CN110650364B

CN110650364B - Video attitude tag extraction method and video-based interaction method

Info

Publication number: CN110650364B
Application number: CN201910926814.0A
Authority: CN
Inventors: 黄容; 李梦
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2019-09-27
Filing date: 2019-09-27
Publication date: 2022-04-01
Anticipated expiration: 2039-09-27
Also published as: CN110650364A

Abstract

The disclosure relates to a video attitude tag extraction method, a video attitude tag extraction device, a server, a video-based interaction method, a video-based interaction device and a terminal. The video attitude tag extraction method comprises the following steps: acquiring a target video; extracting target characteristic information of each preset type of a target video; judging whether each target characteristic information meets a preset condition corresponding to the type of the target characteristic information; and when the judgment result accords with the preset rule, determining the preset attitude tag corresponding to the preset rule as the attitude tag of the target video. The video-based interaction method comprises the following steps: acquiring an attitude tag of a target video; displaying the attitude label according to a first display mode in the playing process of the target video; and when the trigger operation aiming at the attitude label is detected, displaying the attitude label according to a second display mode. By applying the technical scheme provided by the disclosure, the problem that the operation of publishing the watching experience of a user is more complicated due to the fact that corresponding text information needs to be manually input in the related technology can be at least solved.

Description

Video attitude tag extraction method and video-based interaction method

Technical Field

The disclosure relates to the technical field of video processing, in particular to a video attitude tag extraction method and a video-based interaction method.

Background

At present, along with the rapid development of various video software, the user can use various video software to watch various videos shot and uploaded by other users in daily entertainment and work, and in the watching process, the user can interact with other users watching the videos by publishing the watching experience of the user on the watched videos.

In the related art, a method for a user to release the viewing experience of the user on a viewed video includes: in a comment input area in a video display interface, comment content of a watched video is manually input, and the comment content is text information expressing the watching experience of a user on the watched video.

Obviously, in the above related art, when publishing the viewing experience of the user for the viewed video, the user needs to manually input the corresponding text information, so that the operation of publishing the viewing experience by the user is complicated.

Disclosure of Invention

The disclosure provides a video attitude tag extraction method, a video attitude tag extraction device and a server, as well as a video-based interaction method, a video-based interaction device and a video-based interaction terminal, so as to at least solve the problem that in the related art, when a user releases the watching experience of the user on a watched video, the operation of releasing the watching experience of the user is complicated due to the fact that corresponding text information needs to be manually input. The technical scheme of the disclosure is as follows:

according to a first aspect of the embodiments of the present disclosure, there is provided a method for extracting a video attitude tag, which is applied to a server, the method including:

acquiring a target video of an attitude label to be extracted;

extracting target characteristic information of each preset type of the target video;

judging whether each target characteristic information meets a preset condition corresponding to the type of the target characteristic information;

when the judgment result of each target feature information accords with a preset rule, determining a preset attitude tag corresponding to the preset rule as the attitude tag of the target video;

wherein, the preset rule is as follows: and the number and the type of the target characteristic information meeting the corresponding preset conditions in the judgment result are regulated.

Optionally, in a specific implementation manner, when the determination result of each target feature information conforms to a preset rule, determining that the attitude tag of the target video is a preset attitude tag corresponding to the preset rule includes:

and when the judgment result of each target characteristic information meets the preset condition corresponding to the type of the target characteristic information, determining the attitude label of the target video as a preset attitude label corresponding to the preset rule.

Optionally, in a specific implementation manner, the number of the preset attitude tags is multiple; the determining, as the attitude tag of the target video, the preset attitude tag corresponding to the preset rule further includes:

according to the preset priority of each preset attitude tag, sequencing each preset attitude tag from high priority to low priority;

and determining the preset attitude tag arranged in the first number of bits as the attitude tag of the target video.

Optionally, in a specific implementation manner, the method further includes:

acquiring interactive data of the target video, and determining an initial approval value of each attitude tag of the target video based on the interactive data; wherein the interactive data may include at least one of play data, like data and comment data;

and correspondingly storing each attitude label of the target video and the initial approval value of the attitude label.

Optionally, in a specific implementation manner, the step of obtaining the target video with the attitude tag to be extracted includes:

acquiring a candidate video, and extracting target index information of the candidate video on a preset dimension;

judging whether the target index information meets a preset screening rule or not;

and if the target index information meets a preset screening rule, determining the candidate video as the target video of the attitude tag to be extracted.

Optionally, in a specific implementation manner, the method further includes:

extracting a second number of videos to be processed from the target video;

acquiring the matching degree of the video content of each video to be processed and the attitude label;

updating the preset conditions and/or the screening rules based on the matching degree of each video to be processed;

and for each video to be processed, if the matching degree of the video to be processed is smaller than a preset matching threshold value, updating the attitude tag of the video to be processed to obtain the updated attitude tag of the video to be processed.

Optionally, in a specific implementation manner, the method further includes:

acquiring a diffusion video corresponding to each to-be-processed video, taking the diffusion video as a target video of the attitude label to be extracted, and returning to the step of extracting target feature information of each preset type of the target video;

wherein the diffusion video comprises: in the target video, the similarity between the video content and the video content of the video to be processed is greater than the preset similarity in the video of which the matching degree between the video content and the attitude tag is less than the preset matching threshold and the video which is not determined as the target video in the candidate video.

According to a second aspect of the embodiments of the present disclosure, there is provided a video-based interaction method applied to a terminal, the method including:

acquiring an attitude tag of a target video; wherein the attitude tag is extracted by any video attitude tag extraction method provided by the first aspect;

displaying the attitude label according to a first display mode in the playing process of the target video;

and when the trigger operation aiming at the attitude label is detected, displaying the attitude label according to a second display mode.

Optionally, in a specific implementation manner, the step of displaying the attitude tag according to the first display manner includes:

displaying the attitude label and the current approval numerical value of the attitude label according to a first display mode; wherein the current approval value is: a sum of the initial approval value of the attitude tag and the detected number of times of the triggering operation for the attitude tag;

the step of displaying the attitude label according to a second display mode includes:

updating the current approval value;

and displaying the attitude label and the updated current approval numerical value according to a second display mode.

According to a third aspect of the embodiments of the present disclosure, there is provided an apparatus for extracting a video attitude tag, which is applied to a server, the apparatus including:

the video acquisition module is configured to acquire a target video of the attitude tag to be extracted;

the information extraction module is configured to extract target feature information of each preset type of the target video;

the condition judgment module is configured to judge whether each target characteristic information meets a preset condition corresponding to the type of the target characteristic information;

the tag determination module is configured to determine a preset attitude tag corresponding to a preset rule as an attitude tag of the target video when a judgment result of each target feature information conforms to the preset rule;

Optionally, in a specific implementation manner, the tag determining module is specifically configured to:

Optionally, in a specific implementation manner, the number of the preset attitude tags is multiple; the tag determination module includes:

the tag sorting submodule is configured to sort each preset attitude tag according to the preset priority of each preset attitude tag and the sequence of the priority from high to low;

the label determination submodule is configured to determine a preset attitude label with a first number of bits arranged in the front as an attitude label of the target video.

Optionally, in a specific implementation manner, the apparatus further includes:

the setting determination module is configured to acquire interactive data of the target video and determine an initial approval value of each attitude tag of the target video based on the interactive data; wherein the interactive data may include at least one of play data, like data and comment data;

and the value storage module is configured to correspondingly store each attitude tag of the target video and the initial approval value of the attitude tag.

Optionally, in a specific implementation manner, the video obtaining module includes:

the video acquisition sub-module is configured to acquire a candidate video and extract target index information of the candidate video on a preset dimension;

the rule judgment submodule is configured to judge whether the target index information meets a preset screening rule;

and the video determining submodule is configured to determine the candidate video as the target video of which the attitude tag is to be extracted if the target index information meets a preset screening rule.

a video extraction module configured to extract a second number of videos to be processed from the target video;

the matching degree acquisition module is configured to acquire the matching degree of the video content of each video to be processed and the attitude label;

the condition updating module is configured to update the preset conditions and/or the screening rules based on the matching degree of each video to be processed;

and the tag updating module is configured to update the attitude tag of the video to be processed to obtain the updated attitude tag of the video to be processed if the matching degree of the video to be processed is smaller than a preset matching threshold value for each video to be processed.

the diffused video acquisition module is configured to acquire a diffused video corresponding to each to-be-processed video, serve as a target video of the attitude tag to be extracted, and trigger the information extraction module;

According to a fourth aspect of the embodiments of the present disclosure, there is provided a video-based interaction apparatus, applied to a terminal, the apparatus including:

the tag acquisition module is configured to acquire an attitude tag of the target video; wherein the attitude tag is extracted by any video attitude tag extraction method provided by the first aspect;

the first display module is configured to display the attitude tag according to a first display mode in the playing process of the target video;

the second display module is configured to display the attitude tag according to a second display mode when the trigger operation for the attitude tag is detected.

Optionally, in a specific implementation manner, the first display module is specifically configured to:

the second display module is specifically configured to:

updating the current approval value; and displaying the attitude label and the updated current approval numerical value according to a second display mode.

According to a fifth aspect of embodiments of the present disclosure, there is provided a server including:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the steps of any one of the video attitude tag extraction methods provided in the first aspect.

According to a sixth aspect of embodiments of the present disclosure, there is provided a storage medium, where instructions executed by a processor of a server enable the server to perform the steps of any one of the video attitude tag extraction methods provided in the first aspect.

According to a seventh aspect of embodiments of the present disclosure, there is provided a computer program product, which when run on a computer, causes the computer to execute the steps of any one of the video attitude tag extraction methods provided in the first aspect.

According to an eighth aspect of embodiments of the present disclosure, there is provided a terminal, including:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the steps of any of the video-based interaction methods provided by the second aspect above.

According to a ninth aspect of embodiments of the present disclosure, there is provided a storage medium, wherein instructions, when executed by a processor of a server, enable the server to perform the steps of any of the video-based interaction methods provided by the second aspect.

According to a tenth aspect of embodiments of the present disclosure, there is provided a computer program product which, when run on a computer, causes the computer to perform the steps of any of the video-based interaction methods provided by the second aspect described above.

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

by applying the technical scheme provided by the embodiment of the disclosure, the server acquires the target video of the attitude tag to be extracted and extracts the target characteristic information of each preset type of the target video; further, the server can judge whether each target characteristic information meets a preset condition corresponding to the type of the target characteristic information; and when the judgment result of each target characteristic information accords with a preset rule, determining a preset attitude tag corresponding to the preset rule as the attitude tag of the target video. Therefore, when the terminal plays the target video, the attitude label of the target video can be obtained; obviously, the attitude tag of the target video is extracted by the server through the extraction method of the attitude tag of the video; and then, in the playing process of the target video, the terminal displays the attitude label according to a first display mode, and when the triggering operation aiming at the attitude label is detected, the attitude label is displayed according to a second display mode.

That is to say, in the technical solution provided in the embodiment of the present disclosure, the server determines attitude tags of respective target videos in advance, and the content of each attitude tag of a target video is the viewing experience of the video content. Like this, when the user was watching the target video, terminal alright in order to directly show the attitude label of target video to, when the user wants to publish self to the watching of target video and feel, alright in order to directly select the attitude label that accords with the own watching impression from the attitude label that the terminal shows, and trigger operation to the attitude label of selecting, and then, the terminal alright in order to acquire the user and to the watching impression of target video.

Based on this, according to the technical scheme provided by the embodiment of the disclosure, when publishing the viewing experience of the user on the viewed target video, the user can directly select the attitude tag which meets the viewing experience of the user from the attitude tags displayed by the terminal, and perform trigger operation on the selected attitude tag, so that the terminal obtains the viewing experience of the user on the target video without manually inputting corresponding text information. Thus, the manual input of corresponding text information can be simplified.

Furthermore, the situation that input errors occur when corresponding text information is manually input due to the fact that the screen of the terminal is small can be avoided, and a novel video-based interaction method is provided, so that user experience can be improved, and interaction interestingness is increased.

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

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

Fig. 1 is a flow chart illustrating a method for extracting video attitude tags according to an exemplary embodiment.

Fig. 2 is a flow diagram illustrating another method for extracting video attitude tags, according to an example embodiment.

Fig. 3 is a flowchart illustrating a further method for extracting video attitude tags, according to an example embodiment.

Fig. 4 is a flow chart illustrating a video-based interaction method according to an exemplary embodiment.

Fig. 5 is a block diagram illustrating an apparatus for extracting video attitude tags, according to an example embodiment.

FIG. 6 is a block diagram illustrating a video-based interaction device, according to an example embodiment.

FIG. 7 is a block diagram illustrating a server in accordance with an example embodiment.

Fig. 8 is a block diagram illustrating a terminal according to an example embodiment.

Fig. 9(a) is a diagram illustrating a terminal displaying an attitude tag according to a first mode in a specific example;

fig. 9(b) is a diagram illustrating a terminal displaying an attitude tag according to a second mode in a specific example.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in 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 above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

In the related art, a method for a user to publish his own viewing experience of a viewed video is as follows: in a comment input area in a video display interface, comment content of a watched video is manually input, and the comment content is text information expressing the watching experience of a user on the watched video. Obviously, in the above related art, when publishing the viewing experience of the user for the viewed video, the user needs to manually input the corresponding text information, so that the operation of publishing the viewing experience by the user is complicated. In order to solve the technical problem, embodiments of the present disclosure provide a method for extracting a video attitude tag and an interaction method based on a video.

First, a method for extracting a video attitude tag according to an embodiment of the present invention is described below.

Fig. 1 is a flowchart illustrating an extraction method of a video attitude tag, where the extraction method is applied to a server, according to an exemplary embodiment, and as shown in fig. 1, the present disclosure provides an extraction method of a video attitude tag, including the following steps.

In step S11, a target video from which an attitude tag is to be extracted is acquired;

in step S12, extracting target feature information of each preset type of the target video;

in step S13, it is determined whether each target feature information satisfies a preset condition corresponding to the type of the target feature information;

in step S14, when the determination result of each target feature information conforms to the preset rule, determining the preset attitude tag corresponding to the preset rule as the attitude tag of the target video;

wherein, the preset rule is as follows: and the number and type of the target characteristic information meeting the corresponding preset conditions in the judgment result.

As can be seen from the above, by applying the technical scheme provided by the embodiment of the present disclosure, the server obtains the target video of the attitude tag to be extracted, and extracts the target feature information of each preset type of the target video; further, the server can judge whether each target characteristic information meets a preset condition corresponding to the type of the target characteristic information; and when the judgment result of each target characteristic information accords with a preset rule, determining a preset attitude tag corresponding to the preset rule as the attitude tag of the target video. Therefore, when the terminal plays the target video, the attitude label of the target video can be obtained; obviously, the attitude tag of the target video is extracted by the server through the extraction method of the attitude tag of the video; and then, in the playing process of the target video, the terminal displays the attitude label according to a first display mode, and when the triggering operation aiming at the attitude label is detected, the attitude label is displayed according to a second display mode.

In the method for extracting the attitude tag of the video provided by the present disclosure, the server first obtains the target video of the attitude tag to be extracted, that is, executes the step S11. The server may perform the step S11 in various ways, and the embodiment of the present invention is not limited in particular.

The candidate video pool may be preset, where the candidate video pool is a preset storage space for storing videos, a large number of videos are stored in the video pool, and the videos are not extracted with attitude tags, and may be obtained through various ways, for example, videos shot and uploaded by various video authors, videos obtained from video storage spaces of other video software, and the like, which are reasonable.

The candidate video pool may be a partial area of a storage space of the server, may also be a storage space on other electronic devices, and may also be a cloud storage space, which is reasonable.

Further, when the server executes the step S11, the server may obtain the target video from the candidate video pool, where the attitude tag is to be extracted. The server may determine all videos in the candidate video pool as target videos from which attitude tags are to be extracted, or may select a part of videos from the candidate video pool to determine as target videos from which attitude tags are to be extracted.

Based on this, optionally, in a specific implementation manner, as shown in fig. 2, the manner in which the server performs step S11 described above may include the following steps:

in step S111, a candidate video is obtained, and target index information of the candidate video in a preset dimension is extracted;

in step S112, it is determined whether the target index information satisfies a preset screening rule;

in step S113, if the target index information satisfies the preset filtering rule, the candidate video is determined as the target video from which the attitude tag is to be extracted.

In this specific implementation manner, the server first obtains candidate videos from a candidate video pool, where each video in the candidate video pool may be used as a candidate video. Further, the server may extract target index information of the candidate video in a preset dimension, and determine whether the target index information satisfies a preset screening rule. Therefore, if the target index information of the candidate video meets the preset screening rule, the server can determine the candidate video as the target video of the attitude tag to be extracted.

In this way, after traversing each video in the candidate video pool, the server may determine at least one target video from the plurality of candidate videos included in the candidate video pool, where the attitude tag is to be extracted.

Whether a candidate video is a target video with an attitude tag to be extracted is determined based on a judgment result of whether target index information of a preset dimension of the candidate video meets a preset screening condition, so that the preset dimension and the screening condition have a corresponding relation. Moreover, the screening condition may be formed based on index information of one dimension, or may be formed based on index information of multiple dimensions, so that the obtained target index information of the preset dimension may be target index information of one preset dimension, or may be target index information of multiple preset dimensions.

Specifically, as shown in table 1, the screening condition may be that screening is performed according to at least one condition of interactive data of the video, a hotspot of the video, author orientation of the video, and the like, and accordingly, the preset dimension of the obtained target index information of the candidate video may include at least one dimension of the interactive data of the candidate video, video content of the candidate video, author information of the candidate video, and the like. Of course, in addition to the screening conditions referred to in table 1, in practical applications, other screening conditions may also be employed, and the disclosure is not particularly limited thereto.

In table 1, consumption refers to play, praise, and comment interaction for a video.

TABLE 1

Wherein, the consumption index is as follows: playing/commenting/paying attention to/forwarding and the like basic indexes and an algorithm or manually audited quality rating index comprehensive index system;

negative filtration: negative feedback data such as broadcasting completion/reporting/dislike and the like, and negative filtering conditions of different rule items are different based on video content understanding and text matching filtering rules;

directional list: mining a high-quality author list which is automatically found and manually checked and fed back through data analysis;

hot topics: topics with high in-station release and viewing volumes;

searching hot words: searching the query (query word) with higher search heat or the processed keyword in the station;

matching hot spots outside the station: matching the hot spot information or video outside the station with corresponding similar content inside the station;

attitude rule matching: the selected attitude is automatically matched with related video content through an automatic marking rule;

and (3) directing a user list: and mining a found high-quality seed user list through data analysis.

Next, after the target video with the attitude tag to be extracted is acquired, the server may extract target feature information of each preset type of the target video, that is, execute step S12, and further, the server may determine whether each target feature information satisfies a preset condition corresponding to the type of the target feature information, and when a determination result of each target feature information satisfies a preset rule, determine the preset attitude tag corresponding to the preset rule as the attitude tag of the target video, that is, execute steps S13-S14.

The target feature information may include: and the video content information comprises at least one of video author category information, video content text description information, video content label information, video comment information and other various information.

Among them, the authors categories: for marking the category to which the author belongs (such as entertainment, education, and the like), the method is used for mapping the related attitude

Video text description: video cover titles, video descriptions, topic labels and the like are matched with attitude keywords based on text description and used for relevant attitude mapping;

video content labeling: based on the automatic analysis and understanding of the video content, marking content elements (such as 'games', 'singing', 'villages' and the like) in the video pictures for relevant attitude mapping;

video comment: and matching the comments issued by the users with attitude keywords based on the comment texts, and using the matched attitude keywords for relevant attitude mapping.

Specifically, the attitude label of each target video is determined based on a determination result whether the extracted target feature information of each preset type of the target video and the preset condition corresponding to the type of the target feature information meet, the preset condition corresponding to each preset type can be predetermined, and then, the preset attitude labels corresponding to different preset rules, to which the determination result of each target feature information meets, are determined.

The preset attitude label can be determined based on automatic hot word analysis and manual auxiliary selection of text information such as video titles, comments and the like.

In this way, the server may first determine whether each target feature information satisfies the preset condition corresponding to the type of the target feature information, and then determine a determination result whether each preset type of target feature information of the target video satisfies the preset condition corresponding to the type of the target feature information. In this way, the server can determine the preset rule that the judgment result of each target feature information conforms to, and thus, the preset attitude tag corresponding to the preset rule can be determined as the attitude tag of the target video.

Wherein, the preset rule is as follows: and the number and the type of the target characteristic information meeting the corresponding preset conditions in the judgment result. Specifically, when the server executes the step S13 and determines whether each target feature information satisfies the preset condition corresponding to the type of the target feature information, if the determination result is satisfied, the server may record the type of the target feature information; and after all the target characteristic information is judged, counting the number of the target characteristic information which is judged to be satisfied. In this way, the server may generate the preset rule to which the determination result conforms based on the number and type of the target feature information that is satisfied in the determination result of each obtained target feature information.

For example, as shown in table 2, the preset conditions are preset conditions corresponding to preset types, and preset attitude tags corresponding to different preset rules.

TABLE 2

Obviously, when the judgment result of the target video is: the target feature information of each preset type meets a preset condition corresponding to the type of the target feature information, that is, the type of the target feature information meeting the preset condition is as follows: all preset types are n, and further, the preset rule can be expressed as: the condition a1+ the condition a2+ the condition a3+ … + the condition an, and further, if the preset attitude tag corresponding to the preset rule is attitude a, the server may determine the attitude a as the attitude tag of the target video.

When the judgment result of the target video is as follows: the target characteristic information part of each preset type meets the preset condition corresponding to the type of the target characteristic information, and the type of the target characteristic information meeting the corresponding preset condition is as follows: video text descriptions, video content tags, video comments, … …, and other reference information, in amounts of: n-2, the preset rule met by the judgment result can be identified as: the condition B2+ the condition B4+ … + the condition bn, and further, if the preset attitude tag corresponding to the preset rule is the attitude B, the server may determine the attitude B as the attitude tag of the target video.

When the judgment result of the target video is as follows: the target characteristic information part of each preset type meets the preset condition corresponding to the type of the target characteristic information, and the type of the target characteristic information meeting the corresponding preset condition is as follows: author categories, video text descriptions and video comments, the number being: 3, the preset rule met by the judgment result can be identified as: in the condition C1+ the condition C2+ the condition C4, further, if the preset attitude tag corresponding to the preset rule is attitude C, the server may determine the attitude C as the attitude tag of the target video.

Based on this, optionally, in a specific implementation manner, the step S14 may include the following steps:

and when the judgment result of each target characteristic information meets the preset condition corresponding to the type of the target characteristic information, determining the attitude label of the target video as a preset attitude label corresponding to a preset rule.

In this specific implementation manner, the server may determine the preset attitude tag corresponding to the preset rule as the attitude tag of the target video only if the determination result of each target feature information of the target video satisfies the preset condition corresponding to the type of the target feature information.

Correspondingly, when each target feature information of the target video has target feature information which does not meet the preset condition corresponding to the type of the target feature information, the server can not determine the attitude tag of the target video, and further, the server can delete the target video from the acquired target video, namely, the target video cannot be used as the target video again.

Obviously, in this specific implementation manner, the server may further filter the target video by determining whether the attitude tag exists in the target video.

Further, for a target video, the server may determine that a plurality of attitude tags of the target video are obtained, that is, in the step S14, the determined preset attitude tags are multiple, and based on this, in an alternative specific implementation manner, the step S14 may include the following steps:

step 141: according to the preset priority of each preset attitude tag, sequencing each preset attitude tag from high priority to low priority;

step 142: and determining the preset attitude tag arranged at the first number of bits as the attitude tag of the target video.

In this specific implementation manner, when determining a plurality of preset attitude tags, the server may obtain the preset priority of each preset attitude tag at the same time, and then, the server may sort each preset attitude tag according to the order from high to low of the priority, and determine the preset attitude tag arranged in the first number of bits before as the attitude tag of the target video.

Wherein the disclosure does not limit the specific numerical values of the first quantity. For example, the server may determine the preset attitude tag arranged in the first 3 bits as the attitude tag of the target video, that is, obtain 3 attitude tags of the target video.

Optionally, in a specific implementation manner, as shown in fig. 3, the method for extracting a video attitude tag provided by the present disclosure may further include the following steps:

in step S15, extracting a second number of videos to be processed from the target video;

in step S16, obtaining a matching degree between the video content of each to-be-processed video and the attitude tag;

in step S17, updating the preset conditions and/or the filtering rules based on the matching degree of each video to be processed;

in step S18, for each to-be-processed video, if the matching degree of the to-be-processed video is smaller than the preset matching threshold, the attitude tag of the to-be-processed video is updated, so as to obtain an updated attitude tag of the to-be-processed video.

In this specific implementation manner, after the attitude tag of each target video is determined, the server may extract a second number of videos to be processed from the target videos. The second number of videos to be processed may be determined according to a preset extraction ratio and the number of target videos, or may be a fixed number, which is reasonable.

And performing secondary audit on each extracted video to be processed to determine the matching degree of the video content of each video to be processed and the attitude label. Therefore, the server can obtain the matching degree of the video content of each to-be-processed video and the attitude tag, and update the preset conditions and/or the screening rules based on the matching degree of each to-be-processed video.

Optionally, the server may first determine a target proportion occupied by the second number of videos to be processed, which are extracted from the videos to be processed, whose matching degrees are smaller than the preset matching degree value, and then, the server may further determine a size relationship between the target proportion and a preset adjustment threshold. Obviously, when the target ratio is greater than the preset adjustment threshold, it indicates that the number of videos to be processed with a low matching degree between the video content and the attitude tag is large, and further, it may be determined that the matching degree between the attitude tag of each determined target video and the video content of the target video is low, and therefore, in order to ensure the accuracy of the attitude tag of the determined target video, the server needs to update the preset condition and/or the screening rule.

Optionally, the server may first determine whether the matching degree of the extracted second number of videos to be processed is smaller than a preset matching degree value, if so, at this time, no matter whether the target proportion occupied by the second number of extracted videos to be processed of the videos to be processed, the matching degree of which is smaller than the preset matching degree value, is larger than the adjustment threshold value, it indicates that the target videos with the determined attitude tag and the video content of the target videos with lower matching degree can exist in the target videos, therefore, in order to further improve the accuracy of the attitude tag of the determined target video, the server may update the preset condition and/or the screening rule no matter whether the target proportion occupied by the second number of extracted videos to be processed, of which the matching degree is smaller than the preset matching degree value, is larger than the adjustment threshold.

The server may update the preset conditions and/or the screening rules according to the target feature information of each preset type of the target video with a low matching degree between the determined attitude tag and the video content of the target video.

In addition, the server may also obtain target feature information of each preset type of the target video, where the matching degree between the determined attitude tag and the video content of the target video is high, generate a new attitude tag based on the obtained target feature information, and further add the generated new attitude tag to a preset attitude tag corresponding to each preset rule.

Furthermore, for each to-be-processed video with the matching degree smaller than the preset matching threshold, the server may update the attitude tag of the to-be-processed video to obtain the updated attitude tag of the to-be-processed video.

The server can update the attitude tag of the video to be processed by using the updated preset condition, and can also update the attitude tag of the video to be processed in a mode of manually determining the attitude tag, which is reasonable.

Further, on the basis of the embodiment shown in fig. 3, optionally, in a specific implementation manner, the method for extracting the video attitude tag provided by the present disclosure may further include the following steps:

acquiring a diffusion video corresponding to each to-be-processed video, taking the diffusion video as a target video of the to-be-extracted attitude tag, and returning to the step of extracting target feature information of each preset type of the target video;

wherein diffusing the video includes: in the target video, the similarity between the video content and the video content of the video to be processed is greater than the preset similarity in the video of which the matching degree between the video content and the attitude tag is less than the preset matching threshold and the video which is not determined as the target video in the candidate video.

On the basis of the embodiment shown in fig. 3, the matching degree of the attitude tag of each to-be-processed video and the video content is greater than the preset matching threshold, and based on this, the server may obtain the diffusion video corresponding to each to-be-processed video, and use the diffusion video as the target video of the attitude tag to be extracted, and return to the step of extracting the target feature information of each preset type of the target video, that is, return to the step S12.

For each video to be processed, the server can determine the diffusion video corresponding to the video to be processed through various methods.

For example, the server may determine, by means of clustering, a diffuse video corresponding to each video to be processed in a target video in which the matching degree between the video content and the attitude tag is smaller than a preset matching threshold, and/or in a video that is not determined as the target video from among the candidate videos.

For another example, for convenience of description, the matching degree between the video content and the attitude tag may be smaller than a preset matching threshold in the target video, and/or a video that is not determined as the target video in the candidate videos is simply referred to as a to-be-diffused video; in this way, for each video to be processed, the server may extract various features of the video to be processed, such as author features, content elements, classification features, video titles, video comments, user interaction data, user features, and the like. Next, the server may further extract the above-mentioned various features of each video to be diffused. Furthermore, the server can calculate the feature similarity between the video to be processed and each video to be diffused, and further determine the video to be diffused, of which the similarity is greater than the similarity threshold, as the diffused video corresponding to the video to be processed.

Optionally, in an example, when the preset condition is updated, for each to-be-processed video, the server may obtain, from the target video whose matching degree between the video content and the attitude label is smaller than the preset matching threshold, a video whose similarity between the video content and the video content of the to-be-processed video is greater than the preset similarity, as a diffusion video, and return to the step of extracting the target feature information of each preset type of the target video, that is, return to the step S12.

Optionally, in an example, when the filtering rule is updated, for each video to be processed, the server may obtain, from videos that are not determined as the target video in the candidate videos, a video whose similarity between the video content and the video content of the video to be processed is greater than a preset similarity, as a diffusion video, and return to the step of extracting target feature information of each preset type of the target video, that is, return to step S12.

Wherein, the videos not determined as the target video in the candidate videos may include: in the specific implementation shown in fig. 2, at least one type of candidate videos not determined as the target video and candidate videos newly entering the candidate video pool later is selected.

Optionally, in an example, when the preset condition and the filtering rule are updated, for each to-be-processed video, the server may obtain, from the target video whose matching degree between the video content and the attitude label is smaller than the preset matching threshold and the video that is not determined as the target video in the candidate videos, the video whose similarity between the video content and the video content of the to-be-processed video is greater than the preset similarity as the diffuse video, and return to the step of extracting each preset type of target feature information of the target video, that is, return to the step S12.

Optionally, in a specific implementation manner, the method for extracting a video attitude tag provided by the present disclosure may further include the following steps:

step 1: acquiring interactive data of a target video, and determining an initial approval value of each attitude tag of the target video based on the interactive data;

wherein the interactive data may include at least one of play data, like data and comment data;

step 2: and correspondingly storing each attitude tag of the target video and the initial approval value of the attitude tag.

After the attitude tag of the target video is determined, the server can acquire the interactive data of the target video, and further determine the initial approval value of each attitude tag of the target video based on the interactive data. In this way, the server can correspondingly store each attitude tag of the target video and the initial approval value of the attitude tag. Therefore, when the terminal receives a playing instruction of the target video, the terminal can simultaneously acquire the attitude tags of the target video and the initial approval values of the attitude tags.

The interactive data may also include other types of data, and the embodiment of the present invention is not particularly limited thereto.

Optionally, the manner in which the server determines the initial approval value of each attitude tag of the target video may be:

step 11: acquiring a preset weight of each type of interactive data;

step 12: calculating a first product of the data value of each type of interactive data and a preset weight, and calculating a sum of the obtained first products;

step 13: and calculating a second product of the obtained sum value and a preset adjusting coefficient, and determining the second product as an initial approval value of each attitude tag.

The preset weight and the preset adjustment coefficient of each type of interactive data can be determined according to the author information, the video content tag, the video popularity and other related information of the target video, and the disclosure is not particularly limited.

In addition, after the attitude tag of each target video is determined, the server can set recommendation rules of each target video, so that when a user opens video software for watching the target video on the terminal, each target video which is set by the server and recommended on a home page can be seen on the home page, and when the user enters a certain video theme, each target video which is recommended in the video theme set by the server can be seen on a video display interface corresponding to the video theme.

That is, the server can implement automatic distribution of target videos, including cross-topic distribution on the top page and video stream distribution within a single topic tab page.

In the following, a video-based interaction method provided by the present disclosure is explained.

Fig. 4 is a flowchart illustrating a video-based interaction method according to an exemplary embodiment, where the interaction method is applied to a terminal, and the terminal may be any electronic device that needs to perform video-based interaction, for example, a mobile phone, a tablet computer, a notebook computer, and the like.

As shown in fig. 4, the present disclosure provides a video-based interaction method, including the following steps:

in step S41, an attitude tag of the target video is acquired;

wherein, the attitude tag is extracted by any video attitude extraction method provided by the disclosure;

in step S42, during the playing process of the target video, displaying the attitude label according to the first display mode;

in step S43, when the trigger operation for the attitude label is detected, the attitude label is displayed in the second display mode.

When the terminal receives a playing instruction for a target video, the terminal can start playing the target video, and the terminal can synchronously acquire the attitude tag of the target video extracted by the server through any video attitude extraction method provided by the disclosure.

Therefore, in the playing process of the target video, the terminal can display the attitude label according to the first display mode.

When the target video has a plurality of attitude tags, the terminal can display each attitude tag in turn in a display picture of the target video in a rolling playing mode, and can also display all the attitude tags in the display picture of the target video at the same time; in addition, in the display screen of the target video, the position, the shape, and the background color of the display area for displaying each attitude tag, and the content of the background color, the font style, the font size, the font color, and the like of the characters in each attitude tag are not specifically limited in this disclosure.

Next, when the terminal detects a trigger operation for the attitude tag, the attitude tag may be displayed according to a second display mode, and at this time, the terminal may obtain a viewing experience of the user on the target video, where the viewing experience is an experience expressed by the attitude tag to which the trigger operation is directed.

The method for displaying the attitude tags by the terminal according to the second display mode is not specifically limited in the disclosure, for example, the second display mode may be a mode in which the position of a display area displaying each attitude tag in the video display interface is changed; the shape of the display area displaying each attitude label can be changed; it is also possible to change the background color of the display area displaying each attitude label, etc., all of which are reasonable.

For example, as shown in fig. 9(a) and 9(b), when a trigger operation for the attitude tag "this is just like something", is detected, the terminal changes from displaying the attitude tag in the first display mode as shown in fig. 9(a) to displaying the attitude tag in the second display mode as shown in fig. 9 (b).

In addition, the present disclosure also does not limit the specific content of the above-described trigger operation. The triggering operation can be a plurality of operations such as a single-click attitude tag, a double-click attitude tag, a long-click attitude tag and the like. Moreover, when a plurality of attitude tags exist in the target video, it is reasonable that the user can perform a trigger operation on at least one of the attitude tags.

Optionally, in a specific implementation manner, the interaction method may further include the following steps:

and when the cancel operation aiming at the attitude label is detected, displaying the attitude label according to a first display mode.

Specifically, in this specific implementation manner, for the attitude tag in which the trigger operation has been detected, that is, the attitude tag has been selected by the user, the user may cancel the selection of the selected attitude tag by executing a preset cancellation operation. Therefore, when the terminal detects the cancel operation aiming at the attitude tag, the attitude tag can be restored from the second display mode to the first display mode to be displayed.

For example, suppose that clicking the attitude tag for the first time is a trigger operation for the attitude tag, clicking the attitude tag again is a cancel operation for the attitude tag, and after detecting the cancel operation for the attitude tag, when clicking the attitude tag again, the click is recovered to the first click; for a first attitude label of the target video, when a first click on the attitude label is detected, the terminal changes from a first display mode to a second display mode to display the attitude label, namely, the background color of a display area for displaying each attitude label is changed from gray to blue; when the second click on the attitude label is detected, the terminal restores from the second display mode to the first display mode to display the attitude label, namely the background color of the display area displaying each attitude label is restored from blue to grey.

As can be seen from the above, according to the technical solution provided by the embodiment of the present disclosure, the server determines the attitude tags of the target videos in advance, and the content of each attitude tag of the target video is the viewing experience of the video content. Like this, when the user was watching the target video, terminal alright in order to directly show the attitude label of target video to, when the user wants to publish self to the watching of target video and feel, alright in order to directly select the attitude label that accords with the own watching impression from the attitude label that the terminal shows, and trigger operation to the attitude label of selecting, and then, the terminal alright in order to acquire the user and to the watching impression of target video.

In addition, in order to enable a user to visually see the selection condition of each attitude tag of the target video, so that the user can know the distribution of the watching experience of other users on the target video, the terminal can display the current approval number of each attitude tag. Based on this, optionally, in a specific implementation,

the step S42 of displaying the attitude label according to the first display mode may include the following steps:

step 421: displaying the attitude label and the current approval value of the attitude label according to a first display mode;

wherein, the current approved values are: the sum of the initial approval value of the attitude tag and the detected number of times of triggering operation aiming at the attitude tag;

the initial approval value of the attitude tag is determined by the server based on at least one interactive data of the playing data, the approval data and the comment data of the target video, and the current approval value of the attitude tag can be updated when the terminal detects the trigger operation for the attitude tag every time.

Obviously, when the trigger operation of the attitude tag is never detected, the current approval value of the attitude tag is the initial approval value of the attitude tag.

In addition, optionally, when the terminal displays the attitude label according to the first display mode, the terminal may further display an expression image corresponding to the attitude label. For example, as shown in fig. 9(a), an attitude tag "it is just like that", a current approval value 2345 of the attitude tag, and an emoticon of the attitude tag are displayed in the target video.

In view of this, in this specific implementation manner, the step of displaying the attitude label in the second display manner in step S43 includes:

in step 431, the current approval value is updated;

in step 432, the attitude label and the updated current approval value are displayed in a second display mode.

When the trigger operation aiming at the attitude tag is detected, the terminal can firstly update the current approval value of the attitude tag, and then can display the attitude tag and the updated current approval value according to the second display mode.

The manner of updating the current approval value by the terminal may be to add 1 to the current approval value displayed in the first display manner.

In addition, optionally, on the basis of the specific implementation manner, the interaction method may further include:

and when the canceling operation aiming at the attitude tag is detected, updating the current approval value, and displaying the attitude tag and the updated current approval value according to a first display mode.

And if the attitude tag of the trigger operation is detected, namely the attitude tag is selected by the user, the user can cancel the selection of the selected attitude tag by executing a preset cancellation operation. Thus, when the terminal detects a cancel operation for the attitude tag, it is obvious that the current approval value obtained after updating in the above step S431 is no longer appropriate. Based on this, the terminal needs to update the current approval value again, and the current approval value is restored to the current approval value displayed by the terminal according to the first display mode before the step S431 is executed. Furthermore, the terminal can restore from the second display mode to the first display mode to display the attitude tag and the updated current approval value.

The manner of updating the current approval value again by the terminal may be to subtract 1 from the current approval value displayed in the second display manner.

Fig. 5 is a block diagram illustrating an apparatus for extracting a video attitude tag according to an exemplary embodiment, which is applied to a server, and as shown in fig. 5, includes a video obtaining module 510, an information extracting module 520, a condition judging module 530, and a tag determining module 540.

The video obtaining module 510 is configured to obtain a target video of an attitude tag to be extracted;

an information extraction module 520 configured to extract target feature information of each preset type of the target video;

a condition determining module 530 configured to determine whether each target feature information satisfies a preset condition corresponding to the type of the target feature information;

a tag determining module 540, configured to determine, when the determination result of each target feature information conforms to a preset rule, a preset attitude tag corresponding to the preset rule as an attitude tag of the target video;

Optionally, in a specific implementation manner, the tag determining module 540 is specifically configured to:

Optionally, in a specific implementation manner, the number of the preset attitude tags is multiple; the tag determination module 540 includes:

Optionally, in a specific implementation manner, the video obtaining module 510 includes:

Fig. 6 is a block diagram illustrating a video-based interactive apparatus applied to a terminal according to an exemplary embodiment, and as shown in fig. 6, the apparatus includes a tag obtaining module 610, a first display module 620 and a second display module 630.

The tag obtaining module 610 is configured to obtain an attitude tag of a target video; wherein the attitude tag is extracted by the video attitude tag extraction means of any one of claims 1 to 7;

the first display module 620 is configured to display the attitude tag according to a first display mode in the playing process of the target video;

the second display module 630 is configured to display the attitude tag according to a second display manner when the trigger operation for the attitude tag is detected.

Alternatively, in one particular implementation,

the first display module 620 is specifically configured to: displaying the attitude label and the current approval numerical value of the attitude label according to a first display mode; wherein the current approval value is: a sum of the initial approval value of the attitude tag and the detected number of times of the triggering operation for the attitude tag;

the second display module 630 is specifically configured to: updating the current approval value; and displaying the attitude label and the updated current approval numerical value according to a second display mode.

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Fig. 7 is a block diagram illustrating a server 700 for extracting video attitude tags, according to an example embodiment. For example, server 700 may be provided as a server. Referring to fig. 7, server 700 includes a processing component 722 that further includes one or more processors and memory resources, represented by memory 732, for storing instructions, such as applications, that are executable by processing component 722. The application programs stored in memory 732 may include one or more modules that each correspond to a set of instructions. Further, the processing component 722 is configured to execute instructions to perform the steps of any of the video attitude tag extraction methods described above.

The server 700 may also include a power component 726 configured to perform power management of the server 700, a wired or wireless network interface 750 configured to connect the server 700 to a network, and an input output (I/O) interface 758. The server 700 may operate based on an operating system stored in memory 732, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

Fig. 8 is a block diagram illustrating a terminal 800 for video-based interaction, according to an example embodiment. For example, the terminal 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, and the like.

Referring to fig. 8, terminal 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.

The processing component 802 generally controls overall operation of the terminal 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operation at the terminal 800. Examples of such data include instructions for any application or method operating on terminal 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile 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 disks.

Power components 806 provide power to the various components of terminal 800. Power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for terminal 800.

The multimedia component 808 includes a screen providing an output interface between the terminal 800 and the user. 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 an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 800 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the terminal 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

Sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for terminal 800. For example, sensor assembly 814 can detect the open/closed state of device 800, the relative positioning of components, such as a display and keypad of terminal 800, sensor assembly 814 can also detect a change in position of terminal 800 or a component of terminal 800, the presence or absence of user contact with terminal 800, orientation or acceleration/deceleration of terminal 800, and a change in temperature of terminal 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 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 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

Communication component 816 is configured to facilitate communications between terminal 800 and other devices in a wired or wireless manner. The terminal 800 may access a wireless network based on a communication standard, such as WiFi, an operator network (e.g., 2G, 3G, 4G, or 5G), or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 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 terminal 800 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, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a storage medium comprising instructions, such as the memory 804 comprising instructions, executable by the processor 820 of the terminal 800 to perform the above-described method is also provided. Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for extracting video attitude tags is applied to a server, and comprises the following steps:

acquiring a target video of an attitude tag to be extracted, wherein the content of the attitude tag is the watching experience of the video content;

extracting target characteristic information of each preset type of the target video, wherein the target characteristic information comprises at least one of video author category information, video content label information and video comment information;

judging whether each target characteristic information meets a preset condition corresponding to the type of the target characteristic information, if so, recording the type of the target characteristic information, and counting the number of the target characteristic information with the judgment result of meeting after all the target characteristic information is judged;

and when the judgment result of each target characteristic information conforms to the preset rule, determining a preset attitude label corresponding to the preset rule as the attitude label of the target video so that the terminal displays the attitude label in the playing process of the target video.

2. The method according to claim 1, wherein when the determination result of each target feature information conforms to a preset rule, determining that the attitude tag of the target video is a preset attitude tag corresponding to the preset rule includes:

3. The method according to claim 1, wherein the preset attitude tag is plural; the determining, as the attitude tag of the target video, the preset attitude tag corresponding to the preset rule further includes:

4. The method of claim 1, further comprising:

5. The method according to claim 1, wherein the step of obtaining the target video to be extracted with the attitude tag comprises:

6. The method of claim 5, further comprising:

after the attitude label of each target video is determined, extracting a second number of videos to be processed from the target videos;

7. The method of claim 6, further comprising:

8. A video-based interaction method is applied to a terminal, and comprises the following steps:

acquiring an attitude tag of a target video; wherein the attitude tag is extracted by the extraction method of the video attitude tag according to any one of claims 1 to 7;

9. The method of claim 8, wherein the step of displaying the attitude tag in a first display mode comprises:

updating the current approval value;

10. An apparatus for extracting video attitude tags, applied to a server, the apparatus comprising:

the video acquisition module is configured to acquire a target video of an attitude tag to be extracted, wherein the content of the attitude tag is the watching experience of video content;

the information extraction module is configured to extract target feature information of each preset type of the target video, wherein the target feature information comprises at least one of video author category information, video content label information and video comment information;

the condition judgment module is configured to judge whether each target feature information meets a preset condition corresponding to the type of the target feature information, record the type of the target feature information if the judgment result is met, and count the number of the target feature information with the judgment result of meeting after all the target feature information is judged;

and the tag determining module is configured to generate a preset rule which is met by the judgment result based on the number and the type of the target characteristic information which are met by the judgment result in the judgment result of each target characteristic information, and when the judgment result of each target characteristic information is met by the preset rule, determine a preset attitude tag corresponding to the preset rule as an attitude tag of the target video, so that the attitude tag is displayed by the terminal in the playing process of the target video.

11. The apparatus of claim 10, wherein the tag determination module is specifically configured to:

12. The apparatus according to claim 10, wherein the preset attitude tag is plural; the tag determination module includes:

13. The apparatus of claim 10, further comprising:

14. The apparatus of claim 10, wherein the video acquisition module comprises:

15. The apparatus of claim 14, further comprising:

the video extraction module is configured to extract a second number of videos to be processed from the target videos after determining the attitude tag of each target video;

16. The apparatus of claim 15, further comprising:

17. A video-based interactive device, applied to a terminal, the device comprising:

the tag acquisition module is configured to acquire an attitude tag of the target video; wherein the attitude tag is extracted by the video attitude tag extraction means of any one of claims 1 to 7;

18. The apparatus of claim 17, wherein the first display module is specifically configured to:

the second display module is specifically configured to:

19. 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 method of extracting video attitude tags of any of claims 1 to 7.

20. A storage medium in which instructions, when executed by a processor of a server, enable the server to perform the method of extracting a video attitude tag of any one of claims 1 to 7.

21. A terminal, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the video-based interaction method of any of claims 8 to 9.

22. A storage medium in which instructions, when executed by a processor of a terminal, enable a server to perform the video-based interaction method of any one of claims 8 to 9.