WO2020037886A1

WO2020037886A1 - Video associating method and device and computer readable storage medium

Info

Publication number: WO2020037886A1
Application number: PCT/CN2018/120345
Authority: WO
Inventors: 曾金龙
Original assignee: 深圳创维－Rgb电子有限公司
Priority date: 2018-08-24
Filing date: 2018-12-11
Publication date: 2020-02-27
Also published as: CN109040775A

Abstract

Disclosed in the present application are a video associating method and device and a computer readable storage medium, the video associating method comprising the following steps: when receiving a new upload video, acquiring videos to be selected corresponding to the new upload video, wherein there are a plurality of videos contained in the videos to be selected; calculating the similarity level between the new upload video and each video among the videos to be selected, and obtaining a target video on the basis of the calculated similarity level; and associating the new upload video with the target video.

Description

Video association method, device and computer-readable storage medium

Technical field

The present application relates to the technical field of video recommendation, and in particular, to a video association method, device, and computer-readable storage medium.

Background technique

The popularity of the Internet has led to the all-round development of informatization and digitization, and online video has also developed rapidly.

At present, in some video software, users are attracted by short videos, for example, short videos made with wonderful clips in film and television works, thereby increasing the popularity of video software.

At present, this method of attracting users through short videos has the effect of quickly catching the user's attention. However, when a user is interested in a short video, the user is required to manually search for video content related to the short video, and to the user Not convenient enough.

Summary of the Invention

The main purpose of this application is to provide a video association method, device, and computer-readable storage medium, which aims to solve the problem that when a user is interested in a short video in the prior art, the user is required to manually search for a video related to the short video. Video content is not a convenient technical issue for users.

To achieve the above object, the present application provides a video association method, and the video association method includes the following steps:

When a newly uploaded video is received, obtaining a candidate video corresponding to the newly uploaded video, wherein the candidate video includes multiple videos;

Calculating the similarity between the newly uploaded video and each of the videos to be selected, and obtaining the target video based on the calculated similarity;

Associate the newly uploaded video with the target video.

Optionally, when a newly uploaded video is received, the step of obtaining a candidate video corresponding to the newly uploaded video includes:

When a newly uploaded video is received, the title information of the newly uploaded video is obtained; a regular expression is constructed based on the title information, and the regular expression is matched in a video library to obtain the corresponding information of the newly uploaded video. Candidate video.

Optionally, the step of calculating the similarity between the newly uploaded video and each of the videos to be selected includes:

Obtaining a tag vector of the newly uploaded video, and obtaining a tag vector of each of the videos to be selected;

Calculate the similarity between the tag vector of the newly uploaded video and the tag vector of each video in the candidate video.

Optionally, the step of obtaining a tag vector of the newly uploaded video and obtaining a tag vector of each of the videos to be selected includes:

Acquiring video information of the newly uploaded video, performing word segmentation processing on the video information of the newly uploaded video, and obtaining a tag vector of the newly uploaded video;

Acquiring video information of each video in the candidate video, performing word segmentation processing on the video information of each video in the candidate video, and obtaining a label vector of each video in the candidate video.

Optionally, the step of calculating the similarity between the tag vector of the newly uploaded video and the tag vector of each of the videos to be selected includes:

Perform root correction on a label vector of the newly uploaded video to obtain a first label vector, perform root correction on a label vector of each video in the candidate video, and obtain a second label vector group;

Calculate the similarity between the first label vector and each label vector in the second label vector group.

Optionally, the step of obtaining the target video based on the calculated similarity includes:

Sorting each of the videos to be selected according to the similarity order, to obtain a ranking result;

Select a preset number of videos from the first position of the ranking result to get the target video.

Optionally, after associating the newly uploaded video with the target video, the method further includes:

When the association instruction sent by the user account is received, the association relationship between the newly uploaded video and the video corresponding to the association instruction is established.

Optionally, after establishing the association between the newly uploaded video and the video corresponding to the association instruction, the method further includes:

Acquiring feedback information corresponding to the association relationship, and performing reward and punishment measures corresponding to the feedback information to the user account.

In addition, in order to achieve the above-mentioned object, the present application also provides a video-related device. The video-related device includes a memory, a processor, and a video-related program stored on the memory and executable on the processor. The steps of implementing the video association method as described above when the video association program is executed by the processor.

In addition, in order to achieve the above object, the present application also provides a computer-readable storage medium, where the computer-readable storage medium stores a video-associated program, and the video-associated program is implemented by a processor to implement the video association as described above Method steps.

In this application, when a newly uploaded video is received, a candidate video corresponding to the newly uploaded video is obtained, where the candidate video includes multiple videos; and the newly uploaded video and the candidate video are calculated. The similarity of each video, and a target video is obtained based on the calculated similarity; the newly uploaded video is associated with the target video. Through this application, a target video is selected and associated for the newly uploaded video, so that when the user is interested in the newly uploaded video, there is no need to manually search for other videos related to the video, and the associated target video can be directly viewed, which improves the user's Video viewing experience.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic structural diagram of a video association device in a hardware operating environment according to a solution of an embodiment of the present application; FIG.

FIG. 2 is a schematic flowchart of a first embodiment of a video association method according to this application;

FIG. 3 is an association display interface diagram of a first embodiment of a video association method of the present application; FIG.

4 is an association display interface diagram of a second embodiment of a video association method of the present application;

FIG. 5 is a schematic diagram of a user autonomous association scenario according to the first embodiment of the video association method of this application; FIG.

FIG. 6 is a schematic diagram of a user autonomous association scenario according to a second embodiment of a video association method of this application.

The implementation, functional features and advantages of the purpose of this application will be further described with reference to the embodiments and the drawings.

detailed description

It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application.

As shown in FIG. 1, FIG. 1 is a schematic structural diagram of a video association device in a hardware operating environment according to a solution of an embodiment of the present application.

In the embodiment of the present application, the video-related device may be a smart TV, a PC, or a smart phone, a tablet, or an MP4 (Moving Picture Experts Group Audio Layer 4). Players, portable computers, etc. have a display Functional terminal equipment.

As shown in FIG. 1, the video association device may include a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. The communication bus 1002 is used to implement connection and communication between these components. The user interface 1003 may include a display, an input unit such as a keyboard, and the optional user interface 1003 may further include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (for example, a magnetic disk memory). The memory 1005 may optionally be a storage device independent of the foregoing processor 1001.

Optionally, the video association device may further include a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a WiFi module, and the like. Among them, sensors such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor. The ambient light sensor may adjust the brightness of the display screen according to the brightness of the ambient light. The proximity sensor may turn off the display screen and / or when the mobile terminal is moved to the ear. Backlight. As a type of motion sensor, a gravity acceleration sensor can detect the magnitude of acceleration in various directions (generally three axes). It can detect the magnitude and direction of gravity when it is stationary. It can be used to identify the posture of mobile terminals (such as horizontal and vertical screen switching, Related games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tap), etc. Of course, the mobile terminal can also be equipped with other sensors such as gyroscope, barometer, hygrometer, thermometer, infrared sensor, etc., here No longer.

Those skilled in the art can understand that the structure of the video-related device shown in FIG. 1 does not constitute a limitation on the video-related device, and may include more or fewer components than shown in the figure, or some components may be combined, or different components. Layout.

As shown in FIG. 1, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a video-related program.

In the terminal shown in FIG. 1, the network interface 1004 is mainly used to connect to the background server and perform data communication with the background server; the user interface 1003 is mainly used to connect to the client (user) and perform data communication with the client; and the processor 1001 can be used to call a video-related program stored in the memory 1005 and perform the following operations:

Associate the newly uploaded video with the target video.

Further, the processor 1001 may call a video-associated program stored in the memory 1005, and further perform the following operations:

When an association instruction sent by a user account is received, an association relationship between the newly uploaded video and a video corresponding to the association instruction is established.

Referring to FIG. 2, FIG. 2 is a schematic flowchart of a first embodiment of a video association method of the present application.

In one embodiment, the video association method includes:

Step S10: when a newly uploaded video is received, obtaining a candidate video corresponding to the newly uploaded video, where the candidate video includes multiple videos;

In this embodiment, videos are divided into two types: long videos and short videos. Among them, a long video refers to a video whose video duration is greater than or equal to a preset duration, and a short video refers to a video whose video duration is shorter than a preset duration. For example, a video with a video length of 60 minutes or more is called a long video, and a video with a video length of less than 60 minutes is called a short video.

In this embodiment, when the video-associated device receives a newly uploaded video, when the newly uploaded video is a short video, it may obtain a candidate video corresponding to the newly uploaded video from the long video library or obtain it from the short video library. The candidate video corresponding to the newly uploaded video; when the newly uploaded video is a long video, the candidate video corresponding to the newly uploaded video is obtained from the long video library or the candidate video corresponding to the newly uploaded video is obtained from the short video library Select video.

In an optional embodiment of the video association method of the present application, when the newly uploaded video is a short video, the candidate video corresponding to the newly uploaded video from the long video library is used as an example for description. When a newly uploaded video is received, if the duration of the newly uploaded video is detected and it is detected that the video duration of the newly uploaded video is shorter than the preset duration, it is confirmed that the newly uploaded video is a short video. Get the title information of the newly uploaded video (the video will be required to enter the video title when it is uploaded, so you can get the title information of the newly uploaded video based on the input video title), and build a regular expression (regular expression based on the title information) A formula is a logical formula that operates on strings (including ordinary characters (for example, letters between a to z) and special characters (called "meta characters"). It uses certain predefined characters, and The combination of these specific characters forms a "rule string", which is used to express a filtering logic for strings. A regular expression is a text pattern that describes what to match when searching for text One or more strings), and then search and match in the long video library through the constructed regular expression to obtain the candidate video corresponding to the newly uploaded video.

Step S20: Calculate the similarity between the newly uploaded video and each of the videos to be selected, and obtain the target video based on the calculated similarity;

In this embodiment, generally, there are multiple videos to be selected based on step S10. For example, there are 5 candidate videos to be obtained, which are candidate video 1, candidate video 2, candidate video 3, candidate video 4, and candidate video 5. Then, the similarity between the newly uploaded video and the candidate videos 1 to 5 is calculated.

In an embodiment of the present application, calculating the similarity between the newly uploaded video and each of the videos to be selected may be: obtaining video information of the newly uploaded video, where the video information includes related information input when the video is uploaded, such as a video title , Actor name, director name, etc. Then, perform word segmentation processing on the video information of the newly uploaded video to obtain a tag vector of the newly uploaded video. In one embodiment, the video information of the newly uploaded video includes only the video title information (the user often only enters the video title when uploading a short video), such as "Zombie Supreme Huang Ziyang incarnates as a ghost and eats chicken", which is obtained through word segmentation processing The tag vector A of the newly uploaded video is [Zombie Supreme, Huang Ziyang, Li Gui, Eating Chicken]. In this embodiment, word segmentation processing may be performed by using a Chinese word segmentation tool, such as jieba, SnowNLP, THULAC, NLPIR, and the like. Similarly, the video information of each video in the candidate videos (for example, candidate videos 1 to 5) is obtained. Since candidate videos 1 to 5 are videos in the long video library, the video information is relatively It is relatively complete. Generally, video information including video title, actor name, director name, etc. can be obtained or obtained. You can get video information corresponding to video 1 to be selected, video information 2 corresponding to video 2 to be selected, video information 3 corresponding to video 3 to be selected, video information 4 corresponding to video 4 to be selected, and video corresponding to video 5 to be selected. Information 5. Then perform word segmentation processing on video information 1 to video information 5, respectively, to obtain a tag vector corresponding to the video 1 selected, a tag vector corresponding to the video 2 selected, a tag vector 3 corresponding to the video 3 selected, and a tag vector 4 corresponding to the video 4 selected. 2. The candidate video 5 corresponds to the label vector 5. Then, the similarities S1 to S5 of the label vector A and the label vectors 1 to 5 are calculated, respectively. The calculation method is as follows:

Among them, N ₁ and N ₂ are the number of words in the two label vectors, and N ₃ is the number of the same words in the two label vectors. After the above calculation, the similarity between the newly uploaded video and each video in the candidate video can be obtained. For example, the obtained similarity is S1 to S5, and then S1 to S5 are sorted in descending order, such as S2>S3>S5>S2> S1, the corresponding results of the videos 1 to 5 selected are: video 2 to be selected> video 3 to be selected> video 5 to be selected> video 2 to be selected> video 1 to be selected, Then, starting from video 2 to be selected, a preset number of videos (for example, 3, which is set according to actual needs, and there is no limitation here) is selected as the target video.

Step S30: Associate the newly uploaded video with the target video.

In an embodiment of the present application, after step S20, the selected target videos are a candidate video 2, a candidate video 3, and a candidate video 5. Referring to FIG. 3, FIG. 3 is an association display interface diagram of a first embodiment of a video association method of the present application. As shown in FIG. 3, a prompt message is displayed below the newly uploaded video to remind the user that there are 3 associated videos (that is, corresponding target videos) of the newly uploaded video. If the user clicks the display button, the 3 associated videos are displayed. . Referring to FIG. 4, FIG. 4 is an association display interface diagram of a second embodiment of a video association method of the present application. After displaying 3 related videos, users can choose to watch.

In this embodiment, when a newly uploaded video is received, a candidate video corresponding to the newly uploaded video is obtained, where the candidate video includes multiple videos; the newly uploaded video and the candidate video are calculated. The similarity of each video in the video, and obtain the target video based on the calculated similarity; associate the newly uploaded video with the target video. With this embodiment, a target video is selected and associated for the newly uploaded video, so that when the user is interested in the newly uploaded video, the user does not need to manually search for other videos related to the video, and can directly watch the associated target video, which improves the user. Video viewing experience.

Further, in an embodiment of the video association method of this application, step S10 includes:

In this embodiment, based on a regular expression, a candidate video corresponding to a newly uploaded video can be quickly matched, so that a target video can be selected from the candidate videos in the future, narrowing the selection range of subsequent target videos, and improving subsequent selection The relevance of the target video to the newly uploaded video on the other hand reduces the time required to select the target video.

Further, in an embodiment of the video association method of the present application, the step of calculating the similarity between the newly uploaded video and each of the videos to be selected includes:

In an embodiment of the present application, calculating the similarity between the newly uploaded video and each of the videos to be selected may be: obtaining video information of the newly uploaded video, where the video information includes related information input when the video is uploaded, such as a video title , Actor name, director name, etc. Then, perform word segmentation processing on the video information of the newly uploaded video to obtain a tag vector of the newly uploaded video. In one embodiment, the video information of the newly uploaded video includes only the video title information (the user often only enters the video title when uploading a short video), such as "Zombie Supreme Huang Ziyang incarnates as a ghost and eats chicken", which is obtained by word processing The tag vector A of the newly uploaded video is [Zombie Supreme, Huang Ziyang, Li Gui, Eating Chicken]. In this embodiment, word segmentation processing may be performed by using a Chinese word segmentation tool, such as jieba, SnowNLP, THULAC, NLPIR, and the like. Similarly, the video information of each video in the candidate videos (for example, candidate videos 1 to 5) is obtained. Since candidate videos 1 to 5 are videos in the long video library, the video information is relatively It is relatively complete. Generally, video information including video title, actor name, director name, etc. can be obtained or obtained. You can get video information corresponding to video 1 to be selected, video information 2 corresponding to video 2 to be selected, video information 3 corresponding to video 3 to be selected, video information 4 corresponding to video 4 to be selected, and video corresponding to video 5 to be selected. Information 5. Then perform word segmentation processing on video information 1 to video information 5, respectively, to obtain a tag vector corresponding to the video 1 selected, a tag vector corresponding to the video 2 selected, a tag vector 3 corresponding to the video 3 selected, and a tag vector 4 corresponding to the video 4 selected. 2. The candidate video 5 corresponds to the label vector 5. Then, the similarities S1 to S5 of the label vector A and the label vectors 1 to 5 are calculated, respectively. The calculation method is as follows:

Among them, N ₁ and N ₂ are the number of words in the two label vectors, and N ₃ is the number of the same words in the two label vectors. After the above calculation, the similarity between the newly uploaded video and each of the videos to be selected can be obtained.

In this embodiment, the similarity between the newly uploaded video and each of the videos to be selected is calculated, so that the subsequent target video selected based on the similarity is more associated with the newly uploaded video, that is, the target video is more in line with the viewing needs of the user.

Further, in an embodiment of the video association method of the present application, the step of obtaining a tag vector of the newly uploaded video and obtaining a tag vector of each of the videos to be selected includes:

In an embodiment of the present application, calculating the similarity between the newly uploaded video and each of the videos to be selected may be: obtaining video information of the newly uploaded video, where the video information includes related information input when the video is uploaded, such as a video title , Actor name, director name, etc. Then, perform word segmentation processing on the video information of the newly uploaded video to obtain a tag vector of the newly uploaded video. In one embodiment, the video information of the newly uploaded video includes only the video title information (the user often only enters the video title when uploading a short video), such as "Zombie Supreme Huang Ziyang incarnates as a ghost and eats chicken", which is obtained through word segmentation processing. The tag vector A of the newly uploaded video is [Zombie Supreme, Huang Ziyang, Li Gui, Eating Chicken]. In this embodiment, word segmentation processing may be performed by using a Chinese word segmentation tool, such as jieba, SnowNLP, THULAC, NLPIR, and the like. Similarly, the video information of each video in the candidate videos (for example, candidate videos 1 to 5) is obtained. Since candidate videos 1 to 5 are videos in the long video library, the video information is relatively It is relatively complete, and generally can obtain or obtain video information including video title, actor name, director name and other information. You can get video information corresponding to video 1 to be selected, video information 2 corresponding to video 2 to be selected, video information 3 corresponding to video 3 to be selected, video information 4 corresponding to video 4 to be selected, and video corresponding to video 5 to be selected. Information 5. Then perform word segmentation processing on video information 1 to video information 5, respectively, to obtain a tag vector corresponding to the video 1 selected, a tag vector corresponding to the video 2 selected, a tag vector 3 corresponding to the video 3 selected, and a tag vector 4 corresponding to the video 4 selected. 2. The candidate video 5 corresponds to the label vector 5.

Further, in an embodiment of the video association method of the present application, the step of calculating the similarity between the tag vector of the newly uploaded video and the tag vector of each of the videos to be selected includes:

In this embodiment, a word C1 in a tag vector of a newly uploaded video and a word C2 in a tag vector of a candidate video may express the same meaning, but are displayed in different characters. The similarity calculated in this way will deviate from the actual situation, so root correction is required. Taking the English environment as an example, the root of play, playing, and played is play. For example, if C1 is playing and C2 is played, the playing in C1 is corrected to play, the played in C2 is corrected to play, and then the similarity calculation is performed to make the calculated similarity more realistic. That is, the tag vector is corrected by root correction in English. Similarly, in the Chinese environment, because the user may use another name for an actor, such as Zhou Xingchi, Zhou Xingxing, and Xing Ye, these words actually refer to Zhou Xingchi, and "Chou Xingchi" is the word , If C1 is Zhou Xingxing and C2 is Xingye, then the Cing Xingzhi in C1 is corrected to Chow Xingchi, and the Xingye in C2 is corrected to Chow Xingchi. In this embodiment, a derived lexicon can be maintained for each actor to support root correction. For example, in a derivation thesaurus, the roots corresponding to "Xingxing Zhou" and "Xingye" are both "Xingxing Zhou", and then when "Xingxing Zhou" and "Xingye" appear in the label vector, it is automatically corrected to "Xingxing Zhou ".

In this embodiment, before performing similarity calculation, root correction is performed on the tag vector, so that the similarity obtained in subsequent calculations is more in line with reality, so that the subsequently selected target video is more in line with user viewing needs.

Further, in an embodiment of the video association method of the present application, the step of obtaining the target video based on the calculated similarity includes:

In this embodiment, after the similarity calculation is performed, the similarity between the newly uploaded video and each of the videos to be selected can be obtained. For example, the obtained similarity is S1 to S5, and then S1 to S5 are sorted in descending order. Sorting, for example, S2> S3> S5> S2> S1, the sorting results of corresponding videos 1 to 5 are: video 2 to be selected> video 3 to be selected> video 5 to be selected> video 2 to be selected > To-be-selected video 1, then starting from to-be-selected video 2, select a preset number of videos (for example, three, this value is set according to actual needs, there is no limit here) as the target video.

In this embodiment, a candidate video with a large similarity is used as a target video, so that the target video displayed in association with the target video is more in line with the user's viewing needs.

Further, in an embodiment of the video association method of the present application, after step S30, the method further includes:

In this embodiment, the target video may be automatically associated with the newly uploaded video based on steps S10 to S30, and subsequently, the video selected by the user may be associated with the newly uploaded video based on user operations.

In an embodiment of the present application, when a user feels that the target video automatically associated with the newly uploaded video based on steps S10 to S30 is not suitable for the user's needs, he can click the association button and then add the video A to be associated, the video association device When the association instruction triggered by the user operation is received, the association relationship between the newly uploaded video and the video corresponding to the association instruction (that is, the video A that the user chooses to add) is established.

Referring to FIG. 5, FIG. 5 is a schematic diagram of a user's autonomous association scenario according to the first embodiment of the video association method of the present application. As shown in FIG. 5, based on steps S10 to S30, the target video (video to be selected 2, video to be selected 3, video to be selected 5) has been automatically associated with the newly uploaded video, and the user clicks the "+ associated feature" button to enter the The interface shown in Figure 6. Referring to FIG. 6, FIG. 6 is a schematic diagram of a user's autonomous association scenario according to the second embodiment of the video association method of the present application. As shown in FIG. 6, the search input box is used to input a search keyword, and after the search is performed, the search result is displayed. The user clicks a search result to select / deselect it, and finally clicks the OK button to trigger the association instruction.

In this embodiment, the user can participate in the work of video association, which improves the interaction rate with the user and the user's experience. The participation of the user can also make the video association more suitable for the needs of the user.

Further, in an embodiment of the video association method of the present application, after establishing the association between the newly uploaded video and the video corresponding to the association instruction, the method further includes:

In this embodiment, when based on the association instruction sent by the user account A, the established association relationship is: associate video a and video b with the newly uploaded video. Other users can evaluate video a and video b associated with the newly uploaded video. If video a or video b is suitable for viewing needs, they can like video a or video b. If video a or video b is new, Upload videos that are not relevant, you can click dislike. It may be that after the association is established for a period of time (for example, one month later), the feedback information corresponding to the association is obtained, that is, the number of likes Y corresponding to video a or video b and the number N that is marked as dislike. If Y / If the value of N is higher than the first threshold (set according to the actual situation), the user account A will be positively stimulated, such as reward points, upgrade account level, etc .; if the value of Y / N is lower than the second threshold (based on the actual situation) Set), then punish user account A, such as disqualifying the account from participating in video association work.

In this embodiment, a feedback mechanism is established, and rewarding or punishing the user account through the feedback information improves the enthusiasm of the user to participate in the video association work on the one hand, and improves the quality of the video association on the other hand.

In addition, an embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores a video-associated program, and when the video-associated program is executed by a processor, implements the steps of the video-associated method as described above. .

The specific embodiments of the computer-readable storage medium of the present application are basically the same as the embodiments of the video association method described above, and are not repeated here.

It should be noted that, in this article, the terms "including", "including" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, It also includes other elements not explicitly listed, or elements inherent to such a process, method, article, or system. Without more restrictions, an element limited by the sentence "including a ..." does not exclude the existence of other identical elements in the process, method, article, or system that includes the element.

The above-mentioned serial numbers of the embodiments of the present application are merely for description, and do not represent the superiority or inferiority of the embodiments.

Through the description of the above embodiments, those skilled in the art can clearly understand that the methods in the above embodiments can be implemented by means of software plus a necessary universal hardware platform, and of course, also by hardware, but in many cases the former is better. Implementation. Based on such an understanding, the technical solution of this application that is essentially or contributes to the existing technology can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM) as described above. , Magnetic disk, optical disc), including a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the embodiments of the present application.

The above are only optional embodiments of the present application, and thus do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of the application, or directly or indirectly applied to other related technologies The fields are equally included in the patent protection scope of this application.

Claims

A video association method, wherein the video association method includes the following steps:

When a newly uploaded video is received, obtaining a candidate video corresponding to the newly uploaded video, wherein the candidate video includes multiple videos;

Calculating the similarity between the newly uploaded video and each of the videos to be selected, and obtaining the target video based on the calculated similarity;

Associate the newly uploaded video with the target video.
The video association method according to claim 1, wherein after associating the newly uploaded video with the target video, further comprising:

When an association instruction sent by a user account is received, an association relationship between the newly uploaded video and a video corresponding to the association instruction is established.
The video association method according to claim 2, wherein after establishing the association between the newly uploaded video and the video corresponding to the association instruction, further comprising:

Acquiring feedback information corresponding to the association relationship, and performing reward and punishment measures corresponding to the feedback information to the user account.
The video association method according to claim 1, wherein when the newly uploaded video is received, the step of obtaining a candidate video corresponding to the newly uploaded video comprises:

When a newly uploaded video is received, obtaining title information of the newly uploaded video;

A regular expression is constructed based on the title information, and the regular expression is matched in a video library to obtain a candidate video corresponding to the newly uploaded video.
The video association method according to claim 4, wherein after associating the newly uploaded video with the target video, further comprising:

When an association instruction sent by a user account is received, an association relationship between the newly uploaded video and a video corresponding to the association instruction is established.
The video association method according to claim 5, wherein after establishing the association between the newly uploaded video and the video corresponding to the association instruction, further comprising:

Acquiring feedback information corresponding to the association relationship, and performing reward and punishment measures corresponding to the feedback information to the user account.
The video association method according to claim 1, wherein the step of calculating the similarity between the newly uploaded video and each of the videos to be selected comprises:

Obtaining a tag vector of the newly uploaded video, and obtaining a tag vector of each of the videos to be selected;

Calculate the similarity between the tag vector of the newly uploaded video and the tag vector of each video in the candidate video.
The video association method according to claim 7, wherein after associating the newly uploaded video with the target video, further comprising:

When an association instruction sent by a user account is received, an association relationship between the newly uploaded video and a video corresponding to the association instruction is established.
The video association method according to claim 8, wherein after establishing the association between the newly uploaded video and the video corresponding to the association instruction, further comprising:

Acquiring feedback information corresponding to the association relationship, and performing reward and punishment measures corresponding to the feedback information to the user account.
The video association method according to claim 7, wherein the step of obtaining a tag vector of the newly uploaded video and obtaining a tag vector of each of the videos to be selected comprises:

Acquiring video information of the newly uploaded video, performing word segmentation processing on the video information of the newly uploaded video, and obtaining a tag vector of the newly uploaded video;

Acquiring video information of each video in the candidate video, performing word segmentation processing on the video information of each video in the candidate video, and obtaining a label vector of each video in the candidate video.
The video association method according to claim 10, wherein after associating the newly uploaded video with the target video, further comprising:

When an association instruction sent by a user account is received, an association relationship between the newly uploaded video and a video corresponding to the association instruction is established.
The video association method according to claim 11, wherein after establishing the association between the newly uploaded video and the video corresponding to the association instruction, further comprising:

Acquiring feedback information corresponding to the association relationship, and performing reward and punishment measures corresponding to the feedback information to the user account.
The video association method according to claim 7, wherein the step of calculating the similarity between the tag vector of the newly uploaded video and the tag vector of each of the videos to be selected comprises:

Perform root correction on a label vector of the newly uploaded video to obtain a first label vector, perform root correction on a label vector of each video in the candidate video, and obtain a second label vector group;

Calculate the similarity between the first label vector and each label vector in the second label vector group.
The video association method according to claim 13, wherein after associating the newly uploaded video with the target video, further comprising:

When an association instruction sent by a user account is received, an association relationship between the newly uploaded video and a video corresponding to the association instruction is established.
The video association method according to claim 14, wherein after establishing the association between the newly uploaded video and the video corresponding to the association instruction, further comprising:

Acquiring feedback information corresponding to the association relationship, and performing reward and punishment measures corresponding to the feedback information to the user account.
The video association method according to claim 1, wherein the step of obtaining the target video based on the calculated similarity comprises:

Sorting each of the videos to be selected according to the similarity order, to obtain a ranking result;

Select a preset number of videos from the first position of the ranking result to get the target video.
The video association method according to claim 16, wherein after associating the newly uploaded video with the target video, further comprising:

When an association instruction sent by a user account is received, an association relationship between the newly uploaded video and a video corresponding to the association instruction is established.
The video association method according to claim 17, wherein after establishing the association between the newly uploaded video and the video corresponding to the association instruction, further comprising:

Acquiring feedback information corresponding to the association relationship, and performing reward and punishment measures corresponding to the feedback information to the user account.
A video-associated device, wherein the video-associated device includes a memory, a processor, and a video-associated program stored on the memory and executable on the processor; Implement the following steps during execution:

When a newly uploaded video is received, obtaining a candidate video corresponding to the newly uploaded video, wherein the candidate video includes multiple videos;

Calculating the similarity between the newly uploaded video and each of the videos to be selected, and obtaining the target video based on the calculated similarity;

Associate the newly uploaded video with the target video.
A computer-readable storage medium, wherein a video-related program is stored on the computer-readable storage medium, and when the video-related program is executed by a processor, the following steps are implemented:

When a newly uploaded video is received, obtaining a candidate video corresponding to the newly uploaded video, wherein the candidate video includes multiple videos;

Calculating the similarity between the newly uploaded video and each of the videos to be selected, and obtaining the target video based on the calculated similarity;

Associate the newly uploaded video with the target video.