CN109587568A - Video broadcasting method, device, computer readable storage medium - Google Patents

Video broadcasting method, device, computer readable storage medium Download PDF

Info

Publication number
CN109587568A
CN109587568A CN201811297447.4A CN201811297447A CN109587568A CN 109587568 A CN109587568 A CN 109587568A CN 201811297447 A CN201811297447 A CN 201811297447A CN 109587568 A CN109587568 A CN 109587568A
Authority
CN
China
Prior art keywords
video
target
tag along
preference
along sort
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201811297447.4A
Other languages
Chinese (zh)
Inventor
刘诗
徐颖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing QIYI Century Science and Technology Co Ltd
Original Assignee
Beijing QIYI Century Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing QIYI Century Science and Technology Co Ltd filed Critical Beijing QIYI Century Science and Technology Co Ltd
Priority to CN201811297447.4A priority Critical patent/CN109587568A/en
Publication of CN109587568A publication Critical patent/CN109587568A/en
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
    • H04N21/4665—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms involving classification methods, e.g. Decision trees
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/239—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests
    • H04N21/2393—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests involving handling client requests
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
    • H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
    • H04N21/47202—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for requesting content on demand, e.g. video on demand
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/84—Generation or processing of descriptive data, e.g. content descriptors
    • H04N21/8405—Generation or processing of descriptive data, e.g. content descriptors represented by keywords

Abstract

The present invention provides a kind of video broadcasting method, video play device and computer readable storage mediums, this method comprises: receiving film clips playing request；According to the film clips playing request, target video belonging to target user and film clips to be played is identified；Identify the tag along sort of target user's preference described in multiple tag along sorts of the target video；Obtain the matched video clip of tag along sort in the target video with target user's preference；Export the video clip.Compared to same videos recommended informations such as title, the posters that all clients are shown with video, the present invention is by exporting the video clip of target video to match with the tag along sort of user preference, different terminals can be carried out with the personalized push of introductory video information, to promote the target video to the hit rate of each terminal user, the conversion ratio of promotion video clip to video positive.

Description

Video broadcasting method, device, computer readable storage medium
Technical field
The present invention relates to video technique fields, more particularly to a kind of video broadcasting method and device and a kind of computer Readable storage medium storing program for executing.
Background technique
It is watched currently, each video platform can provide various videos for user.Video platform is providing video positive (example Such as the complete video of certain film) before, it can be by showing title, poster figure (such as static map or dynamic of portion's film Figure), the information such as brief introduction portion's film is simply introduced to user, consequently facilitating user is required for searching oneself in numerous videos The video of viewing.
But the information content that title, poster figure (even Dynamic Graph) and brief introduction provide is limited, user is in fact very Difficulty judges whether this film really oneself likes the film seen by these information.By the video data to the end TV into Find for the video of movie channel, there is the duration of the film of 27% user's viewing movie channel not surpass after row statistics It spends 1 minute and exits viewing, there is 41% user also only to have viewed and exited less than 5 minutes.This illustrates that user is selecting certainly Before oneself really wants the film seen, needs to carry out search many times and attempt, can just find oneself favorite video.
Obviously, video information exhibit scheme in the related technology is in the recommended information for showing some video to different terminals When, the recommended information of displaying be it is identical, can not to terminal carry out introductory video information personalized push, there is videos Hit the lower problem of the probability of user.
Summary of the invention
The present invention provides a kind of video broadcasting method and device and a kind of computer readable storage mediums, to solve phase Video information exhibit scheme in the technology of pass in the prevalence of the personalized push that can not carry out introductory video information to terminal, The problem for causing the probability of video hit user lower.
To solve the above-mentioned problems, according to an aspect of the present invention, the invention discloses a kind of video broadcasting method, packets It includes:
Receive film clips playing request；
According to the film clips playing request, target video belonging to target user and film clips to be played is identified；
Identify the tag along sort of target user's preference described in multiple tag along sorts of the target video；
Obtain the matched video clip of tag along sort in the target video with target user's preference；
Export the video clip.
According to another aspect of the present invention, the invention also discloses a kind of video play devices, comprising:
First receiving module, for receiving film clips playing request；
First identification module, for identifying belonging to target user and film clips to be played according to the film clips playing request Target video；
Second identification module, for identification target user's preference described in multiple tag along sorts of the target video point Class label；
First obtains module, matched with the tag along sort of target user's preference in the target video for obtaining Video clip；
Output module, for exporting the video clip.
According to another aspect of the present invention, the invention also discloses a kind of computer readable storage medium, the computers It is stored with computer program on readable storage medium storing program for executing, realizes when the computer program is executed by processor such as any of the above-described institute The step in video broadcasting method stated.
Compared with prior art, the present invention includes the following advantages:
In this way, the embodiment of the present invention according to the film clips playing request that receives determine request play the target user of film clips with And target video belonging to film clips, and identify the contingency table of target user's preference in multiple tag along sorts of the target video Label, then, obtain the video clip of the target video to match with the tag along sort of target user's preference and output.It compares In same videos recommended informations such as title, the posters that all clients are shown with video, the embodiment of the present invention is by regarding target Different terminals can be carried out introductory video information by the video clip output of frequency to match with the tag along sort of user preference Personalized push promotes video clip to video positive to promote the target video to the hit rate of each terminal user Conversion ratio.
Detailed description of the invention
Fig. 1 is a kind of step flow chart of video broadcasting method embodiment of the invention；
Fig. 2 is a kind of step flow chart of video broadcasting method embodiment of the invention；
Fig. 3 is a kind of step flow chart of video broadcasting method embodiment of the invention；
Fig. 4 is a kind of step flow chart of video broadcasting method embodiment of the invention；
Fig. 5 is a kind of step flow chart of video broadcasting method embodiment of the invention；
Fig. 6 is a kind of step flow chart of video broadcasting method embodiment of the invention；
Fig. 7 is a kind of work flow diagram of audio/video player system embodiment of the invention；
Fig. 8 is a kind of structural block diagram of video play device embodiment of the invention.
Specific embodiment
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing and specific real Applying mode, the present invention is described in further detail.
Referring to Fig.1, a kind of step flow chart of video broadcasting method embodiment of the invention is shown, wherein this method It can be applied to terminal device (such as mobile phone, smart television, tablet computer etc.), also can be applied to server.This method tool Body may include steps of:
Step 101, film clips playing request is received；
Wherein, which can be triggered at the interface that any one includes video information.
For example, user can trigger film clips playing request to the interested video item of any one in list of videos interface. The triggering mode of film clips playing request includes but is not limited to click, double click, slide desired guiding trajectory, stops more than preset time etc. Deng.
Optionally, in one embodiment, it when executing step 101, can be triggered by receiving at list of videos interface Film clips playing requests realize.
Wherein, list of videos interface is the interface for including multiple video items, and the video item of some video may include the view The recommended information of frequency, the recommended information include but is not limited to poster, title, brief introduction etc..
Wherein, after which can be user's search video, by the candidate video for meeting user's search need Corresponding video item, and the list of videos interface generated；Alternatively, the list of videos interface can be and search without any of user Rope, directly by the corresponding video item of video platform candidate video recommended to the user, and the list of videos interface generated.
In one example, some video item (such as some video poster) focus can be obtained in list of videos interface In the case where more than preset time (such as mouse stop on some video poster more than 3 seconds), triggering is to the piece of the video item Flower playing request.
In addition, above-mentioned film clips playing request can also be triggered at the interface of some video item.Such as user opens some Behind the brief introduction interface (including the information such as brief introduction, poster, protagonist) of video, user can be triggered at the brief introduction interface of the video to this The film clips playing request of video.Wherein, the triggering mode of film clips playing request is for example above-mentioned enumerates, and which is not described herein again.
Step 102, according to the film clips playing request, the view of target belonging to target user and film clips to be played is identified Frequently；
In a kind of feasible embodiment, the video which can carry the login embodiment of the present invention is flat Therefore the user information (such as target user ID, user name etc.) of platform can identify which is by means of film clips playing request User triggers the film clips playing request.
In a kind of feasible embodiment, which, which can also carry to be triggered, needs to play the mesh of film clips Therefore the information (such as video ID, video name etc.) of mark video can identify that client is asked by means of film clips playing request Seek the film clips for playing which video.
Step 103, the tag along sort of target user's preference described in multiple tag along sorts of the target video is identified；
Wherein, the embodiment of the present invention can be in advance to each video configuration tag along sort in video library.For example, point Class label can include but is not limited to act the leading role name, video subject, video type etc. label relevant to video content.
Wherein, video subject includes but is not limited to campus, workplace, war, imperial palace, science fiction.
Video type includes but is not limited to movement, love, comedy, gunbattle, crime, terrible, terrified, suspense, animation, family Front yard, plot etc..
In addition, can have one or more types when to some video configuration tag along sort and (act the leading role name, view Frequency theme, video type) tag along sort, and one or more assignment can have for the tag along sort of each type (such as the tag along sort of video type may include multiple assignment, respectively movement, love, comedy).
This step can the target video multiple tag along sorts (such as the tag along sort of certain film include love It is feelings, terrible) in, determine that the tag along sort of target user's preference (wherein, in love and terrible two tag along sorts, is compared In the video of terrible type, target user more has a preference for the video for watching love type), therefore, here target user's preference point Class label is love.
The tag along sort of so-called user preference is the preference of the viewing video based on user usually, in the more of the target video In a tag along sort, the tag along sort that identifies.
In addition, the tag along sort of determining target user's preference may include one or more here, the present invention to this simultaneously It does not limit.
Step 104, the matched video clip of tag along sort in the target video with target user's preference is obtained；
Wherein, the embodiment of the present invention is not only configured with tag along sort to each video in video library in advance, also matches to it Multiple film clips are set.Wherein, which is also a kind of introductory video information.
For example, video A has tag along sort 1 and tag along sort 2, then the embodiment of the present invention can in advance generate video A Two groups of film clips, the content of two groups of film clips match with tag along sort 1 and tag along sort 2 respectively.
Such as tag along sort 1 is " love ", tag along sort 2 is performer " chapter XX ", then can extract in video from video A Hold it is relevant to " love " one or more video clips as with " love " matched film clips (wherein, when some film clips includes When multiple video clips, which is a video clip by multiple video clip editings together)；Further, it is also possible to from Extracted in video A " chapter XX " one or more video clips for playing as with " chapter XX " matched film clips (wherein, when certain When a film clips include multiple video clips, which is a video clip by multiple video clip editings together).
Therefore, the different classifications label of a video respectively corresponds to different video clips (i.e. film clips), wherein the video Segment (i.e. film clips) can be to be expanded by one or more original segments of the video.
In this step, although target video has been pre-configured with the multiple film clips for respectively corresponding different classifications label, This step only needs to obtain in multiple film clips of the target video, with the tag along sort of target user's preference (such as " love Feelings ") matched film clips (video clip i.e. in step 104).
Step 105, the video clip is exported.
In a kind of feasible embodiment, when the tag along sort of target user's preference only one when, then export here Video clip be a corresponding tag along sort a video clip, i.e. a film clips.
In another feasible embodiment, when the tag along sort of target user's preference is multiple, then step 104 can Matched multiple film clips, i.e., multiple video clips are distinguished with multiple tag along sort respectively to get.So in this step The corresponding multiple film clips of tag along sort of multiple user preference can be sequentially output.Wherein, the sortord of multiple film clips Can be any one sortord, such as be ranked up according to the sequence of user preference degree from high to low etc..
In this way, the embodiment of the present invention according to the film clips playing request that receives determine request play the target user of film clips with And target video belonging to film clips, and identify the contingency table of target user's preference in multiple tag along sorts of the target video Label, then, obtain the video clip of the target video to match with the tag along sort of target user's preference and output.It compares In same videos recommended informations such as title, the posters that all clients are shown with video, the embodiment of the present invention is by regarding target Different terminals can be carried out introductory video information by the video clip output of frequency to match with the tag along sort of user preference Personalized push promotes video clip to video positive to promote the target video to the hit rate of each terminal user Conversion ratio.
Optionally, in one embodiment, before step 101, referring to Fig. 2, according to the method for the embodiment of the present invention also May include:
S501 records data according to the video tour of target user, determines each video that the target user has browsed；
Wherein, video tour record data can include but is not limited to video playing data (for example, which view played Frequently, the broadcasting time of each video, the video played every time playing duration account for the video total duration percentage), video Search for data (for example, the searching times for searching for which video, each video) etc..It therefore, can be according to the view of target user Frequency browsing record data, to determine which video the target user browsed and (search for and/or play).
S502 obtains the tag along sort of each video；
Wherein, each video in video library is provided with tag along sort in advance, therefore, here can be to target user Each video of browsing, obtains their tag along sort.
S503 records the tag along sort of data and each video according to the video tour, counts the target and uses Multiple candidate classification labels of family preference and the preference of each candidate classification label.
Wherein, the embodiment of the present invention can record data and wherein each video according to video tour using any one Tag along sort mode, multiple candidate classification labels of Lai Tongji target user preference (i.e. interested) and candidate point each The preference of class label.
Optionally, in one embodiment, scheme described in Fig. 2 can be accomplished by the following way:
As described above, video tour record data can include but is not limited to play which video, each be played The broadcasting time of video, the playing duration of the video played every time account for the video total duration percentage, which was searched for Video, searching times of each video etc..
So when counting the candidate classification label of target user's preference, video tour can be recorded into each of data The tag along sort for the video searched for, each video played tag along sort set as target user's preference Candidate classification label.
Wherein, it should be noted that may exist identical tag along sort, candidate classification mark here between different video Label are the tag along sort after duplicate removal.
So to each candidate classification label in multiple candidate classification labels, the target user is counted to each candidate When the preference of tag along sort, for the preference of any one candidate classification label can using the method for weighted sum come It calculates.
It is illustrated by taking the tag along sort 1 in candidate classification label as an example, the parameter for assigning weight includes having contingency table The search total degree of the video of label 1, the broadcasting total degree of video with tag along sort 1, video with tag along sort 1 are broadcast The percentage that duration accounts for the total duration of the video is put, their weight is followed successively by w1, w2 and w3.Such as above-mentioned target user's The video with the tag along sort 1 includes video 1 and video 2 in video tour record data, then with the video of tag along sort 1 Search total degree be that the search total degree of video 1 and the sum of search total degree of video 2 (for example, a), have tag along sort 1 The total degree that plays of video be that the sum of broadcasting total degree for playing total degree and video 2 of video 1 (for example, b), has point The playing duration of the video of class label 1 accounts for the percentage of the total duration of the video and accounts for the total of the video 1 for the playing duration of video 1 The percentage of duration and the playing duration of video 2 account for the sum of percentage of total duration of the video 2 (for example, c).
So preference W=w1*a+w2*b+w3*c of the target user to tag along sort 1.
Similarly, target user can be calculated using similar method to the preference of other candidate classification labels.
It should be noted that the method that the present invention calculates the preference of tag along sort is not limited to the side of above-mentioned weighted sum Method can also be other unlisted other methods, and which is not described herein again.
So in the present embodiment, it when executing step 103, then can be realized by method shown in Fig. 3:
S201 obtains the candidate classification label in multiple tag along sorts of the target video with target user's preference The preference of matched multiple target classification labels and each target classification label；
For example, for example, the candidate classification label of target user's preference includes tag along sort 1 to tag along sort 10, The preference of tag along sort 1 to tag along sort 10 sorts from high to low, the preference of tag along sort 1 to tag along sort 10 according to Secondary is P1 to P10.
And target user requests to play the tag along sort of the target video configuration of film clips to include tag along sort 1, tag along sort 2 With tag along sort 11.
So by using the tag along sort (tag along sort 1, tag along sort 2 and tag along sort 11) of target video and target The candidate classification label (1~tag along sort of tag along sort 10) of family preference is matched, and can determine phase in two fold classification label Mutual matched tag along sort includes tag along sort 1 and tag along sort 2.
Hence, it can be determined that in the tag along sort 1, tag along sort 2 and tag along sort 11 of target video, with target user The target classification label of the candidate classification tag match of preference includes tag along sort 1 and tag along sort 2.Further, it is also possible to determine The preference of tag along sort 1 and tag along sort 2 is followed successively by P1 and P2.
S202 is identified described in the multiple target classification label according to the preference of each target classification label The tag along sort of target user's preference.
Wherein, due to being had determined that in multiple tag along sorts of target video by S201, with target user's preference The target classification label of candidate classification tag match includes tag along sort 1 and tag along sort 2, preference of the target user to them P1 and P2 are followed successively by, in this step, so that it may, should in two tag along sorts to determine according to the preference of the two tag along sorts The tag along sort of target user's preference.
In addition, the tag along sort of the target user's preference recognized in S202 can be one or more tag along sorts, this Invention does not limit this.
In this way, the embodiment of the present invention records data according to the video tour of target user, determine that the target user is clear The each video look at, and the tag along sort of each video is obtained, so as to record data and institute according to the video tour State the tag along sort of each video, the candidate classification label of Lai Tongji target user's preference and each candidate classification label it is inclined Good degree meets so that candidate classification label and its preference are all based on the video tour record of target user and generate The true viewing demand of user；So when target user requests to play the film clips of target video, then it can be regarded according to the target The tag along sort of frequency and above-mentioned candidate classification label, to determine the interested target classification mark of user in above-mentioned tag along sort Label, and then can be obtained with the film clips (i.e. video clip) of target classification tag match simultaneously in multiple film clips of target video Output, so that the film clips for being supplied to the target video of user are specific to user to multiple tag along sorts of the target video Difference preference's degree and personalized push, promote conversion ratio of the film clips to positive.
Optionally, in one embodiment, when executing S202, can by the following ways 1 or in a manner of 2 realize:
Mode 1: it is used using the highest target classification label of preference in the multiple target classification label as the target The tag along sort of family preference；
Continue to include that tag along sort 1 and tag along sort 2 are illustrated with above-mentioned target classification label, tag along sort 1 and contingency table The preference of label 2 is respectively P1 and P2, wherein P1 > P2, then tag along sort 1 can be determined as target user's preference here Tag along sort, thus to user push target video in the matched film clips of tag along sort 1.
Mode 2: preference in the multiple target classification label is greater than the target classification label of preset threshold as institute State the tag along sort of target user's preference.
Continue to include that tag along sort 1 and tag along sort 2 are illustrated with above-mentioned target classification label, tag along sort 1 and contingency table The preference of label 2 is respectively P1 and P2, wherein preset threshold P0, wherein if P1 > P2 > P0, therefore, can will classify here Label 1 and tag along sort 2 are determined as the tag along sort of target user's preference, thus to target user push target video in The matched film clips 1 of tag along sort 1, and with the matched film clips 2 of tag along sort 2.Alternatively, can will classify if P1 > P0 > P2 Tag along sort of the label 1 as target user's preference, to be pushed to target user matched with tag along sort 1 in target video Film clips 1, and do not push and the matched film clips 2 of tag along sort 2.
It should be noted that when step 103 identify target user's preference tag along sort be two or two with When upper, then the sequence of the preferences of multiple tag along sorts of preference from high to low can be sequentially output according to target user and be pushed away It send.
For example the tag along sort of the target user's preference, such as in step 103 recognized includes tag along sort 1 and divides Class label 2, and target user is greater than the preference to tag along sort 2 to the preference of tag along sort 1, such as target video are more In a film clips with the matched film clips of tag along sort 1 be film clips 1, and with the matched film clips of tag along sort 2 be film clips 2, then holding When the operation of the film clips of the two tag along sorts of the output of row step 104, film clips 2 can be exported first, are finished to film clips 2 Export film clips 2 again afterwards.Optionally, loop play film clips 1 and film clips 2 be can also continue to.
In this way, the embodiment of the present invention determines the multiple target in the preference according to each target classification label It, can be using the highest tag along sort of preference as target when the tag along sort of target user's preference described in tag along sort Preference in multiple target classification labels can also be greater than the one or more point of preset threshold by the tag along sort of user preference Class label as target user's preference tag along sort so that output video clip (film clips) tag along sort it is cleverer It is living.
Optionally, in one embodiment, before step 101, referring to Fig. 4, according to the method for the embodiment of the present invention also It may include: S601, multiple tag along sorts extracted to candidate video；S602, according to multiple tag along sorts of the candidate video, Multiple video clips are generated to the candidate video.
Wherein, the multiple video clip matches with the different classifications label in the multiple tag along sort respectively.
Wherein, the quantity of the candidate video can be multiple, and candidate video is selected from the video library of video platform, candidate video It can be all videos or partial video in video library.
For any one candidate video, the method for the embodiment of the present invention can be extracted according to the content of the candidate video The tag along sort of the candidate video, wherein the embodiment that the type of tag along sort is shown in Fig. 1 has been described in, here not It repeats again.In this way, each candidate video is each equipped with multiple tag along sorts relevant to its video content.
In addition, the method for the embodiment of the present invention can also extract video content and point of the candidate video from candidate video The video clip that class label matches, such as the tag along sort that extracts to candidate video include label 1 to label 5, then can be with Extract 5 groups of video clips from the candidate video, the video content of this 5 groups of video clips respectively with label 1 to 5 phase of label Match.
Wherein, each group of video clip, that is, content and the matched film clips of respective labels, wherein one group of video clip can wrap It includes from video clip made of the one or more original segments expansion extracted in candidate video.
So when executing step 104, then the target video can be searched in the candidate video first；Then, In multiple video clips of the target video, obtains tag along sort and the tag along sort of target user's preference matches Video clip.
Wherein, candidate video has been pre-configured with film clips described in the embodiment of the present invention, and each candidate video is preparatory Configured with multiple tag along sorts, the preconfigured multiple film clips of the candidate video respectively with multiple tag along sorts of the candidate video Match.Therefore, after receiving film clips playing request, mesh can be searched in candidate video (substantially multiple candidate videos) Mark video.Since target video is a kind of candidate video, which has been configured with multiple tag along sorts in advance, And it is configured with and distinguishes matched multiple film clips (video clip) with the multiple tag along sort, wherein above-mentioned multiple contingency table Each tag along sort in label has a matching film clips.So can from multiple film clips of the target video, Obtain the matched film clips of tag along sort of tag along sort and target user's preference.
In this way, the embodiment of the present invention, which passes through, extracts multiple tag along sorts to candidate video in advance, and candidate video is generated Multiple video clips (multiple film clips), multiple video clips match the different classifications label in above-mentioned multiple tag along sorts respectively. So after receiving film clips playing request, so that it may search target video from candidate video, and by the multiple of target video It is exported in video clip with the matched video clip of the tag along sort of user preference.It is matched by generating in advance to candidate video The film clips of different classifications label can quickly push the personalized piece for client after receiving film clips playing request Flower, improves film clips pushing efficiency, reduces system delay.
Optionally, in one embodiment, according to the multiple tag along sort, multiple views are generated to the candidate video When frequency segment, it can be realized by following three step:
The first step, for any one tag along sort in the multiple tag along sort, according to the tag along sort, to institute It states candidate video and carries out recognition of face or scene Recognition, the determining and matched multiple segments of the tag along sort；
Specifically, since a candidate video can have multiple tag along sorts, and the type of tag along sort can be with Including acting the leading role name, video subject, video type etc., therefore, for different types of tag along sort, it is being generated therewith When the video clip matched, it can also be handled with differentiation.
It for example, then can be according to protagonist name " chapter when tag along sort includes acting the leading role name (such as " chapter XX ") The face characteristic of XX " to carry out recognition of face to the candidate video, finds multiple segments comprising personage " chapter XX ".
For another example, when tag along sort includes video subject (such as " campus "), and/or, when video type (such as " love "), Multiple scenes (such as " school uniform ", " desk and chair ", " playground " etc.) relevant to " campus " can be then determined first, it is similar It can determine multiple scenes (such as " embracing ", " kissing ", " hand in hand " etc.) relevant to " love "；Then, to candidate video Scene Recognition is carried out, when tag along sort includes " campus ", then the scene identified here includes " school uniform ", " desk and chair ", " behaviour " etc., to determine multiple and " campus " tag match multiple segments in candidate video；Likewise, when the candidate regards When the tag along sort of frequency includes " love ", then the identification with " love " matched scene can be carried out to the candidate video, here The scene of identification includes " embracing ", " kissing ", " hand in hand " etc., to determine multiple and " love " label in candidate video The multiple segments matched.
Second step understands that algorithm carries out video frame expansion to the multiple segment according to video content, with from the candidate Multiple video clips with complete plot are extracted in video；
By tag along sort include " chapter X " " for be illustrated, the multiple segments recognized in the first step be include performer The video frame of the facial image of " chapter XX ", a segment may include a frame or a few frame images, for any one segment, It does not all have complete plot generally, only single a few frame images, and film clips it is to be expressed be candidate video concentration Therefore plot can understand algorithm to carry out video content understanding to candidate video, thus in candidate video according to video content In to obtained in the first step with " chapter XX " matched multiple segments carry out respectively video frame front and back expand, to obtain multiple Video clip with complete plot, such as be here 5 video clips.
It should be noted that any one video clip in multiple video clips with complete plot here can be with It is obtained by the segment expansion in the first step, can also be expanded by multiple segments and be obtained, the present invention does not limit this.
For the video frame extending method of multiple segments of other kinds of tag along sort, with the above-mentioned protagonist name enumerated Multiple segments video frame extending method it is similar, mutually refer to, which is not described herein again.
Third step records data according to the broadcasting of the multiple video clip, chooses one from the multiple video clip A video clip matches matched video clip as with the contingency table.
Continue to be illustrated so that tag along sort includes acting the leading role name " chapter XX " as an example, for what is extracted from candidate video With matched 5 video clips of performer " chapter XX ", they be all can be used as with " chapter XX " matched candidate film clips, then from When choosing one in 5 video clips as with tag along sort " chapter XX " matched film clips.In one embodiment, it can combine Broadcasting that all users generate in above-mentioned 5 video clips of candidate video record data (such as played data, F.F. number According to, rewind data etc., wherein played data includes but is not limited to broadcasting time, playing duration etc.), from above-mentioned 5 piece of video Section in choose one by user play the highest video clip of the frequency, as in the candidate video with the tag along sort " chapter The matched film clips of XX ".
And in another embodiment, it can be combined with all users in above-mentioned 5 video clips of the candidate video The above-mentioned broadcasting generated records data, chooses from above-mentioned 5 video clips and plays the higher multiple videos of the frequency by user Segment, such as 2 video clips, as in the candidate video with tag along sort " chapter XX " the matched film clips, i.e. two pieces Flower；Then, the multiple users for being delivered to preference categories label " chapter XX " that the two film clips are random；Finally, according to multiple User is to the click datas of the two film clips of the candidate video, to select the highest film clips of clicking rate from the two film clips. Using the highest film clips of the clicking rate as in the candidate video with tag along sort " chapter XX " matched film clips.
In this way, the embodiment of the present invention is by carrying out recognition of face or scene Recognition to candidate video, so as in candidate Determined in video with the matched multiple segments of tag along sort, and understand algorithm using video content to regard to multiple segments Frequency frame expands, so as to obtain plot completely multiple video clips, finally, the broadcasting based on multiple video clips records number According to, from multiple video clips choose a video clip as with the matched video clip of the tag along sort, i.e. film clips, Most attractive video clip can be found in candidate video to each tag along sort as the piece of the tag along sort Flower.
Optionally, in another embodiment, when the film clips playing request of step 101 is to trigger at list of videos interface When film clips playing request, then can then be realized by method shown in fig. 5 when executing step 102:
S301, identification trigger the target user of the film clips playing request；
In a kind of feasible embodiment, the video which can carry the login embodiment of the present invention is flat Therefore the user information (such as target user ID, user name etc.) of platform can identify which is by means of film clips playing request User triggers the film clips playing request.
S302 obtains the list of videos with list of videos interphase match；
Wherein, list of videos interface is the interface of the video item composition of multiple videos, here it is possible to obtain the list of videos The corresponding list of videos in interface, wherein the video item of each video in the list of videos may be displayed on list of videos interface.
S303 identifies target video belonging to film clips to be played in the list of videos according to the film clips playing request.
In a kind of feasible embodiment, which, which can also carry to be triggered, needs to play the mesh of film clips Therefore the information (such as video ID, video name etc.) of mark video can identify that client is asked by means of film clips playing request Seek the film clips for playing which video in above-mentioned list of videos.
In this way, the film clips playing request that the embodiment of the present invention is triggered by reception at list of videos interface, so as to root Target user is identified according to film clips playing request, and the corresponding list of videos in list of videos interface is identified according to film clips playing request In which video be user request play film clips video, in this way, user after retrieving video, can mention at list of videos interface For the film clips for meeting user preference of video each in list of videos, hit of each positive to user in list of videos is promoted Rate, and promoted film clips to positive conversion ratio；In addition, the video in the list of videos interface is not obtained from user's search, But the video that is pushed to user of system constitute list of videos interface when, user can be by any in list of videos interface One video item makes requests the operation for playing film clips, and the method for the embodiment of the present invention can be to provide for the client of the user Meet the film clips of the video item of the user preference, promotes video to the hit rate of user.
Optionally, in one embodiment, when the film clips playing request of step 101 is the piece triggered at list of videos interface When flower playing request, after step 105, referring to Fig. 6, can also include: according to the method for the embodiment of the present invention
S401 receives film clips switching request；
Wherein, after list of videos interface is triggered to the film clips playing request of target video, and the target video is exported Film clips after, user can also the target video film clips broadcast interface (i.e. broadcasting step 105 video clip boundary Face) triggering film clips switching request.
The triggering mode of the film clips switching request includes but is not limited to click upper key, down key, wherein upper key, down key can be with It is the physical button of terminal device, the virtual key being also possible in the film clips broadcast interface of target video.In addition, film clips switch The triggering mode of request can also include upper sliding operation, the downslide of finger in the film clips broadcast interface progress finger of target video Operation etc..
S402 identifies next target view belonging to film clips to be played in list of videos according to the film clips switching request Frequently；
Wherein, list of videos is the list of videos with list of videos interphase match.
Such as the list of videos interface is the list of videos interface that video recommended to the user is constituted.
Wherein, the video in the list of videos can sort according to preset condition, which includes but is not limited to heat Degree from high to low, the vertical sequence of the initial of video name etc., which is not described herein again.
Such as triggering the triggering mode of the film clips switching request is upper screen sliding curtain, then mesh can will be arranged in list of videos A nearest video before mark video is determined as next target video of film clips to be played.Wherein, film clips switching request The parameter for indicating the ordinal relation between next target video and target video can be carried, such as next target video is A nearest video before being arranged in target video in list of videos.
Similarly, such as the triggering mode of the film clips switching request is triggered as downslide screen, then can will arrange in list of videos It is listed in next target video that the nearest video after target video is determined as film clips to be played.Wherein, film clips are cut The parameter for indicating the ordinal relation between next target video and target video, such as next target can be carried by changing request Video is the nearest video being arranged in after target video in list of videos.
S403 identifies the contingency table of target user's preference described in multiple tag along sorts of next target video Label；
Wherein, the specific implementation of this step and the step 103 of above-described embodiment and embodiment class relevant with step 103 Seemingly, difference is only in that target video replaces with next target video, and principle is consistent, therefore reference mutually, here not It repeats again.
S404 obtains the matched piece of video of tag along sort in next target video with target user's preference Section；
Wherein, the specific implementation of this step and the step 104 of above-described embodiment and embodiment class relevant with step 104 Seemingly, difference is only in that target video replaces with next target video, and principle is consistent, therefore reference mutually, here not It repeats again.
S405 exports the video clip of next target video.
Wherein, the specific implementation of this step and the step 105 of above-described embodiment and embodiment class relevant with step 105 Seemingly, difference is only in that target video replaces with next target video, and principle is consistent, therefore reference mutually, here not It repeats again.
In this way, the embodiment of the present invention is by exporting video clip (i.e. film clips) to the target video in list of videos interface Later, user can also trigger film clips switching request, so as to which the film clips of broadcasting are quickly switched to list of videos interface The film clips of other videos in corresponding list of videos, and for the piece Huadu of each video played be best suitable in the video User watches the video clip of video preference, improves conversion ratio of the video to the hit rate of user and film clips to positive.
Referring to Fig. 7, a kind of work flow diagram of audio/video player system embodiment of the invention is shown.
Audio/video player system may include that film clips generate subsystem, film clips recommend subsystem, (application is answered APP With program) front end.Wherein, the front end APP can be located at terminal, after film clips generation subsystem and film clips recommend subsystem that can be located at Hold server.
Film clips generate subsystem, are mainly used for generating film clips to the candidate video of storage.
Film clips recommend subsystem, are mainly used for selecting to launch to the front end APP from the film clips that film clips generate subsystem offer Film clips.
The front end APP is mainly used for receiving film clips playing request and plays the film clips that film clips recommend subsystem to launch.
Specifically:
Firstly, film clips generate subsystem to any one candidate video in the candidate video of storage, tag along sort is identified, So that each candidate video has multiple tag along sorts；
Then, film clips generate subsystem for any one candidate video of storage, generate and match the candidate video not With multiple film clips of tag along sort；
In addition, film clips recommendation subsystem can pre-generate the tag along sort of each user preference；
Specifically, each view that film clips recommend subsystem that can record data according to the video tour of user and browse The tag along sort of frequency, the preference of the tag along sort of Lai Shengcheng user preference and each tag along sort.
Then, the front end APP APP open after, can present list of videos interface (such as recommend video clip, packet Include the video item of multiple videos of recommendation)；
Then, APP front end receiver is triggered at the list of videos interface to target user and is asked to the film clips broadcasting of target video It asks；
Then, the front end APP can recommend film clips of the subsystem request corresponding to the target video to film clips；
Then, film clips recommend subsystem can be according to the tag along sort and film clips of pre-generated each user preference Multiple film clips of any one candidate video in subsystem are generated, to obtain the classification with target user's preference of target video The film clips of tag match, and the film clips are launched to the front end APP；
Then, the front end APP can play the film clips of the target video for the target user；
Then, user can cut the target video for playing film clips by the upper and lower key operation to the front end APP It changes, so that target video is switched to next video in the corresponding list of videos in list of videos interface, then proceedes to recycle Above-mentioned process plays the film clips for target user of next video.
In this way, when the list of videos interface is the list of videos interface that each video that system home page is recommended is constituted, After the front end APP has played film clips, that is, enter film clips play mode after, user can by press the front end APP upper down key come The film clips of broadcasting are switched to the film clips of other films in list of videos.That is, user can lead in film clips play mode Cross down key check homepage recommend all films film clips.
It optionally, can be by the sound of the front end APP when the front end APP plays the film clips for the target video of target user Sound is set as mute, so that the broadcasting for reducing film clips when user needs to listen to sound, can pass through interference caused by user security risk The volume key of the front end APP is operable to carry out volume adjustment to sound.
Optionally, during playing film clips, user can also be operated by the acknowledgement key to the front end APP, be come Film clips play mode is switched to the played in full screen mode to target video, in this way, the front end APP can play target video.
Optionally, under film clips play mode, after the Menu key of the front end APP is operated, system is without any feedback, phase Instead, user can by operate the front end APP return key, then the front end APP of the embodiment of the present invention can by current interface from Film clips broadcast interface switches back into the interface before film clips play, for example, above-mentioned list of videos interface.
Optionally, under film clips play mode, user can also be operated by the left and right press key to the front end APP, that Jitter effect is presented in the film clips that the front end APP can control broadcasting.
Optionally, under film clips play mode, after user is not intended to check film clips again, the master of the front end APP can be triggered Page key, then current interface can be switched to system homepage from film clips broadcast interface by the front end APP of the embodiment of the present invention Interface.
Optionally, for each key of the above-mentioned front end APP enumerated, can be entity on the remote control equipment of terminal by Key is also possible to the virtual key of the front end APP.
Different classifications label of the audio/video player system of the embodiment of the present invention based on video, generates different film clips, and base Most probable attracts the segment of the user to play out in the viewing preference selection target video of user, compared in the related technology The scheme of the films recommended information such as identical title and poster figure is provided to each terminal, and the embodiment of the present invention is by difference The front end APP personalized push plays the different film clips of target video, and the tag along sort of the film clips pushed is seen based on user Shadow preference be calculated with its highest label of viewing preference degree of association so that be pushed to user be this film most probable inhale Draw the video clip of the user, so as to further promote the conversion ratio from film clips to positive, can additionally help video Platform excavates attraction of the video on different elements.
It should be noted that for simple description, therefore, it is stated as a series of action groups for embodiment of the method It closes, but those skilled in the art should understand that, embodiment of that present invention are not limited by the describe sequence of actions, because according to According to the embodiment of the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art also should Know, the embodiments described in the specification are all preferred embodiments, and the related movement not necessarily present invention is implemented Necessary to example.
It is corresponding with method provided by the embodiments of the present invention, referring to Fig. 8, show a kind of video playing of the present invention The structural block diagram of Installation practice, can specifically include following module:
First receiving module 61, for receiving film clips playing request；
First identification module 62, for identifying target user and film clips to be played institute according to the film clips playing request The target video of category；
Second identification module 63, for identification target user's preference described in multiple tag along sorts of the target video Tag along sort；
First obtains module 64, matches for obtaining in the target video with the tag along sort of target user's preference Video clip；
Output module 65, for exporting the video clip.
Optionally, described device further include:
Determining module determines what the target user had browsed for recording data according to the video tour of target user Each video；
Second obtains module, for obtaining the tag along sort of each video；
Statistical module counts institute for recording the tag along sort of data and each video according to the video tour State multiple candidate classification labels of target user's preference and the preference of each candidate classification label；
Second identification module 63 includes:
First acquisition submodule, in multiple tag along sorts for obtaining the target video with target user's preference Candidate classification tag match multiple target classification labels and each target classification label preference；
First identification submodule identifies the multiple target for the preference according to each target classification label The tag along sort of target user's preference described in tag along sort.
Optionally, the first identification submodule includes:
First recognition unit, for using the highest target classification label of preference in the multiple target classification label as The tag along sort of target user's preference；
Second recognition unit, for preference in the multiple target classification label to be greater than to the target classification of preset threshold Tag along sort of the label as target user's preference.
Optionally, described device further include:
Extraction module, for extracting multiple tag along sorts to candidate video；
Generation module, for generating multiple video clips to the candidate video according to the multiple tag along sort, In, the multiple video clip matches with the different classifications label in the multiple tag along sort respectively；
Described first, which obtains module 64, includes:
Submodule is searched, for searching the target video in the candidate video；
Second acquisition submodule, in multiple video clips of the target video, obtain tag along sort with it is described The matched video clip of the tag along sort of target user's preference.
Optionally, the generation module includes:
Second identification submodule, any one tag along sort for being directed in the multiple tag along sort, according to described Tag along sort carries out recognition of face or scene Recognition to the candidate video, determines and the tag along sort matched multiple Section；
Expand submodule, for according to video content understand algorithm to the multiple segment carry out video frame expansion, with from Multiple video clips with complete plot are extracted in the candidate video；
Submodule is chosen, for recording data according to the broadcasting of the multiple video clip, from the multiple video clip One video clip of middle selection matches matched video clip as with the contingency table.
Optionally, first receiving module 61 includes:
Receiving submodule, for receiving the film clips playing request in the triggering of list of videos interface；
First identification module 62 includes:
Third identifies submodule, triggers the target user of the film clips playing request for identification；
Third acquisition submodule, for obtaining and the list of videos of list of videos interphase match；
4th identification submodule, for identifying film clips to be played in the list of videos according to the film clips playing request Affiliated target video.
Optionally, it is described first receive 61 pieces of mould include:
Receiving submodule, for receiving the film clips playing request in the triggering of list of videos interface；
Described device further include:
Second receiving module, for receiving film clips switching request；
First identification module 62 is also used to be identified in the list of videos according to the film clips switching request wait broadcast Affiliated next target video is spent in film releasing；
Second identification module 63 is also used to identify mesh described in multiple tag along sorts of next target video Mark the tag along sort of user preference；
Described first obtains module 64, for obtaining point in next target video with target user's preference The matched video clip of class label；
The output module 65 is also used to export the video clip of next target video.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple Place illustrates referring to the part of embodiment of the method.
The embodiment of the invention also provides a kind of computer readable storage medium, deposited on the computer readable storage medium Computer program is contained, the video as described in any one above-mentioned embodiment is realized when the computer program is executed by processor Step in playback method.
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with The difference of other embodiments, the same or similar parts between the embodiments can be referred to each other.
It should be understood by those skilled in the art that, the embodiment of the embodiment of the present invention can provide as method, apparatus or calculate Machine program product.Therefore, the embodiment of the present invention can be used complete hardware embodiment, complete software embodiment or combine software and The form of the embodiment of hardware aspect.Moreover, the embodiment of the present invention can be used one or more wherein include computer can With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code The form of the computer program product of implementation.
The embodiment of the present invention be referring to according to the method for the embodiment of the present invention, terminal device (system) and computer program The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions In each flow and/or block and flowchart and/or the block diagram in process and/or box combination.It can provide these Computer program instructions are set to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals Standby processor is to generate a machine, so that being held by the processor of computer or other programmable data processing terminal devices Capable instruction generates for realizing in one or more flows of the flowchart and/or one or more blocks of the block diagram The device of specified function.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing terminal devices In computer-readable memory operate in a specific manner, so that instruction stored in the computer readable memory generates packet The manufacture of command device is included, which realizes in one side of one or more flows of the flowchart and/or block diagram The function of being specified in frame or multiple boxes.
These computer program instructions can also be loaded into computer or other programmable data processing terminal devices, so that Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus The instruction executed on computer or other programmable terminal equipments is provided for realizing in one or more flows of the flowchart And/or in one or more blocks of the block diagram specify function the step of.
Although the preferred embodiment of the embodiment of the present invention has been described, once a person skilled in the art knows bases This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as Including preferred embodiment and fall into all change and modification of range of embodiment of the invention.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap Those elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, article Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device for including the element.
It above can to a kind of video broadcasting method provided by the present invention, a kind of video play device and a kind of computer Storage medium is read, is described in detail, specific case used herein carries out the principle of the present invention and embodiment It illustrates, the above description of the embodiment is only used to help understand the method for the present invention and its core ideas；Meanwhile for this field Those skilled in the art, according to the thought of the present invention, there will be changes in the specific implementation manner and application range, to sum up Described, the contents of this specification are not to be construed as limiting the invention.

Claims (15)

1. a kind of video broadcasting method characterized by comprising
Receive film clips playing request；
According to the film clips playing request, target video belonging to target user and film clips to be played is identified；
Identify the tag along sort of target user's preference described in multiple tag along sorts of the target video；
Obtain the matched video clip of tag along sort in the target video with target user's preference；
Export the video clip.
2. the method according to claim 1, wherein
Before the reception film clips playing request, the method also includes:
Data are recorded according to the video tour of target user, determine each video that the target user has browsed；
Obtain the tag along sort of each video；
The tag along sort that data and each video are recorded according to the video tour, counts the more of target user's preference The preference of a candidate classification label and each candidate classification label；
The tag along sort of target user's preference described in multiple tag along sorts of the identification target video, comprising:
It obtains more with the candidate classification tag match of target user's preference in multiple tag along sorts of the target video The preference of a target classification label and each target classification label；
According to the preference of each target classification label, identify that target user described in the multiple target classification label is inclined Good tag along sort.
3. according to the method described in claim 2, it is characterized in that, the preference according to each target classification label Degree, identifies the tag along sort of target user's preference described in the multiple target classification label, comprising:
Using the highest target classification label of preference in the multiple target classification label as point of target user's preference Class label；
Or,
Preference in the multiple target classification label is greater than the target classification label of preset threshold as the target user The tag along sort of preference.
4. the method according to claim 1, wherein the method is also before the reception film clips playing request Include:
Multiple tag along sorts are extracted to candidate video；
According to the multiple tag along sort, multiple video clips are generated to the candidate video, wherein the multiple video clip Match respectively with the different classifications label in the multiple tag along sort；
The matched video clip of tag along sort obtained in the target video with target user's preference, comprising:
The target video is searched in the candidate video；
In multiple video clips of the target video, the tag along sort of tag along sort and target user's preference is obtained The video clip matched.
5. according to the method described in claim 4, it is characterized in that, described according to the multiple tag along sort, to the candidate Video generates multiple video clips, comprising:
For any one tag along sort in the multiple tag along sort, according to the tag along sort, to the candidate video Carry out recognition of face or scene Recognition, the determining and matched multiple segments of the tag along sort；
Understand that algorithm carries out video frame expansion to the multiple segment according to video content, to extract tool from the candidate video There are multiple video clips of complete plot；
Data are recorded according to the broadcasting of the multiple video clip, a video clip is chosen from the multiple video clip and is made To match matched video clip with the contingency table.
6. the method according to claim 1, wherein the reception film clips playing request, comprising: receive in video The film clips playing request of list interface triggering；
It is described according to the film clips playing request, identify target video belonging to target user and film clips to be played, comprising:
Identification triggers the target user of the film clips playing request；
Obtain the list of videos with list of videos interphase match；
According to the film clips playing request, target video belonging to film clips to be played in the list of videos is identified.
7. the method according to claim 1, wherein the reception film clips playing request, comprising: receive in video The film clips playing request of list interface triggering；
After the output video clip, the method also includes:
Receive film clips switching request；
According to the film clips switching request, next target video belonging to film clips to be played in the list of videos is identified；
Identify the tag along sort of target user's preference described in multiple tag along sorts of next target video；
Obtain the matched video clip of tag along sort in next target video with target user's preference；
Export the video clip of next target video.
8. a kind of video play device characterized by comprising
First receiving module, for receiving film clips playing request；
First identification module, for identifying mesh belonging to target user and film clips to be played according to the film clips playing request Mark video；
Second identification module, for identification contingency table of target user's preference described in multiple tag along sorts of the target video Label；
First obtains module, for obtaining the matched video of tag along sort in the target video with target user's preference Segment；
Output module, for exporting the video clip.
9. device according to claim 8, which is characterized in that described device further include:
Determining module determines that the target user has browsed for recording data according to the video tour of target user Video；
Second obtains module, for obtaining the tag along sort of each video；
Statistical module counts the mesh for recording the tag along sort of data and each video according to the video tour Mark multiple candidate classification labels of user preference and the preference of each candidate classification label；
Second identification module includes:
First acquisition submodule, the time in multiple tag along sorts for obtaining the target video with target user's preference Select the preference of the matched multiple target classification labels of tag along sort and each target classification label；
First identification submodule identifies the multiple target classification for the preference according to each target classification label The tag along sort of target user's preference described in label.
10. device according to claim 9, which is characterized in that described first identifies that submodule includes:
First recognition unit is used for the highest target classification label of preference in the multiple target classification label as described in The tag along sort of target user's preference；
Second recognition unit, for preference in the multiple target classification label to be greater than to the target classification label of preset threshold Tag along sort as target user's preference.
11. device according to claim 8, which is characterized in that described device further include:
Extraction module, for extracting multiple tag along sorts to candidate video；
Generation module, for generating multiple video clips to the candidate video, wherein institute according to the multiple tag along sort Multiple video clips are stated to match with the different classifications label in the multiple tag along sort respectively；
Described first, which obtains module, includes:
Submodule is searched, for searching the target video in the candidate video；
Second acquisition submodule, for obtaining tag along sort and the target in multiple video clips of the target video The matched video clip of the tag along sort of user preference.
12. device according to claim 11, which is characterized in that the generation module includes:
Second identification submodule, any one tag along sort for being directed in the multiple tag along sort, according to the classification Label carries out recognition of face or scene Recognition, the determining and matched multiple segments of the tag along sort to the candidate video；
Expand submodule, for understanding that algorithm carries out video frame expansion to the multiple segment according to video content, with from described Multiple video clips with complete plot are extracted in candidate video；
Submodule is chosen, for recording data according to the broadcasting of the multiple video clip, is selected from the multiple video clip A video clip is taken to match matched video clip as with the contingency table.
13. device according to claim 8, which is characterized in that
First receiving module includes:
Receiving submodule, for receiving the film clips playing request in the triggering of list of videos interface；
First identification module includes:
Third identifies submodule, triggers the target user of the film clips playing request for identification；
Third acquisition submodule, for obtaining and the list of videos of list of videos interphase match；
4th identification submodule identifies in the list of videos belonging to film clips to be played for according to the film clips playing request Target video.
14. device according to claim 8, which is characterized in that
First receiving module includes:
Receiving submodule, for receiving the film clips playing request in the triggering of list of videos interface；
Described device further include:
Second receiving module, for receiving film clips switching request；
First identification module is also used to identify film clips to be played in the list of videos according to the film clips switching request Affiliated next target video；
Second identification module is also used to identify target user described in multiple tag along sorts of next target video The tag along sort of preference；
Described first obtains module, for obtaining the tag along sort in next target video with target user's preference Matched video clip；
The output module is also used to export the video clip of next target video.
15. a kind of computer readable storage medium, which is characterized in that be stored with computer on the computer readable storage medium Program realizes the video broadcasting method as described in any one of claims 1 to 7 when the computer program is executed by processor In step.
CN201811297447.4A 2018-11-01 2018-11-01 Video broadcasting method, device, computer readable storage medium Pending CN109587568A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811297447.4A CN109587568A (en) 2018-11-01 2018-11-01 Video broadcasting method, device, computer readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811297447.4A CN109587568A (en) 2018-11-01 2018-11-01 Video broadcasting method, device, computer readable storage medium

Publications (1)

Publication Number Publication Date
CN109587568A true CN109587568A (en) 2019-04-05

Family

ID=65921107

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811297447.4A Pending CN109587568A (en) 2018-11-01 2018-11-01 Video broadcasting method, device, computer readable storage medium

Country Status (1)

Country Link
CN (1) CN109587568A (en)

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110225398A (en) * 2019-05-28 2019-09-10 腾讯科技（深圳）有限公司 Multimedia object playback method, device and equipment and computer storage medium
CN110381339A (en) * 2019-08-07 2019-10-25 腾讯科技（深圳）有限公司 Picture transmission method and device
CN110401873A (en) * 2019-06-17 2019-11-01 北京奇艺世纪科技有限公司 Video clipping method, device, electronic equipment and computer-readable medium
CN111258484A (en) * 2020-02-12 2020-06-09 北京奇艺世纪科技有限公司 Video playing method and device, electronic equipment and storage medium
CN111324733A (en) * 2020-02-07 2020-06-23 北京创鑫旅程网络技术有限公司 Content recommendation method, device, equipment and storage medium
CN111432288A (en) * 2020-03-31 2020-07-17 北京达佳互联信息技术有限公司 Video playing method and device, electronic equipment and storage medium
CN111490929A (en) * 2020-03-27 2020-08-04 威比网络科技(上海)有限公司 Video clip pushing method and device, electronic equipment and storage medium
CN111694986A (en) * 2020-06-12 2020-09-22 北京奇艺世纪科技有限公司 Video recommendation method and device, electronic equipment and storage medium
CN111782873A (en) * 2020-06-29 2020-10-16 掌阅科技股份有限公司 Book video-based book recommendation method, electronic device and storage medium
CN111818370A (en) * 2020-06-30 2020-10-23 腾讯科技（深圳）有限公司 Information recommendation method and device, electronic equipment and computer-readable storage medium
CN112019920A (en) * 2019-05-31 2020-12-01 腾讯科技（深圳）有限公司 Video recommendation method, device and system and computer equipment
CN112565838A (en) * 2020-11-12 2021-03-26 深圳市易平方网络科技有限公司 Television-based startup processing method, device, terminal and medium
CN113132753A (en) * 2019-12-30 2021-07-16 阿里巴巴集团控股有限公司 Data processing method and device and video cover generation method and device
CN113259733A (en) * 2020-02-12 2021-08-13 聚好看科技股份有限公司 Display device
CN113301394A (en) * 2021-04-30 2021-08-24 当趣网络科技(杭州)有限公司 Voice control method combined with user grade
CN113645510A (en) * 2020-05-11 2021-11-12 北京达佳互联信息技术有限公司 Video playing method and device, electronic equipment and storage medium
CN114205653A (en) * 2021-12-06 2022-03-18 广东飞翔云计算有限公司 Big data-based preview video pushing method, device, equipment and storage medium
CN114640888A (en) * 2022-03-09 2022-06-17 深圳市雷鸟网络传媒有限公司 Video playing method and device, computer equipment and computer readable storage medium
CN115022720A (en) * 2022-05-20 2022-09-06 北京字跳网络技术有限公司 Video processing method, device, equipment and storage medium
CN115314757A (en) * 2022-08-05 2022-11-08 聚好看科技股份有限公司 Display device and guide window display method
CN116992073A (en) * 2023-09-28 2023-11-03 北京小糖科技有限责任公司 Video clip ordering method, device, equipment and storage medium
CN117014687A (en) * 2023-09-28 2023-11-07 北京小糖科技有限责任公司 Video positioning playing method and device based on user playing portrait

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102724550A (en) * 2012-06-12 2012-10-10 北京奇艺世纪科技有限公司 Video playback method and device
US20140101551A1 (en) * 2012-10-05 2014-04-10 Google Inc. Stitching videos into an aggregate video
CN105979380A (en) * 2016-03-31 2016-09-28 乐视控股（北京）有限公司 Test broadcasting method and device for multimedia contents on demand
CN107105318A (en) * 2017-03-21 2017-08-29 华为技术有限公司 A kind of video hotspot fragment extracting method, user equipment and server
CN107291930A (en) * 2017-06-29 2017-10-24 环球智达科技（北京）有限公司 The computational methods of weight number
CN108307229A (en) * 2018-02-02 2018-07-20 新华智云科技有限公司 A kind of processing method and equipment of video-audio data
CN108460131A (en) * 2018-03-02 2018-08-28 北京奇艺世纪科技有限公司 A kind of tag along sort processing method and processing device

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102724550A (en) * 2012-06-12 2012-10-10 北京奇艺世纪科技有限公司 Video playback method and device
US20140101551A1 (en) * 2012-10-05 2014-04-10 Google Inc. Stitching videos into an aggregate video
CN105979380A (en) * 2016-03-31 2016-09-28 乐视控股（北京）有限公司 Test broadcasting method and device for multimedia contents on demand
CN107105318A (en) * 2017-03-21 2017-08-29 华为技术有限公司 A kind of video hotspot fragment extracting method, user equipment and server
CN107291930A (en) * 2017-06-29 2017-10-24 环球智达科技（北京）有限公司 The computational methods of weight number
CN108307229A (en) * 2018-02-02 2018-07-20 新华智云科技有限公司 A kind of processing method and equipment of video-audio data
CN108460131A (en) * 2018-03-02 2018-08-28 北京奇艺世纪科技有限公司 A kind of tag along sort processing method and processing device

Cited By (33)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110225398A (en) * 2019-05-28 2019-09-10 腾讯科技（深圳）有限公司 Multimedia object playback method, device and equipment and computer storage medium
CN110225398B (en) * 2019-05-28 2022-08-02 腾讯科技（深圳）有限公司 Multimedia object playing method, device and equipment and computer storage medium
CN112019920A (en) * 2019-05-31 2020-12-01 腾讯科技（深圳）有限公司 Video recommendation method, device and system and computer equipment
CN110401873A (en) * 2019-06-17 2019-11-01 北京奇艺世纪科技有限公司 Video clipping method, device, electronic equipment and computer-readable medium
CN110381339A (en) * 2019-08-07 2019-10-25 腾讯科技（深圳）有限公司 Picture transmission method and device
CN113132753A (en) * 2019-12-30 2021-07-16 阿里巴巴集团控股有限公司 Data processing method and device and video cover generation method and device
CN111324733A (en) * 2020-02-07 2020-06-23 北京创鑫旅程网络技术有限公司 Content recommendation method, device, equipment and storage medium
CN111258484A (en) * 2020-02-12 2020-06-09 北京奇艺世纪科技有限公司 Video playing method and device, electronic equipment and storage medium
CN113259733B (en) * 2020-02-12 2022-06-14 聚好看科技股份有限公司 Display device
CN113259733A (en) * 2020-02-12 2021-08-13 聚好看科技股份有限公司 Display device
CN111490929A (en) * 2020-03-27 2020-08-04 威比网络科技(上海)有限公司 Video clip pushing method and device, electronic equipment and storage medium
CN111490929B (en) * 2020-03-27 2022-07-15 深圳市企鹅网络科技有限公司 Video clip pushing method and device, electronic equipment and storage medium
CN111432288A (en) * 2020-03-31 2020-07-17 北京达佳互联信息技术有限公司 Video playing method and device, electronic equipment and storage medium
CN113645510B (en) * 2020-05-11 2023-03-21 北京达佳互联信息技术有限公司 Video playing method and device, electronic equipment and storage medium
CN113645510A (en) * 2020-05-11 2021-11-12 北京达佳互联信息技术有限公司 Video playing method and device, electronic equipment and storage medium
CN111694986A (en) * 2020-06-12 2020-09-22 北京奇艺世纪科技有限公司 Video recommendation method and device, electronic equipment and storage medium
CN111782873A (en) * 2020-06-29 2020-10-16 掌阅科技股份有限公司 Book video-based book recommendation method, electronic device and storage medium
CN111782873B (en) * 2020-06-29 2023-09-08 掌阅科技股份有限公司 Book recommendation method based on book video, electronic equipment and storage medium
CN111818370B (en) * 2020-06-30 2022-03-11 腾讯科技（深圳）有限公司 Information recommendation method and device, electronic equipment and computer-readable storage medium
CN111818370A (en) * 2020-06-30 2020-10-23 腾讯科技（深圳）有限公司 Information recommendation method and device, electronic equipment and computer-readable storage medium
CN112565838A (en) * 2020-11-12 2021-03-26 深圳市易平方网络科技有限公司 Television-based startup processing method, device, terminal and medium
CN113301394B (en) * 2021-04-30 2023-07-11 当趣网络科技(杭州)有限公司 Voice control method combined with user grade
CN113301394A (en) * 2021-04-30 2021-08-24 当趣网络科技(杭州)有限公司 Voice control method combined with user grade
CN114205653A (en) * 2021-12-06 2022-03-18 广东飞翔云计算有限公司 Big data-based preview video pushing method, device, equipment and storage medium
CN114640888A (en) * 2022-03-09 2022-06-17 深圳市雷鸟网络传媒有限公司 Video playing method and device, computer equipment and computer readable storage medium
CN115022720A (en) * 2022-05-20 2022-09-06 北京字跳网络技术有限公司 Video processing method, device, equipment and storage medium
CN115022720B (en) * 2022-05-20 2023-12-12 北京字跳网络技术有限公司 Video processing method, device, equipment and storage medium
CN115314757A (en) * 2022-08-05 2022-11-08 聚好看科技股份有限公司 Display device and guide window display method
CN115314757B (en) * 2022-08-05 2023-10-24 聚好看科技股份有限公司 Display device and guide window display method
CN116992073A (en) * 2023-09-28 2023-11-03 北京小糖科技有限责任公司 Video clip ordering method, device, equipment and storage medium
CN117014687A (en) * 2023-09-28 2023-11-07 北京小糖科技有限责任公司 Video positioning playing method and device based on user playing portrait
CN117014687B (en) * 2023-09-28 2023-12-08 北京小糖科技有限责任公司 Video positioning playing method and device based on user playing portrait
CN116992073B (en) * 2023-09-28 2023-12-08 北京小糖科技有限责任公司 Video clip ordering method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN109587568A (en) Video broadcasting method, device, computer readable storage medium
CN105979398B (en) Use the system and method for playlist
US11636881B2 (en) User interface for video content
CN106686404B (en) Video analysis platform, matching method, and method and system for accurately delivering advertisements
US10009664B2 (en) Providing extrinsic data for video content
US8763041B2 (en) Enhancing video content with extrinsic data
EP1026887B1 (en) Audiovisual information management system and method
JP3810268B2 (en) Audio visual system
JP4107811B2 (en) How to use Audio Visual System
RU2577189C2 (en) Profile based content retrieval for recommender systems
CN105230035B (en) The processing of the social media of time shift multimedia content for selection
US20150172787A1 (en) Customized movie trailers
US20030123850A1 (en) Intelligent news video browsing system and method thereof
US20010020981A1 (en) Method of generating synthetic key frame and video browsing system using the same
KR20070086579A (en) Recording and playback of video clips based on audio selections
CN110019933A (en) Video data handling procedure, device, electronic equipment and storage medium
JP5868978B2 (en) Method and apparatus for providing community-based metadata
CN109766457A (en) A kind of media content search method, apparatus and storage medium
US20200221182A1 (en) Video Pushing Method, Apparatus, Device and Storage Medium
US20180048937A1 (en) Enhancing video content with personalized extrinsic data
CN103180838A (en) Method to display additional information on screen
JP2003169312A (en) Electronic program table supply system, electronic program table supply method, program thereof, and record medium recording the program
CN112533032B (en) Video data processing method and device and storage medium
CN114357199A (en) Server, creation method of auditorium and search method
Kolekar Transmission of highlight clips of a live cricket match on mobile phones

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20190405

RJ01 Rejection of invention patent application after publication