CN110139160B - Prediction system and method - Google Patents
Prediction system and method Download PDFInfo
- Publication number
- CN110139160B CN110139160B CN201910390091.7A CN201910390091A CN110139160B CN 110139160 B CN110139160 B CN 110139160B CN 201910390091 A CN201910390091 A CN 201910390091A CN 110139160 B CN110139160 B CN 110139160B
- Authority
- CN
- China
- Prior art keywords
- video
- playing
- subsystem
- target
- target 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]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/24—Monitoring of processes or resources, e.g. monitoring of server load, available bandwidth, upstream requests
- H04N21/2407—Monitoring of transmitted content, e.g. distribution time, number of downloads
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
- H04N21/4756—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The embodiment of the invention provides a prediction system and a prediction method. The system comprises: the system comprises an information acquisition subsystem and a calculation engine subsystem; the information acquisition subsystem is used for acquiring parameter values of preset playing parameters of the target video in the playing process and sending the acquired parameter values to the calculation engine subsystem; the preset playing parameters are as follows: play parameters associated with the viewing experience; a compute engine subsystem for receiving parameter values; and calculating the film watching experience score of the film watching user corresponding to the target video based on the parameter value. Compared with the prior art, the method and the device for obtaining the film watching experience score can obtain controllability of the film watching experience score.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a prediction system and method.
Background
Currently, with the continuous development of internet technology, more and more users watch videos through video websites as an entertainment activity. For video websites, in order to attract more users, more and more attention is paid to the quality of service.
The film viewing experience of the user is an important index for measuring the service quality of the video website. It can be understood that, under the condition of the same video content, the higher the quality of the playing picture, the shorter the waiting time for starting playing, the smoother the playing process, and the better the viewing experience of the user.
In the prior art, a film watching experience score of a video provided by a video website is obtained by a user in a mode of performing questionnaire survey on the user watching the video. Specifically, when the user quits playing the video of the video website, a questionnaire survey dialog box is popped out from the page, so that the user can score the video watching experience through the dialog box.
However, the inventor finds that the prior art has at least the following problems in the process of implementing the invention:
when the film watching experience score of the user is obtained in the mode, the operation of the user on the questionnaire is depended on, and the specific expression is as follows: if the user fills out the questionnaire survey dialog, the viewing experience score can be obtained, whereas if the user ignores the questionnaire survey dialog, the viewing experience score cannot be obtained. Therefore, the controllability of the prior art for obtaining the film watching experience score is poor.
Disclosure of Invention
The embodiment of the invention aims to provide a prediction system and a prediction method so as to improve controllability of obtaining a film watching experience score. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides a prediction system, where the prediction system includes: the system comprises an information acquisition subsystem and a calculation engine subsystem;
the information acquisition subsystem is used for acquiring parameter values of preset playing parameters of the target video in the playing process and sending the acquired parameter values to the calculation engine subsystem; wherein, the preset playing parameters are as follows: playing parameters related to the film watching experience, wherein the preset playing parameters at least comprise video average code flow rate;
the calculation engine subsystem is used for receiving the parameter values; and calculating the film watching experience score of the film watching user corresponding to the target video based on the parameter value.
Optionally, in a specific implementation manner, the system further includes a message publishing subsystem;
the information acquisition subsystem sends the acquired parameter values to the calculation engine subsystem, and the method comprises the following steps: the information acquisition subsystem sends the acquired parameter values to the message issuing subsystem;
and the message issuing subsystem is used for receiving the parameter values and sending the received parameter values to the calculation engine subsystem.
Optionally, in a specific implementation manner, the system further includes a data storage subsystem;
the information acquisition subsystem is also used for acquiring a target identifier and playing time corresponding to the target video and sending the target identifier and the playing time to the calculation engine subsystem; the playing time is the system time corresponding to the playing process of the target video;
the computing engine subsystem is further configured to receive the target identifier and the playing time corresponding to the target video; sending the target identification, the playing time and the calculated film watching experience score corresponding to the target video to the data storage subsystem;
and the data storage subsystem is used for receiving and storing the target identification, the playing time and the film watching experience score corresponding to the target video.
Optionally, in a specific implementation manner, the system further includes a visualization subsystem;
the visualization subsystem is used for receiving a data query instruction; sending a data acquisition request to the data storage subsystem based on the data query instruction; receiving target data fed back by the data storage subsystem based on the data acquisition request; presenting the target data to the user; the data query instruction comprises an identifier and query time of a video to be queried, the data acquisition request carries the identifier and query time of the video to be queried, and the target data comprises: in the film watching experience scores corresponding to the identifiers of the videos to be inquired, the film watching experience scores of which the corresponding playing time is matched with the inquiring time;
the data storage subsystem is further configured to receive the data acquisition request, extract the identifier of the video to be queried and the query time from the data acquisition request, query a viewing experience score matching the playing time and the query time in the viewing experience score corresponding to the identifier of the video to be queried, and feed back the queried viewing experience score as target data to the visualization subsystem.
Optionally, in a specific implementation manner, the acquiring, by the information acquisition subsystem, a parameter value of a preset playing parameter of the target video in the playing process includes:
acquiring a playing log of the target video fed back by a client when the target video is played; and extracting parameter values of preset playing parameters of the target video from the playing log.
Optionally, in a specific implementation manner, the calculating, by the distributed real-time calculation engine, a rating of viewing experience of a viewing user corresponding to the target video based on the parameter value includes:
inputting the acquired parameter values into a prediction model obtained by pre-training to obtain a prediction result of the target video watching experience score of a target video watching user corresponding to the target video;
wherein the prediction model is: and training a preset model by adopting first type information and second type information corresponding to each sample user to obtain the model, wherein the first type information corresponding to any sample user is a parameter value of a preset playing parameter of a video watched by the sample user in a playing process, and the second type information corresponding to any sample user is a watching experience score of the video watched by the sample user.
Optionally, in a specific implementation manner, the prediction model is:
y is the rating of the film watching experience of the film watching user of any one video to the video; x is a radical of a fluorine atomiThe parameter value of the ith preset playing parameter is the parameter value of the preset playing parameter in the playing process of the video; w is aiThe weight of the ith preset playing parameter is obtained; and lambda is a penalty coefficient.
Optionally, in a specific implementation manner, the prediction model is:
wherein y is the film watching experience evaluation of any video by the film watching user of the videoDividing r into the grade of the video average code flow rate in the video playing process; x is the number ofiThe parameter value of the target playing parameter i is set;
when the level of the video average code flow rate in the video playing process is each level j in a preset level range, the weight of the target playing parameter i is obtained; lambda is a penalty coefficient; sigmar(j) An activation function when the level of the video average code flow rate in the video playing process is each level j in a preset level range; the target playing parameters are as follows: the preset playing parameter or the playing parameter except the video average code flow rate in the preset playing parameter.
Optionally, in a specific implementation manner, the message publishing subsystem is: distributed publish-subscribe messaging system Kafka.
Optionally, in a specific implementation manner, the compute engine subsystem is: a distributed computing framework Spark Streaming for processing Streaming computing problems.
In a second aspect, an embodiment of the present invention provides a prediction method, which is applied to a prediction system, and the method includes:
collecting parameter values of preset playing parameters of a target video in a playing process; wherein, the preset playing parameters are as follows: play parameters associated with the viewing experience;
and calculating the film watching experience score of the film watching user corresponding to the target video based on the parameter value.
In yet another aspect of the present invention, there is also provided a computer-readable storage medium having stored therein instructions, which when run on a computer, cause the computer to perform any of the above-described prediction methods.
In yet another aspect of the present invention, the present invention also provides a computer program product containing instructions, which when run on a computer, causes the computer to execute any of the prediction methods described above.
As can be seen from the above, with the adoption of the scheme provided by the embodiment of the invention, the information acquisition subsystem can acquire the parameter values of the preset playing parameters of the target video in the playing process after the target video is played, and send the acquired parameter values to the calculation engine subsystem, so that the calculation engine subsystem can calculate the watching experience scores of the watching users corresponding to the target video based on the parameter values. Therefore, when the user film watching experience score is obtained, the film watching experience score of the film watching user corresponding to the target video can be calculated by directly utilizing the parameter value of the preset playing parameter of the target video in the playing process without depending on the operation of the user on the questionnaire, and the controllability of obtaining the film watching experience score is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below.
Fig. 1 is a schematic diagram illustrating a first structure of a prediction system according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating a second exemplary architecture of a prediction system according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a third exemplary embodiment of a prediction system;
FIG. 4 is a diagram illustrating a fourth exemplary architecture of a prediction system according to an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating a fifth exemplary architecture of a prediction system according to an embodiment of the present invention;
fig. 6 is a schematic diagram illustrating a sixth configuration of a prediction system according to an embodiment of the present invention;
fig. 7 is a flowchart illustrating a prediction method according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.
When the prior art is adopted to obtain the film watching experience score of a user, the operation of the user on the questionnaire is depended on, and the specific expression is as follows: if the user fills out the questionnaire survey dialog, the viewing experience score can be obtained, whereas if the user ignores the questionnaire survey dialog, the viewing experience score cannot be obtained. It can be seen that the controllability of the prior art for obtaining the film viewing experience score is poor. In order to solve the problems in the prior art, the embodiment of the invention provides a prediction system.
Next, a prediction system provided in an embodiment of the present invention is described.
Fig. 1 is a schematic structural diagram of a prediction system according to an embodiment of the present invention. As shown in FIG. 1, the system may include an information gathering subsystem 110 and a compute engine subsystem 130;
the information collecting subsystem 110 is configured to collect parameter values of preset playing parameters of a target video during playing, and send the collected parameter values to the computing engine subsystem; the preset playing parameters are as follows: playing parameters related to the film watching experience, wherein the preset playing parameters at least comprise video average code flow rate;
the compute engine subsystem 130 for receiving parameter values; and calculating the film watching experience score of the film watching user corresponding to the target video based on the parameter value.
It can be understood that, in the case of the same video content, the higher the playing picture quality of the video, the shorter the waiting time for starting playing, and the smoother the playing process, the better the user will feel when watching the video. That is to say, in the video playing process, there may be some playing parameters that may affect the viewing experience of the user, for example, the number of times of pause representing whether the playing process is smooth, the video average bitrate representing the picture quality, and the like.
By analyzing the existing viewing experience scores obtained by the questionnaire survey method, the viewing experience scores have different differences under different video average code flow rates. The user is more sensitive to the number of clicks and the elapsed time to start up when the video average bitrate is low, compared to when the video average bitrate is high. While in the case of a substantially similar start-up time as the number of clicks, users generally prefer to give videos with lower average coderate video a relatively lower rating for viewing experience and videos with higher average coderate video a relatively higher rating for viewing experience. Obviously, the video average bitrate can have a large impact on the viewing experience of the target video by the target viewing user. Therefore, in the embodiment of the present invention, at least the video average bitrate may be included in the predicted playing parameters.
In addition, the preset playing parameters may further include at least one of the following playing parameters: the playing start time, the playing start time and video time ratio, the pause time, the pause times and the pause time and video time ratio. Of course, the preset playing parameters may also include other playing parameters, and the embodiment of the present invention is not limited in particular.
Since the preset playing parameter is related to the viewing experience, in order to calculate the score of the viewing experience of the viewing user corresponding to the target video on the target video, the information collecting subsystem 110 may first collect the parameter value of the preset playing parameter of the target video in the playing process.
It should be noted that the target video refers to a video for which the viewing experience score of the corresponding viewing user needs to be determined, and does not have any other limiting meaning. The target video may be determined as one or some of the videos, or may be determined as all videos watched by the user. This is all reasonable.
Since the film watching experience of the user may be for a video with a certain duration, the parameter value acquired by the information acquisition subsystem 110 should be a parameter value of a preset playing parameter of the acquired target video in the playing process when the target video is played over, or when the user exits from the playing of the target video after watching for a certain time.
For example, if the user watches a first episode of a series a through a client of the video website a, the duration of the first episode of the series a is 45 minutes, and when the first episode of the series a is completely played, the information acquisition subsystem 110 may acquire parameter values of preset playing parameters of the first episode of the series a within 45 minutes of the playing.
For another example, the user watches a latest heddles program B through the client of the video website a, the duration of the program is 90 minutes, and the user stops watching and quits playing only after watching the 35 th minute due to work reasons, so that after the user quits playing, the information acquisition subsystem 110 may acquire the parameter value of the preset playing parameter of the program within the played 35 minutes.
In this way, when the information collection subsystem 110 collects the parameter values of the preset playing parameters of the target video during the playing process, the parameter values can be sent to the calculation engine subsystem 130. Further, after receiving the parameter values sent by the information acquisition subsystem 110, the calculation engine subsystem 130 may calculate, based on the received parameter values, the rating of the viewing experience of the viewing user corresponding to the target video.
For clarity, the information gathering subsystem 110 and the calculation engine subsystem 130 will be described in detail later.
As can be seen from the above, with the adoption of the scheme provided by the embodiment of the invention, the information acquisition subsystem can acquire the parameter values of the preset playing parameters of the target video in the playing process after the target video is played, and send the acquired parameter values to the calculation engine subsystem, so that the calculation engine subsystem can calculate the watching experience scores of the watching users corresponding to the target video based on the parameter values. Therefore, when the film watching experience score of the user is obtained, the film watching experience score of the film watching user corresponding to the target video can be calculated by directly utilizing the parameter value of the preset playing parameter of the target video in the playing process without depending on the operation of the user on the questionnaire, and the controllability of obtaining the film watching experience score is improved.
The information collection subsystem 110 and the calculation engine subsystem 130 are described in detail below.
The information collecting subsystem 110 may be: the system is composed of at least one electronic device which can acquire parameter values of preset playing parameters of the target video in the playing process and send the parameter values to other electronic devices in communication connection. For example, a server cluster including a plurality of computers, and the like. This is all reasonable.
It should be noted that the information collecting subsystem 110 may collect parameter values of preset playing parameters of the target video in a playing process in a variety of ways, which is not limited in the embodiment of the present invention.
Optionally, in a specific implementation manner, the step of acquiring, by the information acquisition subsystem 110, a parameter value of a preset playing parameter of the target video in the playing process may include step a:
step A: the method comprises the steps of obtaining a playing log of a target video fed back by a client when the target video is played; and extracting parameter values of preset playing parameters of the target video from the playing logs.
Specifically, when a user watches a target video through a client, the client may generate a play log of the target video in a play process of the target video, where the play log may include information of the client itself and related parameters of the target video in the play process. When the target video is played, the client can obtain the play log of the target video in the playing process. The client may be any type, such as a web page, APP (Application, mobile phone software), and the like, which is reasonable.
Specifically, the information of the client itself may include: IP address, ID, login time, etc.; the relevant parameters of the target video in the playing process may include: the system time, playing duration and parameter values of each playing parameter corresponding to the playing process. The parameter values of the playing parameters may include the parameter values of the preset playing parameters.
Thus, when the playing of the target video is finished, the information acquisition subsystem 110 may obtain a playing log of the target video fed back by embedding points on the client, and further, the information acquisition subsystem 110 may extract a parameter value of a preset playing parameter of the target video in the playing process from the playing log. The play log may be actively fed back to the information collecting subsystem 110 when the target video is played by the client.
Further, the compute engine subsystem 130 may be: the system is composed of at least one electronic device which can receive the parameter values sent by the information acquisition subsystem and calculate the film watching experience scores of the film watching users corresponding to the target videos based on the parameter values.
Optionally, in a specific implementation, the calculation engine subsystem 130 may be: a distributed computing framework Spark Streaming for processing Streaming computing problems.
Since Spark Streaming can support parallel processing of multi-thread tasks, in this implementation, parameter values of preset playing parameters of a large amount of target videos acquired by the information acquisition subsystem during playing can be calculated at the same time.
The information collecting subsystem 110 may collect parameter values of preset playing parameters of the target video in the playing process in real time, that is, the information collecting subsystem 110 may collect the parameter values of the preset playing parameters of the target video in the playing process when the playing of the target video is finished. Further, the calculation engine subsystem 130 may calculate, in real time, a film viewing experience score of the film viewing user corresponding to the target video.
It should be noted that the calculation engine subsystem 130 may calculate, in multiple ways, a film viewing experience score of a film viewing user corresponding to the target video, which is not specifically limited in the embodiment of the present invention.
Optionally, in a specific implementation manner, the step of calculating, by the calculation engine subsystem 130, a film viewing experience score of a film viewing user corresponding to the target video includes step B:
and B, step B: and inputting the acquired parameter values into a prediction model obtained by pre-training to obtain a prediction result of the target video watching experience score of a target video watching user corresponding to the target video.
Specifically, after receiving the parameter value of the preset playing parameter of the target video in the playing process, the calculation engine subsystem 130 may input the obtained parameter value into the prediction model obtained by pre-training, to obtain an output result of the prediction model, where the output result is the rating of the target video watching experience of the target video by the target watching user corresponding to the calculated target video.
Wherein, the prediction model is as follows: and training a preset model by adopting first-class information and second-class information corresponding to each sample user to obtain the model, wherein the first-class information corresponding to any sample user is a parameter value of a preset playing parameter of a video watched by the sample user in a playing process, and the second-class information corresponding to any sample user is a watching experience score of the sample user on the watched video.
It should be noted that the device for training the prediction model may be a computing engine subsystem 130; or other electronic devices in communication connection with the calculation engine subsystem 130, after the prediction model is obtained through training in the other electronic devices, the trained prediction model is sent to the calculation engine subsystem 130, so that the calculation engine subsystem 130 can calculate, by using the prediction model, the viewing experience score of the target video for the target viewing user corresponding to the target video.
In addition, the prediction model may be obtained through training in various ways, and the embodiment of the present invention is not limited in particular.
The training process of the prediction model may be: firstly, a preset model is built, then, first-class information corresponding to each sample user is used as input content, and second-class information corresponding to each sample user is used as output content. Therefore, the preset model can learn the characteristics of the first type of information corresponding to each sample user and output the second type of information corresponding to each sample user, and through the learning of the first type of information and the second type of information corresponding to a large number of sample users, the preset model gradually establishes the characteristics of the first type of information corresponding to each sample user and the second type of information corresponding to each sample user, and further obtains the prediction model. Further, when the trained prediction model is obtained, the calculation engine subsystem 130 may input parameter values of preset playing parameters of the target video in the playing process into the prediction model for detection, so that the prediction model may output a viewing experience score of a target video for a target viewing user corresponding to the target video.
It should be noted that, in the embodiments of the present invention, the preset model for training the prediction model is not specifically limited.
Optionally, in a specific implementation manner, the prediction model may be:
y is the film watching experience score of any video for the film watching user of the video; x is a radical of a fluorine atomiThe parameter value of the ith preset playing parameter is the parameter value of the preset playing parameter in the playing process of the video; w is aiThe weight of the ith preset playing parameter; and lambda is a penalty coefficient.
That is, in the training process of the prediction model, y is the second type information corresponding to each sample user, xiAnd presetting the parameter value of the playing parameter i in the first type of information corresponding to each sample user. After the prediction model is obtained through training, the watching experience score of the target video is obtained by the target watching user corresponding to the y target video, and x isiAnd presetting parameter values of the parameter i in the playing process of the target video.
Further, since the video average bitrate may have a great influence on the viewing experience of the target video by the target viewing user, optionally, in a specific implementation manner, the prediction model may be:
wherein y is the video viewing experience score of any video viewing user on the video, and r is the video average code flow rate level in the video playing process; x is the number ofiThe parameter value of the target playing parameter i is set; w is ai jFor the level of video average code flow rate during the playing of the videoThe weight of the target playing parameter i when the target playing parameter is at each level j in a preset level range; lambda is a penalty coefficient; sigmar(j) The activation function is the activation function when the grade of the video average code flow rate in the video playing process is each grade j in the preset grade range; the target playing parameters are as follows: the preset playing parameters or the playing parameters except the video average code flow rate in the preset playing parameters.
Wherein, the activation function σ (r) may be as follows:
obviously, when the level of the video average bitrate during the playing of the video is r, the prediction model in this embodiment may be modified as follows:
when the target playing parameter is the preset playing parameter, the parameter value of the video average code flow rate in the video-based playing process is described, and after the grade of the video average code flow rate is determined, the parameter value of the video average code flow rate is involved in the model training and film watching experience scoring prediction process again.
When the target playing parameter is a playing parameter other than the video average code flow rate in the preset playing parameters, the parameter value of the video average code flow rate in the playing process based on the video is described, and after the grade of the video average code flow rate is determined, the parameter value of the video average code flow rate does not participate in the prediction process of model training and film watching experience scoring.
In the embodiment of the present invention, the video average bitrate can be divided into a plurality of levels according to the specific value of the video average bitrate, and then the relationship between the preset playing parameter and the viewing experience score is further established according to the level of the video average bitrate.
Alternatively, as shown in Table 1, the video average bitrate can be divided into 12 levels of 0-11 as follows.
TABLE 1
Now, in the above dividing manner of the video average bitrate, the range of the level j of the preset video average bitrate is: j belongs to [0,11 ].
Of course, it is reasonable to divide the video average bitrate into another plurality of levels in other ways.
As an implementation manner of the embodiment of the present invention, on the basis of including the information collection subsystem 110 and the calculation engine subsystem 130 shown in fig. 1, as shown in fig. 2, the prediction system provided in the embodiment of the present invention may further include a message publishing subsystem 120;
the step of sending the collected parameter value to the computing engine subsystem by the information collection subsystem 110 may include: the information collecting subsystem 110 sends the collected parameter values to the message publishing subsystem 120;
the message publishing subsystem 120 is configured to receive the parameter value and send the received parameter value to the calculation engine subsystem 130.
That is to say: in this embodiment, after acquiring the parameter value of the preset playing parameter of the target video during the playing process, the information acquiring subsystem 110 does not directly send the acquired parameter value to the calculation engine subsystem 130, but first sends the acquired parameter value to the message publishing subsystem 120.
Furthermore, the message publishing subsystem 120 may receive the parameter values sent by the information collecting subsystem 110, and forward the parameter values to the computing engine subsystem 130, so that the computing engine subsystem 130 may calculate, based on the received parameter values, the viewing experience score of the viewing user corresponding to the target video after receiving the parameter values sent by the message publishing subsystem 120.
The message publishing subsystem 120 may be: a system of at least one electronic device capable of receiving parameter values sent by the information gathering subsystem 110 and forwarding the received parameter values to the compute engine subsystem 130.
Optionally, in a specific implementation, the message publishing subsystem 120 may be: distributed publish-subscribe messaging system Kafka.
Since Kafka is a high-throughput distributed publish-subscribe message system, in this implementation, when the data amount of the parameter value of the preset playing parameter of the target video acquired by the information acquisition subsystem 110 in the playing process is too large, distributed processing may be performed on the large amount of data information, so as to ensure normal operation of the whole prediction system.
It should be noted that, after the calculation engine subsystem 130 calculates the rating of the viewing experience of the viewing user corresponding to the target video, a technician of the video website may wish to adjust the video playing policy provided to the user according to the calculated multiple ratings of the viewing experience corresponding to different time periods and different target videos. Based on this, in a prediction system provided in an embodiment of the present invention, a data storage subsystem may further be included.
Optionally, in a specific implementation manner, on the basis of including the information collecting subsystem 110 and the calculation engine subsystem 130 shown in fig. 1, as shown in fig. 3, the prediction system provided in the embodiment of the present invention may further include a data storage subsystem 140.
The information collecting subsystem 110 is further configured to collect a target identifier and playing time corresponding to the target video, and send the target identifier and the playing time to the calculation engine subsystem 130; the playing time is the system time corresponding to the playing process of the target video;
the calculation engine subsystem 130 is further configured to receive a target identifier and play time corresponding to the target video; sending the target identification, playing time and calculated viewing experience score corresponding to the target video to the data storage subsystem 140;
and the data storage subsystem 140 is configured to receive and store a target identifier, playing time, and a viewing experience score corresponding to the target video. According to the above description of step a, the play log of the target video fed back to the information collection subsystem 110 by the client may include the target identifier and the play time corresponding to the target video. In this way, the information collection subsystem 110 can also extract the target identifier and the playing time corresponding to the target video from the playing log of the target video.
It should be emphasized that the playing time is a system time corresponding to the playing process of the target video, that is, a time corresponding to a moment when the user starts playing the video and exits from playing the video.
For example, if the user plays the third episode of the series B in 2018, 8, month 9, day 10:00 to 10:45, the information collecting subsystem 110 may extract the identifier of the third episode of the series B and the playing time 10:00 to 10:45 from the playing log of the target video.
Furthermore, after the target identifier and the playing time corresponding to the target video are collected, the information collection subsystem 110 may send the collected target identifier and the collected playing time to the calculation engine subsystem 130 together with the parameter value of the preset playing parameter of the collected target video in the playing process.
In this way, the calculation engine subsystem 130 may receive the target identifier, the playing time, and the parameter value of the preset playing parameter of the target video during the playing process, which are sent by the information collecting subsystem 110. Further, after the calculation of the received parameter value is used to obtain the viewing experience score of the viewing user corresponding to the target video, the calculation engine subsystem 130 may send the target identifier, the playing time, and the calculated viewing experience score corresponding to the target video to the data storage subsystem 140. So that the data storage subsystem 140 can receive and store the target identifier, the playing time and the viewing experience score corresponding to the target video sent by the calculation engine subsystem 130.
Optionally, in a specific implementation manner, on the basis of including the information collection subsystem 110, the message publishing subsystem 120, and the calculation engine subsystem 130 shown in fig. 2, as shown in fig. 4, the prediction system provided in the embodiment of the present invention may further include a data storage subsystem 140.
The information collection subsystem 110 is further configured to collect a target identifier and play time corresponding to the target video, and send the target identifier and the play time to the message publishing subsystem 120;
the message publishing subsystem 120 is further configured to receive a target identifier and playing time corresponding to the target video, and send the received target identifier and playing time to the calculation engine subsystem 130;
the calculation engine subsystem 130 is further configured to receive a target identifier and play time corresponding to the target video; sending the target identifier, the playing time and the calculated viewing experience score corresponding to the target video to the data storage subsystem 140;
and the data storage subsystem 140 is configured to receive and store a target identifier, playing time, and a film viewing experience score corresponding to the target video.
It should be noted that, in this implementation manner, the information collecting subsystem 110 does not directly send the target identifier, the playing time, and the parameter value of the preset playing parameter of the target video in the playing process, which correspond to the collected target video, to the calculation engine subsystem 130, but first sends the target identifier, the playing time, and the parameter value to the message publishing subsystem 120, and then the message publishing subsystem 120 forwards the target identifier, the playing time, and the parameter value to the calculation engine subsystem 130. So that the calculation engine subsystem 130 may continue to perform subsequent operations after receiving the target identifier, the playing time, and the parameter value of the preset playing parameter of the target video during the playing process, which correspond to the target video sent by the message publishing subsystem 120.
Among other things, the data storage subsystem 140 may be: the system is composed of at least one electronic device capable of receiving and storing a target identification, playing time and a film watching experience score corresponding to a target video.
It should be noted that, in the implementation manners shown in fig. 3 and fig. 4, the target identifier and the playing time corresponding to the target video and the viewing experience score of the viewing user corresponding to the target video may be stored in the data storage subsystem, so that the user may query the data storage subsystem 140 for information related to the viewing experience score of the target video. In order to facilitate the user to view the content to be queried, the prediction system provided by the embodiment of the invention may further include a visualization subsystem.
Optionally, in a specific implementation manner, on the basis of including the information acquisition subsystem 110, the calculation engine subsystem 130, and the data storage subsystem 140 shown in fig. 3, as shown in fig. 5, the prediction system provided in the embodiment of the present invention may further include a visualization subsystem 150.
The visualization subsystem 150 is configured to receive a data query instruction; sending a data acquisition request to the data storage subsystem 140 based on the data query instruction; receiving target data fed back by the data storage subsystem 140 based on the data acquisition request; displaying the target data to a user;
the data query instruction comprises an identifier and query time of a video to be queried, the data acquisition request carries the identifier and query time of the video to be queried, and the target data comprises: in the film watching experience scores corresponding to the identifiers of the videos to be inquired, the film watching experience scores of which the corresponding playing time is matched with the inquiring time;
the data storage subsystem 140 is further configured to receive a data acquisition request, extract the identifier and query time of the video to be queried from the data acquisition request, query a viewing experience score whose playing time matches the query time in the viewing experience score corresponding to the identifier of the video to be queried, and feed back the queried viewing experience score as target data to the visualization subsystem 150.
Specifically, the user may send a data query instruction to the visualization subsystem 150, where the data query instruction includes an identifier of a video to be queried and a query time, where the query time may be a time point or a time period, and the identifier of the video to be queried may be one or multiple. That is to say: the user wishes to obtain the rating of the viewing experience of the viewing user corresponding to a certain target video or certain target videos at a certain time point or within a certain time period by sending a data query to the visualization subsystem 150.
Wherein the user can send data query instructions to the visualization subsystem 150 in a variety of ways. For example, the data query instruction is transmitted by performing an input operation on the electronic device integrated with the visualization subsystem 150, and for example, the data query instruction is transmitted by performing a click operation on the electronic device integrated with the visualization subsystem 150. The embodiment of the present invention is not particularly limited.
Thus, after the visualization subsystem 150 receives the data query instruction sent by the user, the data query request carrying the identifier of the video to be queried and the query time can be generated based on the data query instruction, and the data query request is sent to the data storage subsystem 150.
Furthermore, when the visualization subsystem 150 receives the data query request, it may extract the identifier and query time of the video to be queried from the data query request, and query the target data in the stored data according to the extracted identifier and query time of the video to be queried.
When storing the target identifier and the playing time corresponding to the target video and the film watching experience score of the film watching user corresponding to the target video, the data storage subsystem 140 may establish a correspondence between the target identifier and the playing time corresponding to the target video and the film watching experience score of the film watching user corresponding to the target video. In this way, the data storage subsystem 140 may store a plurality of viewing experience scores corresponding to each target identifier, where each viewing experience score corresponding to each target identifier corresponds to a playing time.
Based on this, when the data storage subsystem 140 extracts the identifier of the video to be queried and the query time, the identifier of the video to be queried may be matched with the stored target identifier, and the target identifier matched with the identifier of the video to be queried is determined. Further, the data storage subsystem 140 may determine the viewing experience score corresponding to the identifier of the video to be queried according to the correspondence between the stored target identifier and the viewing experience score. Further, according to the stored corresponding relationship between the playing time and the viewing experience score, the viewing experience score matched with the playing time and the query time is determined in the viewing experience score corresponding to the identifier of the video to be queried. In this way, in the film viewing experience scores corresponding to the identifiers of the videos to be queried, the determined film viewing experience score corresponding to the playing time and the query time is the film viewing experience score corresponding to the data query instruction sent by the user by the data storage subsystem 140. The matching between the playing time and the query time may be: the play time and the query time have coincident time points or time periods.
In this manner, data storage subsystem 140 may determine the determined viewing experience score as target data and feed the determined target data back to visualization subsystem 150.
The visualization subsystem 150 may present the received target data to the user after receiving the target data fed back by the data storage subsystem 140.
When displaying the received target data, the visualization subsystem 150 may display the identifier of the video to be queried, the query time, and the corresponding relationship between the target data. In this way, the visualization subsystem 150 can present to the user: within a certain period of time, the film watching experience scores of all target videos at all playing time are distributed; within a certain period of time, the film watching experience scores of a certain target video are distributed at all playing time; and a certain target video corresponds to a certain time point and has various conditions such as film watching experience scoring and the like.
It should be noted that the visualization subsystem may present the received target data in a variety of ways, such as by way of a table, by way of a bar graph, by way of a line graph, and so forth. The embodiment of the present invention is not particularly limited.
In addition, in order to further deeply analyze the film watching experience scores of the film watching users corresponding to the target videos, deep reasons for the distribution of the film watching experience scores are mined. In the embodiment of the present invention, the information collecting subsystem 110 may further send the parameter values of the preset playing parameters of the collected target video during the playing process to the data storage subsystem 140 through the message publishing subsystem 120 and the calculation engine subsystem 130, or through the calculation engine subsystem 130 only. In this way, the data storage subsystem 140 may further establish a corresponding relationship between the target identifier corresponding to the target video, the playing time, the parameter value of the preset playing parameter, and the viewing experience score of the viewing user corresponding to the target video. Therefore, when the target data is fed back to the visualization subsystem 150, the parameter values of the preset playing parameters of the video to be queried during the playing process are fed back at the same time. Therefore, the visualization subsystem 150 can display not only the target data, but also parameter values of preset playing parameters of the video to be queried corresponding to each target data in the playing process.
Optionally, in a specific implementation manner, on the basis of the information collection subsystem 110, the message publishing subsystem 120, the calculation engine subsystem 130, and the data storage subsystem 140 shown in fig. 4, as shown in fig. 6, the prediction system provided in the embodiment of the present invention may further include a visualization subsystem 150.
It should be noted that, in the specific implementation shown in fig. 6, operations performed by the data storage subsystem 140 and the visualization subsystem 150 are the same as those performed in the above-mentioned specific implementation shown in fig. 5, and are not described again here.
Among them, the visualization subsystem 150 may be: a system of at least one electronic device capable of executing a response data query.
It should be noted that, in the embodiment of the present invention, the information collecting subsystem 110, the message publishing subsystem 120, the calculation engine subsystem 130, the data storage subsystem 140, and the visualization subsystem 150 may be integrated in the same electronic device, or may be respectively located in different electronic devices, or a plurality of subsystems therein may be integrated in the same electronic device, and another plurality of subsystems are located in different electronic devices. This is all reasonable.
Compared with the prediction system provided by the embodiment of the invention, the embodiment of the invention provides a prediction method, and the prediction method is applied to the prediction system.
Fig. 7 is a schematic flowchart of a prediction method according to an embodiment of the present invention, and as shown in fig. 7, the method may include the following steps:
s701: collecting parameter values of preset playing parameters of a target video in a playing process; the preset playing parameters are as follows: play parameters associated with the viewing experience;
s702: and calculating the film watching experience score of the film watching user corresponding to the target video based on the parameter value.
Therefore, by applying the scheme provided by the embodiment of the invention, the parameter values of the preset playing parameters of the target video in the playing process can be obtained after the target video is played, and the watching experience score of the watching user corresponding to the target video is calculated based on the parameter values. Therefore, when the user film watching experience score is obtained, the film watching experience score of the film watching user corresponding to the target video can be calculated by directly utilizing the parameter value of the preset playing parameter of the target video in the playing process without depending on the operation of the user on the questionnaire, and the controllability of obtaining the film watching experience score is improved.
Optionally, in a specific implementation manner, the step S701 may include:
the method comprises the steps of obtaining a playing log of a target video fed back by a client when the target video is played; and extracting parameter values of preset playing parameters of the target video from the playing logs.
Optionally, in a specific implementation manner, the prediction method may further include steps a1-a 2.
Step A1: acquiring a target identifier and playing time corresponding to a target video, wherein the playing time is system time corresponding to the playing process of the target video;
step A2: and storing the target identification, the playing time and the film watching experience score corresponding to the target video.
Optionally, in a specific implementation manner, the predicting method may further include:
receiving a data query instruction, wherein the data query instruction comprises an identifier of a video to be queried and query time;
generating a data acquisition request based on the data query instruction, wherein the data acquisition request carries the identifier of the video to be queried and the query time,
inquiring and displaying target data based on the data acquisition request, wherein the target data comprises: and in the film watching experience scores corresponding to the identifiers of the videos to be inquired, the corresponding playing time is matched with the inquiring time, so that the film watching experience scores are obtained.
In yet another embodiment of the present invention, a computer-readable storage medium is further provided, which has instructions stored therein, and when the instructions are executed on a computer, the instructions cause the computer to execute the prediction method described in any one of the above embodiments.
In yet another embodiment provided by the present invention, there is also provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the prediction method described in any of the above embodiments.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to be performed in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
It should be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on differences from other embodiments. In particular, as for the method embodiment, the computer-readable storage medium embodiment, and the computer program product embodiment, since they are substantially similar to the system embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (8)
1. A prediction system, characterized in that the system comprises: the system comprises an information acquisition subsystem, a calculation engine subsystem, a message issuing subsystem, a data storage subsystem and a visualization subsystem;
the information acquisition subsystem is used for acquiring parameter values of preset playing parameters of the target video in the playing process and sending the acquired parameter values to the calculation engine subsystem; wherein, the preset playing parameters are as follows: playing parameters related to the film watching experience, wherein the preset playing parameters at least comprise video average code flow rate;
the calculation engine subsystem is used for receiving the parameter values; calculating the film watching experience score of the film watching user corresponding to the target video based on the parameter value;
the information acquisition subsystem sends the acquired parameter values to the calculation engine subsystem, and the method comprises the following steps: the information acquisition subsystem sends the acquired parameter values to the message issuing subsystem;
the message issuing subsystem is used for receiving the parameter values and sending the received parameter values to the calculation engine subsystem;
the information acquisition subsystem is also used for acquiring a target identifier and playing time corresponding to the target video and sending the target identifier and the playing time to the calculation engine subsystem; the playing time is the time corresponding to the moment when the target video starts to be played and the moment when the target video exits from being played;
the computing engine subsystem is further configured to receive the target identifier and the playing time corresponding to the target video; sending the target identification, the playing time and the calculated film watching experience score corresponding to the target video to the data storage subsystem;
the data storage subsystem is used for receiving and storing the target identification, the playing time and the film watching experience score corresponding to the target video;
the visualization subsystem is used for receiving a data query instruction; sending a data acquisition request to the data storage subsystem based on the data query instruction; receiving target data fed back by the data storage subsystem based on the data acquisition request; presenting the target data to the user; the data query instruction comprises an identifier and query time of a video to be queried, the data acquisition request carries the identifier and the query time of the video to be queried, and the target data comprises: in the film watching experience scores corresponding to the identifiers of the videos to be inquired, the film watching experience scores of which the corresponding playing time is matched with the inquiring time;
the data storage subsystem is further configured to receive the data acquisition request, extract the identifier of the video to be queried and the query time from the data acquisition request, query a viewing experience score matching the playing time and the query time in the viewing experience score corresponding to the identifier of the video to be queried, and feed back the queried viewing experience score as target data to the visualization subsystem.
2. The system of claim 1,
the information acquisition subsystem acquires parameter values of preset playing parameters of a target video in a playing process, and the method comprises the following steps:
after the target video is played, acquiring a playing log of the target video; and extracting parameter values of preset playing parameters of the target video from the playing log.
3. The system of any one of claims 1-2, wherein the computing engine subsystem computes, based on the parameter values, a rating of viewing experience of a viewing user corresponding to the target video, including:
inputting the obtained parameter values into a prediction model obtained by pre-training to obtain a prediction result of the target video viewing experience score of a target video viewing user corresponding to the target video;
wherein the prediction model is: and training a preset model by adopting first-class information and second-class information corresponding to each sample user to obtain the model, wherein the first-class information corresponding to any sample user is a parameter value of the preset playing parameter of the video watched by the sample user in the playing process, and the second-class information corresponding to any sample user is a watching experience score of the video watched by the sample user.
4. The system of claim 3, wherein the predictive model is:
y is the rating of the film watching experience of the film watching user of any one video to the video; x is the number ofiThe parameter value of the ith preset playing parameter is the parameter value of the preset playing parameter in the playing process of the video; w is aiThe weight of the ith preset playing parameter is obtained; and lambda is a penalty coefficient.
5. The system of claim 3, wherein the predictive model is:
wherein y is the watching experience score of any video watching user to the video, and r is the grade of the video average code flow rate in the playing process of the video; x is the number ofiThe parameter value of the target playing parameter i is set;
when the level of the video average code flow rate in the video playing process is each level j in a preset level range, the weight of the target playing parameter i is obtained; lambda is a penalty coefficient; sigmar(j) An activation function when the level of the video average code flow rate in the video playing process is each level j in a preset level range; the target playing parameters are as follows: the preset playing parameter or the playing parameter except the video average code flow rate in the preset playing parameter.
6. The system of claim 1, wherein the message publishing subsystem is to: distributed publish-subscribe messaging system Kafka.
7. The system of claim 1, wherein the compute engine subsystem is: a distributed computing framework Spark Streaming for processing Streaming computing problems.
8. A prediction method is applied to a prediction system, and the method comprises the following steps:
collecting parameter values of preset playing parameters of a target video in a playing process; wherein, the preset playing parameters are: play parameters associated with the viewing experience;
calculating the film watching experience score of the film watching user corresponding to the target video based on the parameter value;
collecting a target identification and playing time corresponding to the target video; wherein, the playing time is as follows: the time corresponding to the moment when the target video starts to be played and the moment when the target video exits from being played;
storing the target identification, the playing time and the film watching experience score corresponding to the target video;
receiving a data query instruction, wherein the data query instruction comprises an identifier of a video to be queried and query time;
generating a data acquisition request based on the data query instruction, wherein the data acquisition request carries the identifier of the video to be queried and the query time;
inquiring and displaying target data based on the data acquisition request, wherein the target data comprises: and in the film watching experience scores corresponding to the identifiers of the videos to be inquired, the corresponding playing time is matched with the inquiring time, so that the film watching experience scores are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910390091.7A CN110139160B (en) | 2019-05-10 | 2019-05-10 | Prediction system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910390091.7A CN110139160B (en) | 2019-05-10 | 2019-05-10 | Prediction system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110139160A CN110139160A (en) | 2019-08-16 |
| CN110139160B true CN110139160B (en) | 2022-07-22 |
Family
ID=67573491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910390091.7A Active CN110139160B (en) | 2019-05-10 | 2019-05-10 | Prediction system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110139160B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115086554A (en) * | 2019-08-20 | 2022-09-20 | 华为技术有限公司 | Video special effect generation method and terminal |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2106153A1 (en) * | 2008-03-28 | 2009-09-30 | Deutsche Telekom AG | Audio-visual quality estimation |
| CN107018408A (en) * | 2017-01-19 | 2017-08-04 | 湖南大学 | The Quality of experience appraisal procedure of mobile terminal HTTP video flowings |
| CN109729433A (en) * | 2019-01-22 | 2019-05-07 | 北京奇艺世纪科技有限公司 | A kind of video playing appraisal procedure and device |
-
2019
- 2019-05-10 CN CN201910390091.7A patent/CN110139160B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2106153A1 (en) * | 2008-03-28 | 2009-09-30 | Deutsche Telekom AG | Audio-visual quality estimation |
| CN107018408A (en) * | 2017-01-19 | 2017-08-04 | 湖南大学 | The Quality of experience appraisal procedure of mobile terminal HTTP video flowings |
| CN109729433A (en) * | 2019-01-22 | 2019-05-07 | 北京奇艺世纪科技有限公司 | A kind of video playing appraisal procedure and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110139160A (en) | 2019-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20160199742A1 (en) | Automatic generation of a game replay video | |
| EP3346718B1 (en) | Methods and systems for displaying contextually relevant information regarding a media asset | |
| US20170094331A1 (en) | Video viewer targeting based on preference similarity | |
| CN108337563B (en) | Video evaluation method, device, equipment and storage medium | |
| CN104768082B (en) | A kind of audio and video playing information processing method and server | |
| CN109478142B (en) | Methods, systems, and media for presenting a user interface customized for predicted user activity | |
| JP5086189B2 (en) | Server, method and program for generating digest video of video content | |
| CN109829064B (en) | Media resource sharing and playing method and device, storage medium and electronic device | |
| WO2018130201A1 (en) | Method for determining associated account, server and storage medium | |
| US20180365709A1 (en) | Personalized creator recommendations | |
| CN110941738A (en) | Recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN108390775B (en) | User experience quality evaluation method and system based on SPICE | |
| US8832083B1 (en) | Combining user feedback | |
| CN110689903A (en) | Method, device, equipment and medium for evaluating intelligent sound box | |
| CN109558542B (en) | Information quality evaluation method, information pushing method and device | |
| CN110139160B (en) | Prediction system and method | |
| CN108769831B (en) | Video preview generation method and device | |
| CN109327739B (en) | Video processing method and device, computing equipment and storage medium | |
| US11011006B2 (en) | Method and system for evaluating and sharing media | |
| CN111107439B (en) | Content distribution method, content distribution device, server and storage medium | |
| CN111143688B (en) | Evaluation method and system based on mobile news client | |
| CN113408470A (en) | Data processing method, data processing apparatus, electronic device, storage medium, and program product | |
| CN114640884A (en) | Online video playing quality analysis method, system and computer storage medium | |
| CN113242470A (en) | Video publishing method and device applied to foreign trade marketing | |
| CN113297398A (en) | User recall method and device, computer equipment and storage medium |
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 |