CN109327739A - A kind of method for processing video frequency, calculates equipment and storage medium at device - Google Patents
A kind of method for processing video frequency, calculates equipment and storage medium at device Download PDFInfo
- Publication number
- CN109327739A CN109327739A CN201811425810.6A CN201811425810A CN109327739A CN 109327739 A CN109327739 A CN 109327739A CN 201811425810 A CN201811425810 A CN 201811425810A CN 109327739 A CN109327739 A CN 109327739A
- Authority
- CN
- China
- Prior art keywords
- recorded broadcast
- video
- efficiency index
- target user
- live streaming
- 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
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
- H04N21/43—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
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
-
- 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
- H04N21/21—Server components or server architectures
- H04N21/218—Source of audio or video content, e.g. local disk arrays
- H04N21/2187—Live feed
-
- 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
- H04N21/433—Content storage operation, e.g. storage operation in response to a pause request, caching operations
- H04N21/4334—Recording operations
-
- 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
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The embodiment of the invention discloses a kind of method for processing video frequency, device, calculate equipment and storage medium.This method comprises: to the recorded broadcast video statistics recorded broadcast behavioral data of target user's publication;Recorded broadcast efficiency index is calculated to the target user according to the recorded broadcast behavioral data;The recorded broadcast efficiency index is input in preset live streaming prediction model, to predict that the target user presides over the live streaming efficiency index of live video view.Guarantee effect when target user presides over live video to select suitable target user to open up the business of live video according to live streaming efficiency index using live streaming prediction model prediction live streaming efficiency index, promote the resource utilization of platform.
Description
Technical field
The present embodiments relate to the technology of live streaming more particularly to a kind of method for processing video frequency, device, calculates equipment and deposit
Storage media.
Background technique
Widely available with the development of the network technology, especially mobile terminal, the development of the recorded broadcasts video such as short-sighted frequency is swift and violent.
It can be used as one of the important tool of relationship between the main maintenance of video and spectators due to being broadcast live, more and more platforms are in original
On the basis of some recorded broadcast videos, newly carry out live broadcast service, allows and video master while safeguarding recorded broadcast video and live video.
But recorded broadcast video and live video are two business of different nature, and partial video master is adapted to recorded broadcast
The characteristic of video, but the characteristic of live video is not necessarily adapted to, so that partial video master effect when presiding over live video is poor,
Cause the resource utilization of platform low.
Summary of the invention
The embodiment of the present invention provides a kind of method for processing video frequency, device, calculates equipment and storage medium, to solve so that portion
Divide video master effect when presiding over live video poor, the problem for causing the resource utilization of platform low.
In a first aspect, the embodiment of the invention provides a kind of method for processing video frequency, comprising:
To the recorded broadcast video statistics recorded broadcast behavioral data of sample of users publication;
The live video statistics live streaming behavioral data that the sample of users is presided over;
Recorded broadcast efficiency index is calculated to the sample of users according to the recorded broadcast behavioral data;
Live streaming efficiency index is calculated to the sample of users according to the live streaming behavioral data;
Training live streaming prediction model is related between the recorded broadcast efficiency index and the live streaming efficiency index to be fitted
Property.
Second aspect, the embodiment of the invention also provides a kind of method for processing video frequency, comprising:
To the recorded broadcast video statistics recorded broadcast behavioral data of target user's publication;
Recorded broadcast efficiency index is calculated to the target user according to the recorded broadcast behavioral data;
The recorded broadcast efficiency index is input in preset live streaming prediction model, to predict that it is straight that the target user presides over
Broadcast the live streaming efficiency index of video view.
The third aspect, the embodiment of the invention also provides a kind of video process apparatus, comprising:
Sample recorded broadcast behavioral data statistical module, the recorded broadcast video statistics recorded broadcast behavior number for being issued to sample of users
According to;
Behavioral data statistical module is broadcast live in sample, and the live video for presiding over to the sample of users counts live streaming behavior
Data;
Sample recorded broadcast efficiency index computing module is recorded for being calculated according to the recorded broadcast behavioral data the sample of users
Broadcast efficiency index;
Efficiency index computing module is broadcast live in sample, straight for being calculated according to the live streaming behavioral data the sample of users
Broadcast efficiency index;
Prediction model training module is broadcast live, for training live streaming prediction model, to be fitted the recorded broadcast efficiency index and institute
State the correlation between live streaming efficiency index.
Fourth aspect, the embodiment of the invention also provides a kind of video process apparatus, comprising:
Target recorded broadcast behavioral data statistical module, the recorded broadcast video statistics recorded broadcast behavior number for being issued to target user
According to;
Target recorded broadcast efficiency index computing module is recorded for being calculated according to the recorded broadcast behavioral data the target user
Broadcast efficiency index;
Efficiency index prediction module is broadcast live in target, predicts mould for the recorded broadcast efficiency index to be input to preset live streaming
In type, to predict that the target user presides over the live streaming efficiency index of live video view.
5th aspect the embodiment of the invention also provides a kind of calculating equipment, including memory, processor and is stored in
On reservoir and the computer program that can run on a processor, the processor realizes first aspect or the when executing described program
The method for processing video frequency that two aspects provide.
6th aspect, also a kind of computer readable storage medium of the embodiment of the present invention are stored thereon with computer program, should
The method for processing video frequency that first aspect or a second aspect of the present invention provides is realized when program is executed by processor.
In embodiments of the present invention, to the recorded broadcast video statistics recorded broadcast behavioral data of target user's publication, according to recorded broadcast row
Recorded broadcast efficiency index is calculated to target user for data, recorded broadcast efficiency index is input in preset live streaming prediction model, with
Predict that target user presides over the live streaming efficiency index of live video view, to select suitable target to use according to live streaming efficiency index
Family opens up the business of live video, guarantees effect when target user presides over live video, promotes the resource utilization of platform.
Detailed description of the invention
Fig. 1 is a kind of flow chart for method for processing video frequency that the embodiment of the present invention one provides;
Fig. 2A and Fig. 2 B is the displaying exemplary diagram for the live video that the embodiment of the present invention one provides;
Fig. 3 is a kind of flow chart of method for processing video frequency provided by Embodiment 2 of the present invention;
Fig. 4 is a kind of structural schematic diagram for video process apparatus that the embodiment of the present invention three provides;
Fig. 5 is a kind of structural schematic diagram for video process apparatus that the embodiment of the present invention four provides;
Fig. 6 is a kind of structural schematic diagram for calculating equipment that the embodiment of the present invention five provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is a kind of flow chart for method for processing video frequency that the embodiment of the present invention one provides, and the present embodiment is applicable to
Carry out the main effect for supporting live video business of platform prediction video of recorded broadcast video traffic, this method can predict mould by live streaming
The training device of type executes, and the training device of the live streaming prediction model can be by hardware and/or software realization, this method is specific
Include the following steps:
S110, the recorded broadcast video statistics recorded broadcast behavioral data that sample of users is issued.
In embodiments of the present invention, platform carries out the business of recorded broadcast video, and so-called recorded broadcast video, is relative to live video
For, it can refer to the video data made offline, for example, short-sighted frequency, micro- film, initiative advertisement, etc..
User issues recorded broadcast video and refers to the platform, and spectators are added by clients such as browser, short Video Applications from the platform
The recorded broadcast video is carried, and is interacted.
It should be noted that the user is also referred to as video master or up master for recorded broadcast video, i.e. publication recorded broadcast regards
The user of frequency, therefore not necessarily its is original for its recorded broadcast video, including reprint recorded broadcast video or by deleted video original part again
It uploads, all referred to as up master.
For platform, user and/or spectators can be recorded in log for the recorded broadcast behavioral data of recorded broadcast video
In, and therefrom select while opening the user of the business of recorded broadcast video and the business of live video to send out it as sample of users
The recorded broadcast video statistics recorded broadcast behavioral data of cloth.
Specifically, the recorded broadcast behavioral data may include following at least one type:
Row is interacted between the publication behavioral data of sample of users, the watching behavior data of spectators, sample of users and spectators
For data.
Wherein, the publication behavioral data of sample of users can refer to that sample of users such as is made to recorded broadcast video, uploaded at the behaviour
When making, the data independently generated, for example, video length, uplink time, video type, upload place etc., at this point, sample is used
It is not interacted between family and spectators.
The watching behavior data of spectators can refer to that spectators when watching the recorded broadcast video of sample of users publication, independently generate
Data, for example, forwarding video, viewing time, viewing amount, viewing place, device model etc., at this point, sample of users and spectators
Between do not interact.
Mutual-action behavior data between sample of users and spectators can refer to spectators in the recorded broadcast view of viewing sample of users publication
Generated data are interacted when frequency, between sample of users and spectators.
So-called interaction can refer to while be related to sample of users and the behavior of spectators, for example, spectators comment to the transmission of recorded broadcast video
By spectators thumb up the recorded broadcast video, etc..
In one example, the recorded broadcast behavioral data counted includes following at least one:
1, average viewing amount
Average viewing amount belongs to the watching behavior data of spectators, and acquisition a period of time is interior, sample of users publication each
The viewing amount of recorded broadcast video, and average value is calculated, obtain average viewing amount.
2, the average amount of thumbing up
Averagely the amount of thumbing up belongs to the mutual-action behavior data between sample of users and spectators, and acquisition is interior for a period of time, sample is used
The amount of thumbing up of each recorded broadcast video of family publication, and calculates average value, averagely the amount of being thumbed up.
It should be noted that thumb up expression is positive emotion of the spectators to sample of users, it is referred to as liking, likes
Love, approval, support, etc..
3, average review amount
Average review amount belongs to the mutual-action behavior data between sample of users and spectators, and acquisition is interior for a period of time, sample is used
The comment amount of each recorded broadcast video of family publication, and average value is calculated, obtain average review amount.
4, average transfer amount
Average transfer amount belongs to the watching behavior data of spectators, and acquisition is interior for a period of time, spectators forward sample of users publication
Each recorded broadcast video quantity, and calculate average value, obtain average transfer amount.
Certainly, the recorded broadcast behavioral data of above-mentioned statistics is intended only as example, in implementing the embodiments of the present invention, can basis
The recorded broadcast behavioral data of other statistics is arranged in actual conditions, and the embodiments of the present invention are not limited thereto.In addition, in addition to above-mentioned system
Outside the recorded broadcast behavioral data of meter, those skilled in the art can also use the recorded broadcast behavior number of other statistics according to actual needs
According to the embodiment of the present invention is also without restriction to this.
It in one embodiment, can be right in order to improve the accuracy for being fitted influence of the recorded broadcast video to live video
The independent recorded broadcast behavioral data of recorded broadcast video statistics.
Specifically, determine while issuing recorded broadcast video and preside over the user of live video, as sample of users, to sample
The recorded broadcast video statistics recorded broadcast behavioral data that this user issues before starting to preside over live video, within a preset period of time.
It is so-called to start to preside over live video, it can refer to that the business for only having opened up recorded broadcast video originally is newly opened on this basis
If the business of live video, i.e., the recorded broadcast video statistics recorded broadcast behavior issued when not opening up the business of live video to sample of users
Data.
Certainly, it carries out the feelings such as counting in the recorded broadcast video that sample of users is issued in inconvenience before starting to preside over live video
Under condition, the recorded broadcast video statistics recorded broadcast behavioral data that sample of users can also be issued after starting to preside over live video, this
Embodiment is without restriction to this.
S120, the live video statistics live streaming behavioral data that the sample of users is presided over.
In embodiments of the present invention, platform carries out the business of live video, and so-called live video is relative to recorded broadcast video
For, it can refer to the video data of real-time manufacturing, for example, media and movable live streaming, game live streaming, show field live streaming, social live streaming,
Etc..
It should be noted that the user is also referred to as network main broadcaster for live video, that is, preside over live video
User, the content of live video can be network main broadcaster itself, or other things.
In one example, as shown in Figure 2 A, recorded broadcast video and live video are in the same page, i.e., in the same page
Recorded broadcast video and live video are shown simultaneously in face, to distinguish live video from a large amount of recorded broadcast video, then can be broadcast live
Prompt information is loaded in the information of video, such as " in live streaming ".
In another example, as shown in Figure 2 B, recorded broadcast video is in the different pages from live video, these pages can
To switch over by TAG (label), recorded broadcast video is shown in the corresponding page of TAG " video ", it is corresponding in TAG " live streaming "
The page shows live video.
Certainly, the exhibition method of above-mentioned live video is intended only as example, in implementing the embodiments of the present invention, can basis
The exhibition method of other live videos is arranged in actual conditions, and the embodiments of the present invention are not limited thereto.In addition, in addition to above-mentioned straight
It broadcasts outside the exhibition method of video, those skilled in the art can also use the displaying side of other live videos according to actual needs
Formula, the embodiment of the present invention are also without restriction to this.
For platform, user and/or spectators can be recorded in log for the live streaming behavioral data of recorded broadcast video
In, and the video master of the business of recorded broadcast video and the business of live video is therefrom selected while opening, as sample of users, to it
The live video statistics live streaming behavioral data of hosting.
Specifically, the recorded broadcast behavioral data may include following at least one type:
Row is interacted between the hosting behavioral data of sample of users, the watching behavior data of spectators, sample of users and spectators
For data.
Wherein, when the publication behavioral data of sample of users can refer to that sample of users supports recorded broadcast operation, the number that independently generates
According to, for example, live streaming duration, live streaming type, Live Site etc., at this point, not interacted between sample of users and spectators.
The watching behavior data of spectators can refer to that spectators when watching the live video that sample of users is supported, independently generate
Data, for example, online number, viewing time, the viewing frequency, viewing place, device model etc., at this point, sample of users and sight
It is not interacted between crowd.
Mutual-action behavior data between sample of users and spectators can refer to the live streaming view that spectators preside in viewing sample of users
Generated data are interacted when frequency, between sample of users and spectators.
So-called interaction can refer to while be related to sample of users and the behavior of spectators, for example, spectators send void to sample of users
Quasi- article, spectators send barrage to recorded broadcast video, and sample of users gives virtual coin to spectators, and sample of users is to spectators' transmission service
Data (such as commodity data), etc..
In one example, the live streaming behavioral data counted includes following at least one:
1, average online number
Average online number belongs to the watching behavior data of spectators, and acquisition a period of time is interior, sample of users hosting each
Live video online number, and calculate average value, obtain averagely online number.
2, the par of the spectators of barrage is sent
The par for sending the spectators of barrage belongs to the mutual-action behavior data between sample of users and spectators, acquires one section
The spectator attendance of barrage is sent in time, in each live video of sample of users publication, and calculates average value, is sent
The par of the spectators of barrage.
3, the par of the spectators of virtual objects is sent
The par for sending the spectators of virtual objects belongs to the mutual-action behavior data between sample of users and spectators, acquires
The quantity of the spectators of virtual objects is sent in a period of time, in each live video that sample of users is presided over, and is calculated average
Value obtains the par for sending the spectators of virtual objects.
Certainly, the live streaming behavioral data of above-mentioned statistics is intended only as example, in implementing the embodiments of the present invention, can basis
The live streaming behavioral data of other statistics is arranged in actual conditions, and the embodiments of the present invention are not limited thereto.In addition, in addition to above-mentioned system
Outside the live streaming behavioral data of meter, those skilled in the art can also use the live streaming behavior number of other statistics according to actual needs
According to the embodiment of the present invention is also without restriction to this.
It in one embodiment, can be right in order to improve the accuracy for being fitted influence of the recorded broadcast video to live video
The independent recorded broadcast behavioral data of recorded broadcast video statistics.
Specifically, determine while issuing recorded broadcast video and preside over the user of live video, as sample of users, to sample
The live video statistics live streaming behavioral data that this user presides over after starting hosting live video, within a preset period of time.
Also, the period of the period and statistics live streaming behavioral data that count recorded broadcast behavioral data keep continuous.
S130, recorded broadcast efficiency index is calculated to the sample of users according to the recorded broadcast behavioral data.
In the concrete realization, the abilities such as recorded broadcast behavioral data and the official documents and correspondence of sample of users, planning are related, high stability,
It can refer to recorded broadcast behavioral data and calculate recorded broadcast efficiency index, intuitive the case where embodying sample of users publication recorded broadcast video.
In one embodiment, weight is configured to each recorded broadcast behavioral data respectively, obtains recorded broadcast characteristic value.
And using linear regression algorithm, calculate the sum of recorded broadcast characteristic value, the recorded broadcast efficiency index as sample of users.
In general, the weight of recorded broadcast behavioral data and the importance of recorded broadcast behavioral data are positively correlated, i.e., more important record
Behavioral data is broadcast, corresponding weight is bigger.
In one example, recorded broadcast efficiency index can be calculated by following formula:
xi=w1*a+w2*b+w3*c+w4*d
Wherein, xiFor the recorded broadcast efficiency index of i-th of sample of users, a is average viewing amount, and b is that the averagely amount of thumbing up, c is
Average review amount, d are average transfer amount, w1、w2、w3、w4For weight.
Furthermore, since the capacity variance between different sample of users is larger, it is poor to may cause recorded broadcast behavioral data
It is different larger, therefore, in order to reduce different sample of users recorded broadcast behavioral data difference, can to recorded broadcast behavioral data carry out normal state
Change processing (such as using 10 as the truth of a matter, carries out Logarithm conversion).
In addition, the numberical range difference of different types of recorded broadcast behavioral data is larger, in order to allow different types of recorded broadcast row
Have comparativity each other for data, recorded broadcast behavioral data can be standardized.
S140, live streaming efficiency index is calculated to the sample of users according to the live streaming behavioral data.
In the concrete realization, the live streaming ability of live streaming behavioral data and live events (as drawn a lottery), sample of users (is such as given a lecture
Eloquence, intelligence and art) etc. correlations, fluctuation is larger, can refer to the live streaming behavioral data calculate live streaming efficiency index, intuitively embody sample
User presides over the case where live video.
In one embodiment, weight is configured to each live streaming behavioral data respectively, obtains live streaming characteristic value.
And using linear regression algorithm, calculate the sum of live streaming characteristic value, the live streaming efficiency index as sample of users.
In general, the weight of live streaming behavioral data and the importance of live streaming behavioral data are positively correlated, i.e., more important is straight
Behavioral data is broadcast, corresponding weight is bigger.
In one example, recorded broadcast efficiency index can be calculated by following formula:
yi=w5*e+w6*f+w7*g
Wherein, yiFor the live streaming efficiency index of i-th of sample of users, e is average online number, and f is the sight for sending barrage
Many pars, g are the par for sending the spectators of virtual objects, w5、w6、w7For weight.
Furthermore, since the capacity variance between different sample of users is larger, it is poor to may cause live streaming behavioral data
It is different larger, therefore, in order to reduce the difference that behavioral data is broadcast live of different sample of users, normal state can be carried out to live streaming behavioral data
Change processing (such as using 10 as the truth of a matter, carries out Logarithm conversion).
In addition, the numberical range difference of different types of live streaming behavioral data is larger, in order to allow different types of live streaming to go
Have comparativity each other for data, live streaming behavioral data can be standardized.
S150, training live streaming prediction model, to be fitted between the recorded broadcast efficiency index and the live streaming efficiency index
Correlation.
In the concrete realization, can be using recorded broadcast efficiency index and live streaming efficiency index as training sample, training live streaming is pre-
Model is surveyed, which can be fitted the correlation between recorded broadcast efficiency index and live streaming efficiency index, be used for basis
Recorded broadcast efficiency index prediction live streaming efficiency index.
In one embodiment, live streaming prediction model is linear regression model (LRM).
In this embodiment, the dependent variable X in live streaming prediction model is set by recorded broadcast efficiency index, effect will be broadcast live
Index is set as the independent variable Y in live streaming prediction model.
Prediction model (Y=β is broadcast live to obtain in the correlation being fitted between the dependent variable and the independent variable0+β1*X)
In model parameter (including the first model parameter β0With the second model parameter β1)。
It certainly, can also be live streaming prediction model by other model trainings, for example, certainly other than linear regression model (LRM)
Plan tree-model, Random Forest model, etc., the present embodiment is without restriction to this.
In embodiments of the present invention, on the one hand, to sample of users publication recorded broadcast video statistics recorded broadcast behavioral data, according to
Recorded broadcast behavioral data calculates recorded broadcast efficiency index to sample of users, on the other hand, counts to the live video that sample of users is presided over
Behavioral data is broadcast live, live streaming efficiency index is calculated to sample of users according to live streaming behavioral data, thus training live streaming prediction model,
Be fitted recorded broadcast efficiency index and be broadcast live efficiency index between correlation, it is subsequent can be in the recorded broadcast efficiency index of target user
On the basis of, using live streaming prediction model prediction live streaming efficiency index, to select suitable target according to live streaming efficiency index
User opens up the business of live video, guarantees effect when target user presides over live video, promotes the resource utilization of platform.
Embodiment two
Fig. 3 is a kind of flow chart of method for processing video frequency provided by Embodiment 2 of the present invention, and the present embodiment is applicable to
Carry out the main effect for supporting live video business of platform prediction video of recorded broadcast video traffic, this method can be by live streaming effect
Prediction processing device executes, and the prediction processing device of the live streaming effect can be by hardware and/or software realization, this method is specific
Include the following steps:
S310, the recorded broadcast video statistics recorded broadcast behavioral data that target user is issued.
In embodiments of the present invention, platform carries out the business of recorded broadcast video, and so-called recorded broadcast video, is relative to live video
For, it can refer to the video data made offline, for example, short-sighted frequency, micro- film, initiative advertisement, etc..
User issues recorded broadcast video and refers to the platform, and spectators are added by clients such as browser, short Video Applications from the platform
The recorded broadcast video is carried, and is interacted.
It should be noted that the user is also referred to as video master or up master for recorded broadcast video, i.e. publication recorded broadcast regards
The user of frequency, therefore not necessarily its is original for its recorded broadcast video, including reprint recorded broadcast video or will be deleted rouble video it is former
Part uploads again, all referred to as up master.
For platform, user and/or spectators can be recorded in log for the recorded broadcast behavioral data of recorded broadcast video
In, and therefrom select while opening the user of the business of recorded broadcast video and the business of live video to send out it as target user
The recorded broadcast video statistics recorded broadcast behavioral data of cloth.
Specifically, the recorded broadcast behavioral data may include following at least one type:
Row is interacted between the publication behavioral data of target user, the watching behavior data of spectators, target user and spectators
For data.
Wherein, the publication behavioral data of target user can refer to that target user such as makes to recorded broadcast video, uploads at the behaviour
When making, the data independently generated, for example, video length, uplink time, video type, upload place etc., at this point, target is used
It is not interacted between family and spectators.
The watching behavior data of spectators can refer to that spectators when watching the recorded broadcast video of target user's publication, independently generate
Data, for example, forwarding video, viewing time, viewing amount, viewing place, device model etc., at this point, target user and spectators
Between do not interact.
Mutual-action behavior data between target user and spectators can refer to spectators in the recorded broadcast view of viewing target user's publication
Generated data are interacted when frequency, between target user and spectators.
So-called interaction can refer to while be related to the behavior of target user and spectators, for example, spectators comment to the transmission of recorded broadcast video
By spectators thumb up the recorded broadcast video, etc..
In one example, the recorded broadcast behavioral data counted includes following at least one:
1, average viewing amount
Average viewing amount belongs to the watching behavior data of spectators, and acquisition a period of time is interior, target user's publication each
The viewing amount of recorded broadcast video, and average value is calculated, obtain average viewing amount.
2, the average amount of thumbing up
Averagely the amount of thumbing up belongs to the mutual-action behavior data between target user and spectators, and acquisition is interior for a period of time, target is used
The amount of thumbing up of each recorded broadcast video of family publication, and calculates average value, averagely the amount of being thumbed up.
It should be noted that thumb up expression is positive emotion of the spectators to target user, it is referred to as liking, likes
Love, approval, support, etc..
3, average review amount
Average review amount belongs to the mutual-action behavior data between target user and spectators, and acquisition is interior for a period of time, target is used
The comment amount of each recorded broadcast video of family publication, and average value is calculated, obtain average review amount.
4, average transfer amount
Average transfer amount belongs to the watching behavior data of spectators, and acquisition is interior for a period of time, spectators forward target user's publication
Each recorded broadcast video quantity, and calculate average value, obtain average transfer amount.
Certainly, the recorded broadcast behavioral data of above-mentioned statistics is intended only as example, in implementing the embodiments of the present invention, can basis
The recorded broadcast behavioral data of other statistics is arranged in actual conditions, and the embodiments of the present invention are not limited thereto.In addition, in addition to above-mentioned system
Outside the recorded broadcast behavioral data of meter, those skilled in the art can also use the recorded broadcast behavior number of other statistics according to actual needs
According to the embodiment of the present invention is also without restriction to this.
In one embodiment, it determines the user for having issued recorded broadcast video and not presided over live video, is used as target
Family, and, to the recorded broadcast video statistics recorded broadcast behavioral data of target user's publication.
It is so-called not preside over live video, it can refer to the business for only having opened up recorded broadcast video, not open up the industry of live video
Business, i.e., the recorded broadcast video statistics recorded broadcast behavioral data issued when not opening up the business of live video to target user.
S320, recorded broadcast efficiency index is calculated to the target user according to the recorded broadcast behavioral data.
In the concrete realization, the abilities such as recorded broadcast behavioral data and the official documents and correspondence of target user, planning are related, high stability,
It can refer to recorded broadcast behavioral data and calculate recorded broadcast efficiency index, it is intuitive to embody the case where target user issues recorded broadcast video.
In one embodiment, weight is configured to each recorded broadcast behavioral data respectively, obtains recorded broadcast characteristic value.
And using linear regression algorithm, calculate the sum of recorded broadcast characteristic value, the recorded broadcast efficiency index as target user.
In general, the weight of recorded broadcast behavioral data and the importance of recorded broadcast behavioral data are positively correlated, i.e., more important record
Behavioral data is broadcast, corresponding weight is bigger.
In one example, recorded broadcast efficiency index can be calculated by following formula:
xj=w1*a+w2*b+w3*c+w4*d
Wherein, xjFor the recorded broadcast efficiency index of j-th of target user, a is average viewing amount, and b is that the averagely amount of thumbing up, c is
Average review amount, d are average transfer amount, w1、w2、w3、w4For weight.
Furthermore, since the capacity variance between different target user is larger, it is poor to may cause recorded broadcast behavioral data
It is different larger, therefore, in order to reduce different target user recorded broadcast behavioral data difference, can to recorded broadcast behavioral data carry out normal state
Change processing (such as using 10 as the truth of a matter, carries out Logarithm conversion).
In addition, the numberical range difference of different types of recorded broadcast behavioral data is larger, in order to allow different types of recorded broadcast row
Have comparativity each other for data, recorded broadcast behavioral data can be standardized.
S330, the recorded broadcast efficiency index is input in preset live streaming prediction model, to predict the target user
Preside over the live streaming efficiency index of live video view.
In the present embodiment, live streaming prediction model can be fitted related between recorded broadcast efficiency index and live streaming efficiency index
Property, for predicting live streaming efficiency index according to recorded broadcast efficiency index.
The recorded broadcast efficiency index of target user is input in the live streaming prediction model and is handled, exportable target user
It presides over the live streaming efficiency index of live video view and presides over live video after prediction target user opens up the business of live video
The case where.
Under normal circumstances, live streaming efficiency index is bigger, and live streaming effect is better, conversely, live streaming efficiency index is smaller, live streaming effect
Fruit is poorer.
In one embodiment, live streaming prediction model is linear regression model (LRM):
Y=β0+β1*X
Wherein, recorded broadcast efficiency index is dependent variable X, and live streaming efficiency index is set as independent variable Y, and the first model parameter is
β0, the second model parameter be β1。
In the present embodiment, it using recorded broadcast efficiency index as dependent variable X, calculates and the second model parameter β1Product β1*
X calculates product β1* X and the first model parameter β0The sum of, obtain the live streaming efficiency index as independent variable Y.
Hereafter, then business processing can be broadcast live to target user according to live streaming efficiency index.
So-called live broadcast service processing, can refer to business processing relevant to being broadcast live.
In one example, target user can be ranked up according to live streaming efficiency index, the target after sequence is used
Family generates list of starting broadcasting.
In this example, in addition to the sequence of target user, recorded broadcast efficiency index (including recorded broadcast behavior number in the list of starting broadcasting
According to) and live streaming efficiency index except, can also carrying target user other information, such as registion time, business revenue index, etc..
The list of starting broadcasting is provided to operation employee, whether opens up the industry of live video to target user for its comprehensive reference
Business.
In another example, live streaming efficiency index can be selected to meet the feature of the preset condition that starts broadcasting from target user
User is such as worth a live streaming efficiency index of highest n (n is positive integer), greater than live streaming efficiency index of preset threshold, etc..
The prompt information that starts broadcasting is sent to feature user, actively suggests opening up the business of live video to this feature user.
In embodiments of the present invention, to the recorded broadcast video statistics recorded broadcast behavioral data of target user's publication, according to recorded broadcast row
Recorded broadcast efficiency index is calculated to target user for data, recorded broadcast efficiency index is input in preset live streaming prediction model, with
Predict that target user presides over the live streaming efficiency index of live video view, to select suitable target to use according to live streaming efficiency index
Family opens up the business of live video, guarantees effect when target user presides over live video, promotes the resource utilization of platform.
To make those skilled in the art more fully understand the present embodiment, illustrate the present embodiment below by way of specific example
The method of middle prediction live streaming effect.
Sample of users i has issued 10 short-sighted frequencies, and statistics, which obtains the average viewing amount of short-sighted frequency, to be 10000 (weight is
0.1), averagely the amount of thumbing up is 8000 (weights 0.2), and average review amount is 2000 (weights 0.4), and average transfer amount is 3000
(weight 0.3), then recorded broadcast efficiency index xi=0.1*10000+0.2*8000+0.4*2000+0.3*3000=4300.
Sample of users i has presided over 10 live streamings, and statistics, which obtains the average online number of live streaming, to be 10000 (weight is
0.5) par for, sending the spectators of barrage is 5000 (weights 0.3), and the par for sending the spectators of virtual objects is
1000 (weights 0.2), then be broadcast live efficiency index yi=0.5*10000+0.3*5000+0.2*1000=6700.
Fitting live streaming prediction model is Y=1540+1.2*X.
Later period counts the recorded broadcast efficiency index x of some target user jj=1000, then the live streaming efficiency index it predictedTo which the effect of its live streaming can be predicted.
Embodiment three
Fig. 4 is the structural schematic diagram of a kind of video process apparatus that the embodiment of the present invention three provides, which specifically can be with
Including following module:
Sample recorded broadcast behavioral data statistical module 410, the recorded broadcast video statistics recorded broadcast behavior for being issued to sample of users
Data;
Behavioral data statistical module 420 is broadcast live in sample, and the live video for presiding over to the sample of users counts live streaming
Behavioral data;
Sample recorded broadcast efficiency index computing module 430, by according to the recorded broadcast behavioral data to the sample of users based on
Calculate recorded broadcast efficiency index;
Sample be broadcast live efficiency index computing module 440, by according to the live streaming behavioral data to the sample of users based on
Calculate live streaming efficiency index;
Be broadcast live prediction model training module 450, for training live streaming prediction model, be fitted the recorded broadcast efficiency index with
Correlation between the live streaming efficiency index.
In one embodiment of the invention, the sample recorded broadcast behavioral data statistical module 410 includes:
Sample of users determines submodule, for determining while issuing recorded broadcast video and preside over the user of live video, makees
For sample of users;
Statistic submodule is issued, the recorded broadcast video for issuing before starting to preside over live video to the sample of users
Count recorded broadcast behavioral data.
In one embodiment of the invention, the sample recorded broadcast efficiency index computing module 430 includes:
Sample recorded broadcast characteristic value computational submodule is obtained for configuring weight to each recorded broadcast behavioral data respectively
Recorded broadcast characteristic value;
Sample recorded broadcast characteristic value summation submodule, for calculating the sum of described recorded broadcast characteristic value, as the sample of users
Recorded broadcast efficiency index.
In one embodiment of the invention, the sample live streaming efficiency index computing module 440 includes:
Characteristic value computational submodule is broadcast live in sample, for configuring weight to each live streaming behavioral data respectively, obtains
Characteristic value is broadcast live;
Characteristic value summation submodule is broadcast live in sample, for calculating the sum of described live streaming characteristic value, as the sample of users
Live streaming efficiency index.
In one embodiment of the invention, the live streaming prediction model training module 450 includes:
Submodule is arranged in dependent variable, the dependent variable for setting the recorded broadcast efficiency index in live streaming prediction model;
Submodule is arranged in independent variable, for setting becoming in the live streaming prediction model certainly for the live streaming efficiency index
Amount;
Correlation is fitted submodule, the correlation for being fitted between the dependent variable and the independent variable, to obtain
State the model parameter in live streaming prediction model.
Video process apparatus provided by the embodiment of the present invention can be performed at video provided by any embodiment of the invention
Reason method has the corresponding functional module of execution method and beneficial effect.
Example IV
Fig. 5 is the structural schematic diagram of a kind of video process apparatus that the embodiment of the present invention three provides, which specifically can be with
Including following module:
Target recorded broadcast behavioral data statistical module 510, the recorded broadcast video statistics recorded broadcast behavior for being issued to target user
Data;
Target recorded broadcast efficiency index computing module 520, by according to the recorded broadcast behavioral data to the target user based on
Calculate recorded broadcast efficiency index;
Efficiency index prediction module 530 is broadcast live in target, pre- for the recorded broadcast efficiency index to be input to preset live streaming
It surveys in model, to predict that the target user presides over the live streaming efficiency index of live video view.
In the concrete realization, the recorded broadcast behavioral data includes following at least one:
Row is interacted between the publication behavioral data of target user, the watching behavior data of spectators, target user and spectators
For data;
Wherein, the watching behavior data of the spectators include average viewing amount and/or average transfer amount;
Mutual-action behavior data between the target user and spectators include the equalization point amount of praising and/or average review amount.
In one embodiment of the invention, the target recorded broadcast behavioral data statistical module 510 includes:
Target user determines submodule, for determining the user for having issued recorded broadcast video and not presided over live video, as
Target user;
Preside over statistic submodule, the recorded broadcast video statistics recorded broadcast behavioral data for issuing to the target user.
In one embodiment of the invention, the target recorded broadcast efficiency index computing module 520 includes:
Target recorded broadcast characteristic value computational submodule is obtained for configuring weight to each recorded broadcast behavioral data respectively
Recorded broadcast characteristic value;
Target recorded broadcast characteristic value summation submodule, for calculating the sum of described recorded broadcast characteristic value, as the target user
Recorded broadcast efficiency index.
In one embodiment of the invention, the live streaming prediction model includes that the first model parameter and the second model are joined
Number;
Efficiency index prediction module 530 is broadcast live in the target
Product computational submodule, for calculating and joining with second model using the recorded broadcast efficiency index as dependent variable
Several products;
Submodule of summing is obtained for calculating the sum of the product and first model parameter as the straight of independent variable
Broadcast efficiency index.
In one embodiment of the invention, further includes:
Live broadcast service processing module, for being broadcast live at business according to the live streaming efficiency index to the target user
Reason.
In one embodiment of the invention, the live broadcast service processing module includes:
Sorting sub-module, for being ranked up according to the live streaming efficiency index to the target user;
List of starting broadcasting generates submodule, for generating list of starting broadcasting to the target user after sequence;
Alternatively,
Feature user selects submodule, preset for selecting the live streaming efficiency index to meet from the target user
The feature user for the condition that starts broadcasting;
The prompt information that starts broadcasting sending submodule, for sending the prompt information that starts broadcasting to the feature user.
Video process apparatus provided by the embodiment of the present invention can be performed at video provided by any embodiment of the invention
Reason method has the corresponding functional module of execution method and beneficial effect.
Embodiment five
Fig. 6 is a kind of structural schematic diagram for calculating equipment that the embodiment of the present invention five provides, as shown in fig. 6, the calculating is set
Standby includes processor 600, memory 610, input unit 620 and output device 630;Calculate the quantity of processor 600 in equipment
It can be one or more, in Fig. 6 by taking a processor 600 as an example;Calculate processor 600 in equipment, memory 610, defeated
Entering device 620 can be connected with output device 630 by bus or other modes, in Fig. 6 for being connected by bus.
Memory 610 is used as a kind of computer readable storage medium, can be used for storing software program, journey can be performed in computer
Sequence and module, if the corresponding program instruction/module of the method for processing video frequency in the embodiment of the present invention is (for example, as shown in Figure 4
Sample recorded broadcast behavioral data statistical module 410, sample live streaming behavioral data statistical module 420, sample recorded broadcast efficiency index calculate
Module 430, sample live streaming efficiency index computing module 440 and live streaming prediction model training module 450, alternatively, as shown in Figure 5
Target recorded broadcast behavioral data statistical module 510, target recorded broadcast efficiency index computing module 520 and target live streaming efficiency index prediction
Module 530).Software program, instruction and the module that processor 600 is stored in memory 610 by operation, thereby executing meter
The various function application and data processing for calculating equipment, that is, realize above-mentioned method for processing video frequency.
Memory 610 can mainly include storing program area and storage data area, wherein storing program area can store operation system
Application program needed for system, at least one function;Storage data area, which can be stored, uses created data etc. according to terminal.This
Outside, memory 610 may include high-speed random access memory, can also include nonvolatile memory, for example, at least one
Disk memory, flush memory device or other non-volatile solid state memory parts.In some instances, memory 610 can be into one
Step includes the memory remotely located relative to processor 600, these remote memories can be set by network connection to calculating
It is standby.The example of above-mentioned network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Input unit 620 can be used for receiving the number or character information of input, and generates and set with the user for calculating equipment
It sets and the related key signals of function control inputs.Output device 630 may include that display screen etc. shows equipment.
Embodiment six
The embodiment of the present invention six also provides a kind of storage medium comprising computer executable instructions, and the computer can be held
Row instruction by computer processor when being executed for executing a kind of method for processing video frequency.
In one embodiment, this method comprises:
To the recorded broadcast video statistics recorded broadcast behavioral data of sample of users publication;
The live video statistics live streaming behavioral data that the sample of users is presided over;
Recorded broadcast efficiency index is calculated to the sample of users according to the recorded broadcast behavioral data;
Live streaming efficiency index is calculated to the sample of users according to the live streaming behavioral data;
Training live streaming prediction model is related between the recorded broadcast efficiency index and the live streaming efficiency index to be fitted
Property.
In another embodiment, this method comprises:
To the recorded broadcast video statistics recorded broadcast behavioral data of target user's publication;
Recorded broadcast efficiency index is calculated to the target user according to the recorded broadcast behavioral data;
The recorded broadcast efficiency index is input in preset live streaming prediction model, to predict that it is straight that the target user presides over
Broadcast the live streaming efficiency index of video view.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
Video processing provided by any embodiment of the invention can also be performed in the method operation that executable instruction is not limited to the described above
Relevant operation in method
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.Based on this understanding, technical solution of the present invention substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions use so that a calculating equipment
(can be personal computer, server or the network equipment etc.) executes method described in each embodiment of the present invention.
It is worth noting that, included each unit and module are only pressed in the embodiment of above-mentioned video process apparatus
It is divided, but is not limited to the above division according to function logic, as long as corresponding functions can be realized;In addition,
The specific name of each functional unit is also only for convenience of distinguishing each other, the protection scope being not intended to restrict the invention.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of method for processing video frequency characterized by comprising
To the recorded broadcast video statistics recorded broadcast behavioral data of target user's publication;
Recorded broadcast efficiency index is calculated to the target user according to the recorded broadcast behavioral data;
The recorded broadcast efficiency index is input in preset live streaming prediction model, to predict that the target user presides over live streaming view
The live streaming efficiency index of frequency view.
2. the method according to claim 1, wherein the recorded broadcast behavioral data includes following at least one:
The mutual-action behavior number of target user issued between behavioral data, the watching behavior data of spectators, target user and spectators
According to;
Wherein, the watching behavior data of the spectators include average viewing amount and/or average transfer amount;
Mutual-action behavior data between the target user and spectators include the equalization point amount of praising and/or average review amount.
3. the method according to claim 1, wherein the recorded broadcast video statistics recorded broadcast to target user's publication
Behavioral data, comprising:
The user for having issued recorded broadcast video and not presided over live video is determined, as target user;
To the recorded broadcast video statistics recorded broadcast behavioral data of target user publication.
4. method according to claim 1-3, which is characterized in that it is described according to the recorded broadcast behavioral data to institute
It states target user and calculates recorded broadcast efficiency index, comprising:
Weight is configured to each recorded broadcast behavioral data respectively, obtains recorded broadcast characteristic value;
The sum of described recorded broadcast characteristic value is calculated, the recorded broadcast efficiency index as the target user.
5. method according to claim 1-3, which is characterized in that the live streaming prediction model includes the first model
Parameter and the second model parameter;
It is described that the recorded broadcast efficiency index is input in preset live streaming prediction model, to predict that it is straight that the target user presides over
Broadcast the live streaming efficiency index of video view, comprising:
Using the recorded broadcast efficiency index as dependent variable, the product with second model parameter is calculated;
The sum of the product and first model parameter are calculated, the live streaming efficiency index as independent variable is obtained.
6. method according to claim 1-3, which is characterized in that further include:
Business processing is broadcast live to the target user according to the live streaming efficiency index.
7. according to the method described in claim 6, it is characterized in that, described use the target according to the live streaming efficiency index
Family is broadcast live business processing, comprising:
The target user is ranked up according to the live streaming efficiency index;
List of starting broadcasting is generated to the target user after sequence;
Alternatively,
The live streaming efficiency index is selected to meet the feature user of the preset condition that starts broadcasting from the target user;
The prompt information that starts broadcasting is sent to the feature user.
8. a kind of video process apparatus characterized by comprising
Target recorded broadcast behavioral data statistical module, the recorded broadcast video statistics recorded broadcast behavioral data for being issued to target user;
Target recorded broadcast efficiency index computing module, for calculating recorded broadcast effect to the target user according to the recorded broadcast behavioral data
Fruit index;
Efficiency index prediction module is broadcast live in target, for the recorded broadcast efficiency index to be input to preset live streaming prediction model
In, to predict that the target user presides over the live streaming efficiency index of live video view.
9. a kind of calculating equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor is realized when executing described program at the video as described in any in claim 1-7
Reason method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The method for processing video frequency as described in any in claim 1-7 is realized when execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811425810.6A CN109327739B (en) | 2018-11-27 | 2018-11-27 | Video processing method and device, computing equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811425810.6A CN109327739B (en) | 2018-11-27 | 2018-11-27 | Video processing method and device, computing equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109327739A true CN109327739A (en) | 2019-02-12 |
CN109327739B CN109327739B (en) | 2022-02-25 |
Family
ID=65259047
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811425810.6A Active CN109327739B (en) | 2018-11-27 | 2018-11-27 | Video processing method and device, computing equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109327739B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111741367A (en) * | 2020-07-23 | 2020-10-02 | 腾讯科技(深圳)有限公司 | Video interaction method and device, electronic equipment and computer readable storage medium |
CN112200639A (en) * | 2020-10-30 | 2021-01-08 | 杭州时趣信息技术有限公司 | Information flow model construction method, device and medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150347416A1 (en) * | 2014-05-28 | 2015-12-03 | Xiaomi Inc. | Method and apparatus for recommending multimedia resource |
CN105893561A (en) * | 2016-03-31 | 2016-08-24 | 北京奇艺世纪科技有限公司 | Ordering method and device |
US20170169040A1 (en) * | 2015-12-15 | 2017-06-15 | Le Holdings (Beijing) Co., Ltd. | Method and electronic device for recommending video |
CN106899856A (en) * | 2017-03-31 | 2017-06-27 | 百度在线网络技术(北京)有限公司 | Method and apparatus for exporting main broadcaster's information |
CN106992974A (en) * | 2017-03-17 | 2017-07-28 | 腾讯科技(深圳)有限公司 | A kind of live video information monitoring method, device and equipment |
-
2018
- 2018-11-27 CN CN201811425810.6A patent/CN109327739B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150347416A1 (en) * | 2014-05-28 | 2015-12-03 | Xiaomi Inc. | Method and apparatus for recommending multimedia resource |
US20170169040A1 (en) * | 2015-12-15 | 2017-06-15 | Le Holdings (Beijing) Co., Ltd. | Method and electronic device for recommending video |
CN105893561A (en) * | 2016-03-31 | 2016-08-24 | 北京奇艺世纪科技有限公司 | Ordering method and device |
CN106992974A (en) * | 2017-03-17 | 2017-07-28 | 腾讯科技(深圳)有限公司 | A kind of live video information monitoring method, device and equipment |
CN106899856A (en) * | 2017-03-31 | 2017-06-27 | 百度在线网络技术(北京)有限公司 | Method and apparatus for exporting main broadcaster's information |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111741367A (en) * | 2020-07-23 | 2020-10-02 | 腾讯科技(深圳)有限公司 | Video interaction method and device, electronic equipment and computer readable storage medium |
CN112200639A (en) * | 2020-10-30 | 2021-01-08 | 杭州时趣信息技术有限公司 | Information flow model construction method, device and medium |
Also Published As
Publication number | Publication date |
---|---|
CN109327739B (en) | 2022-02-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11409792B2 (en) | System and method for streaming individualized media content | |
US10341701B2 (en) | Clustering and adjudication to determine a recommendation of multimedia content | |
Webster | The duality of media: A structurational theory of public attention | |
Napoli | Audience evolution: New technologies and the transformation of media audiences | |
Napoli | The audience as product, consumer, and producer in the contemporary media marketplace | |
CN109783686A (en) | Behavioral data processing method, device, terminal device and storage medium | |
CN109451326A (en) | A kind of methods of exhibiting, device, server and the storage medium of main broadcaster's information | |
Anderson | Beyond the article: Frontiers of editorial and commercial innovation | |
KR20150020570A (en) | System and method for real-time composite broadcast with moderation mechanism for multiple media feeds | |
CN110149525A (en) | A kind of live broadcasting method, device, equipment and storage medium | |
CN109408639A (en) | A kind of barrage classification method, device, equipment and storage medium | |
CN110287372A (en) | Label for negative-feedback determines method, video recommendation method and its device | |
US20200074481A1 (en) | System, method, and device for analyzing media asset data | |
CN103984690A (en) | Creating playlists | |
WO2020007266A1 (en) | Method and device for managing dynamic shared message, storage medium, and terminal | |
Kosterich | Reconfiguring the “hits”: The new portrait of television program success in an era of big data | |
CN108668147A (en) | A kind of method and mobile terminal of optimization live streaming application | |
CN108320168A (en) | A kind of data analysing method and device | |
CN109729377A (en) | A kind of method for pushing, device, computer equipment and the storage medium of main broadcaster's information | |
CN109327739A (en) | A kind of method for processing video frequency, calculates equipment and storage medium at device | |
Noh | Dual portfolio management strategies of online subscription video on demand (SVOD) companies: a genre perspective | |
Martin et al. | Newstream: a multi-device, cross-medium, and socially aware approach to news content | |
CN107810638A (en) | By the transmission for skipping redundancy fragment optimization order content | |
CN109033190A (en) | A kind of method for pushing of recommendation information, device and equipment | |
Chen et al. | A lifetime model of online video popularity |
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 |