequent event occurs within the pre-defined period time.

4. A computer-implemented method as recited in claim 1, wherein said analyzing the communication data includes audio processing performed using speech recognition to generate a text transcription of the communication data stream.

5. A computer-implemented method as recited in claim 1, wherein one or more of the first event or the second event is identified at least in part by extracting keywords or keyphrases from a text transcription of the communication data using natural language processing.

6. A computer-implemented method as recited in claim 1, wherein said analyzing the communication data includes audio processing to identify a change in speaker.

7. A computer-implemented method as recited in claim 1, wherein the communication data includes screen sharing communication data, and wherein said analyzing the communication data includes performing optical character recognition to extract content from a presentation.

8. A computer-implemented method as recited in claim 1, wherein said analyzing the communication data includes video processing performed using facial recognition to identify users captured in the communication session.

9. A computer-implemented method as recited in claim 1, further comprising:

receiving user feedback submitted by users as part of the communication session, the user feedback corresponding to one or more of the first event or the second event; and

modifying one or more of the first relevance value or the second relevance value based on the user feedback.

10. A computer-implemented method as recited in claim 1, wherein the first event and the second event include respective user feedback received during consumption of the communication session, and wherein the algorithm executed to generate the first relevance value and the second relevance value is further executed to modify one or more of the first relevance value or the second relevance value based on the respective user feedback.

11. A system comprising:

one or more processors; and

one or more computer-readable storage media storing computer-executable instructions that, responsive to execution by the one or more processors, cause the system to perform operations including;

analyzing communication data of a communication session to determine a first event and a second event that occurred during the communication session, said analyzing including executing different sets of code instructions that are each configured to detect different content types to analyze the communication data and identify the first event and the second event based on respective content types for the first event and the second event;

generating a first visual representation and a first relevance value for the first event, and a second visual representation and a second relevance value for the second event, the first relevance value and the second relevance value being generated by executing an algorithm to;

compare respective content of the first event and the second event to content attribute data that identifies one or more pre-defined content attributes; and

assign the first relevance value and the second relevance value based on whether the respective content of the first event and the second event matches the one or more content attributes such that the first relevance value is higher than the

second relevance value based on content of the first event more closely corresponding to the one or more content attributes than content of the second event;

storing the first visual representation, the first relevance value, the second visual representation, and the second relevance value as further data associated with the communication data; and

generating user interface data that is executable to display content of the communication session based at least in part on the further data such that the first visual representation and the second visual representation are differently displayable in a user interface based on the first relevance value and the second relevance value, respectively.

12. A system as described in claim 11, wherein:

the second event occurs within a pre-defined period of time after the first event; and

said assigning the first relevance value and the second relevance value is further based on whether the first event and second event occur within a pre-defined period of time such that a relevance value is relatively increased if a subsequent event occurs within the pre-defined period time.

13. A system as described in claim 11, wherein said analyzing the communication data includes audio processing performed using speech recognition to generate a text transcription of the communication data stream.

14. A system as described in claim 11, wherein one or more of the first event or the second event is identified at least in part by extracting keywords or keyphrases from a text transcription of the communication data using natural language processing.

15. A system as described in claim 11, wherein said analyzing the communication data includes audio processing to identify a change in speaker.

16. A system as described in claim 11, wherein the communication data includes screen sharing communication data, and wherein said analyzing the communication data includes performing optical character recognition to extract content from a presentation.

17. A system as described in claim 11, wherein said analyzing the communication data includes video processing performed using facial recognition to identify users captured in the communication session.

18. A system as described in claim 11, wherein the first event and the second event include respective user feedback received during consumption of the communication session, and wherein the algorithm executed to generate the first relevance value and the second relevance value is further executed to modify one or more of the first relevance value or the second relevance value based on the respective user feedback.

19. One or more computer-readable storage devices comprising instructions stored thereon that, responsive to execution by a cloud meeting server, cause the cloud meeting server to perform operations comprising:

analyzing communication data of a communication session to determine a first event and a second event that occurred during the communication session, said analyzing including executing different sets of code instructions that are each configured to detect different content types to analyze the communication data and identify the first event and the second event based on respective content types for the first event and the second event;

generating a first visual representation and a first relevance value for the first event, and a second visual representation and a second relevance value for the second event, the first relevance value and the second relevance value being generated by executing an algorithm to;

compare respective content of the first event and the second event to content attribute data that identifies one or more pre-defined content attributes; and

assign the first relevance value and the second relevance value based on whether the respective content of the first event and the second event matches the one or more content attributes such that the first relevance value is higher than the second relevance value based on content of the first event more closely corresponding to the one or more content attributes than content of the second event;

storing the first visual representation, the first relevance value, the second visual representation, and the second relevance value as further data associated with the communication data; and

generating user interface data that is executable to display content of the communication session based at least in part on the further data such that the first visual representation and the second visual representation are differently displayable in a user interface based on the first relevance value and the second relevance value, respectively.

20. One or more computer-readable storage devices as described in claim 19, wherein the operations further comprise:

receiving user feedback submitted by users as part of the communication session, the user feedback corresponding to one or more of the first event or the second event; and

modifying one or more of the first relevance value or the second relevance value based on the user feedback.