# US 2023/0144326 A1 · Contextual smart switching via multi-modal learning mechanism

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

- Number: US 2023/0144326 A1
- Document ID: US20230144326A1
- Status: Published application
- Kind: A1
- Application number: 17/454,314
- Filed: 2021-11-10
- Published: 2023-05-11
- Earliest claimed: 2021-11-10
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Kunal Sawarkar; Craig M. Trim; Shikhar Kwatra
- Web page: https://patentgrep.com/patent/US20230144326A1

## CPC

- H04N 21/454: Content {or additional data} filtering, e.g. blocking advertisements
- G06V 10/82: using neural networks
- G06V 20/62: Text, e.g. of license plates, overlay texts or captions on TV images
- H04N 21/4394: {involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams (arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58)}
- H04N 21/44008: {involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream (arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59)}
- H04N 21/4542: {Blocking scenes or portions of the received content, e.g. censoring scenes}
- H04N 21/4663: {involving probabilistic networks, e.g. Bayesian networks}
- H04N 21/4666: {using neural networks, e.g. processing the feedback provided by the user}
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The present invention may include a computer receives multimedia data. The computer parses the multimedia data into an audio stream. The computer analyzes the audio stream to identify recognized patterns. The computer calculates a probability of an undesired content based on the recognized patterns and taking an action based on determining the probability is above a threshold.

## Claims

### Claim 1

A processor-implemented method for contextual stream switching, the method comprising:
receiving multimedia data;
parsing an audio stream from the multimedia data;
identifying recognized patterns by analyzing the audio stream;
identifying a user context using a sensor;
determining a risk score based on the user context;
calculating a probability of undesired content based on the recognized patterns and the risk score; and
performing an action when the probability is above a threshold.

### Claim 2 (depends on 1)

The processor-implemented method of claim 1, further comprising:
parsing a video stream from the multimedia data;
identifying recognized video patterns by analyzing the video stream; and
updating the probability of the undesired content based on the recognized video patterns.

### Claim 3 (depends on 2)

The processor-implemented method of claim 2, wherein the analyzing the video stream utilizes a trained convolutional neural network.

### Claim 4 (depends on 3)

The processor-implemented method of claim 3, wherein the trained convolutional neural network was trained to identify brand names in an image.

### Claim 5 (depends on 1)

The processor-implemented method of claim 1, wherein the analyzing the audio stream utilizes a Gaussian mixture model.

### Claim 6

(canceled)

### Claim 7 (depends on 1)

The processor-implemented method of claim 1, wherein the performing the action causes a computing device to switch to an alternative stream.

### Claim 8

A computer system for contextual stream switching, the computer system comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:
receiving multimedia data;
parsing an audio stream from the multimedia data;
identifying recognized patterns by analyzing the audio stream;
identifying a user context using a sensor;
determining a risk score based on the user context;
calculating a probability of undesired content based on the recognized patterns and the risk score; and
performing an action when the probability is above a threshold.

### Claim 9 (depends on 8)

The computer system of claim 8, further comprising:
parsing a video stream from the multimedia data;
identifying recognized video patterns by analyzing the video stream; and
updating the probability of the undesired content based on the recognized video patterns.

### Claim 10 (depends on 9)

The computer system of claim 9, wherein the analyzing the video stream utilizes a trained convolutional neural network.

### Claim 11 (depends on 10)

The computer system of claim 10, wherein the trained convolutional neural network was trained to identify brand names in an image.

### Claim 12 (depends on 8)

The computer system of claim 8, wherein the analyzing the audio stream utilizes a Gaussian mixture model.

### Claim 13

(canceled)

### Claim 14 (depends on 8)

The computer system of claim 8, wherein the performing the action causes a computing device to switch to an alternative stream.

### Claim 15

A computer program product for contextual stream switching, the computer program product comprising:
a computer-readable storage device having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:
receiving multimedia data;
parsing an audio stream from the multimedia data;
identifying recognized patterns by analyzing the audio stream;
identifying a user context using a sensor;
determining a risk score based on the user context;
calculating a probability of undesired content based on the recognized patterns and the risk score; and
performing an action when the probability is above a threshold.

### Claim 16 (depends on 15)

The computer program product of claim 15, further comprising:
parsing a video stream from the multimedia data;
program instructions to identifying recognized video patterns by analyzing the video stream; and
updating the probability of the undesired content based on the recognized video patterns.

### Claim 17 (depends on 16)

The computer program product of claim 16, wherein the analyzing the video stream utilizes a trained convolutional neural network.

### Claim 18 (depends on 17)

The computer program product of claim 17, wherein the trained convolutional neural network was trained to identify brand names in an image.

### Claim 19 (depends on 15)

The computer program product of claim 15, wherein the analyzing the audio stream utilizes a Gaussian mixture model.

### Claim 20 (depends on 15)

The computer program product of claim 15, wherein the performing the action causes a computing device to switch to an alternative stream.
