CN109769128A - Video recommendation method, video recommendations device and computer readable storage medium - Google Patents
Video recommendation method, video recommendations device and computer readable storage medium Download PDFInfo
- Publication number
- CN109769128A CN109769128A CN201811588951.XA CN201811588951A CN109769128A CN 109769128 A CN109769128 A CN 109769128A CN 201811588951 A CN201811588951 A CN 201811588951A CN 109769128 A CN109769128 A CN 109769128A
- Authority
- CN
- China
- Prior art keywords
- video
- candidate
- live
- live streaming
- user
- 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.)
- Granted
Links
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application is about a kind of video recommendation method, video recommendations device and computer readable storage medium.The video recommendation method includes: the history sharing data for obtaining user；Candidate video set and candidate live streaming set are generated according to the history sharing data；All candidate videos in the candidate video set are ranked up；And it will recommend after the candidate video set and the candidate live streaming set fusion after sequence as recommendation.The video recommendation method is recommended by incorporating live streaming in short video recommendations, enhances user to the viewing experience of recommendation and the demand of content variety, more accurately and comprehensively can provide recommendation video for user.
Description
Technical field
The application belongs to computer software application field more particularly to video recommendation method and video recommendations device.
Background technique
" sharing function " of APP plays highly important role in the propagation conversion of product.It is most in the market
The function that APP has third party to share allows user actively to share the content in APP flat to social activity by the flow of social product
On platform, allows more users to watch the content in APP, user is facilitated to watch.In general, in order to more to user
Content selection, can as often as possible recommended user may be in interested short-sighted frequency on the short-sighted frequency display interface shared away
Hold.
But most recommender system is all the recommendation carried out mainly for single category information at present.To share page
For short-sighted frequency is recommended, it can find that user likes degree (such as click, point to short-sighted frequency by the historical behavior data of user
Praise, comment on or share), and these hobbies are measured and given a mark, according to different user to the attitude of identical short-sighted frequency and partially
Good degree calculates the relationship between user, and the recommendation of similar short-sighted frequency is then carried out between the user for having identical hobby.
The inventors discovered that the pattern of the short video sharing page content of this recommended method selection is relatively single, it is not easy to
Attract user, user experience is poor.
Summary of the invention
To overcome the problems in correlation technique, the application discloses a kind of video recommendation method and video recommendations device,
Live video is being broadcast by merging in short video sharing, while being recommended, the recommendation diversity of short-sighted frequency is improved, is being promoted and is used
Family experience.
According to the embodiment of the present application in a first aspect, providing a kind of video recommendation method, comprising:
Obtain the history sharing data of user；
Candidate video set and candidate live streaming set are generated according to the history sharing data；
All candidate videos in the candidate video set are ranked up；And
It will be pushed away after the candidate video set and the candidate live streaming set fusion after sequence as recommendation
It recommends.
Optionally, the video recommendation method further include: the recommendation is sent to user terminal and is shown.
Optionally, the history sharing data includes the concern that history sharing contents and the history sharing contents obtain
Degree.
Optionally, the history sharing contents include history sharing video frequency and are broadcasting live video, according to default rule
The candidate video set and the time are separately added into broadcasting live video by the part history sharing video frequency and part are described
Choosing live streaming set.
Optionally, the video recommendation method further include: live video is being broadcast to all in the candidate live streaming set
It is audited, will be removed broadcasting live video described in the audit fails.
Optionally, be arranged audit time, monitoring every described in the audit state for broadcasting live video, if in the audit
The interior instruction for not receiving audit and passing through, then deletion is described from the candidate live streaming set is broadcasting live video.
Optionally, generating candidate live streaming set according to the history sharing data includes:
It is all in the live streaming ID for broadcasting live video and affiliated main broadcaster ID to inquire current time；
Live video is being broadcast described in each, is counting its attention rate；And
The live video addition candidate live streaming set will be being broadcast described in the higher part of the attention rate.
Optionally, candidate live streaming set is generated according to the history sharing data further include:
Obtain the good friend ID that there is similarity relation with the main broadcaster ID；
The live video addition candidate live streaming set is being broadcast into the part of the good friend ID.
Optionally, recommendation will be used as after the candidate video set and the candidate live streaming set fusion after sequence
Carrying out recommendation includes:
Obtain list of videos of all candidate videos after sequence；
It is ranked up to described broadcasting live video, obtains live streaming list；
The live streaming list is incorporated in the list of videos and is recommended as the recommendation.
According to a second aspect of the embodiments of the present invention, a kind of video recommendations device is provided, comprising:
Module is obtained, for obtaining the history sharing data of user；
Candidate block, for generating candidate video set and candidate live streaming set according to the history sharing data；
Sorting module, for being ranked up to all candidate videos in the candidate video set；And recommending module,
For will recommend after the candidate video set and the candidate live streaming set fusion after sequence as recommendation.
Optionally, the history sharing data includes the concern that history sharing contents and the history sharing contents obtain
Degree.
Optionally, the history sharing contents include history sharing video frequency and are broadcasting live video, select and go through described in part
History sharing video frequency and part is described is separately added into the candidate video set and the candidate live streaming set broadcasting live video.
Optionally, the video recommendations device further include: auditing module, for all in the candidate live streaming set
It is audited, will be removed broadcasting live video described in the audit fails broadcasting live video.
Optionally, be arranged audit time, monitoring every described in the audit state for broadcasting live video, if in the audit
The interior instruction for not receiving audit and passing through, then deletion is described from the candidate live streaming set is broadcasting live video.
Optionally, the candidate block includes:
Enquiry module, it is all in the live streaming ID for broadcasting live video and affiliated main broadcaster ID for inquiring current time；
Statistical module counts its attention rate for broadcasting live video described in each；
First choice module, for the live video addition candidate will to be broadcast directly described in the higher part of the attention rate
Broadcast set.
Optionally, the candidate block further include:
Friend relation obtains module, for obtaining the good friend ID for having similarity relation with the main broadcaster ID；And
Second selecting module, for the live video addition candidate live streaming set to be broadcast in the part of the good friend ID.
Optionally, the recommending module includes:
List of videos obtains module, for obtaining list of videos of all candidate videos after sequence；
List is broadcast live and obtains module, for being ranked up to described broadcasting live video, obtains live streaming list；
Fusion Module is pushed away for incorporating the live streaming list in the list of videos as the recommendation
It recommends.
According to a third aspect of the embodiments of the present invention, a kind of electronic equipment is provided characterized by comprising
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to executing video recommendation method described in above-mentioned any one.
According to a fourth aspect of the embodiments of the present invention, a kind of computer readable storage medium is provided, which is characterized in that described
Computer-readable recording medium storage has computer instruction, and the computer instruction, which is performed, realizes above-mentioned video recommendations side
Method.
The technical solution that embodiments herein provides can include the following benefits:
The video recommendation method generates candidate video according to history sharing data by the history sharing data of acquisition user
Set and candidate live streaming set, then will recommend after candidate video set and candidate live streaming set fusion as recommendation,
So that the content of live streaming is added in the sharing of short-sighted frequency, increase the video recommendations diversity for sharing the page, and in short-sighted frequency
Live form is added in sharing, can more cause the interest of user, promotes the viewing experience of user.
The technical solution that another embodiment of the application provides can include the following benefits:
By being ranked up to all candidate videos in candidate video set, and to arranging broadcasting live video
Sequence by the interested video of most people and live streaming while can be shared according to the result carry out sequence recommendation after sequence,
The demand of most users is adapted to, while guaranteeing the recommendation quality of video, the viewing experience of user is improved, promotes the interest of user.
The technical solution that another embodiment of the application provides can include the following benefits:
To guarantee to recommend the quality of live video, audit time is set, live streaming is being broadcast to all in candidate live streaming set
Video is audited, and is removed the audit fails broadcasting live video, and to user recommend some real-time temperatures it is higher in
Hold, so that video recommendations are more bonded consumer taste, and promotes recommendation quality.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The application can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows and meets implementation of the invention
Example, and be used to explain the principle of the present invention together with specification.
Fig. 1 is the flow chart of video recommendation method shown according to an exemplary embodiment；
Fig. 2 is the flow chart of the video recommendation method shown according to an exemplary embodiment summarized；
Fig. 3 is the partial process view of the exemplary embodiment of step S202 in the video recommendation method shown according to fig. 2；
Fig. 4 is the flow chart of the exemplary embodiment of step S205 in the video recommendation method shown according to fig. 2；
Fig. 5 is the schematic diagram of video recommendations device shown according to an exemplary embodiment；
Fig. 6 is the schematic diagram of the video recommendations device shown according to an exemplary embodiment summarized；
Fig. 7 is the schematic diagram of the video recommendations device shown according to an exemplary embodiment summarized；
Fig. 8 is a kind of block diagram of electronic equipment for executing video recommendation method shown according to an exemplary embodiment；
Fig. 9 is a kind of frame of video recommendations device for executing video recommendation method shown according to an exemplary embodiment
Figure.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with the application.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the application.
Fig. 1 is the flow chart of video recommendation method shown according to an exemplary embodiment, specifically includes following steps.
In step s101, the history sharing data of user is obtained.
As mentioned in the background art, in the sharing of the short video sharing page selected using current video recommendation method
Hold, pattern is relatively single, it is not easy to attract user, it is poor for experiencing, therefore the application proposes a kind of new video recommendations side
Method, the diversity as a result, promotion video recommendations is broadcast live in fusion in short video sharing, increases user interest.
In general, user will do it the browsing of video inside APP, when finding interested short-sighted frequency cover, can click
Into viewing, in the way for watching short-sighted frequency, may also will do it thumb up (expression is liked), comment or reply (delivering interaction),
The sequence of operations such as forwarding (recommending to other people), similarly, user can also have same or class inside APP to the live video of viewing
As operate.And user can generally also pass through various social platforms when watching favourite short-sighted frequency or live video
(such as wechat, friend group etc.) carries out the sharing of video, these videos shared can also be seen by other users, carry out a little
The operation such as praise, watch, commenting on, collecting.
Server receives request of data, will record all operations and short-sighted frequency or live video of the user inside APP
Sharing the page or all by operation note inside APP, these records are finally stored in the form of log, can be with when needing
Extract daily record data.
In the present embodiment, fine reasonable video recommendations are carried out, need to use history sharing data, so to collect use
The daily record data of the history sharing data and extraction user at family whithin a period of time.
In one embodiment, history sharing data includes the concern that history sharing contents and history sharing contents obtain
Degree.As described above, user sees the sharing contents shared in the sharing page, corresponding operation will do it, these are to history point
The operation for enjoying content is considered as attention rate, and attention rate is, for example, number of clicks, number of reviews, viewing time, hop count (user
When watching the content that multiple good friends share on the sharing page of social platform, due to hobby difference, to different sharings
The numbers such as the click and viewing of content are different from, therefore characterize attention rate using above-mentioned several indexs) ... synthesis comment
Valence, overall merit are, for example, to distribute a weighted value to each single item, then convert into the index value of each single item to component number, are closed
The marking of note degree judges the quality of history sharing contents according to the height of final attention rate score value.
User is in the short-sighted frequency or live video for watching these to be shared on the sharing page of social platform, such as thoughts
The video of interest, it will usually which click is checked, or even enters viewing inside APP to understand more more excellent contents, in this way
The viewing interest of user is just improved, and is more in line with the hobby of user, user can independently select the viewing that oneself is liked
Type promotes viewing experience.
In step s 102, candidate video set and candidate live streaming set are generated according to history sharing data.
The core concept of the present embodiment is that the sharing of some live videos is added while recommending short-sighted frequency to user, is mentioned
The diversity and comprehensive recommended is risen, so needing to select the short-sighted frequency and live video as recommendation, by select
Short-sighted frequency is organized in together as candidate video set, and the live video of select is organized in together as candidate's live streaming collection
It closes.According to step S101 it is found that when needing, the history sharing data of user can be extracted from server, so in this step, root
Candidate video set is carried out according to history sharing data and selecting for set is broadcast live in candidate.
In one embodiment, history sharing contents include history sharing video frequency and are broadcasting live video, and history shares view
Frequency is the short-sighted frequency that user shared, and is live video being played on broadcasting live video.According to history sharing video frequency
With the short-sighted frequency and live video for selecting suitable recommendation in the attention rate for broadcasting live video.
Firstly, the history sharing video frequency shared away and all in the live video broadcast is collected, then from largely short-sighted frequencies
With recommendation is recalled in live video according to certain rules, i.e., by partial history sharing video frequency and part broadcasting live video
It is separately added into candidate video set and candidate live streaming set.
For example, recommendation is selected according to the attention rate that history sharing contents obtain, so short-sighted to what is recalled respectively
The attention rate of frequency and live video is ranked up, and sets attention rate threshold value, will be greater than short-sighted frequency and the live streaming of attention rate threshold value
Video is added in recommendation.It can be considered as the real-time temperature of live video in the attention rate for broadcasting live video, short-sighted frequency
Attention rate can be considered as the measurement index of video quality height, it is understood that be a kind of default rule.
In one embodiment, it when progress video is recalled, is first screened, removes no click volume or click volume is lower than
Then the video of pre-determined lower limit calculates the attention rate of other videos again, can save a large amount of time and calculation amount in this way, improves
Screening efficiency.
In one embodiment, the higher short-sighted frequency of minority of attention rate is analyzed, such as 30 attention rates are highest goes through for selection
History sharing video frequency, selected inside APP with the higher partial video of its similarity, also be added candidate video set.
Personalized recommendation can use for reference the thought for calculating " Match " and " Rank " in advertising: " Match " it is i.e. effective with
It is abundant to recall, found as far as possible from full content with the positively related content of user, and return result to " Rank ".Such as
1000 and the maximally related video of user interest are tentatively selected from billions of videos, as the consequently recommended candidate to user
Set.This is an extensive quick screening process, and the method for screening is fairly simple, commonly referred to as " scalping ".
And the content returned to " Match " is ranked up by " Rank " stage, commonly referred to as " phase sorting ", predicts user
A possibility that click on content, the content that most probable is clicked recommend user first.Since the model in " Rank " stage compares
It is complicated, it is impossible to sort to all the elements, so needing to pass through " Match " stage scalping data.And the data of " Match " screening
It directly determines the quality of data in " Rank " stage, largely affects the result of recommendation.
Above-mentioned steps are mainly the coarse sizing carried out in " Match " stage, and the short-sighted frequency and live video that are collected into are made
Gather for the candidate video set and candidate live streaming in " Match " stage, and the following steps are in " Rank " stage to recommendation
It is handled and shows user after being sorted.
In step s 103, all candidate videos in candidate video set are ranked up.
This step is the fine selection carried out to candidate video set, and the short-sighted frequency after selecting is as in final recommendation
Hold.
All candidate videos in the candidate video set recalled are ranked up, some sort algorithms can be used, pressed
Candidate video is ranked up according to attention rate score or video size etc..For example, according to each short-sighted frequency by like time
How much it is ranked up, the short-sighted frequency for extracting top N is recommended, remaining short-sighted frequency is deleted from candidate video set.For example,
It is ranked up according to the playing duration of short-sighted frequency, the too long of short-sighted frequency of play time is deleted from candidate video set, saved and see
It sees the time, improves and share efficiency.
It is short to each according to the operation behavior of history sharing contents and user on the page is shared according to above-mentioned steps
Video and live video have carried out the marking of attention rate, and are sorted according to attention rate height, in the video library recalled
It selects the higher history sharing video frequency of part attention rate and candidate video set is added, selected in broadcasting live video currently all
Part live streaming temperature is higher to broadcast the candidate live streaming set of live video addition.
Share to all short-sighted frequencies in certain social platform and be broadcast live straight from APP for example, collecting in certain time
Video is broadcast, calculates separately whether its attention rate reaches attention rate threshold value, removes the video of not up to attention rate threshold value, it can be to avoid
Recommend second-rate video to user.For example, collecting certain social platform shares the view that the page was issued within past one month
Frequently, and calculate these videos within past 15 days add up obtain like and number of reviews, quantity is liked to video with user
Or touching quantity or number of reviews etc. characterize the attention rate of video acquisition, attention rate threshold value are set up, for example, accumulative obtain
10000 clicks, the video filtering that attention rate is not up to threshold value is fallen, and the video that attention rate is higher than threshold value can be used as wait push away
It recommends video and candidate video set is added.The less video of attention rate can be removed in this way, and it is interested to select most users
Video is recommended, and guarantees the quality for recommending video.
In one embodiment, the candidate video after sequence in candidate video set is audited, for example, right
The content of short-sighted frequency carries out manual examination and verification, selects and meets the short-sighted frequency of situation instantly and temperature and recommended, makes to recommend video tool
There is the flavor of the day, improve the viewing desire of user, promotes user's conversion ratio.
In one embodiment, it sorts again after all candidate videos in candidate video set being classified, for example, will
All short-sighted frequencies are divided according to class of making laughs, emotion class, implied meaning class, music class etc., and every one kind video carries out attention rate again
Sequence, be then ranked up according to class of making laughs, music class, emotion class, implied meaning class ....
After sequence, remaining video is the high-quality video after finely screening, prediction point in candidate video set
Very high clicking rate and conversion ratio are had when enjoying.
In step S104, by after the candidate video set and candidate live streaming set fusion after sequence as recommendation into
Row is recommended.
User is inside APP or when carrying out the viewing of short-sighted frequency on sharing the page, after a short video-see,
Next short-sighted frequency would generally be played automatically, or when watching the live video that other users are shared, turn over to upper and lower or left and right
It is dynamic, other live videos can be watched, store the position of these short-sighted frequencies and live video as recommendation pond.In the present embodiment
The recommendation pond in the recommendation pond of short-sighted frequency and live video is shared, i.e., can both be shown in recommendation pond and recommend short-sighted frequency,
It can show recommendation live video, increase and recommend the rich of pond recommendation.
It has obtained in step s 102 respectively by the short-sighted frequency in the higher part of attention rate and the higher part live streaming view of temperature
The candidate video set of frequency composition and candidate live streaming set, in this step, by candidate video set and candidate live streaming gather into
Row fusion, i.e., by the candidate video set after sequence candidate video (candidate video is short-sighted frequency to be recommended) and candidate
Being merged broadcasting live video in live streaming set carries out video recommendations according to fused sequence.
It, can (such as live video quantity be big according to different quantity when carrying out the fusion of short-sighted frequency and live video
In short number of videos) and different sequences (short-sighted frequency is first recommended to recommend live video or short-sighted frequency and live video are interspersed to push away again
Recommend) it is merged and is recommended, then fused recommendation is added and is recommended in pond.
In one embodiment, it when user sends or shares recommendation, is submitted with user orientation server and sends recommendation
Request, server receive request, video content is sent.
In the present embodiment, by obtaining the history sharing data of user, candidate video collection is generated according to history sharing data
Conjunction and candidate's live streaming are gathered, then are used as recommendation to recommend candidate video set and candidate be broadcast live after set merges, and are made
The content that live streaming is added in the sharing of video is obtained, the drawing that Page user is shared in increase is new, draws conversion ratio of living, and addition live streaming shape
Formula, user are more willing to enter APP internal activity, improve user's conversion ratio in short-sighted frequency social activity sharing.
Fig. 2 is the flow chart of the video recommendation method shown according to an exemplary embodiment summarized.
In step s 201, the history sharing data of user is obtained；
In step S202, candidate video set and candidate live streaming set are generated according to history sharing data；
In step S203, all candidate videos in candidate video set are ranked up；
In step S204, all in candidate live streaming set are audited broadcasting live video, it will the audit fails
Remove broadcasting live video；
In step S205, it will recommend after candidate video set and candidate live streaming set fusion as recommendation.
The present embodiment is the prioritization scheme of Fig. 1, the step S101-S104 phase of step S201-S203 and step S205 and Fig. 1
Together, which is not described herein again.
Embodiment one has been substantially carried out recalling for recommendation, it is desirable to recommend the video of high quality to user, it is also necessary to point
It is other to be merged again to candidate video and after broadcasting live video and finely screen, as shown in step S204.
In step S204, all in candidate live streaming set are audited broadcasting live video, it will the audit fails
Remove broadcasting live video.
This step is e.g. being broadcast to all to all in the fine screening for broadcasting live video in candidate live streaming set
Live video carries out audit filtering, according to auditing result, deletes and audits unacceptable live video.Here audit is, for example, pair
The safety of live video and the audit of legitimacy, illegal video filtering is fallen, and guarantees the safe and healthy of network environment, to
User recommends the live video of green positive energy.
When audit, live video is uploaded, the legitimacy of the live video is detected using detection algorithm, by it is certain when
Between after, feed back to auditing result instruction, e.g. audit the message passed through, then the live video can be used as live streaming to be recommended
Video.
In one embodiment, broadcasting directly using the detection of DPI (Deep Packet Inspection) deep message
The audit of video is broadcast, the detection of DPI deep message is a kind of depth detection technology based on data packet, for different network applications
Layer load (such as HTTP, DNS etc.) carries out depth detection, determines its legitimacy by the payload detection to message, will examine
After survey, there is illegal live video and prohibited broadcasting and warning processing, and deleted from candidate video set.
In one embodiment, audit time (such as T) is set, monitors every in the audit state for broadcasting live video, if
The instruction that audit passes through is not received within audit time, i.e., the instruction passed through after overtime audit time T still without audit indicates
The live streaming cannot push, then delete from candidate's live streaming set and should broadcast live video.
Live video is being broadcast to what the audit fails, is containing information unauthorized in live video if detecting, stops immediately
The only broadcasting of the live video, and live streaming person is prompted, the propagation of such live video is avoided later.It is kept by audit filtering
The living broadcast environment health for recommending live video, correctly guides viewing user.
In one embodiment, video recommendation method further include: recommendation is sent to user terminal and is shown.
In step S205, by the short-sighted frequency after sequence and merging broadcasting live video after audit, as most
Fused recommendation results in this step, are returned to front end and are shown by whole recommendation results, watched convenient for user and point
It enjoys.
When recommendation results being back to user terminal being shown, different recommendation knots can be watched by different operations
Fruit, such as user can switch viewing content when watching a certain short-sighted frequency by horizontally slipping, such as sliding viewing to the left
A upper content, next content is watched in sliding to the right, in this way setting, so that user is to the interested content watched, it can
It is watched repeatedly with sliding into row by a left side, plays memory action, and the displaying sequence of the recommendation in pond is recommended only to need
It carries out once setting before showing.Here slide is a kind of schematical citing, and user can also pass through other
Operation carry out viewing content switching.
In one embodiment, because of the fusion that recommendation results are short-sighted frequency and live video, so can also be by specific
Operational order realize the switching of short-sighted frequency and live video, allow user to be switched to oneself interested viewing at any time
Type for example, referring to that downslide is switched in the broadcasting page for broadcasting live video by three when user watches video in APP, and is led to
It crosses two fingers and glides and be switched to the broadcasting page of short-sighted frequency, while can show watched in conjunction with left cunning and right cunning and not watch
Content.
Switch short-sighted frequency and live video by referring to downslide only is a kind of implementation more, is realized to the present embodiment
Limitation, user for example can also by double-click, the modes such as long-pressing come realize viewing content switching, promote the viewing body of user
It tests.
When user watches recommendation in APP, the sharing of viewing content can also be carried out, sharing operation can be by more
Kind of approach is realized, such as the group being forwarded in APP or good friend, is forwarded to the social platforms such as wechat circle of friends, QQ space, or
Person shares good friend or group to other APP such as wechats.Which, no matter sharing onto platform, when user shares, all can
Shared according to the sequence of the recommendation existing recommendation in pond, such as user is watching one section of short-sighted frequency, and is shared
To wechat circle of friends, then short-sighted frequency or live streaming of other good friends in wechat when watching this short-sighted frequency, before and after the short-sighted frequency
It is identical inside the recommended location and APP of video.For example, user is broadcast live in APP, it is desirable to obtain more concerns
Degree shares live video onto other social platforms, when the good friend in other social platforms watches the live video, in order to
Increase interaction and viewing experience, viewing inside APP may be entered, the viewing interest of user is thereby increased, increase use
The viewing selectivity at family, promotes user experience.
When user when sharing the recommendation that the user in page viewing APP shares, can also pass through in social platform
Operational order realizes the switching of short-sighted frequency and live video, such as short-sighted frequency is watched in sliding selection to the left, sliding selection to the right
Live video is watched, increases the viewing selectivity of user, promotes user experience and the likability to APP.
In the present embodiment, video recommendation method is after generating candidate video set and candidate live streaming set, to candidate video
With broadcast live video respectively carried out sort and audit screening, then again to user show, by candidate video and live streaming
The sequence and audit of video so that the quality of recommendation is guaranteed, and preferentially can recommend synthesis degree higher to user
Video and live streaming increase the viewing interest of user, also ensure the diversity of recommendation, the user experience is improved.
In one embodiment, the video recommendation method of the present embodiment further include: periodically recommendation is updated.
Recommendation includes short-sighted frequency and is broadcasting live video, and, short-sighted frequency very fast in the replacement frequency for broadcasting live video
Temperature also converted at any time, in order to adapt to the viewing interest of user, in conjunction with situation instantly, need to determine recommendation
Shi Gengxin.Its dynamic for being operated all is paid close attention to the recommendation recommended each time in real time, and timing returns the concern of recommendation
Degree, analysis recommendation are recorded the interested type of most users by the favorite degree of user, constantly progress autonomous learning,
When suitably increasing the short-sighted frequency of the type or the recommendation ratio of live video, and recommending each time, all it is added some other
Type guarantees the diversity of recommendation.
By periodically collect each sharing as a result, and be added to as certain influence factor in recommendation next time,
It is constantly iterated calculating, recommendation is updated, adapts to the hobby of user, meet the development trend of the current situation instantly.
Fig. 3 is the partial process view of the exemplary embodiment of step S202 in the video recommendation method shown according to fig. 2, step
Rapid S202 is candidate video set and candidate live streaming set to be generated according to history sharing data, and the present embodiment mainly describes basis
Sharing data generates the process of candidate live streaming set, specifically, including step S2021- step S2023.
In step S2021, inquiry current time is all in the live streaming ID for broadcasting live video and affiliated main broadcaster ID.
ID is the mark for indicating and identifying user identity, and user can obtain a spy when using different APP
Mark of some ID as identity, accordingly, when user issues content in APP, every content also has corresponding ID and carries out
It distinguishes.In the present embodiment, user can have an one's own ID number when logging in APP, and user issued in APP it is short
When video or live video, corresponding video ID can be also obtained, in publication, issues and generally also can in short-sighted frequency or live video
ID number with user shows the ownership for issuing content.
For example, registration user logs in certain client using User ID, and carry out the viewing of video with share, can when sharing
Some information related with the identity of this user, e.g. User ID (user_id) to be added in video link.
When user is broadcast live in APP, the User ID that user uses is considered as main broadcaster ID, and the main broadcaster ID is being carried out
The mark of live video be that live streaming ID, main broadcaster ID and its live streaming ID for being broadcast live form one-to-one relationship, live video
Middle addition main broadcaster ID, shows to belong to.
Candidate live streaming set is added from all parts of selecting in broadcasting live video at current time, so firstly the need of obtaining
Take current time all broadcast live video live streaming ID and therewith to main broadcaster ID.Then live streaming ID representative pair can be used
That answers is broadcasting live video, convenient for selecting for subsequent live video.
In step S2022, live video is being broadcast to each, is counting its attention rate.
According to above-described embodiment it is found that being broadcast live when selecting of video, the concern obtained according to live video is needed
Degree selects live video to be recommended, so to count each in the attention rate for broadcasting live video acquisition.
Collect in the current a certain small period it is all broadcasting live video, live video is being broadcast to each, it is straight to obtain it
ID is broadcast, and inquires viewing number corresponding with the live video is counted, thumb up the details such as number and real-time temperature, will be obtained
Standards of grading of these indexs obtained as attention rate calculate the corresponding attention rate of each live streaming ID using certain algorithm and obtain
Point, attention rate score is represented for example, by using the value after the quantity weighting of machine index.It establishes about " live streaming ID ", " main broadcaster
The table of ID ", " attention rate " are broadcasting live video according to the height progress descending arrangement of attention rate score for all.
In step S2023, the candidate live streaming set of live video addition is being broadcast into the higher part of attention rate.
In previous step, calculated the corresponding attention rate of every live video or live streaming temperature, attention rate it is high
Live video may be considered the interest for meeting majority to a certain extent, by the welcome of user, has and shares value, institute
To be added in candidate live streaming set broadcasting live video from selecting the higher part of attention rate score in table.For example, selecting pass
It is to be recommended that candidate live streaming set etc. is added in preceding 20 live videos of note degree score sequence.
In one embodiment, it to live video progress postsearch screening is being broadcast, first selects a small amount of live video and time is added
Choosing live streaming set, it is higher in the type for broadcasting live video then to count these attention rate scores, is broadcasting live streaming view remaining
Primary screening is carried out in frequency again, the live video for picking out same type is added in candidate live streaming set.
In one embodiment, according to the attention rate score of statistics it is higher select in the type for broadcasting live video it is short-sighted
Frequently, that is, corresponding candidate video set is added in the short-sighted frequency in part for selecting same type；Or it is higher short-sighted according to attention rate score
Frequency type selects live video, a small amount of same from selecting in broadcasting live video according to the higher short video type of attention rate score
The live video of type is added in candidate live streaming set, increases the rich of recommendation.
In one embodiment, the step of set is broadcast live in the generation candidate of the present embodiment further include: obtains and the main broadcaster
ID has the good friend ID of similarity relation.
Usually there is more similitude between good friend, there is many common hobbies between many intimate good friends,
It illustrates by wechat good friend, they are often relatives, classmate, work together or have the friends of certain common hobbies.When a certain
User is in the video that circle of friends viewing good friend shares, often because paying close attention to this good friend or having between this good friend higher
Similitude, that shares to it is video interested.Similarly, in the present embodiment, when a certain user shares short-sighted frequency or straight in APP
When broadcasting video, the content that the good friend in APP shares it is interested, just will do it viewing.Even, have and jointly like
The content that may share between good friend is also much like, for example, makeups intelligents would generally share some makeups videos；Game player
Some game videos, clearance strategy would generally be shared；Gourmet would generally share some cuisines；Sports fan can share
Body-building video etc., so according to the behavior of user, and judge sharing contents with share the set of metadata of similar data of author, can find
There is the sharing author of identical hobby, then inquiry is current shares whether author is sharing short-sighted frequency or live video.
For example, the corresponding main broadcaster I D of the higher live video of the attention rate according to obtained in above-mentioned steps, obtains and its phase
As good friend ID, judge whether the good friend ID is being broadcast live, if the good friend ID at this time be broadcast live share, by the good friend
Candidate live streaming set is added in the live video that ID shares.
In one embodiment, further includes: the candidate live streaming set of live video addition is being broadcast into the part of good friend ID.
Friend relation data are obtained according to the above process, when needing to be broadcast live video recommendations, first according to main broadcaster ID
And its live video shared retrieves similar good friend ID, and part addition is then selected from the live video that good friend ID is being broadcast live
Candidate's live streaming set.
In one embodiment, further includes: the second level friend relation for establishing main broadcaster ID, by second level friend relation corresponding two
Broadcasting the candidate live streaming set of live video addition in the part of grade good friend ID.
Have the good friend ID of similitude for level-one friend relation ID with live streaming ID, and level-one good friend ID is also deposited using inside
In friend relation, this kind of good friend is the second level good friend of main broadcaster ID.For example, being exactly A and B is level-one good friend (mutually concern), B and C
It is level-one good friend (concern mutually), then A and C are exactly second level friend relation, multistage friend relation is such.By multistage good friend
Candidate live streaming set is added in a part in the live video that ID is being broadcasted, can enrich the content of live video, using more
Grade friend relation carries out video recommendations, can increase the rich and diversity of recommendation, user is had more
Viewing selection.
In one embodiment, the live video being newly added is audited, the live video recalled is by auditing it
Afterwards, the similar live video being newly added also needs to be audited, will be straight from candidate not by the live video of audit
It broadcasts in set and rejects, remaining live video guarantees the rich and reasonability for recommending live video as live video is recommended.
Fig. 4 is the flow chart of the exemplary embodiment of step S205 in the video recommendation method shown according to fig. 2, is to time
Being discussed in detail for the process for selecting video collection and candidate live streaming set to be merged, mainly includes step S2051-S2053.
In step S2051, list of videos of all candidate videos after sequence is obtained.
In step S203, the candidate video in candidate video set is audited and sorted, collating sequence is to push away
The playing sequence of short-sighted frequency when recommending, sort method is in step S203 it has been noted which is not described herein again, by the candidate after sequence
Video, which is emitted in table, generates list of videos.Before being merged, list of videos is first transferred, is obtained to be recommended multiple short-sighted
Frequently, these short-sighted frequencies are the videos with quality assurance by finely screening.
In step S2052, to being ranked up broadcasting live video, live streaming list is obtained.
In step S204, to audit filtering has been carried out broadcasting live video in candidate live streaming set, audit is eliminated not
By live video, retained the higher live video of attention rate.It is real according to user's history interest and live streaming in this step
When temperature, the video in candidate live streaming set is ranked up, if foundation when sequence is identical as the judgment criteria of attention rate,
It is directly ranked up according to attention rate score height, if foundation when sequence is different from the judgment criteria of attention rate, carries out weight
New sort forms the recommendation order of live video, and live streaming list is obtained after arrangement and is given according to the live streaming tabulating result after sequence
User recommends personalized live video.
In step S2053, live streaming list is incorporated in list of videos and is recommended as recommendation.
Live video in list of videos to be recommended in insertion live streaming list, when being inserted into live video, according to straight
Being sequentially inserted into for list is broadcast, by the way of the insertion of interval, one or more live videos are inserted into adjacent candidate video,
Or often it is separated by the one or more live videos of candidate video insertion of identical quantity；Or according to same side in list of videos
Method is inserted into the candidate video in list of videos to be recommended.
When being broadcast live list and the fusion of list of videos, it can also be arranged according to other inserted modes, such as by live streaming
Table and list of videos put similar short-sighted frequency and similar live video together according to Type division, and this mode, which will combine, to be worked as
Preceding collating sequence comprehensively considers.
It when being merged, candidate video and is not required in the quantity for broadcasting live video, is adjusted according to actual demand
It is whole.
It when carrying out video recommendations, while joined the recommendation of the higher live video of temperature, the view of recommendation can be increased
The interest of frequency attracts more users, allows user to understand news dynamic in real time, promotes viewing experience.
Fig. 5 is the schematic diagram of video recommendations device shown according to an exemplary embodiment.The video recommendations device 500 packet
It includes and obtains module 501, candidate block 502, sorting module 503 and recommending module 504.
Obtain the history sharing data that module 501 is used to obtain user；
Candidate block 502 is used to generate candidate video set and candidate live streaming set according to history sharing data；
Sorting module 503 is for being ranked up all candidate videos in candidate video set；
Candidate video set of the recommending module 504 for after sorting is used as recommendation after merging with candidate live streaming set
Recommended.
The video recommendations device of the present embodiment is generated by the history sharing data of acquisition user according to history sharing data
Candidate video set and candidate live streaming set, then by after candidate video set and candidate live streaming set fusion as recommendation into
Row is recommended, so that the content of live streaming is added in the sharing of video, increases and shares the recommendation diversity that the page obtains recommendation, and
Live form is added, user is more willing to enter APP internal activity, improves the viewing experience and interest-degree of user.
In one embodiment, history sharing data includes the concern that history sharing contents and history sharing contents obtain
Degree, and history sharing contents then include history sharing video frequency and are broadcasting live video, candidate block 502 is for selecting partial history
Sharing video frequency and part are separately added into candidate video set and candidate live streaming set broadcasting live video.
Fig. 6 is the schematic diagram of the video recommendations device shown according to an exemplary embodiment summarized.
Fig. 6 is the optimization to the embodiment of Fig. 5, and it includes obtaining module 501, candidate block which, which removes,
502, outside sorting module 503 and recommending module 504 further include: auditing module 601.
Auditing module 601 is used to audit all in candidate live streaming set broadcasting live video, and audit is not led to
That crosses removes broadcasting live video.
Optionally, after candidate block 502 selects partial history sharing video frequency addition candidate video set, sorting module 503
Candidate video is ranked up；Candidate block 502 selects part after broadcasting live video and candidate live streaming set is added, auditing module
601 are audited broadcasting live video.Then recommending module 504 by the candidate video set after sequence and passes through the candidate of audit
Recommended after live streaming set fusion as recommendation.
Optionally, candidate block 502 includes candidate live streaming set generation module (not shown) and candidate video set
Generation module (not shown), wherein candidate's live streaming gathers generation module and includes:
Enquiry module, it is all in the live streaming ID for broadcasting live video and affiliated main broadcaster ID for inquiring current time；
Statistical module counts its attention rate for broadcasting live video to each；And
First choice module, for the candidate live streaming set of live video addition to be broadcast in the higher part of attention rate.
In one embodiment, the candidate live streaming set generation module of candidate block 502 further include:
Friend relation obtains module, for obtaining the good friend ID for having similarity relation with main broadcaster ID；And second selection mould
Block, for the candidate live streaming set of live video addition to be broadcast in the part of good friend ID.
In one embodiment, recommending module 503 includes:
List of videos obtains module (not shown), for obtaining list of videos of all candidate videos after sequence；
List is broadcast live and obtains module (not shown), for obtaining live streaming list to being ranked up broadcasting live video；
Fusion Module (not shown) is pushed away for that will be broadcast live in list involvement list of videos as recommendation
It recommends.
In the present embodiment, video recommendations device is after generating candidate video set and candidate live streaming set, to candidate video
With broadcast live video respectively carried out sort and audit screening, then again to user show, by candidate video and live streaming
The sequence and audit of video so that the quality of recommendation is guaranteed, and preferentially can recommend synthesis degree higher to user
Video and live streaming increase the viewing interest of user, also ensure the diversity of recommendation, the user experience is improved.
About the video recommendations device in above-described embodiment, since the function of wherein modules has been pushed away in above-mentioned video
It recommends in the embodiment of method and is described in detail, thus carried out relatively simple description.
Fig. 7 is the schematic diagram of the video recommendations device shown according to an exemplary embodiment summarized.
The video recommendations device 700 of the present embodiment includes off-line module 710 and server-side 720.Wherein, off-line module 710
Including log memory module 711, off-line data memory module 712, sample module 713 and training module 714；Server-side 720 is wrapped
Include sorting module 721, screening module 722, Fusion Module 723, sharing module 724 and front end display module 725.
Log memory module 711 is for collecting the video shared away and live information and record user in operation layer pair
The record of all operations (click, viewing, comment, collection, forwarding etc.) of short-sighted frequency and live streaming, the storage in the form of log, such as
User clicks user behaviors log；
Off-line data memory module 712 is used for according to the video content shared away, collection candidate video, and according to depositing
The log information of storage is collected all in the live video broadcast, and video library is all added by these candidate videos and broadcasting live video,
Result is recalled as preliminary；
Sample module 713 is used to according to user collect the record of all operations of short-sighted frequency and live streaming in operation layer
Video in select partial video candidate video set be added, and broadcasting live streaming in current all parts of selecting in the live streaming broadcast
Candidate live streaming set is added in video；
Training module 714 for being trained using mass data, select with live streaming by autonomous learning video；
It after selecting, generates one and selects model, for adding from different video sharing page Picking videos and live streaming
Enter candidate collection, then server-side 720 uses model, and the candidate video set and candidate live streaming set be collected into model carries out
Fine screening.
Sorting module 721 is used to extract the behavioural characteristic of user, in candidate collection video and live streaming be ranked up；
Screening module 722 is used for carrying out audit filtering broadcasting live video in candidate live streaming set, and according to live streaming
Auditing result deletes and audits unacceptable live streaming；
Fusion Module 723 is used to merge video ranking results with live streaming auditing result, as recommendation；
Sharing module 724 is mainly responsible for the data communication with operation layer, receives request of data and sends recommendation results,
Such as recommendation is shared onto the different pages；
Fused recommendation is returned to front end by front end display module 725, is shown to user.
Fig. 8 is a kind of electronic equipment 1200 for above-mentioned video recommendation method shown according to an exemplary embodiment
Block diagram.For example, electronic equipment 1200 can be mobile phone, computer, digital broadcasting terminal, messaging device, game control
Platform processed, tablet device, Medical Devices, body-building equipment, personal digital assistant etc..
Referring to Fig. 8, electronic equipment 1200 may include following one or more components: processing component 1202, memory
1204, electric power assembly 1206, multimedia component 1208, audio component 1210, the interface 1212 of input/output (I/O), sensor
Component 1214 and communication component 1216.
The integrated operation of the usual controlling electronic devices 1200 of processing component 1202, such as with display, call, data are logical
Letter, camera operation and record operate associated operation.Processing component 1202 may include one or more processors 1220
It executes instruction, to perform all or part of the steps of the methods described above.In addition, processing component 1202 may include one or more
Module, convenient for the interaction between processing component 1202 and other assemblies.For example, processing component 1202 may include multimedia mould
Block, to facilitate the interaction between multimedia component 1208 and processing component 1202.
Memory 1204 is configured as storing various types of data to support the operation in electronic equipment 1200.These numbers
According to example include any application or method for being operated on electronic equipment 1200 instruction, contact data, electricity
Talk about book data, message, picture, video etc..Memory 1204 can be by any kind of volatibility or non-volatile memory device
Or their combination is realized, such as static random access memory (SRAM), electrically erasable programmable read-only memory
(EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM), programmable read only memory (PROM), read-only memory
(ROM), magnetic memory, flash memory, disk or CD.
Power supply module 1206 provides electric power for the various assemblies of electronic equipment 1200.Power supply module 1206 may include power supply
Management system, one or more power supplys and other with for electronic equipment 1200 generate, manage, and distribute associated group of electric power
Part.
Multimedia component 1208 includes the screen of one output interface of offer between the electronic equipment 1200 and user
Curtain.In some embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touching
Panel, screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touchings
Sensor is touched to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or cunning
The boundary of movement, but also detect duration and pressure associated with the touch or slide operation.In some embodiments
In, multimedia component 1208 includes a front camera and/or rear camera.When electronic equipment 1200 is in operation mould
Formula, such as in a shooting mode or a video mode, front camera and/or rear camera can receive external multi-medium data.
Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom energy
Power.
Audio component 1210 is configured as output and/or input audio signal.For example, audio component 1210 includes a wheat
Gram wind (MIC), when electronic equipment 1200 is in operation mode, when such as call mode, recording mode, and voice recognition mode, Mike
Wind is configured as receiving external audio signal.The received audio signal can be further stored in memory 1204 or via
Communication component 1216 is sent.In some embodiments, audio component 1210 further includes a loudspeaker, for exporting audio letter
Number.
I/O interface 1212 provides interface, above-mentioned peripheral interface module between processing component 1202 and peripheral interface module
It can be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and
Locking press button.
Sensor module 1214 includes one or more sensors, for providing the shape of various aspects for electronic equipment 1200
State assessment.For example, sensor module 1214 can detecte the state that opens/closes of electronic equipment 1200, component it is relatively fixed
Position, such as the component are the display and keypad of device 1200, and sensor module 1214 can also detect electronic equipment
1200 or 1,200 1 components of electronic equipment position change, the existence or non-existence that user contacts with electronic equipment 1200, electricity
The temperature change in sub- 1200 orientation of equipment or acceleration/deceleration and electronic equipment 1200.Sensor module 1214 may include approaching
Sensor is configured to detect the presence of nearby objects without any physical contact.Sensor module 1214 may be used also
To include optical sensor, such as CMOS or ccd image sensor, for being used in imaging applications.In some embodiments, the biography
Sensor component 1214 can also include acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensing
Device.
Communication component 1216 is configured to facilitate the logical of wired or wireless way between electronic equipment 1200 and other equipment
Letter.Electronic equipment 1200 can access the wireless network based on communication standard, such as Wi Fi, carrier network (such as 2G, 3G, 4G or
5G) or their combination.In one exemplary embodiment, communication component 1216 is received via broadcast channel from external wide
The broadcast singal or broadcast related information of broadcast management system.In one exemplary embodiment, the communication component 1216 also wraps
Near-field communication (NFC) module is included, to promote short range communication.For example, it can be based on radio frequency identification (RFID) technology in NFC module, it is red
Outer data association (IrDA) technology, ultra wide band (UWB) technology, bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, electronic equipment 1200 can by one or more application specific integrated circuit (ASIC),
Digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field-programmable gate array
It arranges (FPGA), controller, microcontroller, microprocessor or other electronic components to realize, for executing above-mentioned video recommendation method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 1204 of instruction, above-metioned instruction can be executed by the processor 1220 of electronic equipment 1200 to complete above-mentioned side
Method.For example, the non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, magnetic
Band, floppy disk and optical data storage devices etc..
Fig. 9 is a kind of video recommendations device for above-mentioned video recommendation method shown according to an exemplary embodiment
1300 block diagram.For example, device 1300 may be provided as a server.Referring to Fig. 9, device 1300 includes processing component
1322, it further comprise one or more processors, and the memory resource as representated by memory 1332, for storing
It can be by the instruction of the execution of processing component 1322, such as application program.The application program stored in memory 1332 may include
It is one or more each correspond to one group of instruction module.In addition, processing component 1322 is configured as executing instruction,
To execute above-mentioned video recommendation method.
Device 1300 can also include that a power supply module 1326 be configured as the power management of executive device 1300, and one
Wired or wireless network interface 1350 is configured as device 1300 being connected to network and input and output (I/O) interface
1358.Device 1300 can be operated based on the operating system for being stored in memory 1332, such as Windows ServerTM, Mac
OS XTM, UnixTM, LinuxTM, FreeBSDTM or similar.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the application
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the application, these modifications, purposes or
Person's adaptive change follows the general principle of the application and including the undocumented common knowledge in the art of the application
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the application are by following
Claim is pointed out.
It should be understood that the application is not limited to the precise structure that has been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.Scope of the present application is only limited by the accompanying claims.
Claims (10)
1. a kind of video recommendation method characterized by comprising
Obtain the history sharing data of user；
Candidate video set and candidate live streaming set are generated according to the history sharing data；
All candidate videos in the candidate video set are ranked up；And
It will recommend after the candidate video set and the candidate live streaming set fusion after sequence as recommendation.
2. video recommendation method according to claim 1, which is characterized in that the history sharing data includes that history is shared
The attention rate that content and the history sharing contents obtain.
3. video recommendation method according to claim 2, which is characterized in that the history sharing contents include that history is shared
Video and live video is being broadcast, it will the part history sharing video frequency and part is described is broadcasting live video according to default rule
It is separately added into the candidate video set and the candidate live streaming set.
4. video recommendation method according to claim 1, which is characterized in that further include: in the candidate live streaming set
It is all audited broadcasting live video, will remove broadcasting live video described in the audit fails.
5. video recommendation method according to claim 1, which is characterized in that generated according to the history sharing data candidate
Live streaming is gathered
It is all in the live streaming ID for broadcasting live video and affiliated main broadcaster ID to inquire current time；
Live video is being broadcast described in each, is counting its attention rate；And
The live video addition candidate live streaming set will be being broadcast described in the higher part of the attention rate.
6. video recommendation method according to claim 4, which is characterized in that by after sequence the candidate video set and
The candidate live streaming set recommend as recommendation after merging
Obtain list of videos of all candidate videos after sequence；
It is ranked up to described broadcasting live video, obtains live streaming list；
The live streaming list is incorporated in the list of videos and is recommended as the recommendation.
7. a kind of video recommendations device characterized by comprising
Module is obtained, for obtaining the history sharing data of user；
Candidate block, for generating candidate video set and candidate live streaming set according to the history sharing data；
Sorting module, for being ranked up to all candidate videos in the candidate video set；And
Recommending module, in after the candidate video set and the candidate live streaming set fusion after sorting as recommending
Appearance is recommended.
8. video recommendations device according to claim 7, which is characterized in that further include: auditing module, for the time
All in choosing live streaming set are audited broadcasting live video, will be removed broadcasting live video described in the audit fails.
9. a kind of electronic equipment characterized by comprising
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to executing video recommendation method described in the claims 1-6 any one.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has computer to refer to
It enables, the computer instruction is performed realization such as video recommendation method as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811588951.XA CN109769128B (en) | 2018-12-25 | 2018-12-25 | Video recommendation method, video recommendation device and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811588951.XA CN109769128B (en) | 2018-12-25 | 2018-12-25 | Video recommendation method, video recommendation device and computer-readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109769128A true CN109769128A (en) | 2019-05-17 |
| CN109769128B CN109769128B (en) | 2021-07-13 |
Family
ID=66451571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811588951.XA Active CN109769128B (en) | 2018-12-25 | 2018-12-25 | Video recommendation method, video recommendation device and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109769128B (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110297942A (en) * | 2019-06-26 | 2019-10-01 | 广州市百果园信息技术有限公司 | A kind of video heuristic approach, device, equipment and storage medium |
| CN110489655A (en) * | 2019-09-16 | 2019-11-22 | 浙江同花顺智能科技有限公司 | Hot content determination, recommended method, device, equipment and readable storage medium storing program for executing |
| CN110856031A (en) * | 2019-11-18 | 2020-02-28 | 广州市百果园信息技术有限公司 | Media resource display system, method, equipment and storage medium |
| CN110866805A (en) * | 2019-11-13 | 2020-03-06 | 第四范式（北京）技术有限公司 | Method and system for recommending object |
| CN111212299A (en) * | 2020-01-16 | 2020-05-29 | 广州酷狗计算机科技有限公司 | Method and device for acquiring live video tutorial, server and storage medium |
| CN111523050A (en) * | 2020-04-16 | 2020-08-11 | 咪咕文化科技有限公司 | Content recommendation method, server and storage medium |
| CN111614998A (en) * | 2020-05-26 | 2020-09-01 | 上海连尚网络科技有限公司 | Method for processing promotion video, electronic device and computer-readable storage medium |
| CN111737566A (en) * | 2020-05-15 | 2020-10-02 | 深圳市战音科技有限公司 | Work sorting method, device and storage medium |
| CN112051949A (en) * | 2020-09-14 | 2020-12-08 | 北京达佳互联信息技术有限公司 | Content sharing method and device and electronic equipment |
| CN112218114A (en) * | 2019-07-10 | 2021-01-12 | 中国电信股份有限公司 | Video cache control method, device and computer readable storage medium |
| WO2021031917A1 (en) * | 2019-08-20 | 2021-02-25 | 北京字节跳动网络技术有限公司 | Video processing method and apparatus, and electronic device and readable medium |
| CN112565814A (en) * | 2019-09-26 | 2021-03-26 | 腾讯科技（深圳）有限公司 | Video distribution method, device, storage medium and server |
| CN112565797A (en) * | 2019-09-10 | 2021-03-26 | 北京达佳互联信息技术有限公司 | Page request processing method and device, electronic equipment and medium |
| CN112637685A (en) * | 2020-12-11 | 2021-04-09 | 上海连尚网络科技有限公司 | Video processing method and device |
| CN112650884A (en) * | 2020-12-21 | 2021-04-13 | 四川长虹电器股份有限公司 | Video pushing method based on deep learning |
| CN112714327A (en) * | 2020-12-21 | 2021-04-27 | 腾讯科技（深圳）有限公司 | Interaction method, device and equipment based on live application program and storage medium |
| CN112749324A (en) * | 2019-10-31 | 2021-05-04 | 北京达佳互联信息技术有限公司 | Network medium information delivery control method and device, electronic equipment and storage medium |
| CN112765478A (en) * | 2021-03-12 | 2021-05-07 | 北京百度网讯科技有限公司 | Method, apparatus, device, medium, and program product for recommending content |
| CN113205382A (en) * | 2021-04-30 | 2021-08-03 | 北京有竹居网络技术有限公司 | Method, apparatus, device, storage medium and program product for determining object |
| CN113794910A (en) * | 2021-09-14 | 2021-12-14 | 广州方硅信息技术有限公司 | Video pushing method and device, electronic equipment and storage medium |
| CN113886633A (en) * | 2021-10-11 | 2022-01-04 | 平安国际智慧城市科技股份有限公司 | Video recommendation, device, equipment and storage medium based on artificial intelligence |
| CN114430503A (en) * | 2022-01-25 | 2022-05-03 | 上海影宴数码科技有限公司 | Big data superposition recommendation method based on short video |
| CN114520929A (en) * | 2022-02-13 | 2022-05-20 | 武汉斗鱼鱼乐网络科技有限公司 | Video playing method, device, medium and computer equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070124493A1 (en) * | 2005-10-07 | 2007-05-31 | The Board Of Trustees Of The Leland Stanford Jr. University | System and Method for Ordering Content for User Review |
| CN102843602A (en) * | 2011-06-22 | 2012-12-26 | 宏碁股份有限公司 | Television system and method for providing program recommendation list of television system |
| CN105224576A (en) * | 2014-07-01 | 2016-01-06 | 上海视畅信息科技有限公司 | A kind of video display intelligent recommendation method |
| CN107436914A (en) * | 2017-06-06 | 2017-12-05 | 北京小度信息科技有限公司 | Recommend method and device |
| CN108388629A (en) * | 2018-02-13 | 2018-08-10 | 北京奇虎科技有限公司 | A kind of multimedia information push method, device and electronic equipment |
| CN108419088A (en) * | 2018-02-08 | 2018-08-17 | 华南理工大学 | A kind of recommendation of the channels method towards high sudden user's request |
-
2018
- 2018-12-25 CN CN201811588951.XA patent/CN109769128B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070124493A1 (en) * | 2005-10-07 | 2007-05-31 | The Board Of Trustees Of The Leland Stanford Jr. University | System and Method for Ordering Content for User Review |
| CN102843602A (en) * | 2011-06-22 | 2012-12-26 | 宏碁股份有限公司 | Television system and method for providing program recommendation list of television system |
| CN105224576A (en) * | 2014-07-01 | 2016-01-06 | 上海视畅信息科技有限公司 | A kind of video display intelligent recommendation method |
| CN107436914A (en) * | 2017-06-06 | 2017-12-05 | 北京小度信息科技有限公司 | Recommend method and device |
| CN108419088A (en) * | 2018-02-08 | 2018-08-17 | 华南理工大学 | A kind of recommendation of the channels method towards high sudden user's request |
| CN108388629A (en) * | 2018-02-13 | 2018-08-10 | 北京奇虎科技有限公司 | A kind of multimedia information push method, device and electronic equipment |
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110297942B (en) * | 2019-06-26 | 2024-01-05 | 广州市百果园信息技术有限公司 | Video exploration method, device, equipment and storage medium |
| CN110297942A (en) * | 2019-06-26 | 2019-10-01 | 广州市百果园信息技术有限公司 | A kind of video heuristic approach, device, equipment and storage medium |
| CN112218114A (en) * | 2019-07-10 | 2021-01-12 | 中国电信股份有限公司 | Video cache control method, device and computer readable storage medium |
| CN112218114B (en) * | 2019-07-10 | 2023-01-03 | 中国电信股份有限公司 | Video cache control method, device and computer readable storage medium |
| WO2021031917A1 (en) * | 2019-08-20 | 2021-02-25 | 北京字节跳动网络技术有限公司 | Video processing method and apparatus, and electronic device and readable medium |
| CN112565797B (en) * | 2019-09-10 | 2022-08-05 | 北京达佳互联信息技术有限公司 | Page request processing method and device, electronic equipment and medium |
| CN112565797A (en) * | 2019-09-10 | 2021-03-26 | 北京达佳互联信息技术有限公司 | Page request processing method and device, electronic equipment and medium |
| CN110489655A (en) * | 2019-09-16 | 2019-11-22 | 浙江同花顺智能科技有限公司 | Hot content determination, recommended method, device, equipment and readable storage medium storing program for executing |
| CN112565814A (en) * | 2019-09-26 | 2021-03-26 | 腾讯科技（深圳）有限公司 | Video distribution method, device, storage medium and server |
| CN112749324B (en) * | 2019-10-31 | 2024-03-12 | 北京达佳互联信息技术有限公司 | Network medium information delivery control method and device, electronic equipment and storage medium |
| CN112749324A (en) * | 2019-10-31 | 2021-05-04 | 北京达佳互联信息技术有限公司 | Network medium information delivery control method and device, electronic equipment and storage medium |
| CN110866805A (en) * | 2019-11-13 | 2020-03-06 | 第四范式（北京）技术有限公司 | Method and system for recommending object |
| CN110856031B (en) * | 2019-11-18 | 2022-01-18 | 广州市百果园信息技术有限公司 | Media resource display system, method, equipment and storage medium |
| CN110856031A (en) * | 2019-11-18 | 2020-02-28 | 广州市百果园信息技术有限公司 | Media resource display system, method, equipment and storage medium |
| CN111212299A (en) * | 2020-01-16 | 2020-05-29 | 广州酷狗计算机科技有限公司 | Method and device for acquiring live video tutorial, server and storage medium |
| CN111212299B (en) * | 2020-01-16 | 2022-02-11 | 广州酷狗计算机科技有限公司 | Method and device for acquiring live video tutorial, server and storage medium |
| CN111523050A (en) * | 2020-04-16 | 2020-08-11 | 咪咕文化科技有限公司 | Content recommendation method, server and storage medium |
| CN111523050B (en) * | 2020-04-16 | 2023-09-19 | 咪咕文化科技有限公司 | Content recommendation method, server and storage medium |
| CN111737566A (en) * | 2020-05-15 | 2020-10-02 | 深圳市战音科技有限公司 | Work sorting method, device and storage medium |
| CN111614998A (en) * | 2020-05-26 | 2020-09-01 | 上海连尚网络科技有限公司 | Method for processing promotion video, electronic device and computer-readable storage medium |
| CN112051949A (en) * | 2020-09-14 | 2020-12-08 | 北京达佳互联信息技术有限公司 | Content sharing method and device and electronic equipment |
| CN112637685A (en) * | 2020-12-11 | 2021-04-09 | 上海连尚网络科技有限公司 | Video processing method and device |
| CN112637685B (en) * | 2020-12-11 | 2024-01-30 | 上海连尚网络科技有限公司 | Video processing method and device |
| CN112714327B (en) * | 2020-12-21 | 2022-02-25 | 腾讯科技（深圳）有限公司 | Interaction method, device and equipment based on live application program and storage medium |
| CN112650884B (en) * | 2020-12-21 | 2022-04-01 | 四川长虹电器股份有限公司 | Video pushing method based on deep learning |
| CN112650884A (en) * | 2020-12-21 | 2021-04-13 | 四川长虹电器股份有限公司 | Video pushing method based on deep learning |
| CN112714327A (en) * | 2020-12-21 | 2021-04-27 | 腾讯科技（深圳）有限公司 | Interaction method, device and equipment based on live application program and storage medium |
| CN112765478A (en) * | 2021-03-12 | 2021-05-07 | 北京百度网讯科技有限公司 | Method, apparatus, device, medium, and program product for recommending content |
| WO2022228074A1 (en) * | 2021-04-30 | 2022-11-03 | 北京有竹居网络技术有限公司 | Method and apparatus for determining object, and device, storage medium and program product |
| CN113205382A (en) * | 2021-04-30 | 2021-08-03 | 北京有竹居网络技术有限公司 | Method, apparatus, device, storage medium and program product for determining object |
| CN113205382B (en) * | 2021-04-30 | 2024-02-20 | 北京有竹居网络技术有限公司 | Method, apparatus, device, storage medium and program product for determining object |
| CN113794910A (en) * | 2021-09-14 | 2021-12-14 | 广州方硅信息技术有限公司 | Video pushing method and device, electronic equipment and storage medium |
| CN113794910B (en) * | 2021-09-14 | 2024-04-19 | 广州方硅信息技术有限公司 | Video pushing method, device, electronic equipment and storage medium |
| CN113886633A (en) * | 2021-10-11 | 2022-01-04 | 平安国际智慧城市科技股份有限公司 | Video recommendation, device, equipment and storage medium based on artificial intelligence |
| CN114430503B (en) * | 2022-01-25 | 2023-08-04 | 上海影宴数码科技有限公司 | Short video-based big data superposition recommendation method |
| CN114430503A (en) * | 2022-01-25 | 2022-05-03 | 上海影宴数码科技有限公司 | Big data superposition recommendation method based on short video |
| CN114520929A (en) * | 2022-02-13 | 2022-05-20 | 武汉斗鱼鱼乐网络科技有限公司 | Video playing method, device, medium and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109769128B (en) | 2021-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109769128A (en) | Video recommendation method, video recommendations device and computer readable storage medium | |
| US20220156792A1 (en) | Systems and methods for deducing user information from input device behavior | |
| KR101728122B1 (en) | Method for recommending users in social network and the system thereof | |
| CN107820138B (en) | Video broadcasting method, device, terminal and storage medium | |
| US9270918B2 (en) | Method of recommending broadcasting contents and recommending apparatus therefor | |
| CN103914781B (en) | Information processing equipment, information processing method and terminal device | |
| JP6235556B2 (en) | Content presentation method, content presentation apparatus, and program | |
| CN102263999B (en) | Face-recognition-based method and system for automatically classifying television programs | |
| US9448682B2 (en) | Selectively displaying content to a user of a social network | |
| US9955231B2 (en) | Relevant video content pushed to a mobile phone | |
| US9230352B2 (en) | Information processing apparatus, information processing method, and computer program product | |
| CN109684507A (en) | Video recommendation method, video recommendations device and computer readable storage medium | |
| CN107205178A (en) | Direct broadcasting room recommends method and device | |
| CN109299384A (en) | Scene recommended method, apparatus and system, storage medium | |
| CN107241622A (en) | video location processing method, terminal device and cloud server | |
| CN105959749A (en) | Intelligent terminal, remote controller and recommending method and system | |
| CN107071579A (en) | Multimedia resource processing method and device | |
| CN106874308A (en) | It is a kind of to recommend method and apparatus, a kind of device for recommending | |
| US8898259B2 (en) | Bookmarking system | |
| KR20120092457A (en) | Apparatus and method for recommending contents in real time | |
| KR20140092352A (en) | Content evaluation/playback device | |
| CN111435371A (en) | Video recommendation method and system, computer program product and readable storage medium | |
| US20210006866A1 (en) | Method and apparatus for interactive television guides and program rules | |
| KR101431245B1 (en) | Method and system for enabling generation of a summary of a data stream | |
| CN106791965A (en) | TV programme method for pushing and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |