CN109327739B - Video processing method and device, computing equipment and storage medium - Google Patents
Video processing method and device, computing equipment and storage medium Download PDFInfo
- Publication number
- CN109327739B CN109327739B CN201811425810.6A CN201811425810A CN109327739B CN 109327739 B CN109327739 B CN 109327739B CN 201811425810 A CN201811425810 A CN 201811425810A CN 109327739 B CN109327739 B CN 109327739B
- Authority
- CN
- China
- Prior art keywords
- broadcast
- recorded
- behavior data
- live
- video
- 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.)
- Active
Links
Images
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
Abstract
The embodiment of the invention discloses a video processing method, a video processing device, computing equipment and a storage medium. The method comprises the following steps: counting recorded and broadcast behavior data of recorded and broadcast videos issued by target users; calculating a recorded broadcast effect index for the target user according to the recorded broadcast behavior data; and inputting the recorded broadcast effect index into a preset live broadcast prediction model so as to predict the live broadcast effect index of the target user host live broadcast video. And predicting the live broadcast effect index by using the live broadcast prediction model, so that a proper target user is selected to set a live broadcast video service according to the live broadcast effect index, the effect of the target user in hosting the live broadcast video is ensured, and the resource utilization rate of the platform is improved.
Description
Technical Field
The embodiment of the invention relates to a live broadcast technology, in particular to a video processing method, a video processing device, a computing device and a storage medium.
Background
With the development of network science and technology, especially the wide popularization of mobile terminals, recorded and played videos such as short videos and the like are rapidly developed.
Because live broadcasting can be used as one of important tools for maintaining the relation between a video owner and audiences, more and more platforms newly develop live broadcasting services on the basis of the original recorded and broadcast videos, and the video owner can maintain the recorded and broadcast videos and the live broadcast videos at the same time.
However, recorded and broadcast videos and live videos are two services with different properties, and a part of video owners can adapt to the characteristics of the recorded and broadcast videos but do not necessarily adapt to the characteristics of the live videos, so that the part of video owners have poor effect when hosting the live videos, and the resource utilization rate of the platform is low.
Disclosure of Invention
Embodiments of the present invention provide a video processing method and apparatus, a computing device, and a storage medium, so as to solve the problem that a part of video owners have poor effect when hosting a live video, which results in low resource utilization of a platform.
In a first aspect, an embodiment of the present invention provides a video processing method, including:
counting recorded and broadcast behavior data of recorded and broadcast videos issued by sample users;
counting live broadcast behavior data of the live broadcast video hosted by the sample user;
calculating a recording and broadcasting effect index for the sample user according to the recording and broadcasting behavior data;
calculating a live broadcast effect index for the sample user according to the live broadcast behavior data;
and training a live broadcast prediction model to fit the correlation between the recorded broadcast effect index and the live broadcast effect index.
In a second aspect, an embodiment of the present invention further provides a video processing method, including:
counting recorded and broadcast behavior data of recorded and broadcast videos issued by target users;
calculating a recorded broadcast effect index for the target user according to the recorded broadcast behavior data;
and inputting the recorded broadcast effect index into a preset live broadcast prediction model so as to predict the live broadcast effect index of the target user host live broadcast video.
In a third aspect, an embodiment of the present invention further provides a video processing apparatus, including:
the sample recorded broadcast behavior data statistics module is used for counting recorded broadcast behavior data of recorded broadcast videos issued by sample users;
the sample live broadcast behavior data statistics module is used for counting live broadcast behavior data of live broadcast videos hosted by the sample users;
the sample recording and broadcasting effect index calculation module is used for calculating a recording and broadcasting effect index for the sample user according to the recording and broadcasting behavior data;
the sample live broadcast effect index calculation module is used for calculating a live broadcast effect index for the sample user according to the live broadcast behavior data;
and the live broadcast prediction model training module is used for training a live broadcast prediction model so as to fit the correlation between the recorded broadcast effect index and the live broadcast effect index.
In a fourth aspect, an embodiment of the present invention further provides a video processing apparatus, including:
the target recorded broadcast behavior data statistics module is used for counting recorded broadcast behavior data of recorded broadcast videos issued by target users;
the target recorded broadcast effect index calculation module is used for calculating a recorded broadcast effect index for the target user according to the recorded broadcast behavior data;
and the target live broadcast effect index prediction module is used for inputting the recorded broadcast effect index into a preset live broadcast prediction model so as to predict the live broadcast effect index of the target user host live broadcast video.
In a fifth aspect, an embodiment of the present invention further provides a computing device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the video processing method provided in the first aspect or the second aspect when executing the program.
In a sixth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the video processing method provided in the first aspect or the second aspect of the present invention.
In the embodiment of the invention, recorded and broadcast behavior data of recorded and broadcast videos released by a target user are counted, a recorded and broadcast effect index is calculated for the target user according to the recorded and broadcast behavior data, the recorded and broadcast effect index is input into a preset live broadcast prediction model so as to predict the live broadcast effect index of a live broadcast video view hosted by the target user, thus a proper target user is selected to set a live broadcast video service according to the live broadcast effect index, the effect of the live broadcast video hosted by the target user is ensured, and the resource utilization rate of a platform is improved.
Drawings
Fig. 1 is a flowchart of a video processing method according to an embodiment of the present invention;
fig. 2A and fig. 2B are diagrams illustrating a live video according to an embodiment of the present invention;
fig. 3 is a flowchart of a video processing method according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of a video processing apparatus according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of a video processing apparatus according to a fourth embodiment of the present invention;
fig. 6 is a schematic structural diagram of a computing device according to a fifth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a video processing method according to an embodiment of the present invention, where this embodiment is applicable to predicting, on a platform for performing recorded broadcast video services, an effect that a video owner supports live broadcast video services, where the method may be executed by a training device of a live broadcast prediction model, and the training device of the live broadcast prediction model may be implemented by hardware and/or software, and the method specifically includes the following steps:
and S110, counting recorded and broadcast behavior data of the recorded and broadcast video issued by the sample user.
In the embodiment of the present invention, the service of recording and broadcasting a video, so-called recording and broadcasting a video, is video data that can be produced offline, for example, a short video, a micro-movie, a creative advertisement, and the like, with respect to a live video.
The recorded and broadcast video released by the user refers to the platform, and audiences load the recorded and broadcast video from the platform through a browser, a short video application and other clients and perform interaction.
It should be noted that, for recorded video, the user is also referred to as a video master or an up master, that is, a user who distributes recorded video, so that the recorded video is not necessarily original, and includes that the recorded video is re-loaded or a deleted video original is uploaded, which are both referred to as the up master.
For the platform, recording the recorded and broadcast behavior data of the user and/or the audience aiming at the recorded and broadcast video in the log, selecting the user who simultaneously opens the recorded and broadcast video service and the live video service from the log, and taking the selected user as a sample user to count the recorded and broadcast behavior data of the recorded and broadcast video.
Specifically, the recorded broadcast behavior data may include at least one of the following types:
the method comprises the following steps of distributing behavior data of sample users, watching behavior data of audiences and interaction behavior data between the sample users and the audiences.
The release behavior data of the sample user may refer to data independently generated when the sample user performs operations such as making and uploading a recorded and broadcasted video, for example, the video length, the uploading time, the video type, the uploading location, and the like, and at this time, no interaction occurs between the sample user and the audience.
The viewing behavior data of the viewer may refer to data independently generated by the viewer when viewing the recorded video distributed by the sample user, for example, the forwarded video, the viewing time, the viewing amount, the viewing place, the device model, and the like, when no interaction occurs between the sample user and the viewer.
The interaction behavior data between the sample user and the audience can refer to data generated by interaction between the sample user and the audience when the audience watches recorded and broadcast videos released by the sample user.
By interaction, it may be meant a behavior that involves both the sample user and the viewer, e.g., the viewer sending a comment to a recorded video, the viewer liking the recorded video, etc.
In one example, the statistical recorded broadcast behavior data includes at least one of:
1. average amount of viewing
The average watching amount belongs to the watching behavior data of audiences, the watching amount of each recorded and broadcasted video issued by the sample user in a period of time is collected, and the average value is calculated to obtain the average watching amount.
2. Average amount of praise
The average praise amount belongs to interaction behavior data between the sample users and audiences, the praise amounts of all recorded and played videos released by the sample users in a period of time are collected, and the average value is calculated to obtain the average praise amount.
It should be noted that the praise expresses the positive emotion of the audience to the sample user, which may also be called like, favorite, praise, support, and so on.
3. Mean amount of comments
The average comment amount belongs to interaction behavior data between the sample users and audiences, the comment amount of each recorded and broadcasted video published by the sample users in a period of time is collected, and the average value is calculated to obtain the average comment amount.
4. Average forwarding amount
The average forwarding amount belongs to the watching behavior data of audiences, the number of recorded and broadcast videos which are issued by the audience forwarding sample users in a period of time is collected, and the average value is calculated to obtain the average forwarding amount.
Of course, the recorded broadcast behavior data of the statistics is only an example, and when the embodiment of the present invention is implemented, other statistical recorded broadcast behavior data may be set according to an actual situation, which is not limited in this embodiment of the present invention. In addition, in addition to the statistical recording and broadcasting behavior data, a person skilled in the art may also use other statistical recording and broadcasting behavior data according to actual needs, which is not limited in this embodiment of the present invention.
In one embodiment, to improve the accuracy of the fit of the influence of the recorded and broadcast video on the live video, independent recorded and broadcast behavior data may be counted for the recorded and broadcast video.
Specifically, the users who release the recorded and broadcast video and host the live video at the same time are determined to be used as sample users, and recorded and broadcast behavior data of the recorded and broadcast video released by the sample users in a preset time period before the live video starts to be hosted are counted.
The start of hosting the live video refers to that only the recorded and broadcast video service is originally opened, and on the basis, the live video service is newly opened, namely recorded and broadcast video statistical recorded and broadcast behavior data issued when a sample user does not open the live video service is obtained.
Of course, in a case where it is inconvenient to count the recorded and broadcast video distributed by the sample user before the live video starts to be hosted, the recorded and broadcast behavior data of the recorded and broadcast video distributed by the sample user after the live video starts to be hosted may also be counted, which is not limited in this embodiment.
And S120, counting live broadcast behavior data of the live broadcast video hosted by the sample user.
In the embodiment of the present invention, the service of the live video, so-called live video, performed by the platform, refers to video data produced in real time, such as media and activity live broadcast, game live broadcast, show live broadcast, social live broadcast, and the like, as compared with recorded and broadcast video.
It should be noted that, for live video, the user is also referred to as a webcast, that is, a user who hosts the live video, and the content of the live video may be the webcast itself or something else.
In one example, as shown in fig. 2A, the recorded video and the live video are on the same page, that is, the recorded video and the live video are displayed simultaneously on the same page, and in order to distinguish the live video from a large amount of recorded video, prompt information, such as "live" may be loaded in the information of the live video.
In another example, as shown in fig. 2B, the recorded video and the live video are in different pages, and these pages can be switched by TAG (TAG), the recorded video is displayed in the page corresponding to the TAG "video", and the live video is displayed in the page corresponding to the TAG "live".
Of course, the display mode of the live video is only an example, and when the embodiment of the present invention is implemented, display modes of other live videos may be set according to an actual situation, which is not limited in the embodiment of the present invention. In addition, besides the display mode of the live video, a person skilled in the art may also adopt other display modes of the live video according to actual needs, and the embodiment of the present invention is not limited to this.
For the platform, live broadcast behavior data of a user and/or audience aiming at recorded and broadcast videos can be recorded in a log, a video owner which simultaneously opens a recorded and broadcast video service and a live broadcast video service is selected from the log, the video owner is used as a sample user, and live broadcast behavior data are counted for the live broadcast video hosted by the sample user.
Specifically, the recorded broadcast behavior data may include at least one of the following types:
the data of the hosting behavior of the sample user, the data of the viewing behavior of the audience, and the data of the interaction behavior between the sample user and the audience.
The release behavior data of the sample user may refer to data independently generated when the sample user supports recording and playing operations, for example, a live broadcast time length, a live broadcast type, a live broadcast location, and the like, where no interaction occurs between the sample user and the audience.
The viewing behavior data of the audience may refer to data independently generated by the audience while viewing live video supported by the sample user, such as the number of online people, viewing time, viewing frequency, viewing place, device model, and the like, when no interaction occurs between the sample user and the audience.
The interaction behavior data between the sample user and the audience may refer to data generated by the audience interacting between the sample user and the audience while viewing a live video hosted by the sample user.
The interaction may refer to actions related to the sample user and the audience, for example, the audience sends a virtual article to the sample user, the audience sends a barrage to a recorded video, the sample user gives a virtual coin to the audience, the sample user pushes business data (such as commodity data) to the audience, and the like.
In one example, the counted live behavior data includes at least one of:
1. average number of on-line persons
The average online number belongs to the watching behavior data of audiences, the online number of each live broadcast video hosted by the sample user in a period of time is collected, and the average value is calculated to obtain the average online number.
2. Average number of viewers transmitting barrage
The average number of the audiences who send the barrage belongs to the interactive behavior data between the sample users and the audiences, the number of the audiences who send the barrage in each live video released by the sample users in a period of time is collected, and the average value is calculated to obtain the average number of the audiences who send the barrage.
3. Average number of viewers transmitting virtual objects
The average number of the audiences sending the virtual objects belongs to interaction behavior data between the sample user and the audiences, the number of the audiences sending the virtual objects in each live video hosted by the sample user in a period of time is collected, and the average value is calculated to obtain the average number of the audiences sending the virtual objects.
Of course, the counted live broadcast behavior data is only used as an example, and when the embodiment of the present invention is implemented, other counted live broadcast behavior data may be set according to an actual situation, which is not limited in this embodiment of the present invention. In addition, besides the above-mentioned statistical live broadcast behavior data, a person skilled in the art may also adopt other statistical live broadcast behavior data according to actual needs, which is not limited in the embodiment of the present invention.
In one embodiment, to improve the accuracy of the fit of the influence of the recorded and broadcast video on the live video, independent recorded and broadcast behavior data may be counted for the recorded and broadcast video.
Specifically, the method comprises the steps of determining users who release recorded and broadcast videos and host live videos at the same time, using the users as sample users, and counting live broadcast behavior data of the live broadcast videos which are hosted by the sample users in a preset time period after the sample users start hosting the live broadcast videos.
And the time period for counting the recorded broadcasting behavior data and the time period for counting the live broadcasting behavior data are kept continuous.
And S130, calculating a recorded broadcast effect index for the sample user according to the recorded broadcast behavior data.
In the specific implementation, the recorded broadcast behavior data is related to the file, plan and other capabilities of the sample user, the stability is high, the recorded broadcast effect index can be calculated by referring to the recorded broadcast behavior data, and the situation that the sample user issues the recorded broadcast video is visually reflected.
In one embodiment, weights are configured for each recorded broadcast behavior data respectively, and recorded broadcast characteristic values are obtained.
And calculating the sum of the recorded broadcast characteristic values by using a linear regression algorithm to serve as the recorded broadcast effect index of the sample user.
Generally, the weight of the recorded broadcast behavior data is positively correlated with the importance of the recorded broadcast behavior data, i.e. the more important the recorded broadcast behavior data is, the greater the corresponding weight is.
In one example, the recorded broadcast effectiveness index may be calculated by the following formula:
xi＝w1*a+w2*b+w3*c+w4*d
wherein x isiThe index of the recorded broadcast effect of the ith sample user, a is the average watching amount, b is the average praise amount, c is the average appraisal amount, d is the average forwarding amount, w1、w2、w3、w4Are weights.
Further, since the difference in the recording and broadcasting behavior data may be large due to a large difference in the capability between different sample users, in order to reduce the difference in the recording and broadcasting behavior data between different sample users, the recording and broadcasting behavior data may be normalized (for example, by taking 10 as a base number, performing logarithmic conversion).
In addition, the numerical range of the recorded and broadcast behavior data of different types has a large difference, and in order to make the recorded and broadcast behavior data of different types have comparability, the recorded and broadcast behavior data can be subjected to standardized processing.
And S140, calculating a live broadcast effect index for the sample user according to the live broadcast behavior data.
In the specific implementation, the live broadcast behavior data is related to live broadcast activities (such as lottery) and live broadcast capabilities (such as speech talent and talent skill) of the sample users, the volatility is high, the live broadcast effect index can be calculated by referring to the live broadcast behavior data, and the condition that the sample users host live broadcast videos is visually embodied.
In one implementation mode, weights are configured for the live action data respectively, and live characteristic values are obtained.
And calculating the sum of the live broadcast characteristic values by utilizing a linear regression algorithm to serve as the live broadcast effect index of the sample user.
Generally speaking, the weight of the live action data is positively correlated with the importance of the live action data, i.e. the more important the live action data is, the greater the corresponding weight is.
In one example, the recorded broadcast effectiveness index may be calculated by the following formula:
yi＝w5*e+w6*f+w7*g
wherein, yiIs the live broadcast effect index of the ith sample user, e is the average online number of people, f is the average number of the audience sending the barrage, g is the average number of the audience sending the virtual article, w is the average number of the audience sending the virtual article5、w6、w7Are weights.
Further, since the difference in the ability between different sample users is large, the difference in the live broadcast behavior data may be large, and therefore, in order to reduce the difference in the live broadcast behavior data between different sample users, the live broadcast behavior data may be normalized (for example, by taking 10 as a base number, performing logarithmic conversion).
In addition, the numerical range of the live action data of different types is greatly different, and the live action data of different types can be standardized in order to enable the live action data of different types to be comparable with each other.
S150, training a live broadcast prediction model to fit the correlation between the recorded broadcast effect index and the live broadcast effect index.
In specific implementation, the recorded broadcast effect index and the live broadcast effect index can be used as training samples to train a live broadcast prediction model, and the live broadcast prediction model can fit the correlation between the recorded broadcast effect index and the live broadcast effect index and is used for predicting the live broadcast effect index according to the recorded broadcast effect index.
In one embodiment, the live prediction model is a linear regression model.
In this embodiment, the recorded broadcast effect index is set as a dependent variable X in the live broadcast prediction model, and the live broadcast effect index is set as an independent variable Y in the live broadcast prediction model.
Fitting a correlation between the dependent variable and the independent variable toObtaining a live prediction model (Y ═ beta)0+β1X) of the model parameters (including the first model parameter β)0And a second model parameter beta1)。
Of course, besides the linear regression model, other models may be trained as the live prediction model, for example, a decision tree model, a random forest model, and the like, which is not limited in this embodiment.
In the embodiment of the invention, on one hand, recorded and broadcast behavior data of recorded and broadcast videos issued by sample users are counted, recorded and broadcast effect indexes are calculated for the sample users according to the recorded and broadcast behavior data, on the other hand, live broadcast behavior data of live broadcast videos hosted by the sample users are counted, and live broadcast effect indexes are calculated for the sample users according to the live broadcast behavior data, so that a live broadcast prediction model is trained, correlation between the recorded and broadcast effect indexes and the live broadcast effect indexes is fitted, and subsequently, the live broadcast effect indexes can be predicted by using the live broadcast prediction model on the basis of the recorded and broadcast effect indexes of target users, so that appropriate target users are selected according to the live broadcast effect indexes to set up live broadcast video services, the effect of the target users in live broadcast video hosting is ensured, and the resource utilization rate of a platform is improved.
Example two
Fig. 3 is a flowchart of a video processing method according to a second embodiment of the present invention, where this embodiment is applicable to predicting, on a platform that performs a recorded broadcast video service, an effect that a video owner supports a live broadcast video service, and the method may be executed by a live broadcast effect prediction processing apparatus, where the live broadcast effect prediction processing apparatus may be implemented by hardware and/or software, and the method specifically includes the following steps:
and S310, counting recorded and broadcast behavior data of the recorded and broadcast video issued by the target user.
In the embodiment of the present invention, the service of recording and broadcasting a video, so-called recording and broadcasting a video, is video data that can be produced offline, for example, a short video, a micro-movie, a creative advertisement, and the like, with respect to a live video.
The recorded and broadcast video released by the user refers to the platform, and audiences load the recorded and broadcast video from the platform through a browser, a short video application and other clients and perform interaction.
It should be noted that, for recorded broadcast video, the user is also referred to as a video master or an up master, that is, a user who distributes recorded broadcast video, so that the recorded broadcast video is not necessarily original, and includes that the recorded broadcast video is transferred or a deleted lub video original is uploaded, which are both referred to as the up master.
For the platform, recording the recorded and broadcast behavior data of the user and/or the audience aiming at the recorded and broadcast video in the log, selecting the user who simultaneously opens the recorded and broadcast video service and the live video service from the log, and taking the selected user as a target user to count the recorded and broadcast behavior data of the recorded and broadcast video.
Specifically, the recorded broadcast behavior data may include at least one of the following types:
the publishing behavior data of the target user, the watching behavior data of the audience, and the interaction behavior data between the target user and the audience.
The release behavior data of the target user may refer to data independently generated when the target user performs operations such as production and uploading of a recorded and broadcast video, for example, the video length, the uploading time, the video type, the uploading location, and the like, and at this time, no interaction occurs between the target user and the audience.
The viewing behavior data of the viewer may refer to data independently generated when the viewer views the recorded video distributed by the target user, for example, the forwarded video, the viewing time, the viewing amount, the viewing place, the device model, and the like, when no interaction occurs between the target user and the viewer.
The interaction behavior data between the target user and the audience can refer to data generated by interaction between the target user and the audience when the audience watches recorded and broadcast videos issued by the target user.
By interaction, it may be meant a behavior that involves both the target user and the viewer, e.g., the viewer sending a comment to a recorded video, the viewer liking the recorded video, etc.
In one example, the statistical recorded broadcast behavior data includes at least one of:
1. average amount of viewing
The average watching amount belongs to the watching behavior data of audiences, the watching amount of each recorded and broadcasted video released by the target user in a period of time is collected, and the average value is calculated to obtain the average watching amount.
2. Average amount of praise
The average praise amount belongs to interaction behavior data between the target user and the audience, the praise amounts of all recorded and played videos released by the target user in a period of time are collected, and the average value is calculated to obtain the average praise amount.
It should be noted that praise expresses the positive emotion of the target user, which may also be referred to as like, favorite, approval, support, etc.
3. Mean amount of comments
The average comment amount belongs to interaction behavior data between the target user and audiences, the comment amount of each recorded and broadcast video released by the target user in a period of time is collected, and the average value is calculated to obtain the average comment amount.
4. Average forwarding amount
The average forwarding amount belongs to the watching behavior data of audiences, the number of recorded and broadcast videos issued by target users and forwarded by the audiences in a period of time is collected, and the average value is calculated to obtain the average forwarding amount.
Of course, the recorded broadcast behavior data of the statistics is only an example, and when the embodiment of the present invention is implemented, other statistical recorded broadcast behavior data may be set according to an actual situation, which is not limited in this embodiment of the present invention. In addition, in addition to the statistical recording and broadcasting behavior data, a person skilled in the art may also use other statistical recording and broadcasting behavior data according to actual needs, which is not limited in this embodiment of the present invention.
In one embodiment, a user who has released the recorded video and does not host the live video is determined as a target user, and recorded video behavior data is counted for the recorded video released by the target user.
The unsubscribed live video may refer to a service in which only the recorded and broadcast video is opened, and a service in which the live video is not opened, that is, recorded and broadcast video statistical recorded and broadcast behavior data issued when a target user does not open the service in which the live video is opened.
And S320, calculating a recorded broadcast effect index for the target user according to the recorded broadcast behavior data.
In the specific implementation, the recorded broadcast behavior data is related to the file, plan and other capabilities of the target user, the stability is high, the recorded broadcast effect index can be calculated by referring to the recorded broadcast behavior data, and the condition that the target user issues the recorded broadcast video is visually embodied.
In one embodiment, weights are configured for each recorded broadcast behavior data respectively, and recorded broadcast characteristic values are obtained.
And calculating the sum of the recorded broadcast characteristic values by using a linear regression algorithm to serve as the recorded broadcast effect index of the target user.
Generally, the weight of the recorded broadcast behavior data is positively correlated with the importance of the recorded broadcast behavior data, i.e. the more important the recorded broadcast behavior data is, the greater the corresponding weight is.
In one example, the recorded broadcast effectiveness index may be calculated by the following formula:
xj＝w1*a+w2*b+w3*c+w4*d
wherein x isjThe index of the recorded broadcast effect of the jth target user, a is the average watching amount, b is the average praise amount, c is the average appraisal amount, d is the average forwarding amount, w1、w2、w3、w4Are weights.
Further, since the difference in the recording and broadcasting behavior data may be large due to a large difference in the capability between different target users, in order to reduce the difference in the recording and broadcasting behavior data between different target users, the recording and broadcasting behavior data may be normalized (for example, by taking 10 as a base number, performing logarithmic conversion).
In addition, the numerical range of the recorded and broadcast behavior data of different types has a large difference, and in order to make the recorded and broadcast behavior data of different types have comparability, the recorded and broadcast behavior data can be subjected to standardized processing.
S330, inputting the recorded broadcast effect index into a preset live broadcast prediction model so as to predict the live broadcast effect index of the target user host live broadcast video.
In this embodiment, the live broadcast prediction model may fit a correlation between the recorded broadcast effect index and the live broadcast effect index, and is used to predict the live broadcast effect index according to the recorded broadcast effect index.
And inputting the recorded broadcast effect index of the target user into the live broadcast prediction model for processing, outputting the live broadcast effect index of the live broadcast video view hosted by the target user, and predicting the condition of hosting the live broadcast video after the target user sets the service of the live broadcast video.
In general, the larger the live broadcast effect index is, the better the live broadcast effect is, whereas the smaller the live broadcast effect index is, the worse the live broadcast effect is.
In one embodiment, the live prediction model is a linear regression model:
Y＝β0+β1*X
wherein the recording and broadcasting effect index is a dependent variable X, the live broadcasting effect index is set as an independent variable Y, and the first model parameter is beta0The second model parameter is beta1。
In the present embodiment, the recording and broadcasting effect index is used as the dependent variable X, and the second model parameter β is calculated1Product of (b) < beta >1X, calculating product beta1X and a first model parameter β0And summing to obtain a direct broadcast effect index as an independent variable Y.
And then, carrying out live broadcast service processing on the target user according to the live broadcast effect index.
The live service process may refer to a service process related to live broadcast.
In one example, the target users may be sorted by the live effectiveness index, and an playlist may be generated for the sorted target users.
In this example, in addition to the ranking, the recorded broadcast performance index (including recorded broadcast behavior data) and the live broadcast performance index of the target user, other information of the target user, such as registration time, revenue index, etc., may be recorded in the broadcast list.
The broadcast list can be provided for operators to comprehensively refer to whether the service of the live video is opened for the target user.
In another example, a feature user whose live effect index satisfies a preset play condition, such as n (n is a positive integer) live effect indexes with the highest value, a live effect index larger than a preset threshold, and the like, may be selected from the target users.
And sending play prompt information to the characteristic user, and actively proposing to the characteristic user to set up a live video service.
In the embodiment of the invention, recorded and broadcast behavior data of recorded and broadcast videos released by a target user are counted, a recorded and broadcast effect index is calculated for the target user according to the recorded and broadcast behavior data, the recorded and broadcast effect index is input into a preset live broadcast prediction model so as to predict the live broadcast effect index of a live broadcast video view hosted by the target user, thus a proper target user is selected to set a live broadcast video service according to the live broadcast effect index, the effect of the live broadcast video hosted by the target user is ensured, and the resource utilization rate of a platform is improved.
In order to make those skilled in the art better understand the embodiment, the method for predicting the live broadcast effect in the embodiment is described below by using a specific example.
10 short videos are issued by a sample user i, the average watching amount of the statistically obtained short videos is 10000 (the weight is 0.1), the average praise amount is 8000 (the weight is 0.2), the average evaluation amount is 2000 (the weight is 0.4), the average forwarding amount is 3000 (the weight is 0.3), and then the recording and playing effect index x is obtainedi＝0.1*10000+0.2*8000+0.4*2000+0.3*3000＝4300。
The sample user i hosts the live broadcast for 10 times, the average online number of the live broadcast obtained by statistics is 10000 (weight is 0.5), the average number of the audience sending the barrage is 5000 (weight is 0.3), the average number of the audience sending the virtual object is 1000 (weight is 0.2), and then the live broadcast effect index y is obtainedi＝0.5*10000+0.3*5000+0.2*1000＝6700。
The live prediction model was fitted to Y1540 + 1.2X.
The recording and broadcasting effect of a certain target user j is counted at the later stageNumber xj1000, the predicted live broadcast effect index
So that its live effect can be predicted.
EXAMPLE III
Fig. 4 is a schematic structural diagram of a video processing apparatus according to a third embodiment of the present invention, where the apparatus may specifically include the following modules:
the sample recorded broadcast behavior data statistics module 410 is used for counting recorded broadcast behavior data of recorded broadcast videos issued by sample users;
a sample live broadcast behavior data statistics module 420, configured to count live broadcast behavior data of a live broadcast video hosted by the sample user;
the sample recorded broadcast effect index calculation module 430 is configured to calculate a recorded broadcast effect index for the sample user according to the recorded broadcast behavior data;
a sample live broadcast effect index calculation module 440, configured to calculate a live broadcast effect index for the sample user according to the live broadcast behavior data;
and the live broadcast prediction model training module 450 is configured to train a live broadcast prediction model to fit a correlation between the recorded broadcast effect index and the live broadcast effect index.
In an embodiment of the present invention, the sample recorded broadcast behavior data statistics module 410 includes:
the sample user determining submodule is used for determining users who release recorded broadcast videos and host live broadcast videos at the same time to serve as sample users;
and the release statistics submodule is used for counting recorded broadcast behavior data of the recorded broadcast video released by the sample user before the live broadcast video starts to be hosted.
In an embodiment of the present invention, the sample recording and broadcasting effectiveness index calculating module 430 includes:
the sample recorded broadcast characteristic value operator module is used for configuring weight for each recorded broadcast behavior data respectively to obtain recorded broadcast characteristic values;
and the sample recorded broadcast characteristic value summation submodule is used for calculating the sum of the recorded broadcast characteristic values to serve as the recorded broadcast effect index of the sample user.
In an embodiment of the present invention, the sample live effectiveness index calculation module 440 includes:
the sample live broadcast characteristic value operator module is used for configuring weight for each live broadcast behavior data respectively to obtain live broadcast characteristic values;
and the sample live broadcast characteristic value summation submodule is used for calculating the sum of the live broadcast characteristic values to serve as the live broadcast effect index of the sample user.
In one embodiment of the present invention, the live prediction model training module 450 includes:
the dependent variable setting submodule is used for setting the recording and broadcasting effect index as a dependent variable in a live broadcasting prediction model;
the independent variable setting submodule is used for setting the live broadcast effect index as an independent variable in the live broadcast prediction model;
and the correlation fitting sub-module is used for fitting the correlation between the dependent variable and the independent variable so as to obtain model parameters in the live broadcast prediction model.
The video processing device provided by the embodiment of the invention can execute the video processing method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 5 is a schematic structural diagram of a video processing apparatus according to a third embodiment of the present invention, where the apparatus may specifically include the following modules:
a target recorded broadcast behavior data statistics module 510, configured to count recorded broadcast behavior data of a recorded broadcast video issued by a target user;
a target recorded broadcast effect index calculation module 520, configured to calculate a recorded broadcast effect index for the target user according to the recorded broadcast behavior data;
and a target live broadcast effect index prediction module 530, configured to input the recorded broadcast effect index into a preset live broadcast prediction model, so as to predict a live broadcast effect index of the target user hosting a live broadcast video.
In a specific implementation, the recorded broadcast behavior data includes at least one of:
the method comprises the following steps that release behavior data of a target user, watching behavior data of audiences and interaction behavior data between the target user and the audiences are obtained;
wherein the viewer's viewing behavior data comprises an average viewing volume and/or an average forwarding volume;
the interaction behavior data between the target user and the audience comprises average praise amount and/or average comment amount.
In an embodiment of the present invention, the target recorded broadcast behavior data statistics module 510 includes:
the target user determining submodule is used for determining a user who has released the recorded and broadcast video and does not host the live video as a target user;
and the host counting submodule is used for counting recorded and broadcast behavior data of the recorded and broadcast video released by the target user.
In an embodiment of the present invention, the target recording and broadcasting effect index calculating module 520 includes:
the target recorded broadcast characteristic value operator module is used for configuring weight for each recorded broadcast behavior data respectively to obtain recorded broadcast characteristic values;
and the target recorded broadcast characteristic value summation submodule is used for calculating the sum of the recorded broadcast characteristic values to serve as the recorded broadcast effect index of the target user.
In one embodiment of the invention, the live prediction model comprises a first model parameter and a second model parameter;
the target live broadcast effect index prediction module 530 includes:
the product calculation submodule is used for calculating the product of the recording and broadcasting effect index serving as a dependent variable and the second model parameter;
and the summation submodule is used for calculating the sum of the product and the first model parameter to obtain a live broadcast effect index serving as an independent variable.
In one embodiment of the present invention, further comprising:
and the live broadcast service processing module is used for carrying out live broadcast service processing on the target user according to the live broadcast effect index.
In an embodiment of the present invention, the live service processing module includes:
the sequencing submodule is used for sequencing the target users according to the live broadcast effect indexes;
the play list generation submodule is used for generating a play list for the ordered target users;
alternatively, the first and second electrodes may be,
the characteristic user selection submodule is used for selecting the characteristic user of which the live broadcast effect index meets the preset broadcasting condition from the target user;
and the broadcasting prompt information sending submodule is used for sending broadcasting prompt information to the characteristic user.
The video processing device provided by the embodiment of the invention can execute the video processing method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE five
Fig. 6 is a schematic structural diagram of a computing apparatus according to a fifth embodiment of the present invention, as shown in fig. 6, the computing apparatus includes a processor 600, a memory 610, an input device 620, and an output device 630; the number of processors 600 in the computing device may be one or more, and one processor 600 is taken as an example in fig. 6; the processor 600, memory 610, input device 620, and output device 630 in the computing device may be connected by a bus or other means, as exemplified by a bus connection in fig. 6.
The memory 610 is used as a computer-readable storage medium and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the video processing method in the embodiment of the present invention (for example, the sample recorded broadcast behavior data statistics module 410, the sample live broadcast behavior data statistics module 420, the sample recorded broadcast effect index calculation module 430, the sample live broadcast effect index calculation module 440, and the live broadcast prediction model training module 450 shown in fig. 4, or the target recorded broadcast behavior data statistics module 510, the target recorded broadcast effect index calculation module 520, and the target live broadcast effect index prediction module 530 shown in fig. 5). The processor 600 executes various functional applications of the computing device and data processing by executing software programs, instructions and modules stored in the memory 610, that is, implements the video processing method described above.
The memory 610 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 610 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 610 may further include memory located remotely from processor 600, which may be connected to a computing device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 620 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function controls of the computing device. The output device 630 may include a display device such as a display screen.
EXAMPLE six
An embodiment of the present invention also provides a storage medium containing computer-executable instructions for performing a video processing method when executed by a computer processor.
In one embodiment, the method comprises:
counting recorded and broadcast behavior data of recorded and broadcast videos issued by sample users;
counting live broadcast behavior data of the live broadcast video hosted by the sample user;
calculating a recording and broadcasting effect index for the sample user according to the recording and broadcasting behavior data;
calculating a live broadcast effect index for the sample user according to the live broadcast behavior data;
and training a live broadcast prediction model to fit the correlation between the recorded broadcast effect index and the live broadcast effect index.
In another embodiment, the method comprises:
counting recorded and broadcast behavior data of recorded and broadcast videos issued by target users;
calculating a recorded broadcast effect index for the target user according to the recorded broadcast behavior data;
and inputting the recorded broadcast effect index into a preset live broadcast prediction model so as to predict the live broadcast effect index of the target user host live broadcast video.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the operations of the method described above, and may also perform related operations in the video processing method provided by any embodiment of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computing device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the video processing apparatus, the included units and modules are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (9)
1. A video processing method, comprising:
counting recorded and broadcast behavior data of recorded and broadcast videos issued by target users;
calculating a recorded broadcast effect index for the target user according to the recorded broadcast behavior data;
inputting the recorded broadcast effect index into a preset live broadcast prediction model so as to predict the live broadcast effect index of the target user host live broadcast video;
the calculating a recorded broadcast effect index for the target user according to the recorded broadcast behavior data comprises:
respectively configuring weights for each recorded broadcast behavior data to obtain recorded broadcast characteristic values;
and calculating the sum of the recorded broadcast characteristic values to be used as the recorded broadcast effect index of the target user.
2. The method of claim 1, wherein the recorded broadcast behavior data comprises at least one of:
the method comprises the following steps that release behavior data of a target user, watching behavior data of audiences and interaction behavior data between the target user and the audiences are obtained;
wherein the viewer's viewing behavior data comprises an average viewing volume and/or an average forwarding volume;
the interaction behavior data between the target user and the audience comprises average praise amount and/or average comment amount.
3. The method of claim 1, wherein the statistical recorded broadcast behavior data of the recorded broadcast video distributed to the target user comprises:
determining a user who has released the recorded and broadcast video and does not host the live broadcast video as a target user;
and counting recorded and broadcast behavior data of the recorded and broadcast video issued by the target user.
4. The method of any of claims 1-3, wherein the live predictive model comprises a first model parameter and a second model parameter;
the inputting the recorded broadcast effect index into a preset live broadcast prediction model to predict the live broadcast effect index of the target user host live broadcast video comprises the following steps:
taking the recorded broadcast effect index as a dependent variable, and calculating the product of the recorded broadcast effect index and the second model parameter;
and calculating the sum of the product and the first model parameter to obtain a direct broadcast effect index serving as an independent variable.
5. The method according to any one of claims 1-3, further comprising:
and carrying out live broadcast service processing on the target user according to the live broadcast effect index.
6. The method of claim 5, wherein the performing live service processing on the target user according to the live effectiveness index comprises:
sequencing the target users according to the live broadcast effect indexes;
generating an opening list for the ordered target users;
alternatively, the first and second electrodes may be,
selecting characteristic users with the live broadcast effect indexes meeting preset broadcasting conditions from the target users;
and sending broadcast prompt information to the feature user.
7. A video processing apparatus, comprising:
the target recorded broadcast behavior data statistics module is used for counting recorded broadcast behavior data of recorded broadcast videos issued by target users;
the target recorded broadcast effect index calculation module is used for calculating a recorded broadcast effect index for the target user according to the recorded broadcast behavior data;
the target live broadcast effect index prediction module is used for inputting the recorded broadcast effect index into a preset live broadcast prediction model so as to predict the live broadcast effect index of the live broadcast video hosted by the target user;
the target recorded broadcast effect index calculation module comprises:
the target recorded broadcast characteristic value operator module is used for configuring weight for each recorded broadcast behavior data respectively to obtain recorded broadcast characteristic values;
and the target recorded broadcast characteristic value summation submodule is used for calculating the sum of the recorded broadcast characteristic values to serve as the recorded broadcast effect index of the target user.
8. A computing device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the video processing method of any of claims 1-6 when executing the program.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the video processing method according to any one of claims 1 to 6.
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 CN109327739A (en) | 2019-02-12 |
| CN109327739B true 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) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111741367B (en) * | 2020-07-23 | 2021-06-04 | 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 (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105893561A (en) * | 2016-03-31 | 2016-08-24 | 北京奇艺世纪科技有限公司 | Ordering method and device |
| 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 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104035982B (en) * | 2014-05-28 | 2017-10-20 | 小米科技有限责任公司 | Multimedia resource recommends method and device |
| US20170169040A1 (en) * | 2015-12-15 | 2017-06-15 | Le Holdings (Beijing) Co., Ltd. | Method and electronic device for recommending video |
-
2018
- 2018-11-27 CN CN201811425810.6A patent/CN109327739B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109327739A (en) | 2019-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109241425B (en) | Resource recommendation method, device, equipment and storage medium | |
| KR101913793B1 (en) | Platform show pages | |
| KR102112973B1 (en) | Estimating and displaying social interest in time-based media | |
| US9278288B2 (en) | Automatic generation of a game replay video | |
| CN111698575B (en) | Live highlight video editing method, device, equipment and storage medium | |
| US8839309B2 (en) | Methods and systems for displaying contextually relevant information from a plurality of users in real-time regarding a media asset | |
| CN107705005A (en) | A kind of movie and television contents Valuation Method | |
| CN109829379B (en) | Information processing method, information processing apparatus, server, and storage medium | |
| Cheng et al. | Television meets facebook: The correlation between tv ratings and social media | |
| KR20160046332A (en) | Facepile integrated communications | |
| CN109327739B (en) | Video processing method and device, computing equipment and storage medium | |
| Pickard | The Misinformation Society | |
| Brown | Interoperability as a tool for competition regulation | |
| Shon et al. | Are global over-the-top platforms the destroyers of ecosystems or the catalysts of innovation? | |
| CN113766256A (en) | Live broadcast wind control method and device | |
| CN111581521A (en) | Group member recommendation method, device, server, storage medium and system | |
| CN105956061B (en) | Method and device for determining similarity between users | |
| CN105260906A (en) | Method and device for pushing interactive link | |
| US11541319B2 (en) | System and method for filtering stream chats | |
| CN110139160B (en) | Prediction system and method | |
| CN104991973B (en) | A kind of determination method and apparatus in user interest field | |
| CN111629236B (en) | Friend relationship establishing method, device, equipment and computer readable storage medium | |
| CN111107342B (en) | Audio and video evaluation method, device, equipment and storage medium | |
| Turk et al. | The adoption of terrestrial digital TV: technology push, political will or users' choice? | |
| CN116340813B (en) | User behavior analysis system and method for live platform |
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 |