CN112672208B

CN112672208B - Video playing method, device, electronic equipment, server and system

Info

Publication number: CN112672208B
Application number: CN202011381477.0A
Authority: CN
Inventors: 杨立; 张曼
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2020-11-30
Filing date: 2020-11-30
Publication date: 2023-06-20
Anticipated expiration: 2040-11-30
Also published as: CN112672208A

Abstract

The embodiment of the disclosure provides a video playing method, a video playing device, electronic equipment, a server and a video playing system. The method comprises the following steps: responding to a first playing triggering operation, and acquiring a first video to be played and associated video information, wherein the associated video information comprises video information of at least one second video associated with the first video on video content; playing the first video; and when the playing state of the first video is detected to be in accordance with a preset condition, displaying a playing inlet of the second video according to the associated video information. Therefore, according to the embodiment of the invention, the playing entrance of the associated video can be provided timely according to the video watching state of the user, so that the user can continuously watch the associated video without tedious operation, and the video watching experience of the user is improved.

Description

Video playing method, device, electronic equipment, server and system

Technical Field

The disclosure relates to the field of computer technology, and in particular, to a video playing method, a device, an electronic device, a server and a system.

Background

With the rapid development of mobile communication technology, various short video APP layers are endless. The user watches short videos released by other users in the video APP.

Currently, users usually find out short videos of interest in short videos APP by sliding up and down and optionally browsing. After watching the interested short video, the user also wants to watch the short video related to the short video (for example, other short videos in the short video set with the same theme published by the author of the short video), and often needs to find the homepage of the author of the short video to search or input the theme of the short video to search, which results in that the related short video cannot be continuously watched, and affects the short video watching experience of the user.

Disclosure of Invention

The embodiment of the disclosure provides a video playing method, a video playing device, an electronic device, a server and a video playing system, and the technical scheme of the disclosure is as follows:

according to a first aspect of an embodiment of the present disclosure, there is provided a video playing method, including:

responding to a first playing triggering operation, and acquiring a first video to be played and associated video information, wherein the associated video information comprises video information of at least one second video associated with the first video on video content;

playing the first video;

and when the playing state of the first video is detected to be in accordance with a preset condition, displaying a playing inlet of the second video according to the associated video information.

Optionally, the process of acquiring the associated video information includes:

in the pre-stored videos, acquiring videos of which authors are the same as the authors of the first video, wherein the videos are used as candidate videos;

and when the content information of the first video is identified, selecting at least one second video associated with the first video on video content from the candidate videos according to the content information of the first video, and taking the video information of the selected at least one second video as the associated video information.

Optionally, the process of identifying the content information of the first video includes:

acquiring characteristic information of the first video;

and inputting the characteristic information of the first video into a pre-established content identification model for identifying video content, and outputting the content information of the first video.

Optionally, the acquiring the feature information of the first video includes:

extracting key frames of the first video;

acquiring color characteristics of each key frame of the first video to serve as characteristic information of a first dimension of the first video;

acquiring color characteristics of the first video to serve as characteristic information of a second dimension of the first video;

Identifying characteristic information of a moving object in each key frame of the first video as characteristic information of a third dimension of the first video;

and acquiring the audio characteristic information of the first video to serve as the characteristic information of the fourth dimension of the first video.

Optionally, the acquiring the color feature of the first video includes:

acquiring a first target type of a subject object in each key frame of the first video;

determining a weight value corresponding to the first target type according to a predetermined corresponding relation between the object type and the weight value, wherein the weight value is used as a weight value of a key frame where a subject object to which the first target type belongs is located;

obtaining the product of the color characteristic and the weight value of each key frame of the first video to be used as a first parameter of each key frame of the first video;

and obtaining the sum of the first parameters of each key frame of the first video to serve as the color characteristic of the first video.

Optionally, the process for establishing the content identification model includes:

acquiring characteristic information of a plurality of sample videos;

and taking the characteristic information of one sample video and the content information of the predetermined sample video as a training sample, and training the training sample by adopting a recurrent neural network to obtain the content recognition model.

Optionally, the acquiring the feature information of the plurality of sample videos includes:

for each of the sample videos, performing the following process:

extracting key frames of the sample video;

acquiring color characteristics of each key frame of the sample video to serve as characteristic information of a first dimension of the sample video;

acquiring color characteristics of the sample video to serve as characteristic information of a second dimension of the sample video;

identifying characteristic information of a moving object in each key frame of the sample video as characteristic information of a third dimension of the sample video;

and acquiring the audio characteristic information of the sample video to serve as the characteristic information of the fourth dimension of the sample video.

Optionally, the acquiring the color feature of the sample video includes:

acquiring a second target type of a subject object in each key frame of the sample video;

determining a weight value corresponding to the second target type according to a predetermined corresponding relation between the object type and the weight value, wherein the weight value is used as a weight value of a key frame where a theme object to which the second target type belongs is located;

obtaining the product of the color characteristic and the weight value of each key frame of the sample video to be used as a second parameter of each key frame of the sample video;

And obtaining the sum of the second parameters of each key frame of the sample video to serve as the color characteristic of the sample video.

Optionally, the content information includes: the episode name of the episode to which the video belongs;

the selecting at least one second video associated with the first video on video content from the candidate videos according to the content information of the first video comprises:

at least one candidate video whose episode name matches the episode name of the first video is selected from the candidate videos as a second video associated with the first video on video content.

Optionally, the process of acquiring the associated video information further includes:

and under the condition that the content information of the first video is not identified, selecting candidate videos with the similarity between the video cover and the video cover of the first video being larger than a preset threshold value from the candidate videos, and taking the video information of the selected candidate videos as the associated video information.

Optionally, the selecting, from the candidate videos, a candidate video with a similarity between a video cover and a video cover of the first video greater than a preset threshold value includes:

And selecting candidate videos with the similarity between the video cover and the video cover of the first video larger than a preset threshold value from the candidate videos by adopting a similar image retrieval technology based on a perceptual hash algorithm.

Optionally, the selecting, by using a similar image retrieval technique based on a perceptual hash algorithm, a candidate video with a similarity between a video cover and a video cover of the first video greater than a preset threshold value from the candidate videos includes:

acquiring a first hash value of a video cover of each candidate video and a second hash value of the video cover of the first video;

acquiring the Hamming distance between the second hash value and each first hash value;

and taking the candidate video of the video cover of which the first hash value corresponding to the Hamming distance smaller than the preset distance belongs as the candidate video of which the similarity between the video cover and the video cover of the first video is larger than a preset threshold value.

Optionally, the video information of the second video includes identification information of the second video;

the displaying the play entry of the second video according to the associated video information includes:

acquiring a video cover of a second video to which the target identification information belongs according to the target identification information to serve as a target video cover, wherein the target identification information comprises identification information of the second video related to the associated video information;

And displaying the target video cover as a playing inlet of the second video.

Optionally, the video information of the second video further includes an episode number of the second video;

the displaying the target video cover as the playing entrance of the second video includes:

according to the arrangement sequence of the sequence numbers of the target episodes, the target video covers are displayed as the playing inlets of the second videos;

the target episode number includes an episode number of a second video related to the associated video information.

Optionally, the method further comprises:

receiving a second play triggering operation of one of the video covers of the second video;

and responding to the second playing triggering operation, and playing a second video to which the video cover aimed by the second playing triggering operation belongs.

Optionally, the video information of the second video includes an episode number of the second video; the method further comprises the steps of:

displaying a preset icon;

receiving a first preset operation on the preset icon;

and responding to the first preset operation, acquiring the episode number of the first video, and playing a second video to which the next sequence number of the episode number of the first video belongs.

Optionally, the process of acquiring the associated video information includes:

and receiving the associated video information sent by the server.

According to a second aspect of embodiments of the present disclosure, there is provided a video playing method, the method including:

sending a first video and associated video information to a client device, so as to play the first video on the client device, and displaying a play inlet of a second video on the client device according to the associated video information when the play state of the first video meets a preset condition;

wherein the associated video information includes video information of at least one of the second videos associated with the first video in the presence of video content.

According to a third aspect of embodiments of the present disclosure, there is provided a video playing device, the device comprising:

the associated information acquisition module is configured to respond to a first playing triggering operation and acquire first video to be played and associated video information, wherein the associated video information comprises video information of at least one second video associated with the first video on video content;

a first play module configured to play the first video;

And the entrance display module is configured to display the playing entrance of the second video according to the associated video information when detecting that the playing state of the first video meets the preset condition.

According to a fourth aspect of embodiments of the present disclosure, there is provided a video playing device, the device comprising:

the information sending module is configured to send a first video and associated video information to the client device so as to play the first video on the client device, and when the playing state of the first video meets a preset condition, a playing inlet of a second video is displayed on the client device according to the associated video information;

According to a fifth aspect of embodiments of the present disclosure, there is provided an electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the video playing method described in the first aspect.

According to a sixth aspect of embodiments of the present disclosure, there is provided a server comprising:

A processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the video playing method according to the second aspect.

According to a seventh aspect of an embodiment of the present disclosure, there is provided a video playing system, including the electronic device described in the fifth aspect and the server described in the sixth aspect.

According to an eighth aspect of embodiments of the present disclosure, there is provided a storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform any one of the video playback methods described above.

According to a ninth aspect of embodiments of the present disclosure, there is provided a computer program product comprising instructions which, when run on a computer, cause the computer to implement the video playback method of any one of the above.

According to the technical scheme provided by the embodiment of the disclosure, the first video to be played and the associated video information can be obtained in response to the first play triggering operation, so that the first video is played, and when the play state of the first video is detected to meet the preset condition, the play entrance of the second video is displayed according to the associated video information, wherein the associated video information comprises video information of at least one second video managed on the video content with the first video.

Therefore, in the embodiment of the disclosure, when the play triggering operation for the first video is received, the video information of the first video and at least one second video associated with the first video on the video content is obtained, and when the play state of the first video meets the preset condition, the play entrance of the second video can be displayed according to the video information of the second videos, so that the play entrance of the associated video can be provided timely according to the state of the user watching the video, the user can continuously watch the associated video without tedious operation, and the video watching experience of the user is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

FIG. 1 is a flowchart illustrating a video playback method according to an exemplary embodiment;

FIG. 2 is a flowchart illustrating another video playback method according to an exemplary embodiment;

FIG. 3 is a flow diagram illustrating a process for building a content recognition model, according to an example embodiment;

FIG. 4 is a schematic illustration of a display of a target video cover shown in accordance with an exemplary embodiment;

FIG. 5 is a flowchart illustrating another video playback method according to an exemplary embodiment;

FIG. 6 is a flowchart illustrating another video playback method according to an exemplary embodiment;

fig. 7 is a block diagram of a video playback device according to an exemplary embodiment;

FIG. 8 is a block diagram of another video playback device, according to an example embodiment;

FIG. 9 is a block diagram of an electronic device, shown in accordance with an exemplary embodiment;

FIG. 10 is a block diagram of another electronic device shown in accordance with an exemplary embodiment;

fig. 11 is a block diagram of a server, according to an example embodiment.

Detailed Description

In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.

In order to solve the problem that in the prior art, a user cannot continuously watch an associated short video, so that short video watching experience of the user is affected, the embodiment of the disclosure provides a video playing method, device, electronic equipment, server and system.

In one aspect of the disclosed embodiments, a video playing method is provided, which can be applied to an electronic device. As shown in fig. 1, the video playing method may include the steps of:

step 101: and responding to the first playing triggering operation, and acquiring the first video to be played and associated video information.

The first play trigger operation may be a click operation on a play entry of the first video (e.g., a video cover of the first video).

In addition, the associated video information includes video information of at least one second video associated with the first video present on video content. The videos associated on the video content belong to the same episode, wherein the episode is typically a video in the form of a series or story. Alternatively, the video information of the second video may include identification information of the second video. The identification information may be a video ID.

As can be seen from the foregoing, in the embodiments of the present disclosure, when a play trigger operation for a first video is received, video information of the first video and at least one second video associated with the first video on video content are acquired together.

Step 102: and playing the first video.

Step 103: and when the playing state of the first video is detected to be in accordance with a preset condition, displaying a playing inlet of the second video according to the associated video information.

The playing entrance of the second video is an entrance entering the playing interface of the second video, for example, clicking the playing entrance of the second video can play the second video.

In one possible implementation manner, the preset condition includes that the remaining playing duration of the first video reaches a preset duration. That is, the client device may display the play entry of the second video when the remaining play duration of the first video reaches a preset duration (for example, 3 seconds) after the first video is played.

As can be seen from the foregoing steps 101 to 103, the video playing method provided in the embodiments of the present disclosure may obtain, in response to a first playing trigger operation, a first video to be played and associated video information, so as to play the first video, and when detecting that a playing state of the first video meets a preset condition, display a playing entry of a second video according to the associated video information, where the associated video information includes video information of at least one second video managed on video content with the first video.

Therefore, in the video playing method provided by the embodiment of the disclosure, when the playing triggering operation for the first video is received, the video information of the first video and at least one second video associated with the first video on the video content is obtained, when the playing state of the first video meets the preset condition, the playing entrance of the second video can be displayed according to the video information of the second videos, so that the playing entrance of the associated video can be provided timely according to the state of the user watching the video, the user can continuously watch the associated video without tedious operation, and the video watching experience of the user is improved.

In yet another aspect of the disclosure, a video playing method is also provided, where the video playing method may be applied to an electronic device. As shown in fig. 2, the video playing method may include the steps of:

step 201: and responding to the first playing triggering operation, and acquiring the first video to be played and associated video information.

In addition, the associated video information includes video information of at least one second video associated with the first video present on video content. The videos associated on the video content belong to the same episode, wherein the episode is typically a video in the form of a series or story. The video information of the second video includes identification information of the second video. The identification information may be a video ID.

Step 202: and playing the first video.

Step 203: when the playing state of the first video is detected to be in accordance with a preset condition, acquiring a video cover of a second video to which the target identification information belongs according to the target identification information, and taking the video cover as a target video cover.

In one possible implementation manner, the preset condition includes that the remaining playing duration of the first video reaches a preset duration. I.e. the client device may perform step 203 described above when the remaining playing time of the first video reaches a preset time period (e.g. 3 seconds) after the first video is played.

In addition, the target identification information includes identification information of a second video to which the associated video information relates. In other words, in the embodiment of the present disclosure, when the play state of the first video is detected to meet the preset condition, the video cover of the second video is obtained according to the identification information of the second video related to the associated video information, so as to be displayed as the play entry of the second video. For example, the identification information of the second video related to the associated video information includes identification information of A, B, C three videos, and then the video covers of the three videos need to be acquired A, B, C for display.

In addition, after the client device receives the first play triggering operation, the client device may obtain the video cover of the second video according to the identification information of the second video, or the client device may request the video cover of the second video from the server according to the identification information of the second video.

Step 204: and displaying the target video cover as a playing inlet of the second video.

As can be seen from the foregoing steps 201 to 204, the video playing method provided in the embodiment of the present disclosure may obtain, in response to a first playing trigger operation, a first video to be played and associated video information, so as to play the first video, and when detecting that a playing state of the first video meets a preset condition, obtain, according to identification information of a second video related to the associated video information, a video cover of the second video, so as to serve as a playing entry of the second video for displaying, where the associated video information includes video information of at least one second video managed on video content with the first video.

Therefore, in the video playing method provided by the embodiment of the disclosure, when the playing triggering operation for the first video is received, the first video and the identification information of at least one second video associated with the first video on the video content are acquired, when the playing state of the first video meets the preset condition, the video cover of the second video can be acquired according to the identification information of the second videos to be displayed as the playing inlet of the second video, so that the playing inlet of the associated video can be provided timely according to the state of the user watching the video, the user can continuously watch the associated video without tedious operation, and the video watching experience of the user is improved.

In one possible implementation, the process of acquiring the associated video information includes:

Optionally, the content information includes an episode name, an episode serial number, and an episode type.

As can be seen from the foregoing, in the embodiments of the present disclosure, after receiving the first play trigger operation, the client device may automatically identify the content information of the first video, so that at least one second video associated with the first video on the video content may be selected from the pre-stored videos having the same author as the first video according to the content information of the first video.

In addition, when a user views a video in a short video APP using a client device, after one video is viewed, if other videos related to the video on the video content need to be searched, the video of the same author is often focused, but in the embodiment of the disclosure, the video which belongs to the same author as the first video is screened out of the videos stored in advance as candidate videos, and then a second video related to the first video on the video content is selected from the candidate videos, that is, in the embodiment of the disclosure, the second video which belongs to the same author as the first video and is related to the video content can be automatically selected, so that the video cover of the second video which belongs to the same author as the first video and is related to the video content can be displayed on the client, thereby being closer to the actual use requirement of the user, and further avoiding the user to screen the videos for himself.

In one possible implementation, the process of identifying content information of the first video includes:

acquiring characteristic information of the first video;

It can be known that, in the embodiment of the present disclosure, a content recognition model for recognizing video content may be established in advance, and then, when content information of a first video needs to be recognized, feature information of the first video may be extracted, so that the feature information of the first video is input into the content recognition model, and further, the content information of the first video may be output.

Based on the prior art, the manner of determining at least one second video associated with the first video on the video content is easily thought of, often, by providing a setting option in a short video APP, marking the content information of the uploaded short video in the setting option by an author in the process of uploading the video in the short video APP, so that the server counts which videos are associated on the video content according to the content information of each video marked by the author. However, the development difficulty of the short video APP is high, and the authors uploading the video need to be guided to label the video content information, so that the burden is increased for the authors uploading the video.

In the embodiment of the disclosure, the content information of the video is automatically identified through the pre-established content identification model, setting options do not need to be provided in the short video APP, and an author does not need to manually label the content information of the video, so that the process of identifying the content information of the video is greatly simplified, and the interactive operation experience of a user is further improved.

In a possible implementation manner, the acquiring the feature information of the first video includes:

extracting key frames of the first video;

Wherein, the frame is the single image picture of the minimum unit in the animation, which is equivalent to each frame of the lens on the film. The frames appear as a grid or a mark on the time axis of the animation software. The key frame is equivalent to the original picture in the two-dimensional animation, and refers to the frame in which the key action in the movement or change of the character or the object is located.

In addition, the color features may be RGB features.

Further, the above-mentioned audio feature information may include at least one of musical instruments employed by background music in the video, pitches, frequencies, decibels of sounds existing in the video other than the background music, and voice information of persons existing in the video.

It is known that the video feature information of the first video includes feature information of multiple dimensions, such as the above-described feature information of the first dimension of the first video (may be referred to as a frame-level picture color feature), feature information of the second dimension (may be referred to as a video-level color feature), feature information of the third dimension, and feature information of the fourth dimension. In the embodiment of the disclosure, compared with identifying the content information of the first video according to the single-dimensional feature information of the first video, the feature information of multiple dimensions of the first video is extracted to identify the content information of the first video, so that the content information of the first video can be identified more accurately, that is, the accuracy of identifying the content information of the video is further improved.

In a possible implementation manner, the acquiring the color feature of the first video includes:

For example, 5 key frames are extracted from the first video, the color characteristics of each key frame are respectively X1, X2, X3, X4, and X5, and the weight values of each key frame are respectively k1, k2, k3, k4, and k5, so that the characteristic information of the second dimension of the first video is x1×k1+x2×k2+x3×k3+x4+x5×k5.

In one possible implementation manner, the process for establishing the content identification model includes:

acquiring characteristic information of a plurality of sample videos;

It can be known that in the embodiment of the disclosure, the content information of the plurality of sample videos may be predetermined, then the feature information of the plurality of sample videos may be extracted, further the feature information and the content information of one sample video may be used as a training sample, and the recurrent neural network may be used to train the training sample, so as to obtain the content recognition model for recognizing the video content.

In one possible implementation manner, the acquiring feature information of the plurality of sample videos includes:

for each of the sample videos, performing the following process:

extracting key frames of the sample video;

Therefore, the process of acquiring the feature information of each sample video is the same as the process of acquiring the feature information of the first video, and will not be described herein.

The method comprises the steps of extracting characteristic information of multiple dimensions of a sample video, and establishing a content identification model according to the characteristic information, so that the established content identification model can more accurately identify the content information of the video.

In a possible implementation manner, the acquiring the color feature of the sample video includes:

As can be seen from this, the process of acquiring the color feature of each sample video is the same as the process of acquiring the color feature of the first video, and will not be described here again.

From the foregoing, it can be seen that, in the embodiment of the disclosure, a specific implementation of establishing a content recognition module may be shown in fig. 3. The specific steps are as follows:

firstly, collecting a plurality of video samples;

secondly, video features are extracted, i.e. the following procedure is performed for each sample video:

the first step: extracting key frames of sample video (i.e. the picture retains complete video frames, such as a head-shaking video, and the video frames with complete faces are key frames), and extracting audio information;

and a second step of: aiming at key frames, RGB features of each key frame are obtained;

and a third step of: obtaining a subject object included in each key frame, determining the weight of each key frame according to the corresponding relation between the predetermined object type and the weight, and then calculating the product of RGB features of the key frame and the weight of the key frame, so that all the products are added to obtain a weighted average value, wherein the weighted average value is the video-level RGB feature;

fourth step: identifying which objects in the keyframe are moving objects;

fifth step: extracting audio features from the audio information;

finally: and establishing a multi-modal fusion classification/identification model (namely establishing a content identification model) according to the different dimensional characteristics extracted in the steps.

In one possible implementation, the content information includes: the episode name of the episode to which the video belongs;

It can be seen that, in the embodiments of the present disclosure, when the episode name of the first video is identified, the second video associated with the first video on the video content may be directly searched for in the candidate videos according to the episode name.

In one possible embodiment, the method further comprises:

As can be seen, in the embodiment of the present disclosure, if the content information of the first video is not identified, the second video associated with the first video on the video content may be selected from the candidate videos according to the video cover of the first video, so that the defect that the content information of the video cannot be identified is overcome by using the method of identifying the associated video by the video cover.

In a possible implementation manner, the selecting, from the candidate videos, a candidate video with a similarity between a video cover and a video cover of the first video greater than a preset threshold value includes:

It can be seen that, in the embodiment of the present disclosure, an image retrieval technology based on a perceptual hash algorithm may be used to select a video cover with a similarity greater than a preset value. It is to be understood that the method for selecting the video cover with the similarity larger than the preset value is not limited thereto.

In one possible implementation manner, the selecting, by using a similar image retrieval technique based on a perceptual hash algorithm, a candidate video having a similarity between a video cover and a video cover of the first video greater than a preset threshold value from the candidate videos includes:

The perceptual hash algorithm is to generate a fingerprint character string for each picture by using the hash algorithm, and then compare fingerprints of different pictures, wherein the smaller the Hamming distance between the fingerprints is, the more similar the pictures are represented. For example, a hamming distance of 0, then the two pictures are very similar; for example, hamming distances less than 5, indicate somewhat different, but relatively similar; for example, hamming distances greater than 10, then a completely different picture is indicated.

In addition, the process of calculating the hash value of one video cover may be as follows:

firstly, reducing the size of a video cover; the fastest method for removing high frequency and detail is to shrink the picture to 8x8 size and 64 pixels in total, wherein the picture difference caused by different sizes and proportions can be abandoned by changing the picture into 8x8 square instead of maintaining the aspect ratio.

Secondly, simplifying the color, namely converting 8x8 pictures into gray images;

Again, the average value, i.e. the gray average value of all 64 pixels, is calculated;

again, the gray scale of the pixels is compared, namely, the gray scale of each pixel is compared with the average value and is larger than or equal to the average value and recorded as 1; less than the average, recorded as 0.

Finally, calculating a hash value, namely combining the comparison results of the previous step to form a 64-bit integer, namely the hash value of the video cover.

In a possible implementation manner, the content information further includes an episode number of the episode to which the video belongs, and the method further includes:

acquiring the episode serial number of the second video;

and storing the second video and the first video in a target container according to the episode serial number of the second video and the identified arrangement sequence of the episode serial numbers of the first video.

That is, in embodiments of the present disclosure, videos associated on video content are stored in one target container and ordered by episode number of the videos.

If the second video related to the first video on the video content is not found in the candidate videos, a target container is newly built, so that the first video is stored in the newly built target container, and is matched with the first video on the video content after other videos are received later.

In a possible implementation manner, the content information further includes an episode type of an episode to which the video belongs, and the method further includes:

and storing the target container in a classified manner according to the episode type of the video stored in the target container.

Wherein the videos stored in the same target container are associated with each other in video content, and thus the episode types of the videos stored in the same target container are the same or similar. And further, according to the episode types of the videos stored in the target container, the target container is stored in a classified mode, so that the videos with the same or similar episode types can be further stored together, and further, the classified management of the videos is facilitated.

In a possible implementation manner, the video information of the second video further includes an episode number of the second video;

The target video covers are displayed according to the sequence of the episode serial numbers, so that a user can more clearly know the episode sequence of the second videos to which the target video covers belong, and the user can conveniently select which second video to watch.

In addition, the episode number of the second video to which the target video cover belongs can be displayed on the target video cover, so that a user can more clearly know the episode number of the second video to which the target video cover belongs, and the user can further conveniently select the second video to be watched.

Specifically, for example, the target video cover includes a first cover 401, a second cover 402, and a third cover 403, where the sequence of the episode numbers is the first cover 401, the second cover 402, and the third cover 403, and the three video covers may be displayed according to the sequence of the episode numbers and according to the top-to-bottom position distribution, as shown in fig. 4, for example.

In one possible embodiment, the method further comprises:

The second play triggering operation may be a click operation on a video cover of the second video.

As can be seen from the foregoing, in the embodiments of the present disclosure, a user may select one video cover from the target video covers displayed on the client device, so that the client device may be triggered to play the second video to which the selected video cover belongs, that is, the user may select, according to his own needs, which second video associated with the first video on the video content needs to be watched, thereby further improving the interactive experience of the user.

In one possible implementation, the video information of the second video includes an episode number of the second video; the method further comprises the steps of:

displaying a preset icon;

receiving a first preset operation on the preset icon;

The preset icon may be displayed when the playing state of the first video meets a preset condition. In addition, the method comprises the following steps. The first preset operation may be a click operation on a preset icon.

As can be seen from the foregoing, in the embodiment of the present disclosure, the client device may further obtain the episode number of the first video, and the episode number of the second video associated with the first video on the video content, so that after the user performs the first preset operation on the preset icon displayed on the client device, the client device may automatically play the second video to which the next sequence number of the episode number of the first video belongs, thereby avoiding the complexity of the user to select the second video to which the next sequence number of the episode number of the first video belongs, and further improving the interactive operation experience of the user.

and receiving the associated video information sent by the server.

It follows that in embodiments of the present disclosure, associated video information (i.e., video information of at least one second video associated with a first video present on video content) may also be sent by a server to a client device. In this case, the server is required to acquire the associated video information before transmitting it to the client device. The process of obtaining the management video information by the server may be the same as the process of obtaining the associated video information by the client device, which is described in detail above, and will not be repeated here.

It follows that in embodiments of the present disclosure, a server may be issued to a client device along with video information of at least one second video associated with the video content thereof when issuing a first video to the client device.

In particular, the server may, upon pushing the first video to the client device, issue to the client device along with video information of at least one second video associated with it on the video; or the server may further issue video information of the first video and at least one second video associated with the first video on the video content to the client device after receiving a request message indicating that the client device requests the first video.

After receiving the first video pushed by the server and the video information of at least one second video associated with the first video, the client device may play the first video when receiving a first play trigger operation of a user for the first video, so as to send a request message for requesting a video cover of the second video to the server when a play state of the first video meets a preset condition.

For example, after a certain short video APP is started, the server pushes the first video to the client device according to the browsing record of the user, and when the first video is pushed, the server can push the first video to the client device together with the identification information of at least one second video associated with the first video on the video content, so that the client device starts to play the first video after receiving a first play triggering operation of the user for the first video, and when the remaining play duration of the first video reaches a preset duration, the client device sends first request information to the server, namely, the video covers of the second videos to which the identification information belongs are requested to the server according to the identification information of the at least one second video, and after receiving the video covers of the second videos sent by the server, the video covers are displayed, so that the client device can avoid the need to switch the play interface of the first video to other interfaces, and further avoid the trouble that the user looks up the video covers of the at least one second video associated with the first video on the video content, and then searches the video profile of the author to be operated one by one video on the first video content.

In summary, for more and more short video APP producers upload videos related to a lot of episode content, the embodiments of the present disclosure can identify the video content by using a multimedia intelligent identification (Multimedia Understanding, MMU) technology, associate the episodes related to the author, and then send the identification information of the associated episodes to the client device, so that the user can quickly and smoothly locate the next episode of the currently browsed video, improve the viewing experience, and make the carefully-developed content of the producer quickly acquired by the audience, thereby establishing the relationship between the producer and the consumer.

In yet another aspect of the disclosure, a video playing method is also provided, where the video playing method may be applied to a server. As shown in fig. 5, the video playing method may include the steps of:

step 501: and sending the first video and the associated video information to the client equipment so as to play the first video on the client equipment, and displaying a play inlet of the second video on the client equipment according to the associated video information when the play state of the first video meets the preset condition.

Wherein the associated video information includes video information of at least one of the second videos associated with the first video in the presence of video content. The videos associated on the video content belong to the same episode, wherein the episode is typically a video in the form of a series or story. Alternatively, the video information of the second video may include identification information of the second video. The identification information may be a video ID.

As can be seen from the above, in embodiments of the present disclosure, a server may push a first video to a client device along with video information of at least one second video associated with the first video on video content as the first video is pushed to the client device.

In addition, the play entrance of the second video is an entrance entering the play interface of the second video, for example, clicking the play entrance of the second video can play the second video.

In summary, in the video playing method provided by the embodiment of the present disclosure, when the first video is sent to the client device, the first video is sent to the client device together with the video information of at least one second video associated with the first video on the video content, so that when the state of playing the first video by the client device meets the preset condition, the playing entrance of the second video is displayed according to the associated video information, so that the playing entrance of the associated video is provided timely according to the state of viewing the video by the user, so that the user can continuously view the associated video without complicated operation, and the video viewing experience of the user is improved.

In yet another aspect of the disclosure, a video playing method is also provided, where the video playing method may be applied to a server. As shown in fig. 6, the video playing method may include the steps of:

step 601: in the pre-stored videos, videos of which authors are the same as those of the first video are acquired as candidate videos.

When a user views a video in a short video APP, after the user views the video, if other videos related to the video on the video content need to be searched, the video of the same author is often focused, but in the embodiment of the disclosure, the video which belongs to the same author as the first video in the pre-stored videos can be screened out as a candidate video, and then a second video related to the first video on the video content is selected from the candidate videos, that is, in the embodiment of the disclosure, the second video which belongs to the same author as the first video and is related to the video content can be automatically selected, so that the video cover of the second video which belongs to the same author as the first video and is related to the video content can be displayed on the client, thereby being more close to the actual use requirement of the user, and further avoiding the user to screen the video for the author.

Step 602: and when the content information of the first video is identified, selecting at least one second video associated with the first video on video content from the candidate videos according to the content information of the first video, and taking the video information of the selected at least one second video as the associated video information.

In one possible embodiment, the content information includes an episode name, an episode serial number, and an episode type.

In an embodiment of the present disclosure, content information of a first video may be automatically identified, so that at least one second video associated with the first video on video content may be selected from among pre-stored videos of which authors are the same as authors of the first video, based on the content information of the first video.

Step 603: and sending the first video and the associated video information to the client device so as to play the first video on the client device, and displaying a play inlet of the second video on the client device according to the associated video information when the play state of the first video meets the preset condition.

As can be seen from the above, the associated video information includes video information of at least one of the second videos associated with the first video in the video content. The videos associated on the video content belong to the same episode, wherein the episode is typically a video in the form of a series or story. Alternatively, the video information of the second video may include identification information of the second video. The identification information may be a video ID.

As can be appreciated, in embodiments of the present disclosure, a server may push a first video to a client device along with video information of at least one second video associated with the first video on video content as the first video is pushed to the client device.

In summary, according to the video playing method provided by the embodiment of the disclosure, the content information of the first video may be automatically identified, so that the second video associated with the first video on the video content is screened from the candidate videos same as the author of the first video according to the content information of the first video, and then when the first video is sent to the client device, the second video is sent to the client device together with the video information of at least one second video associated with the first video on the video content, so that when the state of playing the first video by the client device meets the preset condition, the playing inlet of the second video is displayed according to the associated video information, so that the playing inlet of the associated video is timely provided according to the state of viewing the video by the user, the user can continuously view the associated video without complicated operations, and the video viewing experience of the user is improved.

acquiring characteristic information of the first video;

extracting key frames of the first video;

In addition, the color features may be RGB features.

acquiring characteristic information of a plurality of sample videos;

for each of the sample videos, performing the following process:

extracting key frames of the sample video;

firstly, collecting a plurality of video samples;

fourth step: identifying which objects in the keyframe are moving objects;

fifth step: extracting audio features from the audio information;

In one possible embodiment, the method further comprises:

Secondly, simplifying the color, namely converting 8 x 8 pictures into gray images;

acquiring the episode serial number of the second video;

and storing the target container in a classified manner according to the episode type of the episode to which the video belongs.

In still another aspect of the present disclosure, there is also provided a video playing apparatus, as shown in fig. 7, the video playing apparatus 700 includes:

an associated information obtaining module 701 configured to obtain, in response to a first play trigger operation, a first video to be played and associated video information including video information of at least one second video associated with the first video on video content;

A first playing module 702 configured to play the first video;

the entry presentation module 703 is configured to present the play entry of the second video according to the associated video information when detecting that the play status of the first video meets a preset condition.

In one possible implementation manner, the association information obtaining module 701 includes:

a first filtering submodule 7011 configured to acquire, from among pre-stored videos, videos of which authors are the same as that of the first video, as candidate videos;

the second filtering sub-module 7012 is configured to select at least one second video associated with the first video on video content from the candidate videos according to the content information of the first video, and take the video information of the selected at least one second video as the associated video information, when the content information of the first video is identified.

In a possible implementation, the apparatus further includes a content identification module 704 configured to identify content information of the first video;

wherein the content identification module 704 includes:

a first feature information acquisition sub-module 7041 configured to acquire feature information of the first video;

The content information output sub-module 7042 is configured to input the feature information of the first video into a content identification model which is established in advance and is used for identifying video content, and output the content information of the first video.

In one possible implementation, the first feature information obtaining sub-module 7041 is specifically configured to:

extracting key frames of the first video;

In one possible implementation manner, the first feature information obtaining sub-module 7041 is specifically configured to, when obtaining the color feature of the first video:

In a possible implementation manner, the apparatus further includes a model building module 705 configured to build the content recognition model;

wherein the model building module 705 comprises:

a second feature information acquisition sub-module 7051 configured to acquire feature information of a plurality of sample videos;

the model training submodule 7052 is configured to take feature information of one sample video and content information of the predetermined sample video as a training sample, and train the training sample by adopting a recurrent neural network to obtain the content recognition model.

In one possible implementation, the second feature information acquisition sub-module 7051 is specifically configured to:

For each of the sample videos, performing the following process:

extracting key frames of the sample video;

In one possible implementation, the second feature information obtaining sub-module 7051 is specifically configured to, when obtaining the color feature of the sample video:

In one possible implementation, the content information includes: the episode name of the episode to which the video belongs; the second screening sub-module 7012 is specifically configured to:

In a possible implementation manner, the association information obtaining module 701 further includes:

the third filtering sub-module 7013 is configured to select, from the candidate videos, a candidate video with a similarity between a video cover and a video cover of the first video greater than a preset threshold, and take video information of the selected candidate video as the associated video information, where the content information of the first video is not identified.

In one possible implementation, the third screening sub-module 7013 is specifically configured to:

In one possible implementation manner, the third screening sub-module 7013 is specifically configured to, when using a similar image retrieval technique based on a perceptual hash algorithm to select, from the candidate videos, a candidate video with a similarity between a video cover and a video cover of the first video greater than a preset threshold:

In a possible implementation manner, the video information of the second video includes identification information of the second video; the inlet presentation module 703 is specifically configured to:

And displaying the target video cover as a playing inlet of the second video.

In a possible implementation manner, the video information of the second video further includes an episode number of the second video; the entry presentation module 703, when presenting the target video cover as the play entry of the second video, is specifically configured to:

In one possible embodiment, the apparatus further comprises:

a first receiving module 706 configured to receive a second play triggering operation on one of the video covers of the second video that is presented;

and the second playing module 707 is configured to respond to the second playing triggering operation and play the second video to which the video cover targeted by the second playing triggering operation belongs.

In one possible implementation, the video information of the second video includes an episode number of the second video; the apparatus further comprises:

An icon display module 708 configured to display a preset icon;

a second receiving module 709 configured to receive a first preset operation on the preset icon;

and the third playing module 710 is configured to obtain the episode number of the first video in response to the first preset operation, and play a second video to which a next sequence number of the episode number of the first video belongs.

In a possible implementation manner, the association information obtaining module 701 is specifically configured to:

and receiving the associated video information sent by the server.

As can be seen from the foregoing, the video playing device provided in the embodiments of the present disclosure is capable of responding to a first playing trigger operation, obtaining a first video to be played and associated video information, thereby playing the first video, and displaying a playing entry of a second video according to the associated video information when detecting that a playing state of the first video meets a preset condition, where the associated video information includes video information of at least one second video managed on video content with the first video.

Therefore, when receiving the play triggering operation for the first video, the video playing device provided by the embodiment of the disclosure obtains the video information of the first video and at least one second video associated with the first video on the video content, and when the play state of the first video meets the preset condition, the play inlet of the second video can be displayed according to the video information of the second videos, so that the play inlet of the associated video can be provided timely according to the state of the user watching the video, the user can continuously watch the associated video without tedious operation, and the video watching experience of the user is improved.

In still another aspect of the present disclosure, there is also provided a video playing apparatus, as shown in fig. 8, the video playing apparatus 800 includes:

an information sending module 801, configured to send a first video and associated video information to a client device, so as to play the first video on the client device, and when a play state of the first video meets a preset condition, display a play entry of a second video on the client device according to the associated video information;

In a possible implementation manner, the apparatus further includes an information acquisition module 802 configured to acquire the associated video information;

wherein, the information obtaining module 802 includes:

a first filtering submodule 8021 configured to acquire, from among pre-stored videos, videos of which authors are the same as that of the first video, as candidate videos;

a second filtering sub-module 8022, configured to select at least one second video associated with the first video on video content from the candidate videos according to the content information of the first video, and take the video information of the selected at least one second video as the associated video information, when the content information of the first video is identified.

In a possible implementation, the apparatus further includes a content identification module 803 configured to identify content information of the first video;

wherein the content identification module 803 includes:

a first feature information acquisition sub-module 8031 configured to acquire feature information of the first video;

the content information output sub-module 8032 is configured to input the feature information of the first video into a content identification model which is established in advance and is used for identifying video content, and output the content information of the first video.

In a possible implementation manner, the first feature information obtaining sub-module 8031 is specifically configured to:

extracting key frames of the first video;

In a possible implementation manner, the first feature information obtaining sub-module 8031 is specifically configured to, when obtaining the color feature of the first video:

In a possible implementation manner, the apparatus further includes a model building module 804 configured to build the content identification model;

wherein the model building module 804 includes:

a second feature information acquisition sub-module 8041 configured to acquire feature information of a plurality of sample videos;

the model training submodule 8042 is configured to take the characteristic information of one sample video and the predetermined content information of the sample video as a training sample, and train the training sample by adopting a recurrent neural network to obtain the content identification model.

In one possible implementation, the second feature information acquiring sub-module 8041 is specifically configured to:

for each of the sample videos, performing the following process:

extracting key frames of the sample video;

In a possible implementation manner, the second feature information obtaining sub-module 8041 is specifically configured to, when obtaining the color feature of the sample video:

In one possible implementation, the content information includes: the episode name of the episode to which the video belongs; the second screening sub-module 8022 is specifically configured to:

In one possible implementation, the information obtaining module 802 further includes:

the third screening sub-module 8023 is configured to select, from the candidate videos, a candidate video with a similarity between a video cover and a video cover of the first video being greater than a preset threshold, and take video information of the selected candidate video as the associated video information, where the content information of the first video is not identified.

In one possible implementation, the third screening submodule 8023 is specifically configured to:

In one possible implementation manner, when the third filtering sub-module 8023 selects, from the candidate videos, a candidate video whose similarity between the video cover and the video cover of the first video is greater than a preset threshold by adopting a similar image retrieval technology based on a perceptual hash algorithm, the third filtering sub-module is specifically configured to:

In a possible implementation manner, the content information further includes an episode number of the episode to which the video belongs, and the apparatus further includes:

a sequence number acquisition module 805 configured to acquire an episode sequence number of the second video;

The storage module 806 is configured to store the second video and the first video in a target container according to the episode number of the second video and the identified arrangement order of the episode numbers of the first video.

In a possible implementation manner, the content information further includes an episode type of an episode to which the video belongs, and the apparatus further includes:

and a classification module 807 configured to store the target container in a classification manner according to the episode type of the episode to which the video stored in the target container belongs.

As can be seen from the foregoing, in the video playing device provided by the embodiment of the present disclosure, when a play trigger operation for a first video is received, video information of the first video and at least one second video associated with the first video on video content is obtained, and when a play state of the first video meets a preset condition, a play entry of the second video can be displayed according to the video information of the second videos, so that the play entry of the associated video is provided timely according to a state of a user watching the video, and thus, the user can continuously watch the associated video without tedious operations, and video watching experience of the user is improved.

In yet another aspect of the disclosure, an electronic device is also provided. Referring to fig. 9, the electronic apparatus includes:

a processor 910;

a memory 920 for storing instructions executable by the processor 910;

wherein the processor 910 is configured to execute the instructions to implement the video playing method applied to the electronic device.

In yet another aspect of the disclosure, an electronic device is also provided. As shown in fig. 10, the electronic device 1000 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, or the like.

Referring to fig. 10, an electronic device 1000 may include one or more of the following components: a processing component 1002, a memory 1004, a power component 1006, a multimedia component 1008, an audio component 1010, an input/output (I/O) interface 1012, a sensor component 1014, and a communication component 1016.

The processing component 1002 generally controls overall operation of the electronic device 1000, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 1002 can include one or more processors 1020 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 1002 can include one or more modules that facilitate interaction between the processing component 1002 and other components. For example, the processing component 1002 can include a multimedia module to facilitate interaction between the multimedia component 1008 and the processing component 1002.

The memory 1004 is configured to store various types of data to support operations at the electronic device 1000. Examples of such data include instructions for any application or method operating on the electronic device 1000, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 1004 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply component 1006 provides power to the various components of the electronic device 1000. The power components 1006 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 1000.

The multimedia component 1008 includes a screen between the electronic device 1000 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia assembly 1008 includes a front-facing camera and/or a rear-facing camera. When the electronic device 1000 is in an operational mode, such as a shooting mode or a video mode, the front-facing camera and/or the rear-facing camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 1010 is configured to output and/or input audio signals. For example, the audio component 1010 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 1000 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in memory 1004 or transmitted via communication component 1016. In some embodiments, the audio component 1010 further comprises a speaker for outputting audio signals.

The I/O interface 1012 provides an interface between the processing assembly 1002 and peripheral interface modules, which may be a keyboard, click wheel, buttons, and the like. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 1014 includes one or more sensors for providing status assessment of various aspects of the electronic device 1000. For example, the sensor assembly 1014 may detect an on/off state of the electronic device 1000, a relative positioning of components such as a display and keypad of the electronic device 1000, the sensor assembly 1014 may also detect a change in position of the electronic device 1000 or a component of the electronic device 1000, the presence or absence of a user's contact with the electronic device 1000, an orientation or acceleration/deceleration of the electronic device 1000, and a change in temperature of the electronic device 1000. The sensor assembly 1014 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. The sensor assembly 1014 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1014 can also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 1016 is configured to facilitate communication between the electronic device 1000 and other devices, either wired or wireless. The electronic device 1000 may access a wireless network based on a communication standard, such as WiFi, an operator network (e.g., 2G, 3G, 8G, or 5G), or a combination thereof. In one exemplary embodiment, the communication component 1016 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1016 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 1000 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for performing the video playback method described above.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 1004, including instructions executable by processor 1020 of electronic device 1000 to perform the above-described method. Alternatively, for example, the storage medium may be a non-transitory computer-readable storage medium, which may be, for example, ROM, random-access memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.

In yet another aspect of the disclosure, there is also provided a server, as shown in fig. 11, including:

a processor 1110;

a memory 1120 for storing instructions executable by the processor 1110;

wherein the processor 1110 is configured to execute the instructions to implement the video playing method applied to the server.

In still another aspect of the disclosure, a video playing system is provided, including the electronic device and the server.

In the video playing system, the electronic device is used as a client device.

Namely, in the video playing system provided by the embodiment of the disclosure, a first video and associated video information are sent to the electronic equipment through the server, wherein the associated video information comprises video information of at least one second video which is associated with the first video on video content;

playing the first video through the electronic equipment;

when the electronic equipment detects that the playing state of the first video accords with a preset condition, displaying a playing inlet of the second video according to the associated video information through the electronic equipment.

Therefore, in the video playing system provided by the embodiment of the disclosure, when the first video and the video information (i.e., the associated video information) of at least one second video associated with the first video on the video content are sent to the electronic device together through the server, so that when the state of playing the first video meets the preset condition, the electronic device displays the playing entrance of the second video according to the associated video information, and the playing entrance of the associated video is provided timely according to the state of watching the video by the user, so that the user can continuously watch the associated video without complicated operation, and the video watching experience of the user is improved.

In yet another aspect of the disclosure implementation, there is also provided a storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform the video playing method described above.

In yet another aspect of the disclosed embodiments, there is also provided a computer program product containing instructions that, when run on a computer, cause the computer to implement the video playback method described above.

The video playback schemes provided herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a system constructed with aspects of the present invention will be apparent from the description above. In addition, the present invention is not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.

Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functions of some or all of the components in an information extraction scheme according to embodiments of the present disclosure may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present invention can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names.

Claims

1. A video playing method is characterized in that:

responding to a first playing triggering operation, and acquiring a first video to be played and associated video information, wherein the associated video information comprises video information of at least one second video associated with the first video on video content; the process of acquiring the associated video information comprises the following steps: selecting at least one second video associated with the first video on video content from the pre-stored videos of which the authors are the same as the authors of the first video according to the content information of the first video; the content information of the first video is obtained by identification according to the extracted characteristic information of multiple dimensions of the first video; the feature information of the plurality of dimensions comprises a color feature of each key frame of the first video, a color feature of the first video, feature information of a moving object in each key frame of the first video, and audio feature information of the first video;

Playing the first video;

2. The video playing method according to claim 1, wherein the process of acquiring the associated video information includes:

3. The video playback method as recited in claim 2, wherein the process of identifying content information of the first video comprises:

acquiring characteristic information of the first video;

And receiving the associated video information sent by the server.

4. The method for playing video according to claim 3, wherein the obtaining the feature information of the first video includes:

extracting key frames of the first video;

5. The method of video playback as set forth in claim 4, wherein said obtaining the color characteristics of the first video includes:

6. The video playing method according to claim 3, wherein the process of creating the content recognition model includes:

acquiring characteristic information of a plurality of sample videos;

7. The method for playing video according to claim 6, wherein the obtaining feature information of the plurality of sample videos includes:

for each of the sample videos, performing the following process:

extracting key frames of the sample video;

8. The video playing method according to claim 7, wherein the acquiring the color feature of the sample video includes:

9. The video playback method as recited in claim 2, wherein the content information includes: the episode name of the episode to which the video belongs;

10. The video playing method according to claim 2, wherein the process of acquiring the associated video information further comprises:

11. The method for playing video according to claim 10, wherein selecting a candidate video having a similarity between a video cover and a video cover of the first video greater than a preset threshold value from the candidate videos comprises:

12. The video playing method according to claim 11, wherein selecting a candidate video with a similarity between a video cover and a video cover of the first video greater than a preset threshold from the candidate videos by using a similar image retrieval technique based on a perceptual hash algorithm, comprises:

13. The video playback method as recited in claim 1, wherein the video information of the second video includes identification information of the second video;

And displaying the target video cover as a playing inlet of the second video.

14. The video playing method according to claim 13, wherein the video information of the second video further includes an episode number of the second video;

15. The video playback method as recited in claim 13, wherein the method further comprises:

16. The video playing method according to claim 1, wherein the video information of the second video includes an episode number of the second video; the method further comprises the steps of:

Displaying a preset icon;

receiving a first preset operation on the preset icon;

17. The video playing method according to claim 1, wherein the process of acquiring the associated video information includes:

and receiving the associated video information sent by the server.

18. A video playing method, the method comprising:

sending a first video and associated video information to a client device, so as to play the first video on the client device, and displaying a play inlet of a second video on the client device according to the associated video information when the play state of the first video meets a preset condition; the process for acquiring the associated video information comprises the following steps: selecting at least one second video associated with the first video on video content from the pre-stored videos of which the authors are the same as the authors of the first video according to the content information of the first video; the content information of the first video is obtained by identification according to the extracted characteristic information of multiple dimensions of the first video; the feature information of the plurality of dimensions comprises a color feature of each key frame of the first video, a color feature of the first video, feature information of a moving object in each key frame of the first video, and audio feature information of the first video;

19. The video playback method of claim 18, wherein the process of obtaining the associated video information comprises:

20. The video playback method as recited in claim 19, wherein the process of identifying content information of the first video comprises:

acquiring characteristic information of the first video;

21. The method for playing video according to claim 20, wherein the obtaining the feature information of the first video includes:

Extracting key frames of the first video;

22. The method of video playback as recited in claim 21, wherein said obtaining color characteristics of the first video comprises:

23. The video playing method according to claim 20, wherein the process of creating the content recognition model includes:

acquiring characteristic information of a plurality of sample videos;

24. The method for playing video according to claim 23, wherein the obtaining feature information of the plurality of sample videos includes:

for each of the sample videos, performing the following process:

extracting key frames of the sample video;

25. The video playback method of claim 24, wherein the obtaining the color characteristics of the sample video comprises:

26. The video playback method of claim 19, wherein the content information comprises: the episode name of the episode to which the video belongs;

27. The video playback method of claim 19, wherein the process of obtaining the associated video information further comprises:

28. The method for playing video according to claim 27, wherein selecting a candidate video having a similarity between a video cover and a video cover of the first video greater than a preset threshold value from the candidate videos comprises:

29. The method for playing video according to claim 28, wherein selecting a candidate video having a similarity between a video cover and a video cover of the first video greater than a preset threshold from the candidate videos by using a similar image retrieval technique based on a perceptual hash algorithm, comprises:

30. The video playing method according to claim 19 or 27, wherein the content information further includes an episode number of the episode to which the video belongs, the method further comprising:

acquiring the episode serial number of the second video;

31. The video playback method of claim 30, wherein the content information further comprises an episode type of an episode to which the video belongs, the method further comprising:

32. A video playback device, the device comprising:

the associated information acquisition module is configured to respond to a first playing triggering operation and acquire first video to be played and associated video information, wherein the associated video information comprises video information of at least one second video associated with the first video on video content; the process of acquiring the associated video information comprises the following steps: selecting at least one second video associated with the first video on video content from the pre-stored videos of which the authors are the same as the authors of the first video according to the content information of the first video; the content information of the first video is obtained by identification according to the extracted characteristic information of multiple dimensions of the first video; the feature information of the plurality of dimensions comprises a color feature of each key frame of the first video, a color feature of the first video, feature information of a moving object in each key frame of the first video, and audio feature information of the first video;

a first play module configured to play the first video;

33. The video playback device of claim 32, wherein the association information acquisition module comprises:

a first screening sub-module configured to acquire, from pre-stored videos, videos of which authors are the same as that of the first video as candidate videos;

and the second screening sub-module is configured to select at least one second video associated with the first video on video content from the candidate videos according to the content information of the first video and take the video information of the selected at least one second video as the associated video information when the content information of the first video is identified.

34. The video playback device of claim 33, wherein the device further comprises:

a content identification module configured to identify content information of the first video;

wherein the content identification module comprises:

the first characteristic information acquisition sub-module is configured to acquire characteristic information of the first video;

and the content information output sub-module is configured to input the characteristic information of the first video into a pre-established content identification model for identifying video content and output the content information of the first video.

35. The video playback device of claim 34, wherein the first feature information acquisition sub-module is specifically configured to:

extracting key frames of the first video;

36. The video playback device of claim 35, wherein the first feature information acquisition sub-module, when acquiring the color feature of the first video, is specifically configured to:

37. The video playback device of claim 34, wherein the device further comprises a model building module configured to build the content recognition model;

wherein, the model establishment module includes:

a second feature information obtaining sub-module configured to obtain feature information of a plurality of sample videos;

the model training sub-module is configured to take the characteristic information of one sample video and the predetermined content information of the sample video as a training sample, and train the training sample by adopting a recurrent neural network to obtain the content recognition model.

38. The video playback device of claim 37, wherein the second feature information acquisition submodule is specifically configured to:

for each of the sample videos, performing the following process:

extracting key frames of the sample video;

39. The video playback device of claim 38, wherein the second feature information acquisition sub-module, when acquiring the color features of the sample video, is specifically configured to:

40. The video playback device of claim 33, wherein the content information comprises: the episode name of the episode to which the video belongs; the second screening sub-module is specifically configured to:

41. The video playback device of claim 33, wherein the association information acquisition module further comprises:

and the third screening sub-module is configured to select candidate videos with the similarity between the video cover and the video cover of the first video being greater than a preset threshold value from the candidate videos under the condition that the content information of the first video is not identified, and take the video information of the selected candidate videos as the associated video information.

42. The video playback device of claim 41, wherein the third screening submodule is specifically configured to:

43. The video playback device of claim 42, wherein the third filtering sub-module, when selecting a candidate video with a similarity between the video cover and the video cover of the first video greater than a predetermined threshold from the candidate videos using a similar image retrieval technique based on a perceptual hash algorithm, is specifically configured to:

44. The video playback device of claim 32, wherein the video information of the second video includes identification information of the second video; the inlet presentation module is specifically configured to:

and displaying the target video cover as a playing inlet of the second video.

45. The video playback device of claim 44, wherein the video information for the second video further comprises an episode number for the second video; the entry presentation module, when presenting the target video cover as a play entry for the second video, is specifically configured to:

46. The video playback device of claim 44, wherein the device further comprises:

the first receiving module is configured to receive a second playing triggering operation of one of the video covers of the second video;

And the second playing module is configured to respond to the second playing triggering operation and play a second video to which the video cover aimed by the second playing triggering operation belongs.

47. The video playback device of claim 32, wherein the video information of the second video comprises an episode number of the second video; the apparatus further comprises:

an icon display module configured to display a preset icon;

the second receiving module is configured to receive a first preset operation on the preset icon;

and the third playing module is configured to respond to the first preset operation, acquire the episode number of the first video and play a second video of the next sequence number of the episode number of the first video.

48. The video playback device of claim 32, wherein the association information acquisition module is specifically configured to:

and receiving the associated video information sent by the server.

49. A video playback device, the device comprising:

the information sending module is configured to send a first video and associated video information to the client device so as to play the first video on the client device, and when the playing state of the first video meets a preset condition, a playing inlet of a second video is displayed on the client device according to the associated video information; the process of acquiring the associated video information comprises the following steps: selecting at least one second video associated with the first video on video content from the pre-stored videos of which the authors are the same as the authors of the first video according to the content information of the first video; the content information of the first video is obtained by identification according to the extracted characteristic information of multiple dimensions of the first video; the feature information of the plurality of dimensions comprises a color feature of each key frame of the first video, a color feature of the first video, feature information of a moving object in each key frame of the first video, and audio feature information of the first video;

50. The video playback device of claim 49, wherein the device further comprises an information acquisition module configured to acquire the associated video information;

wherein, the information acquisition module includes:

51. The video playback device of claim 50, wherein the device further comprises a content identification module configured to identify content information of the first video;

wherein the content identification module comprises:

52. The video playback device of claim 51, wherein the first feature information acquisition sub-module is specifically configured to:

extracting key frames of the first video;

53. The video playback device of claim 52, wherein the first feature information acquisition sub-module, when acquiring color features of the first video, is specifically configured to:

54. The video playback device of claim 51, wherein the device further comprises a model building module configured to build the content recognition model;

wherein, the model establishment module includes:

55. The video playback device of claim 54, wherein the second characteristic information acquisition submodule is specifically configured to:

for each of the sample videos, performing the following process:

extracting key frames of the sample video;

56. The video playback device of claim 55, wherein the second feature information acquisition sub-module, when acquiring color features of the sample video, is specifically configured to:

57. The video playback device of claim 50, wherein the content information comprises: the episode name of the episode to which the video belongs; the second screening sub-module is specifically configured to:

58. The video playback device of claim 50, wherein the information acquisition module further comprises:

59. The video playback device of claim 58, wherein the third screening submodule is specifically configured to:

60. The video playback device of claim 59, wherein the third filtering sub-module, when selecting a candidate video from the candidate videos that has a similarity between a video cover and a video cover of the first video that is greater than a predetermined threshold using a similar image retrieval technique based on a perceptual hash algorithm, is specifically configured to:

61. The video playback device of claim 50 or 58, wherein the content information further comprises an episode number for the video in the episode to which the video belongs, the device further comprising:

the serial number acquisition module is configured to acquire the episode serial number of the second video;

and the storage module is configured to store the second video and the first video in a target container according to the episode number of the second video and the identified arrangement sequence of the episode numbers of the first video.

62. The video playback device of claim 61, wherein the content information further comprises an episode type of an episode to which the video belongs, the device further comprising:

and the classification module is configured to store the target container in a classified manner according to the episode type of the episode to which the video stored in the target container belongs.

63. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the video playback method of any one of claims 1 to 17.

64. A server, comprising:

A processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the video playback method of any one of claims 18 to 31.

65. A video playback system comprising an electronic device as recited in claim 63, and a server as recited in claim 64.

66. A storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the video playback method of any one of claims 1 to 17, or to perform the video playback method of any one of claims 18 to 31.