Systems and methods for logging and reviewing a meeting

• US 10,733,574 B2
• Filed: 04/01/2019
• Issued: 08/04/2020
• Est. Priority Date: 11/16/2017
• Status: Active Grant

• Current Assignee: Beijing Xiyu Information Technology Co. Ltd.
• Original Assignee: Melo Inc. (Ucommune International Ltd.)
• Inventors: Shen, Guobin, Han, Zheng
• Primary Examiner(s): Jeanty, Romain
• Application Number:
  US16/371,600
• Publication Number:
  US 20190228380A1
• Time in Patent Office: 491 Days
• Field of Search: 705 713
• CPC Class Codes: G06F 16/24568 Data stream processing; Continuous queries
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• CPC Class Codes: G06Q 10/1091 Recording time for administrative or management purposes
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques

Abstract

Embodiments of the disclosure provide systems and methods for logging a meeting. The system may include a memory storing computer-executable instructions and a processor. The processor may be configured to execute the instructions to perform operations. The operations may include receiving audio of the meeting captured by at least one microphone device and determining an arriving angle of speech from at least one attendee of the meeting based on the captured audio. The operations may also include generating a data stream based at least in part on the arriving angle of speech, determining an identification of the at least one attendee, and matching the identification to the data stream.

Claims

1. A system for logging a meeting, comprising:

a memory storing computer-executable instructions; and

a processor in communication with the memory, wherein the computer-executable instructions, when executed by the processor, cause the processor to perform operations comprising;

receiving, through a communication interface, one or more digital streams of audio of the meeting captured by at least one microphone device;

determining an arriving angle of speech from at least one attendee of the meeting based on spatial filtering the one or more digital streams of the captured audio;

generating a data stream based at least in part on the arriving angle of speech;

determining an identification of the at least one attendee;

matching the identification to the data stream; and

producing a log of the meeting, wherein the log comprises the data stream matched with the identification.

2. The system of claim 1, wherein the operations comprise:

receiving, from the communication interface, video of the meeting captured by at least one camera device; and

determining the arriving angle of speech based on the captured video.

3. The system of claim 1, wherein the operations comprise:

matching the identification to the data stream based on a comparison of characteristics of the data stream and characteristics of the attendee.

4. The system of claim 1, wherein the data stream comprises a voice stream and the operations comprise:

generating a transcript stream corresponding to the voice stream.

5. The system of claim 4, wherein the operations comprise:

generating at least one of an index of key words or a topic list based on at least one of the voice stream or the transcript stream.

6. The system of claim 5, wherein the operations comprise:

receiving a search parameter including at least one of a key word or a topic; and

selectively causing at least one of the voice stream or the transcript stream to be shown on a portal based on a comparison of the search parameter with the index of key words or the topic list.

7. The system of claim 1, wherein the operations comprise:

receiving, through the communication interface, video of the meeting captured by an array of cameras configured to capture a plurality of views of the meeting.

8. The system of claim 7, wherein the operations comprise:

detecting and tracking a position of a display used during the meeting based on the captured video;

cropping the plurality of views of the meeting based on the tracked position of the display; and

generating a display position stream based on the cropped views.

9. The system of claim 7, wherein the operations comprise:

detecting and tracking a position of an attendee of the meeting based on the captured video;

cropping the plurality of views of the meeting based on the tracked position of the attendee of the meeting; and

generating an attendee position stream for the attendee of the meeting based on the cropped views.

10. The system of claim 1, wherein the operations comprise:

causing the data stream to be shown on a portal based on a user selection of the identification of the at least one attendee; and

receiving, through the communication interface, at least one user review input captured during the showing of the data stream on the portal.

11. The system of claim 10, wherein the operations comprise:

generating an amendment data stream based on the captured at least one user review input; and

linking the amendment data stream to the data stream being shown on the portal.

12. The system of claim 11, wherein the operations comprise:

causing an indication to be shown on the portal when the amendment data stream is available for viewing in connection with the data stream being shown on the portal.

13. The system of claim 12, wherein the operations comprise:

receiving a selection of the indication by the user; and

in response to the reception of the selection, causing the amendment data stream to be shown on the portal.

14. The system of claim 1, wherein the operations comprise:

generating a plurality of data streams based on the capture audio; and

wrapping the plurality of data streams together with the captured audio into a common file.

15. A method for logging a meeting, comprising:

receiving, through a communication interface, one or more digital streams of audio of the meeting captured by at least one microphone device;

determining, by a processor, an arriving angle of speech from at least one attendee of the meeting based on spatial filtering the one or more digital streams of the captured audio;

generating, by the processor, a data stream based at least in part on the arriving angle of speech;

determining, by the processor, an identification of the at least one attendee;

matching, by the processor, the identification of the at least one attendee to the data stream; and

producing, by the processor, a log of the meeting, wherein the log comprises the data stream matched with the identification.

16. The method of claim 15, comprising:

matching the identification to the data stream based on a comparison of characteristics of the data stream and characteristics of the attendee.

17. The method of claim 15, wherein the data stream comprises a voice stream and the method comprises:

generating a transcript stream corresponding to the voice stream;

generating at least one of an index of key words or a topic list based on at least one of the voice stream or the transcript stream;

receiving a search parameter including at least one of a key word or a topic; and

selectively showing at least one of the voice stream or the transcript stream on a portal based on a comparison of the search parameter with the index of key words or the topic list.

18. The method of claim 15, comprising:

receiving, through the communication interface, video of the meeting captured by an array of cameras configured to capture a plurality of views of the meeting;

detecting and tracking a position of a display used during the meeting based on the captured video;

making a first cropping of the plurality of views of the meeting based on the tracked position of the display;

generating a display position stream based on the first cropping;

detecting and tracking a position of an attendee of the meeting based on the captured video;

making a second cropping of the plurality of views of the meeting based on the tracked position of the attendee of the meeting; and

generating an attendee position stream for the attendee of the meeting based on the second cropping.

19. The method of claim 15, comprising:

causing the data stream to be shown on a portal based on a user selection of the identification of the at least one attendee;

receiving, through the communication interface, at least one user review input captured during the showing of the data stream;

generating an amendment data stream based on the at least one user review input; and

linking the amendment data stream to the data stream being shown on the portal.

20. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to perform a method for logging a meeting, the method comprising:

receiving one or more digital streams of audio of the meeting captured by at least one microphone device;

determining an arriving angle of speech from at least one attendee of the meeting based on spatial filtering the one or more digital streams of the captured audio;

generating a data stream based at least in part on the arriving angle of speech;

determining an identification of the at least one attendee;

matching the identification to the data stream; and

producing a log of the meeting, wherein the log comprises the data stream matched with the identification.