Computer support for meetings

Patent metadata

Field	Value
Publication number	US-12051046-B2
Application number	US-202117395175-A
Country	US
Kind code	B2
Filing date	Aug 5, 2021
Priority date	Mar 22, 2018
Publication date	Jul 30, 2024
Grant date	Jul 30, 2024

Abstract

A system and method to provide computer support for a meeting of invitees comprises accessing one or more sensory data streams providing digitized sensory data responsive to an activity of one or more of the invitees during the meeting, the one or more sensory data streams including at least one audio stream. The method also comprises subjecting the at least one audio stream to phonetic and situational computer modeling to recognize a sequence of words in the audio stream and to assign each word to an invitee, subjecting the sequence of words to semantic computer modeling to recognize a sequence of directives in the sequence of words, and releasing one or more output data streams based on the sequence of directives, the one or more output data streams including one or more notifications.

First claim

The invention claimed is:

1. A method to provide computer support for a meeting of invitees, the method comprising:
accessing digital data including email or document data to extract a sequence of words from a portion of the email or document data
subjecting the sequence of words to semantic computer modeling by a machine-learning model to programmatically generate one or more agenda items to be discussed during the meeting;
assembling, in advance of the meeting and without intervention by an invitee, the one or more agenda items into a meeting agenda comprising a list of the one or more agenda items by at least filtering a portion of the one or more agenda items, wherein information indicating modification to the meeting agenda or one or more agenda items by one or more invitees is usable to refine the machine learning model;
transmitting the meeting agenda to the one or more invitees; and
refining the machine-learning model based on feedback obtained from the information indicating the modification.

2. The method of claim 1 , wherein the semantic computer modeling includes topic extraction via the machine-learning model.

3. The method of claim 2 , wherein the machine-learning model is configured to convert text into a representation amenable to the topic extraction.

4. The method of claim 2 , wherein the semantic computer modeling includes ranking of one or more topics extracted from the digital data via the machine-learning model.

5. The method of claim 1 , further comprising determining, after the meeting, at least one agenda item of the one or more agenda items is not removed from the meeting agenda by the invitee and refining the machine-learning model based on the at least one agenda item.

6. The method of claim 1 , comprising determining, based at least in part on the one or more agenda items, that a task is assigned to a first invitee.

7. The method of claim 6 , wherein transmitting the meeting agenda comprises alerting the first invitee that the task is assigned to the first invitee.

8. At least one memory device, excluding a signal per se, having embodied thereon computer-executable instructions which, when executed by one or more processors, implement a method of providing support for a meeting of invitees, the method comprising:
accessing digital data including email or document data to extract a sequence of words from a portion of the email or document data;
subjecting the sequence of words to semantic computer modeling by a machine-learning model to programmatically generate one or more agenda items to be discussed during the meeting;
assembling, in advance of the meeting and without intervention by an invitee, the one or more agenda items into a meeting agenda comprising a list of the one or more agenda items by at least filtering a portion of the one or more agenda items, wherein information indicating modification to the meeting agenda or one or more agenda items by one or more invitees is usable to refine the machine learning model;
refining the machine-learning model based on the information indicating the modification; and
transmitting the meeting agenda to the one or more invitees.

9. The at least one memory device, excluding a signal per se, of claim 8 , wherein machine-learning model identifies at least one agenda item of the one or more agenda items based on a subject line included in an email accessed from the digital data.

10. The at least one memory device, excluding a signal per se, of claim 8 , the method further comprising receiving a list of topics actually discussed during the meeting and refining the machine-learning model based on the list of topics.

11. The at least one memory device, excluding a signal per se, of claim 8 , the method further comprising determining, based at least in part on the one or more agenda items, to prompt a first invitee to perform at least one agenda item included in the list of the one or more agenda items.

12. The at least one memory device, excluding a signal per se, of claim 8 , wherein the digital data further comprises at least one of: whitepapers, slide decks, pre-prints, and e-notes.

13. The at least one memory device, excluding a signal per se, of claim 8 , wherein the machine-learning model identifies at least one agenda item of the one or more agenda items based on an association in the digital data included in at least one of a subject line, message body, attachments, file, document authored by the invitee of the one or more of invitees, and web link.

14. The at least one memory device, excluding a signal per se, of claim 8 , wherein the machine-learning model identifies at least one agenda item of the one or more agenda items based on a previous meeting.

15. An automated meeting-support system comprising:
at least one processor;
computer memory storing computer-executable instructions which, when executed by the at least one processor, implement a method comprising:
accessing digital data including email or document data to extract a sequence of words from a portion of the email or document data;
subjecting the sequence of words to semantic computer modeling by a machine-learning model to programmatically generate one or more agenda items to be discussed during the meeting;
assembling, in advance of the meeting and without intervention by an invitee, the one or more agenda items into a meeting agenda comprising a list of the one or more agenda items by at least filtering a portion of the one or more agenda items, wherein information indicating modification to the meeting agenda or one or more agenda items by one or more invitees is usable to refine the machine learning mode;

transmitting the meeting agenda to the one or more invitees; and
refining the machine-learning model based on the information indicating the modification to the meeting agenda or one or more agenda items.

16. The automated meeting-support system of claim 15 wherein the semantic computer modeling includes topic extraction via the machine-learning model.

17. The automated meeting-support system of claim 16 , wherein the semantic computer modeling includes ranking of one or more topics extracted from the digital data via the machine-learning model.

18. The automated meeting-support system of claim 16 , the method further comprising receiving a list of topics actually discussed during the meeting and refining the machine-learning model based on the list of topics.

19. The automated meeting-support system of claim 15 , the method further comprising determining, based at least in part on the one or more agenda items, that a task is assigned to a first invitee.

20. The automated meeting-support system of claim 16 , wherein the semantic computer modeling includes filtering candidate topics via the machine-learning model.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Sim Robert Alexander
• Mendes Hasegawa Marcello
• White Ryen William
• Jain Mudit
• Hermelin Tomer
• Gerzi Rosenthal Adi
• HILLELI Sagi

Classifications

• G06Q10/1093 Primary

  Calendar-based scheduling for persons or groups · CPC title

• G06F40/10

  Text processing (natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40) · CPC title

• G06N20/00

  Machine learning · CPC title

• G10L2015/025

  Phonemes, fenemes or fenones being the recognition units · CPC title

• G10L15/02

  Feature extraction for speech recognition; Selection of recognition unit · CPC title