# US 2023/0054480 A1 · Viewpoint analysis of video data

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

- Number: US 2023/0054480 A1
- Document ID: US20230054480A1
- Status: Published application
- Kind: A1
- Application number: 17/407,121
- Filed: 2021-08-19
- Published: 2023-02-23
- Earliest claimed: 2021-08-19
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Ziqiumin Wang; WEI JUN ZHENG; QING LU; Yuan Jin; Xiao Feng Ji
- Web page: https://patentgrep.com/patent/US20230054480A1

## CPC

- H04L 12/1831: {Tracking arrangements for later retrieval, e.g. recording contents, participants activities or behavior, network status}
- G06F 18/23: Clustering techniques
- G06N 20/00: Machine learning
- H04L 12/1822: {Conducting the conference, e.g. admission, detection, selection or grouping of participants, correlating users to one or more conference sessions, prioritising transmission}
- H04L 12/1827: {Network arrangements for conference optimisation or adaptation}
- G06N 3/045: Combinations of networks
- G06N 3/084: Backpropagation, e.g. using gradient descent
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Video analysis by receiving video data associated with a multi-participant meeting, identifying a first participant viewpoint, a related argument and an authority level of a viewpoint-argument, from the video data using a machine learning model, identifying a first topic within the video data, correlating the first participant viewpoint to the first topic, determining a distance between the first participant viewpoint and a second participant viewpoint, the second participant viewpoint correlated to the first topic, and providing a depiction of a relationship between the first participant viewpoint and the second participant viewpoint according to the distance.

## Claims

### Claim 1

A computer implemented method for video analysis, the method comprising:
receiving, by one or more computer processors, video data associated with a multi-participant meeting;
identifying, by the one or more computer processors, a first participant viewpoint, a related argument and an authoritative rank of a viewpoint-argument, from the video data using a machine learning model;
identifying, by the one or more computer processors, a first topic within the video data;
correlating, by the one or more computer processors, the first participant viewpoint to the first topic;
determining, by the one or more computer processors, a distance between the first participant viewpoint and a second participant viewpoint, the second participant viewpoint correlated to the first topic; and
providing, by the one or more computer processors, a depiction of a relationship between the first participant viewpoint, the related argument, the authoritative rank of the viewpoint-argument, and the second participant viewpoint according to the distance.

### Claim 2 (depends on 1)

The computer implemented method according to claim 1, further comprising:
converting, by the one or more computer processors, non-text portions of the video data to text data.

### Claim 3 (depends on 2)

The computer implemented method according to claim 2, further comprising predicting, by the one or more computer processors, a viewpoint-argument logical relationship between two input portions of the text data.

### Claim 4 (depends on 1)

The computer implemented method according to claim 1, further comprising:
clustering, by the one or more computer processors, the first participant viewpoint and the second participant viewpoint according to the distance.

### Claim 5 (depends on 1)

The computer implemented method according to claim 1, further comprising receiving, by the one or more computer processors, labeled viewpoint-argument logical relationship data; and training the machine learning model according to the viewpoint-argument logical relationship data.

### Claim 6 (depends on 1)

The computer implemented method according to claim 1, further comprising predicting, by the one or more computer processors, an authoritative rank of the viewpoint-argument according to an authoritative vector embedding associated with labeled viewpoint-argument data.

### Claim 7 (depends on 1)

The computer implemented method according to claim 1, further comprising training, by the one or more computer processors, the machine learning model using at least one of token embeddings, segment embeddings, position embeddings, line embeddings, and topic embeddings, determined from the video data.

### Claim 8

A computer program product for video analysis, the computer program product comprising one or more computer readable storage devices and collectively stored program instructions on the one or more computer readable storage devices, the stored program instructions comprising:
program instructions to receive video data associated with a multi-participant meeting;
program instructions to identify a first participant viewpoint, a related argument and an authoritative rank of a viewpoint-argument, from the video data using a machine learning model;
program instructions to identify a first topic within the video data;
program instructions to correlate the first participant viewpoint to the first topic;
program instructions to determine a distance between the first participant viewpoint and a second participant viewpoint, the second participant viewpoint correlated to the first topic; and
program instructions to provide a depiction of a relationship between the first participant viewpoint, the related argument, the authoritative rank of the viewpoint-argument, and the second participant viewpoint according to the distance.

### Claim 9 (depends on 8)

The computer program product according to claim 8, the stored program instructions further comprising:
program instructions to convert non-text portions of the video data to text data.

### Claim 10 (depends on 9)

The computer program product according to claim 9, the stored program instructions further comprising program instructions to predict a viewpoint-argument logical relationship between two input portions of the text data.

### Claim 11 (depends on 8)

The computer program product according to claim 8, the stored program instructions further comprising:
program instructions to cluster the first participant viewpoint and the second participant viewpoint according to the distance.

### Claim 12 (depends on 8)

The computer program product according to claim 8, the stored program instructions further comprising program instructions to receive labeled viewpoint-argument logical relationship data; and program instructions to train the machine learning model according to the viewpoint-argument logical relationship data.

### Claim 13 (depends on 8)

The computer program product according to claim 8, the stored program instructions further comprising program instructions to predict an authoritative rank of the viewpoint-argument according to an authoritative vector embedding associated with labeled viewpoint-argument data.

### Claim 14 (depends on 8)

The computer program product according to claim 8, the stored program instructions further comprising program instructions to train the machine learning model using at least one of token embeddings, segment embeddings, position embeddings, line embeddings, and topic embeddings, determined from the video data.

### Claim 15

A computer system for video analysis, the computer system comprising:
one or more computer processors;
one or more computer readable storage devices; and
stored program instructions on the one or more computer readable storage devices for execution by the one or more computer processors, the stored program instructions comprising:
program instructions to receive video data associated with a multi-participant meeting;
program instructions to identify a first participant viewpoint, a related argument and an authoritative rank of a viewpoint-argument, from the video data using a machine learning model;
program instructions to identify a first topic within the video data;
program instructions to correlate the first participant viewpoint to the first topic;
program instructions to determine a distance between the first participant viewpoint and a second participant viewpoint, the second participant viewpoint correlated to the first topic; and
program instructions to provide a depiction of a relationship between the first participant viewpoint, the related argument, the authoritative rank of the viewpoint-argument, and the second participant viewpoint according to the distance.

### Claim 16 (depends on 15)

The computer system according to claim 15, the stored program instructions further comprising:
program instructions to convert non-text portions of the video data to text data.

### Claim 17 (depends on 16)

The computer system according to claim 16, the stored program instructions further comprising program instructions to predict a viewpoint-argument logical relationship between two input portions of the text data.

### Claim 18 (depends on 15)

The computer system according to claim 15, the stored program instructions further comprising:
program instructions to cluster the first participant viewpoint and the second participant viewpoint according to the distance.

### Claim 19 (depends on 15)

The computer system according to claim 15, the stored program instructions further comprising program instructions to receive labeled viewpoint-argument logical relationship data; and program instructions to train the machine learning model according to the viewpoint-argument logical relationship data.

### Claim 20 (depends on 15)

The computer system according to claim 15, the stored program instructions further comprising program instructions to predict an authoritative rank of the viewpoint-argument according to an authoritative vector embedding associated with labeled viewpoint-argument data.
