VIDEO RECOMMENDING METHOD, SERVER, AND STORAGE MEDIA

• US 20180007409A1
• Filed: 09/14/2017
• Published: 01/04/2018
• Est. Priority Date: 07/06/2015
• Status: Active Grant

• Current Assignee: Tencent Technology Shenzhen Company Limited (Tencent Holdings Limited)
• Original Assignee: Tencent Technology Shenzhen Company Limited (Tencent Holdings Limited)
• Inventors: XIE, Yiran, ZHANG, Wenyu, XU, Zhao, XIANG, Yu
• Granted Patent: US 10,575,037 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/71 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/735 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/7867 using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
• CPC Class Codes: 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
• CPC Class Codes: H04N 21/25891 being end-user preferences retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/44204 Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched monitoring of user activities for profile generation for accessing a video database G06F16/739; protecting generic digital content where the protection is independent of the precise nature of the content G06F21/10; arrangements for monitoring the use made of the broadcast services in broadcast systems H04H60/31
• CPC Class Codes: H04N 21/44222 Analytics of user selections, e.g. selection of programs or purchase activity monitoring of user selections in data processing systems G06F11/34; arrangements for monitoring the user's behaviour or opinions in broadcast systems H04H60/33
• CPC Class Codes: H04N 21/4826 using recommendation lists, e.g. of programs or channels sorted out according to their score
• CPC Class Codes: H04N 21/6582 Data stored in the client, e.g. viewing habits, hardware capabilities, credit card number arrangements where receivers interact with the broadcast H04H20/38
• CPC Class Codes: H04N 21/8405 represented by keywords

Abstract

A video recommending method, including: obtaining videos, the video including long videos and short videos; obtaining a subset of the long videos, of which video attribute values are greater than corresponding attribute thresholds; obtaining a watching record of a user, and obtaining similarities between the short videos and videos in the watching record, to extract a preset quantity of short videos having highest similarities; and recommending the subset of the long videos, of which video attribute values are greater than corresponding attribute thresholds, to the user, and/or recommending the preset quantity of short videos having highest similarities to the user.

Claims

1. A video recommending method, comprising:

obtaining, by a device comprising a memory storing instructions and a processor in communication with the memory, videos comprising long videos and short videos;

obtaining, by the device, a subset of the long videos, wherein values of video attributes of the subset of the long videos are greater than corresponding attribute thresholds;

obtaining, by the device, a watching record of a user;

obtaining, by the device, similarities between the short videos and videos in the watching record to extract a preset quantity of the short videos having highest similarities; and

recommending, by the device, the subset of the long videos or the preset quantity of the short videos to the user.

2. The method according to claim 1, wherein:

video attributes comprise watching times and a watching completion rate; and

the obtaining the subset of the long videos comprises;

obtaining, by the device, according to preset priority data, the subset of the long videos, wherein;

the long videos are updated within preset time, and

the watching times of the subset of the long videos are greater than a times threshold, or the watching completion rate of the subset of the long videos is greater than a completion rate threshold.

3. The method according to claim 1, wherein:

video attributes comprise watching times and a watching completion rate; and

the obtaining the subset of the long videos comprises;

obtaining, by the device, according to preset priority data, the subset of the long videos, wherein;

the long videos are updated within preset time, and

the watching times of the subset of the long videos are greater than a times threshold, and the watching completion rate of the subset of the long videos is greater than a completion rate threshold.

4. The method according to claim 1, further comprising:

detecting, by the device, whether exposure times of a video in long videos updated within preset time reach an exposure threshold, or whether a video in the long videos updated within the preset time appears in the watching record; and

when it is detected that the exposure times of the video in the long videos updated within the preset time reach the exposure threshold, or the video in the long videos updated within the preset time appears in the watching record, filtering out, by the device, the video from recommending to the user.

5. The method according to claim 1, wherein the obtaining the similarities between the short videos and the videos in the watching record to extract the preset quantity of the short videos having highest similarities comprises:

performing, by the device, word segmentation on a video title of a short video that is most recently watched in the watching record, to obtain individual words;

querying in, by the device, a pre-established video inverted index table by separately using the individual words as keywords, to obtain video sets formed by corresponding video identifiers;

calculating, by the device, the similarity between a video title of each short video in each video set and the video title of the short video that is most recently watched in the watching record; and

extracting, by the device, the preset quantity of the short videos having highest similarities.

6. The method according to claim 5, wherein the calculating the similarity between the video title of each short video in the each video set and the video title of the short video that is most recently watched in the watching record comprises:

obtaining, by the device, one or more words, which are in both the video title of each short video in the each video set and in the video title of the short video that is most recently watched in the watching record, and using a maximum weight in weights of the one or more words as the similarity.

7. A server, comprising a memory and a processor, the memory storing instructions, and the instructions, when executed by the processor, causing the processor to perform:

obtaining videos, the video comprising long videos and short videos;

obtaining a subset of the long videos, wherein values of video attributes of the subset of the long videos are greater than corresponding attribute thresholds;

obtaining a watching record of a user;

obtaining similarities between the short videos and videos in the watching record, to extract a preset quantity of the short videos having highest similarities; and

recommending the subset of the long videos or the preset quantity of the short videos to the user.

8. The server according to claim 7, wherein:

video attributes comprise watching times and a watching completion rate; and

when the instructions cause the processor to perform the obtaining the subset of the long videos, the instructions cause the processor to perform;

obtaining, according to preset priority data, the subset of the long videos, wherein;

the long videos are updated within preset time, and

the watching times of the subset of the long videos are greater than a times threshold, or the watching completion rate of the subset of the long videos is greater than a completion rate threshold.

9. The server according to claim 7, wherein:

video attributes comprise watching times and a watching completion rate; and

when the instructions cause the processor to perform the obtaining the subset of the long videos, the instructions cause the processor to perform;

obtaining, according to preset priority data, the subset of the long videos, wherein;

the long videos are updated within preset time, and

the watching times of the subset of the long videos are greater than a times threshold, and the watching completion rate of the subset of the long videos is greater than a completion rate threshold.

10. The server according to claim 7, wherein the instructions, when executed by the processor, further cause the processor to perform:

detecting whether exposure times of a video in long videos updated within preset time reach an exposure threshold, or whether a video in the long videos updated within the preset time appears in the watching record; and

when it is detected that the exposure times of the video in the long videos updated within the preset time reach the exposure threshold, or the video in the long videos updated within the preset time appears in the watching record, filtering out the video from recommending to the user.

11. The server according to claim 7, wherein, when the instructions cause the processor to perform the obtaining the similarities between the short videos and the videos in the watching record, to extract the preset quantity of the short videos having highest similarities, the instructions cause the processor to perform:

performing word segmentation on a video title of a short video that is most recently watched in the watching record, to obtain individual words;

querying in a pre-established video inverted index table by separately using the individual words as keywords, to obtain video sets formed by corresponding video identifiers;

calculating the similarity between a video title of each short video in each video set and the video title of the short video that is most recently watched in the watching record; and

extracting the preset quantity of the short videos having highest similarities.

12. The server according to claim 11, wherein, when the instructions cause the processor to perform the calculating the similarity between the video title of each short video in the each video set and the video title of the short video that is most recently watched in the watching record, the instructions cause the processor to perform:

obtaining one or more words, which are in both the video title of each short video in the each video set and in the video title of the short video that is most recently watched in the watching record, and using a maximum weight in weights of the one or more words as the similarity.

13. A non-transitory computer readable storage medium storing computer executable instructions, the computer executable instructions, when executed by one or more processors, causing the one or more processors to perform:

obtaining videos, the videos comprising long videos and short videos;

obtaining a subset of the long videos, wherein values of video attributes of the subset of the long videos are greater than corresponding attribute thresholds;

obtaining a watching record of a user;

obtaining similarities between the short videos and videos in the watching record, to extract a preset quantity of the short videos having highest similarities; and

recommending the subset of the long videos or the preset quantity of the short videos to the user.

14. The non-transitory computer readable storage medium according to claim 13, wherein:

video attributes comprise watching times and a watching completion rate; and

when the computer executable instructions cause the one or more processors to perform the subset of the long videos, the computer executable instructions cause the one or more processors to perform;

obtaining, according to preset priority data, the subset of the long videos, wherein;

the long videos are updated within preset time, and

the watching times of the subset of the long videos are greater than a times threshold, or the watching completion rate of the subset of the long videos is greater than a completion rate threshold.

15. The non-transitory computer readable storage medium according to claim 13, wherein:

video attributes comprise watching times and a watching completion rate; and

when the computer executable instructions cause the one or more processors to perform the subset of the long videos, the computer executable instructions cause the one or more processors to perform;

obtaining, according to preset priority data, the subset of the long videos, wherein;

the long videos are updated within preset time, and

the watching times of the subset of the long videos are greater than a times threshold, and the watching completion rate of the subset of the long videos is greater than a completion rate threshold.

16. The non-transitory computer readable storage medium according to claim 13, wherein the computer executable instructions, when executed by the one or more processors, further cause the one or more processors to perform:

detecting whether exposure times of a video in long videos updated within preset time reach an exposure threshold, or whether a video in the long videos updated within the preset time appears in the watching record; and

when it is detected that the exposure times of the video in the long videos updated within the preset time reach the exposure threshold, or the video in the long videos updated within the preset time appears in the watching record, filtering out the video from recommending to the user.

17. The non-transitory computer readable storage medium according to claim 13, wherein, when the computer executable instructions cause the one or more processors to perform the obtaining the similarities between the short videos and the videos in the watching record, to extract the preset quantity of the short videos having highest similarities, the computer executable instructions cause the one or more processors to perform:

performing word segmentation on a video title of a short video that is most recently watched in the watching record, to obtain individual words;

querying in a pre-established video inverted index table by separately using the individual words as keywords, to obtain video sets formed by corresponding video identifiers;

calculating the similarity between a video title of each short video in each video set and the video title of the short video that is most recently watched in the watching record; and

extracting the preset quantity of the short videos having highest similarities.

18. The non-transitory computer readable storage medium according to claim 17, wherein, when the computer executable instructions cause the one or more processors to perform the calculating the similarity between the video title of each short video in each video set and the video title of the short video that is most recently watched in the watching record, the computer executable instructions cause the one or more processors to perform:

obtaining one or more words, which are in both the video title of each short video in the each video set and in the video title of the short video that is most recently watched in the watching record, and using a maximum weight in weights of the one or more words as the similarity.