# US 12,003,807 B2 · Electronic device for removing advertisement thumbnail from display screen for providing list of live sports and operating method thereof

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

- Number: US 12,003,807 B2
- Document ID: US12003807B2
- Status: Granted
- Kind: B2
- Application number: 17/502,293
- Filed: 2021-10-15
- Published: 2022-04-21
- Granted: 2024-06-04
- Earliest claimed: 2020-10-16
- Assignees: Naver Corporation
- Applicants: Naver Corporation
- Inventors: Kyung Tae Kang; Jun Bong Baek; Dongho Lee; Hyungwoo Kim
- Web page: https://patentgrep.com/patent/US12003807B2

## CPC

- H04N 21/2187: Live feed
- H04N 21/4316: {for displaying supplemental content in a region of the screen, e.g. an advertisement in a separate window}
- G06F 18/2433: Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
- G06V 10/82: using neural networks
- G06V 20/42: {of sport video content}
- G06V 20/46: {Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames}
- 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 21/454: Content {or additional data} filtering, e.g. blocking advertisements
- H04N 21/466: Learning process for intelligent management, e.g. learning user preferences for recommending movies {(services using the results of monitoring in broadcast systems H04H60/61)}
- H04N 21/812: {involving advertisement data (advertising per se G06Q30/02)}
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Provided are an electronic device for removing an advertisement thumbnail from a display screen for providing a list of sports and an operating method of the electronic device that may retrieve an image thumbnail extracted from a game video being broadcast live, determine whether the image thumbnail is a game thumbnail or an advertisement thumbnail using a pre-trained deep learning model, and display the game thumbnail on a display screen when the image thumbnail is the game thumbnail and remove the advertisement thumbnail on the display screen when the image thumbnail is the advertisement thumbnail.

## Claims

### Claim 1

An operating method of an electronic device, the method comprising:
retrieving an image thumbnail extracted from a game video being broadcast live;
determining whether the image thumbnail is a game thumbnail or an advertisement thumbnail using a pre-trained deep learning model;
in response to a result of the determining indicating that the image thumbnail is the game thumbnail, displaying the game thumbnail on a display screen; and
in response to the result of the determining indicating that the image thumbnail is the advertisement thumbnail, removing the advertisement thumbnail on the display screen,
wherein the pre-trained deep learning model is implemented by,
acquiring a plurality of image thumbnails from the game video,
classifying the acquired image thumbnails into game thumbnails and advertisement thumbnails,
training a deep learning model based on the game thumbnails and advertisement thumbnails, and
running a test on the pre-trained deep learning model, and wherein the pre-trained deep learning model is implemented by,
if a ratio of a number of the game thumbnails to a number of the advertisement thumbnails exceeds a range,
generating at least one advertisement thumbnail based on at least one of the advertisement thumbnails and increasing the number of advertisement thumbnails, and
training the deep learning model based on the number of the game thumbnails and the increased number of the advertisement thumbnails.

### Claim 2 (depends on 1)

The method of claim 1, wherein the pre-trained deep learning model comprises:
a preprocessing model configured to extract at least one feature point from the image thumbnail; and
a classification model configured to analyze the feature point and determine whether the image thumbnail is the game thumbnail or the advertisement thumbnail.

### Claim 3 (depends on 1)

The method of claim 1, wherein the retrieving comprises retrieving one of the plurality of image thumbnails extracted from the game video and stored over time, the plurality of image thumbnails including the image thumbnail.

### Claim 4 (depends on 3)

The method of claim 3, wherein the retrieving comprises retrieving one of the image thumbnails at a time interval.

### Claim 5 (depends on 1)

The method of claim 1, wherein the pre-trained deep learning model is trained using another game video corresponding to the same event as that of the game video being broadcast live, as training data.

### Claim 6 (depends on 1)

The method of claim 1, wherein
the deep learning model is trained based on a portion of the game thumbnails and a portion of the advertisement thumbnails, and
the test is run on the pre-trained deep learning model based on a remaining portion of the game thumbnails and a remaining portion of the advertisement thumbnails.

### Claim 7 (depends on 1)

A non-transitory computer-readable record medium storing instructions that, when executed by a processor, cause an electronic device to perform the method of claim 1.

### Claim 8

An electronic device comprising:
a memory; and
a processor configured to connect to the memory and to execute at least one instruction stored in the memory,
wherein the processor is configured to,
retrieve an image thumbnail extracted from a game video being broadcast live,
determine whether the image thumbnail is a game thumbnail or an advertisement thumbnail using a pre-trained deep learning model,
in response to a determination result indicating the image thumbnail is the game thumbnail, display the game thumbnail on a display screen, and
in response to the determination result indicating the image thumbnail is the advertisement thumbnail, remove the advertisement thumbnail on the display screen,
wherein the pre-trained deep learning model is implemented by,
acquiring a plurality of image thumbnails from the game video,
classifying the acquired image thumbnails into game thumbnails and advertisement thumbnails,
training a deep learning model based on the game thumbnails and the advertisement thumbnails, and
running a test on the pre-trained deep learning model, and
wherein the pre-trained deep learning model is implemented by,
if a ratio of a number of the game thumbnails to a number of the advertisement thumbnails exceeds a range,
generating at least one advertisement thumbnail based on at least one of the advertisement thumbnails and increasing the number of the advertisement thumbnails, and
training the deep learning model based on the number of the game thumbnails and the increased number of the advertisement thumbnails.

### Claim 9 (depends on 8)

The electronic device of claim 8, wherein the pre-trained deep learning model comprises:
a preprocessing model configured to extract at least one feature point from the image thumbnail; and
a classification model configured to analyze the feature point and to determine whether the image thumbnail is the game thumbnail or the advertisement thumbnail.

### Claim 10 (depends on 8)

The electronic device of claim 8, wherein the processor is configured to retrieve one of the plurality of image thumbnails extracted from the game video and stored over time, the plurality of image thumbnails including the image thumbnail.

### Claim 11 (depends on 10)

The electronic device of claim 10, wherein the processor is configured to retrieve one of the image thumbnails at a time interval.

### Claim 12 (depends on 8)

The electronic device of claim 8, wherein the pre-trained deep learning model is trained using another game video corresponding to a same event as that of the game video being broadcast live, as training data.

### Claim 13 (depends on 8)

The electronic device of claim 8, wherein
the deep learning model is trained based on a portion of the game thumbnails and a portion of the advertisement thumbnails, and
the test is run on the pre-trained deep learning model based on a remaining portion of the game thumbnails and a remaining portion of the advertisement thumbnails.