# US 2025/0063215 A1 · Next Event and Frame Prediction System for Live Video

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

- Number: US 2025/0063215 A1
- Document ID: US20250063215A1
- Status: Published application
- Kind: A1
- Application number: 18/449,136
- Filed: 2023-08-14
- Published: 2025-02-20
- Earliest claimed: 2023-08-14
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Sathya Santhar; Sridevi Kannan; Sarbajit K. Rakshit
- Web page: https://patentgrep.com/patent/US20250063215A1

## CPC

- H04N 21/23418: {involving operations for analysing video streams, e.g. detecting features or characteristics (television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59)}
- H04N 21/2187: Live feed
- H04N 21/23424: {involving splicing one content stream with another content stream, e.g. for inserting or substituting an advertisement}
- H04N 21/251: {Learning process for intelligent management, e.g. learning user preferences for recommending movies (details of learning user preferences for the retrieval of video data in a video database G06F16/739; computer systems using learning methods G06N3/08)}
- H04N 21/812: {involving advertisement data (advertising per se G06Q30/02)}
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A computer implemented method predicts a next frame. A number of processor units receives a sequence of frames for a live video stream for an activity. The number of processor units predicts a next frame for the live video stream for using the sequence of frames for the activity. The number of processor units determines a set of advertisement spaces in the next frame predicted for live video stream.

## Claims

### Claim 1

A computer implemented method for predicting a next frame, the computer implemented method comprising:
receiving, by a number of processor units, a sequence of frames for a live video stream for an activity;
predicting, by the number of processor units, the next frame for the live video stream for using the sequence of frames for the activity; and
determining, by the number of processor units, a set of advertisement spaces in the next frame predicted for live video stream.

### Claim 2 (depends on 1)

The computer implemented method of claim 1, wherein predicting, by the number of processor units, the next frame comprises:
predicting, by the number of processor units, the next frame using the sequence of frames received in the live video stream and a frame prediction machine learning model trained to predict the next frame for the live video stream.

### Claim 3 (depends on 2)

The computer implemented method of claim 2, wherein the frame prediction machine learning model is trained to predict the next frame from the sequence of frames received in the live video stream and static video frames of an environment in which the activity takes place.

### Claim 4 (depends on 1)

The computer implemented method of claim 1, wherein predicting, by the number of processor units, the next frame comprises:
predicting, by the number of processor units, an event for the next frame from the sequence of frames; and
predicting, by the number of processor units, the next frame for the live video stream using the sequence of frames and the event predicted from the sequence of frames.

### Claim 5 (depends on 1)

The computer implemented method of claim 1, wherein determining, by the number of processor units, the set of advertisement spaces comprises:
detecting, by the number of processor units, objects in the next frame; and determining, by the number of processor units, the set of advertisement spaces in the next frame based on positions of objects relative to potential advertising spaces in the next frame.

### Claim 6 (depends on 1)

The computer implemented method of claim 1 further comprising:
determining, by the number of processor units, a bid for the set of advertisement spaces in the next frame.

### Claim 7 (depends on 6)

The computer implemented method of claim 6, wherein determining the bid for the set of advertisement spaces comprises:
predicting, by the number of processor units, a criticality for the set of advertising spaces in the next frame; and
determining, by the number of processor units, the bid for the set of advertisement spaces based on the criticality determined for the set of advertising spaces in the next frame.

### Claim 8 (depends on 1)

The computer implemented method of claim 1 further comprising:
determining, by the number of processor units, whether the next frame matches a current frame received in the live video stream; and
placing, by the number of processor units, a bid for the set of advertising spaces in the next frame based on a criticality for the next frame determined in response to the next frame matching the current frame received in the live video stream.

### Claim 9 (depends on 1)

The computer implemented method of claim 1, wherein the sequence of frames comprises a current frame and a number of past frames in the live video stream.

### Claim 10

A computer system comprising:
a number of processor units, wherein the number of processor units executes program instructions to:
receive a sequence of frames for a live video stream for an activity;
predict a next frame for the live video stream for using the sequence of frames for the activity; and
determine a set of advertisement spaces in the next frame predicted for live video stream.

### Claim 11 (depends on 10)

The computer system of claim 10, wherein as part of predicting the next frame, the number of processor units further executes program instructions to:
predict the next frame using the sequence of frames received in the live video stream and a frame prediction machine learning model trained to predict the next frame for the live video stream.

### Claim 12 (depends on 11)

The computer system of claim 11, wherein the frame prediction machine learning model is trained to predict the next frame from the sequence of frames received in the live video stream and static video frames of an environment in which the activity takes place.

### Claim 13 (depends on 10)

The computer system of claim 10, wherein as part of predicting the next frame, the number of processor units further executes program instructions to:
predict an event for the next frame from the sequence of frames; and
predict the next frame for the live video stream using the sequence of frames and the event predicted from the sequence of frames.

### Claim 14 (depends on 10)

The computer system of claim 10, wherein as part of determining the set of advertisement spaces, the number of processor units further executes program instructions to:
detect objects in the next frame; and
determine the set of advertisement spaces in the next frame based on positions of objects relative to potential advertising spaces in the next frame.

### Claim 15 (depends on 10)

The computer system of claim 10, wherein the number of processor units further executes program instructions to:
determine a bid for the set of advertisement spaces in the next frame.

### Claim 16 (depends on 15)

The computer system of claim 15, wherein as part of determining the bid for the set of advertisement spaces, the number of processor units further executes program instructions to:
predict a criticality for the set of advertising spaces in the next frame; and
determine the bid for the set of advertisement spaces based on the criticality determined for the set of advertising spaces in the next frame.

### Claim 17 (depends on 10)

The computer system of claim 10, wherein the number of processor units further executes program instructions to:
determine whether the next frame matches a current frame received in the live video stream; and
place a bid for the set of advertising spaces in the next frame based on a criticality for the next frame determined in response to the next frame matching the current frame received in the live video stream.

### Claim 18 (depends on 10)

The computer system of claim 10, wherein the sequence of frames comprises a current frame and a number of past frames in the live video stream.

### Claim 19

A computer program product for predicting a next frame, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer system to cause the computer system to:
receive a sequence of frames for a live video stream for an activity;
predict the next frame for the live video stream for using the sequence of frames for the activity; and
determine a set of advertisement spaces in the next frame predicted for live video stream.

### Claim 20 (depends on 19)

The computer program product of claim 19, wherein as part of predicting the next frame, the program instructions are further executable by the computer system and further cause the computer system to:
predict the next frame using the sequence of frames received in the live video stream and a frame prediction machine learning model trained to predict the next frame for the live video stream.
