CN108632670B - Video satisfaction determining method and device - Google Patents

Video satisfaction determining method and device Download PDF

Info

Publication number
CN108632670B
CN108632670B CN201810215681.1A CN201810215681A CN108632670B CN 108632670 B CN108632670 B CN 108632670B CN 201810215681 A CN201810215681 A CN 201810215681A CN 108632670 B CN108632670 B CN 108632670B
Authority
CN
China
Prior art keywords
sample
video
time length
duration
historical
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
Application number
CN201810215681.1A
Other languages
Chinese (zh)
Other versions
CN108632670A (en
Inventor
赵晓萌
陈英傑
胡军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing QIYI Century Science and Technology Co Ltd
Original Assignee
Beijing QIYI Century Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing QIYI Century Science and Technology Co Ltd filed Critical Beijing QIYI Century Science and Technology Co Ltd
Priority to CN201810215681.1A priority Critical patent/CN108632670B/en
Publication of CN108632670A publication Critical patent/CN108632670A/en
Application granted granted Critical
Publication of CN108632670B publication Critical patent/CN108632670B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing 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
    • H04N21/442Monitoring 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
    • H04N21/44204Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4667Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Television Signal Processing For Recording (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

The invention provides a method and a device for determining video satisfaction degree, and belongs to the technical field of computers. According to the method and the device for determining the video satisfaction degree, provided by the embodiment of the invention, the time length parameter of the target user for the playing operation of the target video is firstly obtained, then the time length parameter threshold corresponding to the target video is determined according to the attribute parameter of the target video and at least one preset time length parameter threshold function, and finally, whether the target user is satisfied with the target video is determined according to the time length parameter threshold and the time length parameter.

Description

Video satisfaction determining method and device
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a video satisfaction degree determining method and device.
Background
With the continuous development of computer technology, more and more videos are available in a video platform, and video search is also widely applied. In video searching, the mobile terminal will often rank the search results based on the user's satisfaction with each video in the search results. As an important parameter of video sequencing, how to determine the satisfaction degree of a user on a video becomes a problem of great attention.
In the prior art, it is common to determine whether the user is satisfied with the video based on a fixed duration threshold of 30 seconds (second, s). Specifically, when the click time of the user on the video is greater than 30s, it is determined that the user is satisfied with the video.
However, since the duration of each video is different, the click duration of a video with a longer duration is easy to reach 30s, but the user cannot be satisfied with the video when watching the video for 30s, and then the video unsatisfactory to the user is determined to be the video satisfactory to the user, and accordingly, for the video with a shorter duration, the video duration may not reach 30s, the click duration of the user for the video for this type is difficult to reach the fixed duration threshold, and then the video satisfactory to the user is determined to be the video unsatisfactory to the user, so that the video satisfaction determination method in the prior art is low in accuracy and poor in determination effect.
Disclosure of Invention
The invention provides a method and a device for determining video satisfaction, which are used for solving the problems of low accuracy and poor determination effect caused by judging the satisfaction of a user to a video based on a fixed time length threshold.
According to a first aspect of the present invention, there is provided a video satisfaction determining method, the method comprising:
acquiring a time length parameter of a target video playing operation of a target user; the time length parameter comprises the playing time length or the clicking time length of the target video in the playing operation of the target user;
determining a time length parameter threshold corresponding to the target video according to the attribute parameters of the target video and at least one preset time length parameter threshold function; the attribute parameters at least comprise the duration of the target video;
determining whether the target user is satisfied with the target video according to the time length parameter threshold and the time length parameter;
the preset duration parameter threshold function is a predetermined function reflecting the corresponding relation between the duration of the video and the duration parameter threshold, wherein in the preset duration parameter threshold function, the duration parameter threshold is a dependent variable, and the duration of the video is an independent variable.
Optionally, before the step of obtaining the duration parameter of the playing operation of the target user on the target video, the method further includes:
determining sample historical playing information corresponding to each sample video according to a sample log corresponding to each sample video; the sample historical playing information at least comprises the time length of the sample video and a historical time length parameter;
based on the duration of each sample video, dividing the sample historical playing information corresponding to each sample video into a plurality of sample data sets;
and determining at least one preset time threshold function according to the historical time parameter included in the historical playing information of each sample in each sample data set.
Optionally, the dividing, based on the duration of each sample video, the sample historical play information corresponding to each sample video into a plurality of sample data sets includes:
when the sample historical playing information comprises the time length of the sample video and the historical time length parameter, adding the contained sample historical playing information with the same time length of the sample video to the same data set to obtain a plurality of sample data sets;
and when the sample historical playing information comprises the time length of the sample video, the type of the historical playing end and the historical time length parameter, adding the sample historical playing information which contains the sample videos with the same type of the historical playing end and the same time length of the sample video to the same data set to obtain a plurality of sample data sets.
Optionally, the step of determining the historical sample play information corresponding to each sample video according to the sample log corresponding to each sample video includes:
determining at least one piece of historical playing information corresponding to each sample video according to the sample log corresponding to each sample video;
acquiring at most m pieces of historical playing information corresponding to each sample video to obtain the historical playing information corresponding to each sample video; and m is the maximum number of the sample historical playing information corresponding to each predefined sample video.
Optionally, the step of determining at least one preset duration threshold function according to the historical duration parameter included in the historical playing information of each sample data set includes:
determining a sample data set of which the time length of each corresponding sample video is greater than a first time length threshold value as a first sample data set, and determining a sample data set of which the time length of each corresponding sample video is not greater than the first time length threshold value as a second sample data set;
calculating a first quartile of a historical time length parameter in each first sample data set, and taking the first quartile and the time length of a sample video corresponding to the first sample data set as first sample points to obtain a plurality of first sample points;
calculating a third quartile of the historical duration parameter in each second sample data set, and taking the third quartile and the duration of the sample video corresponding to the second sample data set as second sample points to obtain a plurality of second sample points;
and constructing the at least one preset time threshold function according to the plurality of first sample points and the plurality of second sample points.
Optionally, when the sample data set includes sample historical play information with a sample video having a same time length, the step of constructing the at least one preset time length threshold function according to the plurality of first sample points and the plurality of second sample points includes:
and performing linear fitting by using the plurality of first sample points and the plurality of second sample points to obtain a preset duration threshold function.
Optionally, when the sample data set includes sample historical play information with the same sample video duration and the same historical play end type, the at least one preset duration parameter threshold function at least includes: a first preset duration parameter threshold function corresponding to the PC terminal and a second preset duration parameter threshold function corresponding to the mobile terminal;
the step of constructing the at least one preset duration threshold function according to the plurality of first sample points and the plurality of second sample points comprises:
performing linear fitting by using a first sample point with the corresponding type of the historical playing end as the PC end and a second sample point with the corresponding type of the historical playing end as the PC end to obtain a first preset time parameter threshold function;
and performing linear fitting by using the first sample point with the corresponding type of the historical playing end as the mobile end and the second sample point with the corresponding type of the historical playing end as the mobile end to obtain a second preset time parameter threshold function.
Optionally, the attribute parameter is a duration of the target video;
the step of determining the time length parameter threshold corresponding to the target video according to the attribute parameters of the target video and at least one preset time length parameter threshold function comprises the following steps:
and if the time length of the target video is within the independent variable value range of the preset time length parameter threshold function, substituting the time length of the target video as the independent variable into the preset time length parameter threshold function to obtain the time length parameter threshold corresponding to the target video.
Optionally, the attribute parameters are a duration of the target video and a type of a playing end corresponding to the target video in the playing operation, where the type of the playing end at least includes a PC end and a mobile end;
the step of determining the time length parameter threshold corresponding to the target video according to the attribute parameters of the target video and at least one preset time length parameter threshold function comprises the following steps:
determining a playing end type corresponding to the target video in the playing operation to obtain a target playing end type;
determining a preset duration parameter threshold function corresponding to the type of the target playing end as a target function;
and if the time length of the target video is within the independent variable value range of the target function, substituting the time length of the target video as the independent variable into the target function to obtain a time length parameter threshold corresponding to the target video.
According to a second aspect of the present invention, there is provided a video satisfaction determining apparatus, comprising:
the acquisition module is used for acquiring the time length parameter of the playing operation of the target user on the target video; the time length parameter comprises the playing time length or the clicking time length of the target video in the playing operation of the target user;
the first determining module is used for determining a time length parameter threshold value corresponding to the target video according to the attribute parameters of the target video and at least one preset time length parameter threshold value function; the attribute parameters at least comprise the duration of the target video;
a second determining module, configured to determine whether the target user is satisfied with the target video according to the duration parameter threshold and the duration parameter;
the preset duration parameter threshold function is a predetermined function reflecting the corresponding relation between the duration of the video and the duration parameter threshold, wherein in the preset duration parameter threshold function, the duration parameter threshold is a dependent variable, and the duration of the video is an independent variable.
Optionally, the apparatus further comprises:
the third determining module is used for determining the historical playing information of the sample corresponding to each sample video according to the sample log corresponding to each sample video; the sample historical playing information at least comprises the time length of the sample video and a historical time length parameter;
the dividing module is used for dividing the sample historical playing information corresponding to each sample video into a plurality of sample data sets based on the time length of each sample video;
and the fourth determining module is used for determining at least one preset duration threshold function according to the historical duration parameter included in the historical playing information of each sample in each sample data set.
Optionally, the dividing module is configured to:
when the sample historical playing information comprises the time length of the sample video and the historical time length parameter, adding the contained sample historical playing information with the same time length of the sample video to the same data set to obtain a plurality of sample data sets;
and when the sample historical playing information comprises the time length of the sample video, the type of the historical playing end and the historical time length parameter, adding the sample historical playing information which contains the sample videos with the same type of the historical playing end and the same time length of the sample video to the same data set to obtain a plurality of sample data sets.
Optionally, the third determining module is configured to:
determining at least one piece of historical playing information corresponding to each sample video according to the sample log corresponding to each sample video;
acquiring at most m pieces of historical playing information corresponding to each sample video to obtain the historical playing information corresponding to each sample video; and m is the maximum number of the sample historical playing information corresponding to each predefined sample video.
Optionally, the fourth determining module includes:
the determining submodule is used for determining the sample data set of which the duration of each corresponding sample video is greater than the first time threshold value as a first sample data set, and determining the sample data set of which the duration of each corresponding sample video is not greater than the first time threshold value as a second sample data set;
the first calculating submodule is used for calculating a first quartile of the historical time parameter in each first sample data set, and the first quartile and the time length of a sample video corresponding to the first sample data set are used as first sample points to obtain a plurality of first sample points;
the second calculation submodule is used for calculating a third quartile of the historical duration parameter in each second sample data set, and the third quartile and the duration of the sample video corresponding to the second sample data set are used as second sample points to obtain a plurality of second sample points;
and the constructing submodule is used for constructing the at least one preset duration threshold function according to the plurality of first sample points and the plurality of second sample points.
Optionally, when the sample data set includes sample historical playing information with the same sample video duration, the constructing sub-module is configured to:
and performing linear fitting by using the plurality of first sample points and the plurality of second sample points to obtain a preset duration threshold function.
Optionally, when the sample data set includes sample historical playing information with the same sample video time length and the same historical playing end type, the at least one preset time length parameter threshold function at least includes: a first preset duration parameter threshold function corresponding to the PC terminal and a second preset duration parameter threshold function corresponding to the mobile terminal;
the building submodule is used for:
performing linear fitting by using a first sample point with the corresponding type of the historical playing end as the PC end and a second sample point with the corresponding type of the historical playing end as the PC end to obtain a first preset time parameter threshold function;
and performing linear fitting by using the first sample point with the corresponding type of the historical playing end as the mobile end and the second sample point with the corresponding type of the historical playing end as the mobile end to obtain a second preset time parameter threshold function.
Optionally, the attribute parameter is a duration of the target video;
the first determining module is configured to:
and if the time length of the target video is within the independent variable value range of the preset time length parameter threshold function, substituting the time length of the target video as the independent variable into the preset time length parameter threshold function to obtain the time length parameter threshold corresponding to the target video.
Optionally, the attribute parameters are a duration of the target video and a type of a playing end corresponding to the target video in the playing operation, where the type of the playing end at least includes a PC end and a mobile end;
the first determining module is configured to:
determining a playing end type corresponding to the target video in the playing operation to obtain a target playing end type;
determining a preset duration parameter threshold function corresponding to the type of the target playing end as a target function;
and if the time length of the target video is within the independent variable value range of the target function, substituting the time length of the target video as the independent variable into the target function to obtain a time length parameter threshold corresponding to the target video.
Aiming at the prior art, the invention has the following advantages:
the method comprises the steps of obtaining a duration parameter of a playing operation of a target user on a target video, determining a duration parameter threshold corresponding to the target video according to an attribute parameter of the target video and at least one preset duration parameter threshold function, and finally determining whether the target user is satisfied with the target video according to the duration parameter threshold and the duration parameter.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart illustrating steps of a video satisfaction determining method according to an embodiment of the present invention;
fig. 2-1 is a flowchart illustrating steps of a video satisfaction determining method according to a second embodiment of the present invention;
FIG. 2-2 is a schematic diagram of a first curve provided in the second embodiment of the present invention;
FIGS. 2-3 are schematic diagrams of another first curve provided in the second embodiment of the present invention;
fig. 3 is a block diagram of a video satisfaction determining apparatus according to a third embodiment of the present invention;
fig. 4 is a block diagram of a video satisfaction determining apparatus according to a fourth embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Example one
Fig. 1 is a flowchart illustrating steps of a video satisfaction determining method according to an embodiment of the present invention, where as shown in fig. 1, the method may include:
step 101, obtaining a duration parameter of a playing operation of a target user on a target video.
In the embodiment of the present invention, the duration parameter may include a playing duration or a click duration of the target video in the playing operation of the target user. The playing time length refers to the time length between the time point when the target video is opened by the target user and the time point when the target video is closed by the target user, and the clicking time length refers to the time length between the time point when the target video is opened by the target user and the time point of the next action of the target user.
For example, suppose the user "Zhang three" is 8 in 1/2/2018: 00 video a is opened, playing is started, and then, zhang is again 8: 20 opens video B and plays video a and video B simultaneously until destination 8: 22 close video a, it can be determined that the click duration of video a is 20 minutes and the play duration is 22 minutes.
Specifically, when the duration parameter is the playing duration, a behavior log generated when a target user opens a target video can be acquired from a background of a video application, a timestamp in the behavior log is extracted, so that a time point when the target video is opened by the target user is obtained, the behavior log generated when the target user closes the target video is acquired, the timestamp in the behavior log is extracted, so that a time point when the target video is closed by the target user is obtained, a duration between the time point when the target video is opened and the time point when the target video is closed is calculated, and a duration parameter is obtained; correspondingly, when the duration parameter is the click duration, a behavior log generated when the target video is opened by the target user may be obtained from a background of the video application, a timestamp in the behavior log is extracted, a time point at which the target video is opened by the target user is further obtained, a next behavior of the target user is obtained, the generated behavior log, the timestamp in the behavior log is extracted, a time point at which the target user executes the next behavior is further obtained, a duration between the time point at which the target video is opened and the time point at which the next behavior is executed is calculated, and a duration parameter is further obtained.
Step 102, determining a duration parameter threshold corresponding to the target video according to the attribute parameters of the target video and at least one preset duration parameter threshold function.
In this embodiment of the present invention, the attribute parameter at least includes a duration of the target video, and the attribute parameter may further include a type of a playing end corresponding to the target video in a playing operation. Further, the preset duration parameter threshold function may be a predetermined function that may reflect a correspondence between the duration of the video and the duration parameter threshold, where in the preset duration parameter threshold function, the duration parameter threshold is a dependent variable, and the duration of the video is an independent variable. Specifically, when the attribute parameter only includes the time length of the target video, a preset time length parameter threshold function may be predetermined; when the attribute parameters include the duration of the target video and the type of the playing end corresponding to the target video in the playing operation, preset duration parameter threshold functions corresponding to different types of the playing end can be predetermined.
Specifically, the attribute parameters of different target videos may be different, and therefore, the duration parameter threshold corresponding to each target video may be different, and the duration parameter threshold corresponding to each target video is determined according to the attribute parameters of the target video, and therefore, the duration parameter threshold can represent the duration parameter when the target user is satisfied with the target video.
And 103, determining whether the user is satisfied with the target video according to the time length parameter threshold and the time length parameter.
In the embodiment of the invention, when the duration parameter is not less than the duration parameter threshold, the satisfaction of the user on the target video can be determined. The time length parameter threshold is determined according to the attribute parameters of the target video and can represent the time length parameter when the target user is satisfied with the target video, so that whether the target user is satisfied with the target video can be more accurately determined by taking the time length parameter threshold as a judgment basis.
In summary, in the method for determining video satisfaction provided in the embodiment of the present invention, a duration parameter of a playing operation performed on a target video by a target user is first obtained, then a duration parameter threshold corresponding to the target video is determined according to an attribute parameter of the target video and at least one preset duration parameter threshold function, and finally, whether the target user is satisfied with the target video is determined according to the duration parameter threshold and the duration parameter.
Example two
Fig. 2-1 is a flowchart illustrating steps of a video satisfaction determining method according to a second embodiment of the present invention, and as shown in fig. 2-1, the method may include:
step 201, determining sample historical playing information corresponding to each sample video according to a sample log corresponding to each sample video.
Specifically, step 201 may include:
step 2011, at least one piece of historical playing information corresponding to each sample video is determined according to the sample log corresponding to each sample video.
In this step, the historical playing information may at least include the duration of the sample video and a historical duration parameter, where the historical duration parameter may include a historical playing duration or a historical click duration. Further, the history playing information may also include other content, for example, a history playing end type of the sample video is included, each piece of history playing information corresponding to each sample video represents a record of the sample video played by the user, and the history playing information may represent a type of playing end and a specific click duration or a specific playing duration of the sample video during the playing.
Specifically, when determining at least one piece of historical play information corresponding to each sample video, a log corresponding to the sample video may be obtained from a background of a video platform to obtain a sample log corresponding to the video, where the log corresponding to the sample video may be all logs accumulated since the sample video enters the video platform, or may be a log accumulated in a certain time period by the sample video, which is not limited in this embodiment of the present invention. Then, each sample log can be analyzed one by one according to the time sequence generated by the sample logs, generally, a user can generate logs aiming at each behavior of a video, and the logs generally comprise a click time point, an ID of a clicked video, a type of a playing end corresponding to the clicked video and a time length of the clicked video. For example, taking the example that the historical playing information includes the historical playing end type of the sample video, the time length of the sample video, and the historical time length parameter is the playing time length, it is assumed that 20, which indicates that the sample video a is in the 1, 15, purpose of 2018 in the first sample log 1 corresponding to the sample video a: 00 is opened at the mobile terminal, and the second sample log 2 corresponding to the sample video a represents 20 of the sample video a in 2018, 1, month and 15 meshes: 02 is turned off at the mobile terminal, historical playing information a corresponding to the sample video a may be generated, and assuming that the ID of the sample video a is 001 and the duration is 40 minutes, the historical playing information a may be represented as:
a play _ id (mobile end) \ t doc _ id (001) \ t duration (40min) \ t play (2 min);
wherein, the playlist _ ID represents the playing end type of the sample video in the playing, doc _ ID represents the ID of the sample video, duration represents the duration of the sample video, and playtime represents the playing duration of the sample video in the playing.
Step 2012, at most m pieces of historical play information corresponding to each sample video are obtained, and the historical play information of the sample corresponding to each sample video is obtained.
In this step, m is the maximum number of pieces of sample historical playing information corresponding to each predefined sample video. The specific numerical value of m may be set by a developer according to actual experience, and since some sample videos have a large number of click behaviors and further have a corresponding large number of sample logs, compared with sample videos with fewer click behaviors, the proportion occupied by the historical play information of the sample videos with a large number of click behaviors is large, so that data distribution is unbalanced, and further, the preset duration function determined according to the data is inaccurate.
Specifically, during the obtaining, if the number of the pieces of all the historical playing information corresponding to the sample video is not greater than m, obtaining all the historical playing information corresponding to the sample video to obtain the sample historical playing information corresponding to the sample video, and if the number of the pieces of all the historical playing information corresponding to the sample video is greater than m, randomly selecting m pieces of the historical playing information from all the historical playing information corresponding to the sample video to serve as the sample historical playing information corresponding to the sample video. Of course, other obtaining manners may also be adopted, and the embodiment of the present invention is not limited thereto as long as the number of selected pieces is not greater than m.
Step 202, based on the duration of each sample video, dividing the sample historical playing information corresponding to each sample video into a plurality of sample data sets.
Specifically, when the sample historical playing information includes the time length of the sample video and the historical time length parameter, a first division manner may be adopted: and adding the historical playing information of the samples with the same time length of the contained sample videos to the same data set to obtain a plurality of sample data sets. Or when the sample historical playing information includes the time length of the sample video, the type of the historical playing end and the historical time length parameter, adopting a second division mode: and adding the historical playing information of the samples, which has the same historical playing end type and the same sample video duration, to the same data set to obtain a plurality of sample data sets.
Because the volume of the video content in the video platform is huge, in the step, when the data set is divided according to the time length, the data set can be divided by taking the second as the unit of the time length of the sample video. For example, taking a division manner one as an example, sample history playing information with a time length of 10 seconds of a contained sample video may be added to the data set 1, sample history playing information with a time length of 11 seconds of a contained sample video may be added to the data set 2 …, sample history playing information with a time length of 2700 seconds of a contained sample video may be added to the data set Z, and a plurality of sample data sets may be obtained. Taking the dividing mode two as an example, sample historical playing information that the time length seconds of the contained sample video is 10s and the type of the historical playing end is the PC end can be added into the data set 1 ', sample historical playing information that the time length seconds of the contained sample video is 11s and the type of the historical playing end is the PC end is added into the data set 2'.
When the data set is divided, the whole data volume is huge aiming at the historical playing information of the samples corresponding to all the sample videos, so that the division of the sample data set can be realized by adopting a bucket division algorithm so as to improve the efficiency of the division of the sample data set. The bucket dividing algorithm is to distribute data to different buckets according to the hash value of the data so as to complete the bucket dividing process of the data, wherein the buckets are sample data sets. The hash function used in the bucket dividing algorithm may be selected according to the data type.
Step 203, determining at least one preset time threshold function according to the historical time parameter included in the historical playing information of each sample in each sample data set.
Specifically, step 203 may include:
step 2031, determining each sample data set with the time length of the corresponding sample video greater than the first time length threshold as a first sample data set, and determining each sample data set with the time length of the corresponding sample video not greater than the first time length threshold as a second sample data set.
In this step, the first duration threshold may be set by a developer according to practical experience, and for example, the first duration threshold may be 10 s. Assuming that the time length of a sample video corresponding to the sample data set 1 to the sample data set 10 is not more than 10s, and assuming that the time length of a sample video corresponding to the sample data set 11 to the sample data set 3000 is more than 10s, the sample data set 11 to the sample data set may be determined as a first sample, and the sample data set 1 to the sample data set 10 of the data set 3000 may be determined as a second sample.
Step 2032, calculating a first quartile of the historical time duration parameter in each first sample data set, and taking the first quartile and the time duration of the sample video corresponding to the first sample data set as first sample points to obtain a plurality of first sample points.
In this step, when calculating the first quartile of the historical duration parameter in the first sample data set, the historical duration parameters in the historical playing information of each sample in the first sample data set may be arranged in an order from large to small, taking the historical duration parameter as the playing duration as an example, the playing durations in the historical playing information of each sample in the first sample data set may be arranged in an order from small to large to form a number series, and then the (n +1)/4 th number in the number series is determined as the first quartile of the historical duration parameter in the first sample data set. Further, assuming that the first quartile of the historical duration parameter in the first sample data set 23 is 10 and the duration of the sample video corresponding to the first sample data set 23 is 30s, (20, 23) may be determined as the first sample point corresponding to the first sample data set 23.
Step 2033, calculating a third quartile of the historical time length parameter in each second sample data set, and taking the third quartile and the time length of the sample video corresponding to the second sample data set as second sample points to obtain a plurality of second sample points.
In this step, when calculating the third quartile of the historical duration parameter in the second sample data set, the historical duration parameters in the historical play information of each sample in the second sample data set may be arranged in an order from large to small, taking the historical duration parameter as the play duration as an example, the play durations in the historical play information of each sample in the second sample data set may be arranged in an order from small to large to form a sequence, and then the 3(n +1)/4 number in the sequence is determined as the third quartile of the historical duration parameter in the second sample data set. Further, assuming that the third quartile of the historical duration parameter in the second sample data set 9 is 3, and the duration of the sample video corresponding to the second sample data set 9 is 9s, then (3, 9) may be determined as the third sample point corresponding to the second sample data set 23.
When the time length of the sample video is short, if the first quartile is continuously adopted as the sample point, it is easy to judge that the user is satisfied with the sample video by the false click of the user aiming at the sample video in the subsequent process, for example, for the video with the time length of 9s, the first quartile is only 3s, the false click of the user can easily reach the playing time length of 3s, and if the first quartile is taken as the standard, the false click can be easily determined as one satisfactory watching of the video. In the embodiment of the invention, the third quartile is taken as the sample point of the second sample data set, so that the problem of inaccurate judgment in the subsequent process can be avoided
Step 2034, constructing the at least one preset duration threshold function according to the plurality of first sample points and the plurality of second sample points.
Specifically, when the sample data set includes sample historical playing information with the same sample video duration, step 2034 may be implemented by the following sub-step (1):
substep (1): and performing linear fitting by using the plurality of first sample points and the plurality of second sample points to obtain a preset duration threshold function.
In this step, the duration of the sample video may be taken as a horizontal axis of a reference coordinate system, a first quartile or a third quartile of the historical duration parameter is taken as a vertical axis of the coordinate system, each first sample point and each second sample point are determined in the reference coordinate system, then each first sample point and each second sample point are sequentially connected to obtain a first curve, then the first curve is analyzed to obtain a preset duration threshold function, and in a specific implementation, the analysis may be performed by using MATLAB application, which is not limited in the embodiment of the present invention.
It should be noted that, in an actual application scenario, the number of videos with too long duration is small, and therefore, as the duration of the sample video increases, the first curve may have a large fluctuation, for example, fig. 2-2 is a schematic diagram of the first curve provided in the second embodiment of the present invention, as can be seen from fig. 2-2, a second half portion of the first curve has a significant fluctuation, and therefore, after obtaining the first curve, the portion with the large fluctuation in the first curve may be truncated, and only a portion with normal fluctuation is retained for analysis, for example, fig. 2-3 is another schematic diagram of the first curve provided in the second embodiment of the present invention, as can be seen from fig. 2-3, after truncating the portion of the first curve, the first curve becomes gentle.
When the sample data set includes sample historical playing information with the same sample video time length and the same historical playing end type, step 2034 may be implemented by the following substeps (2) to (3):
substep (2): and performing linear fitting by using the first sample point with the corresponding type of the historical playing end as the PC end and the second sample point with the corresponding type of the historical playing end as the PC end to obtain a first time parameter threshold function.
Since the behavior for the video is mainly generated at the mobile terminal and the PC terminal, and the other terminals are fewer and have small statistical significance, in the embodiment of the present invention, the types of the playing terminal may include the mobile terminal and the PC terminal, and of course, in another optional embodiment of the present invention, the types of the playing terminal may also include other terminals, such as a television terminal, and the like.
Further, the type of the historical playing end corresponding to the first sample data set corresponding to the first sample point is the type of the historical playing end corresponding to the first sample point, so that each first sample point calculated based on the first sample data set with the corresponding type of the historical playing end as the PC end and each second sample point calculated based on the second sample data set with the corresponding type of the historical playing end as the PC end can be determined in the reference coordinate system, and then the determined points are sequentially connected to obtain a second curve, and the second curve is analyzed to obtain a first preset duration parameter threshold function corresponding to the PC end.
Substep (3): and performing linear fitting by using the first sample point with the corresponding type of the history playing end as the mobile end and the second sample point with the corresponding type of the history playing end as the mobile end to obtain a second time length parameter threshold function.
In this step, each first sample point calculated based on the first sample data set with the corresponding type of the historical playing end as the moving end and each second sample point calculated based on the second sample data set with the corresponding type of the historical playing end as the moving end may be determined in the reference coordinate system, then the determined points are sequentially connected to obtain a third curve, and the third curve is analyzed to obtain a second preset duration parameter threshold function corresponding to the moving end.
Since the behavior characteristics of the user at the PC and the mobile terminal are obviously different, other operations may be performed at the PC, such as browsing a web page, and the duration parameter at the PC is generally greater than the duration parameter at the mobile terminal, for example, developers count, through statistics in advance, that the average values of the play duration and the click duration at the PC are 574.91s and 805.29s, respectively, 574.91, and the average values of the play duration and the click duration at the mobile terminal are 515.82s and 662.35s, respectively, so that it can be seen that the duration parameter at the PC is generally greater than the duration parameter at the mobile terminal. Therefore, in the embodiment of the invention, the accuracy of the preset duration parameter threshold function can be improved by determining the preset duration parameter threshold function corresponding to the different playing end types, so that the accuracy of determining the video satisfaction is improved.
It should be noted that, in the process of using the terminal, the user may browse other web pages while playing the video, which may result in poor representation of the click duration for the actual desire of the user for the video, and therefore, preferably, the play duration is used as the history duration parameter, so as to more accurately determine whether the target user is satisfied with the target video. It should be noted that, in an actual application scenario, since each video platform may be independent from each other, that is, a developer of the video platform a may not be able to obtain all background data of the video platform B, and the difficulty of obtaining the playing time of videos in other video platforms is high, in actual application, the developer may use the playing time of the video in the video platform as a historical time parameter, and use the click time of videos in other video platforms as a historical time parameter. Further, when the preset duration parameter threshold function is determined, a first preset duration parameter threshold function corresponding to the PC end can be determined in advance based on the playing duration, a first preset duration parameter threshold function corresponding to the PC end is determined based on the clicking duration, a second preset duration parameter threshold function corresponding to the mobile end is determined based on the playing duration, a second preset duration parameter threshold function corresponding to the mobile end is determined based on the clicking duration, four groups of preset duration parameter threshold functions are obtained, and the satisfaction degree of a user on videos in the platform and videos in other platforms can be conveniently and simultaneously determined.
And 204, acquiring a time length parameter of the target user for playing the target video.
Specifically, the implementation manner of this step may refer to step 101 described above, and details of the embodiment of the present invention are not described herein.
Step 205, determining a duration parameter threshold corresponding to the target video according to the attribute parameters of the target video and at least one preset duration parameter threshold function.
Specifically, when the sample data set includes sample historical playing information with the same sample video duration, that is, when a preset duration parameter threshold function is predetermined through the foregoing steps 201 to 203, the attribute parameter may include the duration of the target video, and accordingly, the step 205 may be implemented through the following step 2051:
and step 2051, if the duration of the target video is within the argument range of the preset duration parameter threshold function, substituting the duration of the target video as an argument into the preset duration parameter threshold function to obtain a duration parameter threshold corresponding to the target video.
For example, assuming that the time length of the target video is 2000s, and the argument range of the preset time length parameter threshold function is [1, 2500], 2000s may be substituted into the preset time length parameter threshold function to obtain the time length parameter threshold corresponding to the target video.
When the sample data set includes sample historical play information with the same sample video duration and the same historical play end type, that is, when a first preset duration parameter threshold function corresponding to the PC end and a second preset duration parameter threshold function corresponding to the mobile end are predetermined through the above steps 201 to 203, the attribute parameter may include the duration of the target video and the play end type corresponding to the target video in the play operation of this time, and accordingly, the step 205 may be implemented through the following steps:
and step 2052, determining a playing end type corresponding to the target video in the playing operation to obtain a target playing end type.
In this step, a log corresponding to the play operation may be obtained from background data of the video platform, and a play end type corresponding to the target video in the play operation is determined by extracting a key field in the log, so as to obtain the target play end type.
And step 2053, determining a preset duration parameter threshold function corresponding to the type of the target playing end as a target function.
For example, assuming that the type of the target player is a PC end, a first time parameter threshold function corresponding to the PC end may be determined as the target function.
And step 2054, if the duration of the target video is within the argument range of the target function, substituting the duration of the target video as an argument into the target function to obtain a duration parameter threshold corresponding to the target video.
It should be noted that, when the duration of the target video is not within the argument range of the preset duration parameter threshold function, the maximum value of the dependent variable of the preset duration parameter threshold function, that is, the maximum duration parameter threshold, may be determined as the duration parameter threshold corresponding to the target video.
And step 206, determining whether the target user is satisfied with the target video according to the time length parameter threshold and the time length parameter.
Specifically, the implementation manner of this step may refer to step 103, which is not described herein again in this embodiment of the present invention.
In another optional embodiment of the present invention, after determining the satisfaction degree of the user based on the preset duration parameter threshold function, a manual evaluation mode may be further adopted, and with the partial videos as evaluation objects, the determination effects of the videos in the mode of determining the satisfaction degree of the user based on the preset duration parameter threshold function and the mode of determining the satisfaction degree of the user based on the conventional fixed duration threshold are counted, so as to further improve the method in the present invention. Specifically, the percentage of unsatisfied clicks in all clicks can be counted in a mode of determining the satisfaction degree of the user based on a preset duration parameter threshold function and a mode of determining the satisfaction degree of the user based on a traditional fixed duration threshold, then, based on videos with the percentage difference larger than 0.2 corresponding to the two modes and search keywords corresponding to the videos, whether the quality of the videos meets the corresponding search keywords or not is judged manually, if yes, a determination mode with a low percentage is determined to win, if not, a determination mode with a high percentage is determined to win, and through specific experiments, the success rate of the method for determining the satisfaction degree of the user based on the preset duration parameter threshold function provided by the embodiment of the invention can be obtained to be about 92%.
To sum up, in the video satisfaction determining method provided by the second embodiment of the present invention, the sample historical play information corresponding to each sample video is determined according to the sample log corresponding to each sample video, then the sample historical play information corresponding to each sample video is divided into a plurality of sample data sets based on the time length of each sample video, at least one preset time length threshold function is determined based on the data sets, then the time length parameter of the play operation of the target user on the target video is obtained, then the time length parameter threshold corresponding to the target video is determined according to the attribute parameter of the target video and the at least one preset time length parameter threshold function, and finally, whether the target user is satisfied with the target video is determined according to the time length parameter threshold and the time length parameter, compared with the manner that the same fixed time length threshold is adopted as the judgment basis for all videos in the prior art, in the embodiment of the invention, the time length parameter threshold corresponding to the target video is determined according to the attribute parameters of the target video, so that the judgment basis of different target videos is ensured to be determined according to the attributes of the different target videos, and the accuracy of determining the video satisfaction is further improved.
EXAMPLE III
Fig. 3 is a block diagram of a video satisfaction determining apparatus according to a third embodiment of the present invention, and as shown in fig. 3, the apparatus 30 may include:
an obtaining module 301, configured to obtain a duration parameter of a playing operation performed on a target video by a target user; the time length parameter comprises the playing time length or the clicking time length of the target video in the playing operation of the target user;
a first determining module 302, configured to determine a duration parameter threshold corresponding to the target video according to the attribute parameter of the target video and at least one preset duration parameter threshold function; the attribute parameters at least comprise the duration of the target video;
a second determining module 303, configured to determine whether the target user is satisfied with the target video according to the duration parameter threshold and the duration parameter;
the preset duration parameter threshold function is a predetermined function reflecting the corresponding relation between the duration of the video and the duration parameter threshold, wherein in the preset duration parameter threshold function, the duration parameter threshold is a dependent variable, and the duration of the video is an independent variable.
In summary, in the video satisfaction determining apparatus provided in the third embodiment of the present invention, the obtaining module first obtains the duration parameter of the playing operation of the target video by the target user, then the first determining module determines the time length parameter threshold value corresponding to the target video according to the attribute parameters of the target video and at least one preset time length parameter threshold value function, and finally, the second determining module determines whether the target user is satisfied with the target video according to the time length parameter threshold and the time length parameter, and compared with the prior art in which the same fixed time length threshold is adopted for all videos as a judgment basis, in the embodiment of the present invention, the corresponding time length parameter threshold of the target video is determined according to the attribute parameters of the target video, the judgment basis of different target videos is ensured to be determined according to the attributes of the different target videos, and the accuracy of determining the video satisfaction is further improved.
Example four
Fig. 4 is a block diagram of a video satisfaction determining apparatus according to a third embodiment of the present invention, and as shown in fig. 4, the apparatus 40 may include:
an obtaining module 401, configured to obtain a duration parameter of a playing operation performed on a target video by a target user; the time length parameter comprises the playing time length or the clicking time length of the target video in the playing operation of the target user;
a first determining module 402, configured to determine a duration parameter threshold corresponding to the target video according to the attribute parameter of the target video and at least one preset duration parameter threshold function; the attribute parameters at least comprise the duration of the target video;
a second determining module 403, configured to determine whether the target user is satisfied with the target video according to the duration parameter threshold and the duration parameter;
the preset duration parameter threshold function is a predetermined function reflecting the corresponding relation between the duration of the video and the duration parameter threshold, wherein in the preset duration parameter threshold function, the duration parameter threshold is a dependent variable, and the duration of the video is an independent variable.
Optionally, the apparatus 40 further includes:
a third determining module 404, configured to determine, according to a sample log corresponding to each sample video, sample historical playing information corresponding to each sample video; the sample historical playing information at least comprises the time length of the sample video and a historical time length parameter;
a dividing module 405, configured to divide sample historical playing information corresponding to each sample video into multiple sample data sets based on a duration of each sample video;
a fourth determining module 406, configured to determine at least one preset duration threshold function according to a history duration parameter included in history playing information of each sample data set.
Optionally, the dividing module 405 is configured to:
when the sample historical playing information comprises the time length of the sample video and the historical time length parameter, adding the contained sample historical playing information with the same time length of the sample video to the same data set to obtain a plurality of sample data sets;
and when the sample historical playing information comprises the time length of the sample video, the type of the historical playing end and the historical time length parameter, adding the sample historical playing information which contains the sample videos with the same type of the historical playing end and the same time length of the sample video to the same data set to obtain a plurality of sample data sets.
Optionally, the third determining module 404 is configured to:
determining at least one piece of historical playing information corresponding to each sample video according to the sample log corresponding to each sample video;
acquiring at most m pieces of historical playing information corresponding to each sample video to obtain the historical playing information corresponding to each sample video; and m is the maximum number of the sample historical playing information corresponding to each predefined sample video.
Optionally, the fourth determining module 406 includes:
the determining submodule is used for determining the sample data set of which the duration of each corresponding sample video is greater than the first time threshold value as a first sample data set, and determining the sample data set of which the duration of each corresponding sample video is not greater than the first time threshold value as a second sample data set;
the first calculating submodule is used for calculating a first quartile of the historical time parameter in each first sample data set, and the first quartile and the time length of a sample video corresponding to the first sample data set are used as first sample points to obtain a plurality of first sample points;
the second calculation submodule is used for calculating a third quartile of the historical duration parameter in each second sample data set, and the third quartile and the duration of the sample video corresponding to the second sample data set are used as second sample points to obtain a plurality of second sample points;
and the constructing submodule is used for constructing the at least one preset duration threshold function according to the plurality of first sample points and the plurality of second sample points.
Optionally, when the sample data set includes sample historical playing information with the same sample video duration, the constructing sub-module is configured to:
and performing linear fitting by using the plurality of first sample points and the plurality of second sample points to obtain a preset duration threshold function.
Optionally, when the sample data set includes sample historical play information with the same sample video duration and the same historical play end type, the at least one preset duration parameter threshold function at least includes: a first preset duration parameter threshold function corresponding to the PC terminal and a second preset duration parameter threshold function corresponding to the mobile terminal;
the building submodule is configured to:
performing linear fitting by using a first sample point with the corresponding type of the historical playing end as the PC end and a second sample point with the corresponding type of the historical playing end as the PC end to obtain a first preset time parameter threshold function;
and performing linear fitting by using the first sample point with the corresponding type of the historical playing end as the mobile end and the second sample point with the corresponding type of the historical playing end as the mobile end to obtain a second preset time parameter threshold function.
Optionally, the attribute parameter is a duration of the target video;
the first determining module 402, configured to:
and if the time length of the target video is within the independent variable value range of the preset time length parameter threshold function, substituting the time length of the target video as the independent variable into the preset time length parameter threshold function to obtain the time length parameter threshold corresponding to the target video.
Optionally, the attribute parameters are a duration of the target video and a type of a playing end corresponding to the target video in the playing operation, where the type of the playing end at least includes a PC end and a mobile end;
the first determining module 402, configured to:
determining a playing end type corresponding to the target video in the playing operation to obtain a target playing end type;
determining a preset duration parameter threshold function corresponding to the type of the target playing end as a target function;
and if the time length of the target video is within the independent variable value range of the target function, substituting the time length of the target video as the independent variable into the target function to obtain a time length parameter threshold corresponding to the target video.
To sum up, in the video satisfaction determining apparatus provided in the fourth embodiment of the present invention, the third determining module determines the sample historical playing information corresponding to each sample video according to the sample log corresponding to each sample video, the dividing module divides the sample historical playing information corresponding to each sample video into a plurality of sample data sets based on the time length of each sample video, the fourth determining module determines at least one preset time length threshold function based on the data sets, the obtaining module obtains the time length parameter of the target video playing operation performed by the target user, the first determining module determines the time length parameter threshold corresponding to the target video according to the attribute parameter of the target video and the at least one preset time length parameter threshold function, and the second determining module determines whether the target user is satisfied with the target video according to the time length parameter threshold and the time length parameter, compared with the mode that the same fixed time length threshold is adopted as the judgment basis for all videos in the prior art, the method and the device for judging the video satisfaction degree determine the time length parameter threshold corresponding to the target video according to the attribute parameters of the target video, ensure that the judgment basis of different target videos is determined according to the attributes of the different target videos, and further improve the accuracy of determining the video satisfaction degree.
For the above device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for the relevant points, refer to the partial description of the method embodiment.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As is readily imaginable to the person skilled in the art: any combination of the above embodiments is possible, and thus any combination between the above embodiments is an embodiment of the present invention, but the present disclosure is not necessarily detailed herein for reasons of space.
The video satisfaction determination methods provided herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The structure required to construct a system incorporating aspects of the present invention will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of the method of identifying background music in video according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Claims (16)

1. A method for video satisfaction determination, the method comprising:
acquiring a time length parameter of a target video playing operation of a target user; the time length parameter comprises the playing time length or the clicking time length of the target video in the playing operation of the target user;
determining a time length parameter threshold corresponding to the target video according to the attribute parameters of the target video and at least one preset time length parameter threshold function; the attribute parameters at least comprise the duration of the target video;
determining whether the target user is satisfied with the target video according to the time length parameter threshold and the time length parameter;
the preset duration parameter threshold function is a predetermined function reflecting the corresponding relation between the duration of the video and a duration parameter threshold, wherein in the preset duration parameter threshold function, the duration parameter threshold is a dependent variable, and the duration of the video is an independent variable;
the click duration is the duration between the time point of the target video opened by the target user and the time point of the next behavior of the target user;
before the step of obtaining the duration parameter of the playing operation of the target user on the target video, the method further includes:
determining sample historical playing information corresponding to each sample video according to a sample log corresponding to each sample video; the sample historical playing information at least comprises the time length of the sample video and a historical time length parameter;
based on the time length of each sample video, adding sample historical playing information corresponding to the sample videos with the same time length to the same sample data set to obtain a plurality of sample data sets;
and determining at least one preset time threshold function according to the historical time parameter included in the historical playing information of each sample in each sample data set.
2. The method of claim 1, wherein the partitioning the sample historical play information corresponding to each sample video into a plurality of sample data sets based on the duration of each sample video comprises:
when the sample historical playing information comprises the time length of the sample video and the historical time length parameter, adding the contained sample historical playing information with the same time length of the sample video to the same data set to obtain a plurality of sample data sets;
and when the sample historical playing information comprises the time length of the sample video, the type of the historical playing end and the historical time length parameter, adding the sample historical playing information which contains the sample videos with the same type of the historical playing end and the same time length of the sample video to the same data set to obtain a plurality of sample data sets.
3. The method of claim 1, wherein the step of determining the sample historical playing information corresponding to each sample video according to the sample log corresponding to each sample video comprises:
determining at least one piece of historical playing information corresponding to each sample video according to the sample log corresponding to each sample video;
acquiring at most m pieces of historical playing information corresponding to each sample video to obtain the historical playing information corresponding to each sample video; and m is the maximum number of the sample historical playing information corresponding to each predefined sample video.
4. The method according to claim 1, wherein the step of determining at least one preset duration threshold function according to the historical duration parameter included in the historical playing information of each sample data set comprises:
determining a sample data set of which the time length of each corresponding sample video is greater than a first time length threshold value as a first sample data set, and determining a sample data set of which the time length of each corresponding sample video is not greater than the first time length threshold value as a second sample data set;
calculating a first quartile of a historical time length parameter in each first sample data set, and taking the first quartile and the time length of a sample video corresponding to the first sample data set as first sample points to obtain a plurality of first sample points;
calculating a third quartile of the historical duration parameter in each second sample data set, and taking the third quartile and the duration of the sample video corresponding to the second sample data set as second sample points to obtain a plurality of second sample points;
and constructing the at least one preset time threshold function according to the plurality of first sample points and the plurality of second sample points.
5. The method according to claim 4, wherein when the sample data set includes sample historical playing information with sample video duration being the same, the step of constructing the at least one preset duration threshold function according to the plurality of first sample points and the plurality of second sample points comprises:
and performing linear fitting by using the plurality of first sample points and the plurality of second sample points to obtain a preset duration threshold function.
6. The method according to claim 4, wherein when the sample data set includes sample historical playing information with the same sample video duration and the same historical playing end type, the at least one preset duration parameter threshold function at least includes: a first preset duration parameter threshold function corresponding to the PC terminal and a second preset duration parameter threshold function corresponding to the mobile terminal;
the step of constructing the at least one preset duration threshold function according to the plurality of first sample points and the plurality of second sample points comprises:
performing linear fitting by using a first sample point with the corresponding type of the historical playing end as the PC end and a second sample point with the corresponding type of the historical playing end as the PC end to obtain a first preset time parameter threshold function;
and performing linear fitting by using the first sample point with the corresponding type of the historical playing end as the mobile end and the second sample point with the corresponding type of the historical playing end as the mobile end to obtain a second preset time parameter threshold function.
7. The method of claim 5, wherein the attribute parameter is a duration of the target video;
the step of determining the time length parameter threshold corresponding to the target video according to the attribute parameters of the target video and at least one preset time length parameter threshold function comprises the following steps:
and if the time length of the target video is within the independent variable value range of the preset time length parameter threshold function, substituting the time length of the target video as the independent variable into the preset time length parameter threshold function to obtain the time length parameter threshold corresponding to the target video.
8. The method according to claim 6, wherein the attribute parameters are duration of the target video and a type of a player corresponding to the target video in the playing operation, and the type of the player at least includes a PC (personal computer) terminal and a mobile terminal;
the step of determining the time length parameter threshold corresponding to the target video according to the attribute parameters of the target video and at least one preset time length parameter threshold function comprises the following steps:
determining a playing end type corresponding to the target video in the playing operation to obtain a target playing end type;
determining a preset duration parameter threshold function corresponding to the type of the target playing end as a target function;
and if the time length of the target video is within the independent variable value range of the target function, substituting the time length of the target video as the independent variable into the target function to obtain a time length parameter threshold corresponding to the target video.
9. A video satisfaction determination apparatus, characterized in that said apparatus comprises:
the acquisition module is used for acquiring the time length parameter of the playing operation of the target user on the target video; the time length parameter comprises the playing time length or the clicking time length of the target video in the playing operation of the target user;
the first determining module is used for determining a time length parameter threshold value corresponding to the target video according to the attribute parameters of the target video and at least one preset time length parameter threshold value function; the attribute parameters at least comprise the duration of the target video;
a second determining module, configured to determine whether the target user is satisfied with the target video according to the duration parameter threshold and the duration parameter;
the preset duration parameter threshold function is a predetermined function reflecting the corresponding relation between the duration of the video and a duration parameter threshold, wherein in the preset duration parameter threshold function, the duration parameter threshold is a dependent variable, and the duration of the video is an independent variable;
the click duration is the duration between the time point of the target video opened by the target user and the time point of the next behavior of the target user; wherein the apparatus further comprises:
the third determining module is used for determining the historical playing information of the sample corresponding to each sample video according to the sample log corresponding to each sample video; the sample historical playing information at least comprises the time length of the sample video and a historical time length parameter;
the dividing module is used for adding sample historical playing information corresponding to sample videos with the same duration to the same sample data set based on the duration of each sample video to obtain a plurality of sample data sets;
and the fourth determining module is used for determining at least one preset duration threshold function according to the historical duration parameter included in the historical playing information of each sample in each sample data set.
10. The apparatus of claim 9, wherein the partitioning module is configured to:
when the sample historical playing information comprises the time length of the sample video and the historical time length parameter, adding the contained sample historical playing information with the same time length of the sample video to the same data set to obtain a plurality of sample data sets;
and when the sample historical playing information comprises the time length of the sample video, the type of the historical playing end and the historical time length parameter, adding the sample historical playing information which contains the sample videos with the same type of the historical playing end and the same time length of the sample video to the same data set to obtain a plurality of sample data sets.
11. The apparatus of claim 9, wherein the third determining module is configured to:
determining at least one piece of historical playing information corresponding to each sample video according to the sample log corresponding to each sample video;
acquiring at most m pieces of historical playing information corresponding to each sample video to obtain the historical playing information corresponding to each sample video; and m is the maximum number of the sample historical playing information corresponding to each predefined sample video.
12. The apparatus of claim 9, wherein the fourth determining module comprises:
the determining submodule is used for determining the sample data set of which the duration of each corresponding sample video is greater than the first time threshold value as a first sample data set, and determining the sample data set of which the duration of each corresponding sample video is not greater than the first time threshold value as a second sample data set;
the first calculating submodule is used for calculating a first quartile of the historical time parameter in each first sample data set, and the first quartile and the time length of a sample video corresponding to the first sample data set are used as first sample points to obtain a plurality of first sample points;
the second calculation submodule is used for calculating a third quartile of the historical duration parameter in each second sample data set, and the third quartile and the duration of the sample video corresponding to the second sample data set are used as second sample points to obtain a plurality of second sample points;
and the constructing submodule is used for constructing the at least one preset duration threshold function according to the plurality of first sample points and the plurality of second sample points.
13. The apparatus according to claim 12, wherein when the sample data set includes sample historical playing information with sample video duration being the same, the constructing sub-module is configured to:
and performing linear fitting by using the plurality of first sample points and the plurality of second sample points to obtain a preset duration threshold function.
14. The apparatus according to claim 12, wherein when the sample data set includes sample historical playing information with the same sample video duration and the same historical playing end type, the at least one preset duration parameter threshold function at least includes: a first preset duration parameter threshold function corresponding to the PC terminal and a second preset duration parameter threshold function corresponding to the mobile terminal;
the building submodule is used for:
performing linear fitting by using a first sample point with the corresponding type of the historical playing end as the PC end and a second sample point with the corresponding type of the historical playing end as the PC end to obtain a first preset time parameter threshold function;
and performing linear fitting by using the first sample point with the corresponding type of the historical playing end as the mobile end and the second sample point with the corresponding type of the historical playing end as the mobile end to obtain a second preset time parameter threshold function.
15. The apparatus according to claim 13, wherein the attribute parameter is a duration of the target video;
the first determining module is configured to:
and if the time length of the target video is within the independent variable value range of the preset time length parameter threshold function, substituting the time length of the target video as the independent variable into the preset time length parameter threshold function to obtain the time length parameter threshold corresponding to the target video.
16. The apparatus according to claim 14, wherein the attribute parameters are duration of the target video and a type of a player corresponding to the target video in the playing operation, and the type of the player at least includes a PC terminal and a mobile terminal;
the first determining module is configured to:
determining a playing end type corresponding to the target video in the playing operation to obtain a target playing end type;
determining a preset duration parameter threshold function corresponding to the type of the target playing end as a target function;
and if the time length of the target video is within the independent variable value range of the target function, substituting the time length of the target video as the independent variable into the target function to obtain a time length parameter threshold corresponding to the target video.
CN201810215681.1A 2018-03-15 2018-03-15 Video satisfaction determining method and device Active CN108632670B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810215681.1A CN108632670B (en) 2018-03-15 2018-03-15 Video satisfaction determining method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810215681.1A CN108632670B (en) 2018-03-15 2018-03-15 Video satisfaction determining method and device

Publications (2)

Publication Number Publication Date
CN108632670A CN108632670A (en) 2018-10-09
CN108632670B true CN108632670B (en) 2021-03-26

Family

ID=63706230

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810215681.1A Active CN108632670B (en) 2018-03-15 2018-03-15 Video satisfaction determining method and device

Country Status (1)

Country Link
CN (1) CN108632670B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110769286B (en) * 2019-11-06 2021-04-27 山东科技大学 Channel-based recommendation method and device and storage medium

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102263992A (en) * 2011-08-08 2011-11-30 上海文广互动电视有限公司 Program recommendation degree estimation method based on user viewing record
CN102740143A (en) * 2012-07-03 2012-10-17 合一网络技术(北京)有限公司 Network video ranking list generation system based on user behavior and method thereof
CN103577505A (en) * 2012-08-10 2014-02-12 腾讯科技(深圳)有限公司 Method and system for predicting interestingness of media files
CN104506894A (en) * 2014-12-22 2015-04-08 合一网络技术(北京)有限公司 Method and device for evaluating multi-media resources
CN105573887A (en) * 2015-12-14 2016-05-11 合一网络技术(北京)有限公司 Quality evaluation method and device of search engine
CN105828117A (en) * 2016-03-02 2016-08-03 乐视云计算有限公司 Video automatic push method based on user behavior analysis and video automatic push device thereof
CN105843876A (en) * 2016-03-18 2016-08-10 合网络技术(北京)有限公司 Multimedia resource quality assessment method and apparatus
CN105898426A (en) * 2015-12-14 2016-08-24 乐视网信息技术(北京)股份有限公司 Multimedia content processing method and device and server
CN106028156A (en) * 2016-06-24 2016-10-12 合肥工业大学 Television viewer interest modeling method and system
CN106534976A (en) * 2016-10-12 2017-03-22 南京邮电大学 Intelligent prediction method of user satisfaction in IPTV video business
CN106658091A (en) * 2016-12-01 2017-05-10 北京学之途网络科技有限公司 TV viewing information processing method and device
CN107493512A (en) * 2016-06-12 2017-12-19 阿里巴巴集团控股有限公司 The focus mask method and device of video
CN107592572A (en) * 2017-09-21 2018-01-16 广州华多网络科技有限公司 Video recommendation method, device and its equipment
CN107766360A (en) * 2016-08-17 2018-03-06 北京神州泰岳软件股份有限公司 A kind of video temperature Forecasting Methodology and device

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101566311B1 (en) * 2008-11-11 2015-11-05 삼성전자 주식회사 Image processing apparatus and method of processing image
CN102769781B (en) * 2012-07-17 2015-01-21 青岛海信传媒网络技术有限公司 Method and device for recommending television program
CN103747343B (en) * 2014-01-09 2018-01-30 深圳Tcl新技术有限公司 The method and apparatus that resource is recommended at times
CN103974084B (en) * 2014-05-07 2017-02-08 南京邮电大学 Streaming media data block caching method, file recommendation method and streaming media server
CN104935967B (en) * 2015-06-19 2017-12-01 北京数码视讯科技股份有限公司 The interest recognition methods of video terminal user a kind of and device
CN106331778B (en) * 2015-07-06 2020-08-14 腾讯科技(深圳)有限公司 Video recommendation method and device
CN106227883B (en) * 2016-08-05 2019-09-13 北京数码视讯科技股份有限公司 A kind of the temperature analysis method and device of multimedia content
CN106604137B (en) * 2016-12-29 2020-06-12 Tcl科技集团股份有限公司 Method and device for predicting video watching duration
CN107506367B (en) * 2017-07-03 2021-12-24 创新先进技术有限公司 Method and device for determining application display content and server

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102263992A (en) * 2011-08-08 2011-11-30 上海文广互动电视有限公司 Program recommendation degree estimation method based on user viewing record
CN102740143A (en) * 2012-07-03 2012-10-17 合一网络技术(北京)有限公司 Network video ranking list generation system based on user behavior and method thereof
CN103577505A (en) * 2012-08-10 2014-02-12 腾讯科技(深圳)有限公司 Method and system for predicting interestingness of media files
CN104506894A (en) * 2014-12-22 2015-04-08 合一网络技术(北京)有限公司 Method and device for evaluating multi-media resources
CN105898426A (en) * 2015-12-14 2016-08-24 乐视网信息技术(北京)股份有限公司 Multimedia content processing method and device and server
CN105573887A (en) * 2015-12-14 2016-05-11 合一网络技术(北京)有限公司 Quality evaluation method and device of search engine
CN105828117A (en) * 2016-03-02 2016-08-03 乐视云计算有限公司 Video automatic push method based on user behavior analysis and video automatic push device thereof
CN105843876A (en) * 2016-03-18 2016-08-10 合网络技术(北京)有限公司 Multimedia resource quality assessment method and apparatus
CN107493512A (en) * 2016-06-12 2017-12-19 阿里巴巴集团控股有限公司 The focus mask method and device of video
CN106028156A (en) * 2016-06-24 2016-10-12 合肥工业大学 Television viewer interest modeling method and system
CN107766360A (en) * 2016-08-17 2018-03-06 北京神州泰岳软件股份有限公司 A kind of video temperature Forecasting Methodology and device
CN106534976A (en) * 2016-10-12 2017-03-22 南京邮电大学 Intelligent prediction method of user satisfaction in IPTV video business
CN106658091A (en) * 2016-12-01 2017-05-10 北京学之途网络科技有限公司 TV viewing information processing method and device
CN107592572A (en) * 2017-09-21 2018-01-16 广州华多网络科技有限公司 Video recommendation method, device and its equipment

Also Published As

Publication number Publication date
CN108632670A (en) 2018-10-09

Similar Documents

Publication Publication Date Title
CN107483843B (en) Audio-video matches clipping method and device
CN108108821B (en) Model training method and device
CN110008378B (en) Corpus collection method, device, equipment and storage medium based on artificial intelligence
CN109144610B (en) Audio playing method and device, electronic device and computer readable storage medium
CN107526846B (en) Method, device, server and medium for generating and sorting channel sorting model
US8230039B2 (en) Systems and methods for accelerated playback of rich internet applications
CN107967280B (en) Method and system for recommending songs by tag
CN109257612B (en) Game live broadcast potential evaluation method and device, computer storage medium and server
CN104038473A (en) Method of audio ad insertion, device, equipment and system
CN109977300A (en) Enterprise's public sentiment acquisition methods, device, terminal and computer storage medium
CN110727785A (en) Recommendation method, device and storage medium for training recommendation model and recommending search text
CN113849760B (en) Sensitive information risk assessment method, system and storage medium
US20170245010A1 (en) Video playing detection method and apparatus
CN105260393A (en) Information pushing method and device and electronic equipment
CN108334626B (en) News column generation method and device and computer equipment
CN110895594A (en) Page display method and related equipment
CN108777801A (en) High-quality main broadcaster's usage mining method, apparatus and computer storage media, server
CN108632670B (en) Video satisfaction determining method and device
CN111371605A (en) Network service scoring method and device
CN107644094B (en) Method, device, server and storage medium for constructing boutique resource library
CN108228802B (en) Recommendation method and device for input association
CN116310994A (en) Video clip extraction method and device, electronic equipment and medium
CN113468369A (en) Audio track identification method and device and readable storage medium
CN104636366B (en) Method and device for acquiring search result queue
CN111199148B (en) Text similarity determination method and device, storage medium and electronic equipment

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