# US 11,310,559 B2 · Method and apparatus for recommending video

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

- Number: US 11,310,559 B2
- Document ID: US11310559B2
- Status: Granted
- Kind: B2
- Application number: 16/255,725
- Filed: 2019-01-23
- Published: 2019-08-15
- Granted: 2022-04-19
- Earliest claimed: 2018-02-12
- Assignees: Beijing Baidu Netcom Science Technology Co., Ltd.
- Applicants: Beijing Baidu Netcom Science and Technology Co., Ltd.
- Inventors: Hang Jiang; Minghao Liu; Yang Liang; Shuangshuang Qiao; Siyu An; Kaihua Song; Xiangyue Lin; Hua Chai; Faen Zhang; Jiangliang Guo; Jingbo Huang; Xu Li; Jin Tang; Shiming Yin
- Web page: https://patentgrep.com/patent/US11310559B2

## CPC

- H04N 21/4668: {for recommending content, e.g. movies}
- H04N 21/47202: {for requesting content on demand, e.g. video on demand}
- 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 21/251: {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 21/26603: {for automatically generating descriptors from content, e.g. when it is not made available by its provider, using content analysis techniques}
- H04N 21/4662: {characterized by learning algorithms}
- H04N 21/4826: {using recommendation lists, e.g. of programmes or channels sorted out according to their score}
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

Embodiments of the present disclosure disclose a method and apparatus for recommending a video. A specific implementation of the method includes: finding a recommended video corresponding to a target video from all candidate videos based on similarities of content characteristics of the videos, the target video being a video to be played on a terminal of a user; and sending play information of the recommended video corresponding to the target video to the terminal of the user. The method finds a video similar on video content to the target video that the user desires to view based on the content characteristic of the video, and recommends the video similar on video content to the target video that the user desires to view to the user.

## Claims

### Claim 1

A method for recommending a video, the method comprising:
generating, by using a pre-trained neural network, a content characteristic vector for each candidate video of all candidate videos based on a plurality of images in the each candidate video, wherein a component of the content characteristic vector generated for the each candidate video corresponds to a content characteristic comprising a text in an image in the each candidate video;
finding a similar candidate video corresponding to each candidate video based on a similarity of content characteristic vectors, comprising: clustering content characteristic vectors of all the candidate videos to obtain a plurality of clustering results; for the content characteristic vector of each candidate video in each clustering result of the plurality of clustering results, determining the similarity between the content characteristic vector of the candidate video and the content characteristic vector of each of other candidate videos in the clustering result, sorting the other candidate videos in a descending order based on similarities of the content characteristic vectors of the other candidate videos to the content characteristic vector of the candidate video, defining a top preset number of the sorted candidate videos as cluster similar videos of the candidate video in the clustering result, and defining the cluster similar video corresponding to each candidate video in the clustering result as the similar candidate video corresponding to each candidate video, each component of the content characteristic vector of the candidate video corresponding to a content characteristic of the candidate video, the content characteristic of the candidate video comprising text in an image in the candidate video;
finding a recommended video corresponding to a target video from all the candidate videos based on similarities of content characteristics of the videos, the target video being a video to be played on a terminal of a user; and
sending play information of the recommended video corresponding to the target video to the terminal of the user.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the target video is a candidate video among all the candidate videos; and
the finding a recommended video corresponding to a target video from all candidate videos based on similarities of content characteristics of the videos comprises:
defining a similar candidate video corresponding to the target video as the recommended video corresponding to the target video.

### Claim 3

An apparatus for recommending a video, the apparatus comprising:
at least one processor; and
a memory storing instructions, the instructions when executed by the at least one processor, cause the at least one processor to perform operations, the operations comprising:
generating, by using a pre-trained neural network, a content characteristic vector for each candidate video of all candidate videos based on a plurality of images in the each candidate video, wherein a component of the content characteristic vector generated for the each candidate video corresponds to a content characteristic comprising a text in an image in the each candidate video;
finding a similar candidate video corresponding to each candidate video based on a similarity of content characteristic vectors, comprising: clustering content characteristic vectors of all the candidate videos to obtain a plurality of clustering results; for the content characteristic vector of each candidate video in each clustering result of the plurality of clustering results, determining the similarity between the content characteristic vector of the candidate video and the content characteristic vector of each of other candidate videos in the clustering result, sorting the other candidate videos in a descending order based on similarities of the content characteristic vectors of the other candidate videos to the content characteristic vector of the candidate video, defining a top preset number of the sorted candidate videos as cluster similar videos of the candidate video in the clustering result, and defining the cluster similar video corresponding to each candidate video in the clustering result as the similar candidate video corresponding to each candidate video, each component of the content characteristic vector of the candidate video corresponding to a content characteristic of the candidate video, the content characteristic of the candidate video comprising text in an image in the candidate video;
finding a recommended video corresponding to a target video from all the candidate videos based on similarities of content characteristics of the videos, the target video being a video to be played on a terminal of a user; and
sending play information of the recommended video corresponding to the target video to the terminal of the user.

### Claim 4 (depends on 3)

The apparatus according to claim 3, wherein the target video is a candidate video among all the candidate videos, and
the finding a recommended video corresponding to a target video from all candidate videos based on similarities of content characteristics of the videos comprises:
defining a similar candidate video corresponding to the target video as the recommended video corresponding to the target video.

### Claim 5

A non-transitory computer storage medium storing a computer program, the computer program when executed by one or more processors, causes the one or more processors to perform operations, the operations comprising:
generating, by using a pre-trained neural network, a content characteristic vector for each candidate video of all candidate videos based on a plurality of images in the each candidate video, wherein a component of the content characteristic vector generated for the each candidate video corresponds to a content characteristic comprising a text in an image in the each candidate video;
finding a similar candidate video corresponding to each candidate video based on a similarity of content characteristic vectors, comprising: clustering content characteristic vectors of all the candidate videos to obtain a plurality of clustering results; for the content characteristic vector of each candidate video in each clustering result of the plurality of clustering results, determining the similarity between the content characteristic vector of the candidate video and the content characteristic vector of each of other candidate videos in the clustering result, sorting the other candidate videos in a descending order based on similarities of the content characteristic vectors of the other candidate videos to the content characteristic vector of the candidate video, defining a top preset number of the sorted candidate videos as cluster similar videos of the candidate video in the clustering result, and defining the cluster similar video corresponding to each candidate video in the clustering result as the similar candidate video corresponding to each candidate video, each component of the content characteristic vector of the candidate video corresponding to a content characteristic of the candidate video, the content characteristic of the candidate video comprising text in an image in the candidate video;
finding a recommended video corresponding to a target video from all the candidate videos based on similarities of content characteristics of the videos, the target video being a video to be played on a terminal of a user; and
sending play information of the recommended video corresponding to the target video to the terminal of the user.