# US 2024/0202555 A1 · Method and system for providing virtual assistant in a meeting

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0202555 A1
- Document ID: US20240202555A1
- Status: Published application
- Kind: A1
- Application number: 18/109,538
- Filed: 2023-02-14
- Published: 2024-06-20
- Earliest claimed: 2022-12-20
- Assignees: JPMorgan Chase Bank, N.A.
- Applicants: JPMorgan Chase Bank, N.A.
- Inventors: Abhishek MITRA; Ajay VERMA; Apoorva JAISWAL; Yogita RANI; Gaurav KARKAL
- Web page: https://patentgrep.com/patent/US20240202555A1

## CPC

- G06N 5/043: Distributed expert systems; Blackboards
- G06V 40/20: Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16)
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 17/22: Interactive procedures; Man-machine interfaces
- G10L 25/63: for estimating an emotional state
- G10L 25/90: Pitch determination of speech signals
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A method and system for providing a virtual assistant to participants in a meeting. The method includes receiving a set of data associated with the meeting. The set of data includes meeting details, participant details, discussion details, audio details, and video details. Next, the method includes analyzing, using a trained model, the set of data to provide the virtual assistant to the participants in the meeting. Thereafter, the method includes assisting the participants in the meeting based on the analysis of the set of data.

## Claims

### Claim 1

A method for providing a virtual assistant to participants in a meeting, the method comprising:
receiving, at a processor, a set of data associated with the meeting;
analyzing, by the processor using a trained model, the set of data to provide the virtual assistant to the participants in the meeting;
assisting, by the processor, the participants in the meeting based on the analysis of the set of data.

### Claim 2 (depends on 1)

The method as claimed in claim 1, wherein the set of data comprises meeting details, participant details, discussion details, audio details, and video details.

### Claim 3 (depends on 1)

The method as claimed in claim 1, wherein the assisting of the participants in the meeting comprises:
receiving, at the processor, audio data associated with a speaker that is participating in the meeting;
transcribing, by the processor, the received audio data into raw textual data;
processing, by the processor, the raw textual data into processed textual data, wherein the processed textual data comprises a name of the speaker, corresponding text, a start time at which the speaker begins speaking, and an end time at which the speaker stops speaking; and
displaying, by the processor via a display, the processed textual data based on a requirement of the participants.

### Claim 4 (depends on 1)

The method as claimed in claim 1, wherein the assisting of the participants in the meeting comprises:
receiving, by the processor, geographic details and time zone details of the participants;
analyzing, by the processor, the geographic details and the time zone details of the participants to determine a variation among the geographic details and the time zone details of the participants in the meeting; and
displaying, by the processor via a display, a notification that relates to the variation among the geographic details and the time zone details of the participants in the meeting.

### Claim 5 (depends on 1)

The method as claimed in claim 1, wherein the assisting of the participants in the meeting comprises:
receiving, at the processor, audio data associated with the at least one speaker that is participating in the meeting;
analyzing, by the processor using the trained model, the audio data in real-time to detect unconscious bias words used by the at least one speaker;
displaying, by the processor via a display, a notification to the at least one speaker that relates to the unconscious bias words; and
suggesting, by the processor, a replacement of the unconscious bias words to the at least one speaker.

### Claim 6 (depends on 1)

The method as claimed in claim 1, wherein the assisting of the participants in the meeting comprises:
receiving, at the processor, audio data associated with the participants in the meeting;
analyzing, by the processor using the trained model, the audio data to detect a pitch of one of the participants, text spoken by the one of the participants, and a time duration of a spoken sentence; and
displaying, by the processor via a display, a notification associated with at least one event for which the pitch of the one of the participants is higher than a predefined threshold level based on the analysis of the audio data.

### Claim 7 (depends on 1)

The method as claimed in claim 1, wherein the assisting of the participants in the meeting comprises:
receiving, at the processor, video data associated with the participants in the meeting;
analyzing, by the processor using the trained model, the video data to detect a gesture and an emotion of one of the participants, text spoken by the one of the participants, and a time duration of a spoken sentence; and
displaying, by the processor via a display, a notification associated with at least one event for which the emotion of the one of the participants is identified as being an unfavorable emotion.

### Claim 8

A computing device configured to implement an execution of a method for providing a virtual assistant to participants in a meeting, the computing device comprising:
a processor;
a memory; and
a communication interface coupled to each of the processor and the memory, wherein the processor is configured to:
receive, via the communication interface, a set of data associated with the meeting;
analyze a set of data using a trained model to provide the virtual assistant to the participants in the meeting; and
assist the participants in the meeting based on the analysis of the set of data.

### Claim 9 (depends on 8)

The computing device as claimed in claim 8, wherein set of data comprises meeting details, participant details, discussion details, audio details, and video details.

### Claim 10 (depends on 8)

The computing device as claimed in claim 8, wherein the processor is further configured to assist the participants in the meeting by:
receiving, via the communication interface, audio data associated with a speaker that is participating in the meeting;
transcribing the received audio data into raw textual data;
processing the raw textual data into processed textual data, wherein the processed textual data comprises a name of the speaker, corresponding text, a start time at which the speaker begins speaking, and an end time at which the speaker stops speaking; and
displaying the processed textual data based on a requirement of the participants.

### Claim 11 (depends on 8)

The computing device as claimed in claim 8, wherein the processor is further configured to assist the participants in the meeting by:
receiving, via the communication interface, geographic details and time zone details of the participants;
analyzing the geographic details and the time zone details of the participants to determine a variation among the geographic details and time zone details of the participants in the meeting;
displaying a notification that relates to the variation among the geographic details and the time zone details of the participants in the meeting.

### Claim 12 (depends on 8)

The computing device as claimed in claim 8, wherein the processor is further configured to assist the participants in the meeting by:
receiving, via the communication interface, audio data associated with at least one speaker that is participating in the meeting;
analyzing the audio data using the trained model in real-time to detect unconscious bias words used by the at least one speaker;
displaying a notification to the at least one speaker that relates to the unconscious bias words; and
suggesting a replacement of the unconscious bias words to the at least one speaker.

### Claim 13 (depends on 8)

The computing device as claimed in claim 8, wherein the processor is further configured to assist the participants in the meeting by:
receiving, via the communication interface, audio data associated with the participants in the meeting;
analyzing the audio data using the trained model to detect a pitch of one of the participants, text spoken by the one of the participants, and a time duration of a spoken sentence; and
displaying a notification at least one event for which the pitch of the one of the participants is higher than a predefined threshold level based on the analysis of the audio data.

### Claim 14 (depends on 8)

The computing device as claimed in claim 8, wherein the processor is further configured to assist the participants in the meeting by:
receiving, via the communication interface, video data associated with the participants in the meeting;
analyzing the video data to detect a gesture and an emotion of one of the participants, text spoken by the one of the participants, and a time duration of a spoken sentence; and
displaying a notification associated with at least one event for which the emotion of the one of the participants is identified as being an unfavorable emotion.

### Claim 15

A non-transitory computer readable storage medium storing instructions for providing a virtual assistant to participants in a meeting, the instructions comprising executable code which, when executed by a processor, causes the processor to:
receive a set of data associated with the meeting;
analyze a set of data using a trained model to provide the virtual assistant to the participants in the meeting; and
assist the participants in the meeting based on the analysis of the set of data.

### Claim 16 (depends on 15)

The storage medium as claimed in claim 15, wherein the set of data comprises meeting details, participants details, discussion details, audio details, and video details.

### Claim 17 (depends on 15)

The storage medium as claimed in claim 15, wherein when executed by the processor, the executable code further causes the processor to assist the participants in the meeting by:
receiving audio data associated with a speaker that is participating in the meeting;
transcribing the received audio data into raw textual data;
processing the raw textual data into processed textual data, wherein the processed textual data comprises a name of the speaker, corresponding text, a start time at which the speaker begins speaking, and an end time at which the speaker stops speaking; and
displaying the processed textual data based on a requirement of the participants.

### Claim 18 (depends on 15)

The storage medium as claimed in claim 15, wherein when executed by the processor, the executable code further causes the processor to assist the participants in the meeting by:
receiving geographic details and time zone details of the participants;
analyzing the geographic details and the time zone details of the participants to determine a variation among the geographic details and the time zone details of the participants in the meeting; and
displaying a notification that relates to the variation among the geographic details and the time zone details of the participants in the meeting.

### Claim 19 (depends on 15)

The storage medium as claimed in claim 15, wherein when executed by the processor, the executable code further causes the processor to assist the participants in the meeting by:
receiving audio data associated with the at least one speaker that is participating in the meeting;
analyzing the audio data using the trained model in real-time to detect unconscious bias words used by the at least one speaker;
displaying a notification to the at least one speaker that relates to the unconscious bias words; and
suggesting a replacement of the unconscious bias words to the at least one speaker.

### Claim 20 (depends on 15)

The storage medium as claimed in claim 15, wherein when executed by the processor, the executable code further causes the processor to assist the participants in the meeting by:
receiving audio and video data associated with the participants in the meeting;
analyzing the audio and video data using the trained model to detect a pitch of one of the participants, a gesture of the one of the participants, an emotion of the one of the participants, text spoken by the one of the participants, and a time duration of a spoken sentence; and
displaying a notification associated with at least one event for which the pitch of the one of the participants is higher than a predefined threshold level.
