Back to results
US 2026/0303393 A1Published application
Emoji-driven intelligent ai summaries for meetings
AssigneeMicrosoft Technology Licensing, LLC
InventorMrinal Kumar SHARMA
Life of this patent
Estimating the term…
Abstract
The techniques disclosed herein leverage emoji reactions during meetings to dynamically create AI-enhanced summaries that capture both the content and sentiment of the discussion. This approach prioritizes key takeaways, highlights areas needing clarification or action, and tailors insights based on role-specific feedback. By integrating sentiment analysis into meeting summaries, this innovation ensures greater team alignment and actionable outcomes. The described features reimagine the way emoji reactions are leveraged during meetings to create intelligent and actionable AI-generated summaries. By interpreting emojis as real-time indicators of sentiment and engagement, the system dynamically highlights key discussion points, unresolved questions, and areas requiring follow-up.
Claims20
A computer-implemented method for generating a meeting summary based on meeting content comprising text communication and expressive illustrations (emojis), the computer-implemented method for execution on a system comprising:
- receiving the meeting content that is communicated between a plurality of participants of a meeting, the meeting content comprising expressive illustrations (emojis) each communicated from individual participants of the meeting, the meeting content further comprising sections of text that is derived from messages communicated between the plurality of participants and comments within files shared between the plurality of participants, wherein the expressive illustrations are each associated with at least one section of text;
- generating a prompt comprising:
- grounding data that associates individual expressive illustrations with individual sentiment descriptions, wherein an individual class of the expressive illustrations is associated with an individual sentiment description,
- meeting content comprising the sections of text derived from messages communicated between the plurality of participants and the comments within the files shared between the plurality of participants, and data defining an association between each of the expressive illustrations and at least one section of text, wherein each section of text is associated with at least one message or at least one at least one comment;
- instructions for causing a Large Language Model to generate a meeting summary describing one or more topics of the meeting content and a summary of one or more individual sentiment descriptions associated with the one or more topics, the summary describing the one or more individual sentiment descriptions characterized by a number of occurrences of individual categories of the expressive illustrations, the instructions are further configured to cause the LLM to generate a description associating the one or more topics with the summary of one or more individual sentiment descriptions;
- communicating of the prompt to the LLM causing the LLM to generate the meeting summary describing the one or more topics of the meeting content and one or more individual sentiment descriptions that is based on the number of occurrences of individual categories of the expressive illustrations, the prompt further causing the LLM to generate the description associating the one or more topics with the one or more individual sentiment descriptions;
- receiving the meeting summary describing the one or more topics of the meeting content and one or more individual sentiment descriptions;
- and
- causing a display of the meeting summary describing the one or more topics of the meeting content and the summary of one or more individual sentiment descriptions, wherein the meeting summary also includes the description associating the one or more topics with the summary of one or more individual sentiment descriptions.
6 more elements
A computing system for generating a meeting summary based on meeting content comprising text communication and expressive illustrations (emojis), the computing system comprising:
- one or more processing units;
- and
- a computer-readable storage medium having encoded thereon computer-executable instructions to cause the one or more processing units to:
- receive the meeting content that is communicated between a plurality of participants of a meeting, the meeting content comprising expressive illustrations (emojis) each communicated from individual participants of the meeting, the meeting content further comprising sections of text that is derived from messages communicated between the plurality of participants and comments within files shared between the plurality of participants, wherein the expressive illustrations are each associated with at least one section of text;
- generate a prompt comprising:
- grounding data that associates individual expressive illustrations with individual sentiment descriptions, wherein an individual class of the expressive illustrations is associated with an individual sentiment description,
- meeting content comprising the sections of text derived from messages communicated between the plurality of participants and the comments within the files shared between the plurality of participants, and data defining an association between each of the expressive illustrations and at least one section of text, wherein each section of text is associated with at least one message or at least one at least one comment;
- instructions for causing a Large Language Model to generate a meeting summary describing one or more topics of the meeting content and a summary of one or more individual sentiment descriptions associated with the one or more topics, the summary describing the one or more individual sentiment descriptions characterized by a number of occurrences of individual categories of the expressive illustrations, the instructions are further configured to cause the LLM to generate a description associating the one or more topics with the summary of one or more individual sentiment descriptions;
- communicating of the prompt to the LLM causing the LLM to generate the meeting summary describing the one or more topics of the meeting content and one or more individual sentiment descriptions that is based on the number of occurrences of individual categories of the expressive illustrations, the prompt further causing the LLM to generate the description associating the one or more topics with the one or more individual sentiment descriptions;
- receiving the meeting summary describing the one or more topics of the meeting content and one or more individual sentiment descriptions;
- and
- causing a display of the meeting summary describing the one or more topics of the meeting content and the summary of one or more individual sentiment descriptions, wherein the meeting summary also includes the description associating the one or more topics with the summary of one or more individual sentiment descriptions.
9 more elements
A computer-readable storage medium having encoded thereon computer-executable instructions for generating a meeting summary based on meeting content comprising text communication and expressive illustrations, the computer-executable instructions configured to cause one or more processing units of a computing system to:
- receive the meeting content that is communicated between a plurality of participants (10A-10I) of a meeting, the meeting content comprising expressive illustrations (emojis) each communicated from individual participants of the meeting, the meeting content further comprising sections of text that is derived from messages communicated between the plurality of participants and comments within files shared between the plurality of participants, wherein the expressive illustrations are each associated with at least one section of text;
- generate a prompt comprising:
- grounding data that associates individual expressive illustrations with individual sentiment descriptions, wherein an individual class of the expressive illustrations is associated with an individual sentiment description,
- meeting content comprising the sections of text derived from messages communicated between the plurality of participants and the comments within the files shared between the plurality of participants, and data defining an association between each of the expressive illustrations and at least one section of text, wherein each section of text is associated with at least one message or at least one at least one comment;
- instructions for causing a Large Language Model (LLM) to generate a meeting summary describing one or more topics of the meeting content and a summary of one or more individual sentiment descriptions associated with the one or more topics, the summary describing the one or more individual sentiment descriptions characterized by a number of occurrences of individual categories of the expressive illustrations, the instructions are further configured to cause the LLM to generate a description associating the one or more topics with the summary of one or more individual sentiment descriptions;
- communicating of the prompt to the LLM causing the LLM to generate the meeting summary describing the one or more topics of the meeting content and one or more individual sentiment descriptions that is based on the number of occurrences of individual categories of the expressive illustrations, the prompt further causing the LLM to generate the description associating the one or more topics with the one or more individual sentiment descriptions;
- receiving the meeting summary describing the one or more topics of the meeting content and one or more individual sentiment descriptions;
- and
- causing a display of the meeting summary describing the one or more topics of the meeting content and the summary of one or more individual sentiment descriptions, wherein the meeting summary also includes the description associating the one or more topics with the summary of one or more individual sentiment descriptions.
6 more elements
Dependencies are inferred from the claim text.