Information handling system and method for automatically generating a meeting summary
A method and apparatus for automatically generating a meeting summary is disclosed herein. Meeting audio is recorded and converted into a text-based transcript. Handwritten meeting notes are converted into notes text. The transcript and notes text are correlated to provide correlated meeting text. Meeting topics are determined from the correlated meeting text. A meeting summary is generated from the meeting topics.
1. A method, comprising:
receiving, at an information handling system, a meeting agenda comprising matters to be discussed during a meeting;
receiving, at the information handling system, a meeting record comprising a record of words spoken during the meeting and meeting timestamps comprising times when the words were spoken;
receiving, at the information handling system, meeting notes comprising notes written by one or more meeting participants and notes timestamps comprising times when the meeting notes were written;
correlating, by the information handling system, the meeting agenda, meeting notes, and the meeting record to generate correlated meeting text, wherein the correlating step comprises matching the notes timestamps to the meeting timestamps and wherein the correlated meeting text comprises the meeting agenda, meeting record, and the meeting notes;
determining, by the information handling system, action items from the correlated meeting text;
determining, by the information handling system, an importance score associated with each action item based, at least in part, on the correlated meeting text; and
generating, by the information handling system, a meeting summary comprising the action items and associated importance scores.
2. The method of claim 1 further comprising converting, by the information handling system, the meeting record from audio data into text data after receiving the meeting record and wherein the correlated meeting text comprises the text data.
3. The method of claim 1 further comprising converting, by the information handling system, the meeting notes from handwritten symbols into text data after receiving the meeting notes and wherein the correlated meeting text comprises the text data.
4. The method of claim 1 , wherein the determining action items step comprises segregating the action items from decided items in the correlated meeting text.
5. The method of claim 1 , wherein the generating the meeting summary comprises generating a prioritized action item list.
6. The method of claim 1 , wherein the determining an importance score step comprises applying sentiment analysis on the correlated meeting text.
7. The method of claim 1 , wherein the determining an importance score step comprises applying named entity recognition on the correlated meeting text and identifying titles of recognized named entities.
8. An apparatus, comprising: a processor and memory coupled to the processor, wherein the processor is configured to perform steps comprising:
receiving a meeting agenda comprising matters to be discussed during a meeting;
receiving a meeting record comprising a record of words spoken during a meeting and meeting timestamps comprising times when the words were spoken;
receiving meeting notes comprising notes written by one or more meeting participants and notes timestamps comprising times when the meeting notes were written;
correlating the meeting agenda, meeting notes, and the meeting record to generate correlated meeting text, wherein the correlating step comprises matching the notes timestamps to the meeting timestamps and wherein the correlated meeting text comprises the meeting record and the meeting notes;
determining action items from the correlated meeting text;
determining an importance score associated with each action item based, at least in part, on the correlated meeting text; and
generating a meeting summary comprising the action items and associated importance scores.
9. The apparatus of claim 8 , wherein the processor is further configured to perform steps comprising: converting the meeting record from audio data into text data after receiving the meeting record, and wherein the correlated meeting text comprises the text data.
10. The apparatus of claim 8 , wherein the processor is further configured to perform steps comprising: converting the meeting notes from handwritten symbols into text data after receiving the meeting notes, and wherein the correlated meeting text comprises the text data.
11. The apparatus of claim 8 , wherein the determining action items step comprises segregating the action items from decided items in the correlated meeting text.
12. The apparatus of claim 8 , wherein the generating step comprises generating a prioritized action item list.
13. The apparatus of claim 8 , wherein the determining an importance score step comprises applying sentiment analysis on the correlated meeting text.
14. The apparatus of claim 8 , wherein the determining an importance score step comprises applying named entity recognition on the correlated meeting text and identifying titles of recognized named entities.
15. An information handling system, comprising: a processor and a memory coupled to the processor, wherein the processor is configured to execute:
an audio processing service for converting meeting audio into a meeting transcript;
an optical character recognition service, the optical character recognition service for converting handwritten notes into notes text;
a natural language processing service for converting a meeting agenda into agenda action items, for converting the meeting transcript into meeting action items, for converting the notes text into notes action items; and
a machine learning service for correlating the agenda action items and meeting action items with the notes action items to create correlated action items by matching meeting timestamps to notes timestamps and for creating a meeting summary by summarizing the correlated action items.
16. The processor of claim 15 further configured to execute a dashboard for providing access to meeting participants to view the meeting summary by accessing the dashboard.
17. The processor of claim 15 , wherein the meeting summary comprises an action item heat map.
18. The processor of claim 15 , wherein the meeting summary comprises a prioritized action item list.
19. The processor of claim 15 , wherein the machine learning service determines an importance score of an action item by applying sentiment analysis to the correlated action items.
20. The processor of claim 15 , wherein the machine learning service determines an importance score of an action item by applying named entity recognition on the correlated action items and identifying titles of recognized named entities.