CN108632670A - A kind of video satisfaction determines method and device - Google Patents
A kind of video satisfaction determines method and device Download PDFInfo
- Publication number
- CN108632670A CN108632670A CN201810215681.1A CN201810215681A CN108632670A CN 108632670 A CN108632670 A CN 108632670A CN 201810215681 A CN201810215681 A CN 201810215681A CN 108632670 A CN108632670 A CN 108632670A
- Authority
- CN
- China
- Prior art keywords
- sample
- duration
- video
- history
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management 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
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4667—Processing 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)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Television Signal Processing For Recording (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of video satisfactions to determine method and device, belongs to field of computer technology.Video satisfaction provided in an embodiment of the present invention determines method and device, duration parameters of the target user to the play operation of target video can first be obtained, then according to the property parameters of target video and at least one preset duration parameter threshold function, determine the corresponding duration parameters threshold value of target video, finally, it can be according to duration parameters threshold value and duration parameters, determine whether target user is satisfied with target video, mode of the identical fixed duration threshold value as basis for estimation is all made of to all videos in compared to the prior art, in the embodiment of the present invention, the corresponding duration parameters threshold value of target video can be determined according to the property parameters of target video, ensure that the basis for estimation of different target videos is determined according to self attributes, and then improve the accuracy for determining video satisfaction.
Description
Technical field
The invention belongs to field of computer technology, and method and device is determined more particularly to a kind of video satisfaction.
Background technology
With the continuous development of computer technology, the video in video platform is more and more, and video search has also obtained more
Add and is widely applied.In video search, mobile terminal often based on user to the satisfaction of each video in search result,
Search result is ranked up.As the important parameter of video sequence, how to determine that user becomes people to the satisfaction of video
The problem of extensive concern.
In the prior art, be normally based on fixed duration threshold value 30 seconds (second, s) determine user to the video whether
It is satisfied.Specifically, when user is more than 30s to the click duration of video, determine that user is satisfied with the video.
But due to the duration of each video difference, clicks duration relative to the longer video of duration and easily reach
30s, but user, which is satisfied with video, to be illustrated for such video-see 30s, and then will appear user is unsatisfied
Video is determined as customer satisfaction system video, accordingly for the shorter video of duration, it is possible to which video length does not all reach
30s is extremely difficult to fixed duration threshold value for the click duration of such video user, and then can determine customer satisfaction system video
For the unsatisfied video of user, therefore, video satisfaction in the prior art determines that method accuracy is relatively low, determine effect compared with
Difference.
Invention content
A kind of video satisfaction of present invention offer determines method and device, to solve to use based on fixed duration threshold decision
To the satisfaction of video, caused accuracy is relatively low at family, determines the poor problem of effect.
According to the present invention in a first aspect, providing a kind of video satisfaction determines that method, this method include:
Obtain duration parameters of the target user to the play operation of target video;The duration parameters include that the target is used
Family is in the play operation, the playing duration to the target video or click duration;
According to the property parameters of the target video and at least one preset duration parameter threshold function, the mesh is determined
Mark the corresponding duration parameters threshold value of video;The property parameters include at least the duration of the target video;
According to the duration parameters threshold value and the duration parameters, determine that the target user is to the target video
No satisfaction;
Wherein, the preset duration parameter threshold function is predetermined the duration and duration parameters threshold value of reflecting video
The function of correspondence, in the preset duration parameter threshold function, duration parameters threshold value is dependent variable, video when it is a length of from
Variable.
Optionally, before the step of acquisition target user is to the duration parameters of the play operation of target video, institute
The method of stating further includes:
According to the corresponding sample daily record of each Sample video, determine that the corresponding sample history of each Sample video plays letter
Breath;The sample history broadcast information includes at least the duration and history duration parameters of Sample video;
Based on the duration of each Sample video, the corresponding sample history broadcast information of each Sample video is divided to multiple
Sample data set;
The history duration parameters that every sample history broadcast information includes are concentrated according to each sample data, determine at least one
A preset duration threshold function table.
Optionally, the corresponding sample history of each Sample video is played letter by the duration based on each Sample video
Breath is divided to multiple sample data sets, including:
When the sample history broadcast information includes the duration and history duration parameters of Sample video, by comprising sample
The identical sample history broadcast information of duration of this video is added to same data set, obtains multiple sample data sets;
Include the duration of Sample video, history broadcasting end type and history duration ginseng in the sample history broadcast information
When number, by comprising history play that end type is identical and the identical sample history broadcast information of duration of Sample video is added to together
One data set obtains multiple sample data sets.
Optionally, the corresponding sample daily record of each Sample video of the basis determines the corresponding sample of each Sample video
The step of history broadcast information, including:
According to the corresponding sample daily record of each Sample video, determine that corresponding at least one history of each Sample video plays
Information;
The corresponding at most m history broadcast information of each Sample video is obtained, the corresponding sample of each Sample video is obtained
History broadcast information;The m is the maximum item number of the pre-defined corresponding sample history broadcast information of each Sample video.
Optionally, each sample data of the basis concentrates the history duration ginseng that every sample history broadcast information includes
The step of counting, determining at least one preset duration threshold function table, including:
The duration of each corresponding Sample video is more than to the sample data set of the first duration threshold value, is determined as first sample
The duration of each corresponding Sample video is not more than the sample data set of the first duration threshold value, is determined as the second sample by data set
Notebook data collection;
The first quartile for calculating history duration parameters in each first sample data set, by the first quartile
The duration of Sample video corresponding with the first sample data set obtains multiple first sample points as first sample point;
The third quartile that each second sample data concentrates history duration parameters is calculated, by the third quartile
The duration of Sample video corresponding with second sample data set obtains multiple second sample points as the second sample point;
According to the multiple first sample point and the multiple second sample point, at least one preset duration is built
Threshold function table.
Optionally, when sample data concentration includes the identical sample history broadcast information of Sample video duration, institute
It states according to the multiple first sample point and the multiple second sample point, builds at least one preset duration threshold value letter
Several steps, including:
Linear fit is carried out using the multiple first sample point and the multiple second sample point, obtains preset duration
Threshold function table.
Optionally, when sample data concentration includes that Sample video duration is identical and history plays the identical sample of end type
When this history broadcast information, at least one preset duration parameters threshold function table includes at least:Corresponding with the ends PC first
Preset duration parameter threshold function and the second preset duration parameter threshold function corresponding with mobile terminal;
It is described according to the multiple first sample point and the multiple second sample point, structure is described at least one default
The step of duration threshold function table, including:
It is PC to play end type using the first sample point and corresponding history that corresponding history broadcasting end type is the ends PC
Second sample point at end carries out linear fit, obtains the first preset duration parameter threshold function;
Playing end type using the first sample point and corresponding history that corresponding history broadcasting end type is mobile terminal is
Second sample point of mobile terminal carries out linear fit, obtains the second preset duration parameter threshold function.
Optionally, the property parameters are the duration of the target video;
The property parameters according to the target video and at least one preset duration parameter threshold function, determine institute
The step of stating target video corresponding duration parameters threshold value, including:
If the duration of the target video is in the preset duration parameter threshold argument of function value range, by institute
The duration of target video is stated as independent variable, substitutes into the preset duration parameter threshold function, obtains the target video pair
The duration parameters threshold value answered.
Optionally, the property parameters are the duration of the target video and the target video in the play operation
In corresponding broadcasting end type, broadcasting end type include at least the ends computer PC and mobile terminal;
The property parameters according to the target video and at least one preset duration parameter threshold function, determine institute
The step of stating target video corresponding duration parameters threshold value, including:
It determines the target video corresponding broadcasting end type in the play operation, obtains target and play end type;
Preset duration parameter threshold function corresponding with target broadcasting end type is determined as object function;
If the duration of the target video is in the independent variable value range of the object function, by the target video
Duration is substituted into as independent variable in the object function, obtains the corresponding duration parameters threshold value of the target video.
Second aspect according to the present invention, provides a kind of video satisfaction determining device, which includes:
Acquisition module, the duration parameters for obtaining target user to the play operation of target video;The duration parameters
Including the target user in the play operation, the playing duration to the target video or click duration;
First determining module is used for the property parameters according to the target video and at least one preset duration parameter threshold
Value function determines the corresponding duration parameters threshold value of the target video;The property parameters include at least the target video
Duration;
Second determining module, for according to the duration parameters threshold value and the duration parameters, determining that the target is used
Whether family is satisfied with the target video;
Wherein, the preset duration parameter threshold function is predetermined the duration and duration parameters threshold value of reflecting video
The function of correspondence, in the preset duration parameter threshold function, duration parameters threshold value is dependent variable, video when it is a length of from
Variable.
Optionally, which is characterized in that described device further includes:
Third determining module, for according to the corresponding sample daily record of each Sample video, determining that each Sample video corresponds to
Sample history broadcast information;The sample history broadcast information includes at least the duration and history duration ginseng of Sample video
Number;
Division module is used for the duration based on each Sample video, and the corresponding sample history of each Sample video is played
Information is divided to multiple sample data sets;
4th determining module, when for concentrating the history that every sample history broadcast information includes according to each sample data
Long parameter determines at least one preset duration threshold function table.
Optionally, which is characterized in that the division module is used for:
When the sample history broadcast information includes the duration and history duration parameters of Sample video, by comprising sample
The identical sample history broadcast information of duration of this video is added to same data set, obtains multiple sample data sets;
Include the duration of Sample video, history broadcasting end type and history duration ginseng in the sample history broadcast information
When number, by comprising history play that end type is identical and the identical sample history broadcast information of duration of Sample video is added to together
One data set obtains multiple sample data sets.
Optionally, which is characterized in that the third determining module is used for:
According to the corresponding sample daily record of each Sample video, determine that corresponding at least one history of each Sample video plays
Information;
The corresponding at most m history broadcast information of each Sample video is obtained, the corresponding sample of each Sample video is obtained
History broadcast information;The m is the maximum item number of the pre-defined corresponding sample history broadcast information of each Sample video.
Optionally, which is characterized in that the 4th determining module, including:
Determination sub-module, the sample data for the duration of each corresponding Sample video to be more than to the first duration threshold value
Collection, is determined as first sample data set, and the duration of each corresponding Sample video is not more than to the sample number of the first duration threshold value
According to collection, it is determined as the second sample data set;
First computational submodule, the first quartile for calculating history duration parameters in each first sample data set
Number, using the duration of the first quartile and the corresponding Sample video of the first sample data set as first sample point,
Obtain multiple first sample points;
Second computational submodule concentrates the third quartile of history duration parameters for calculating each second sample data
Number, using the duration of the third quartile and the corresponding Sample video of second sample data set as the second sample point,
Obtain multiple second sample points;
Submodule is built, for according to the multiple first sample point and the multiple second sample point, described in structure
At least one preset duration threshold function table.
Optionally, which is characterized in that when sample data concentration includes that the identical sample history of Sample video duration is broadcast
When putting information, the structure submodule is used for:
Linear fit is carried out using the multiple first sample point and the multiple second sample point, obtains preset duration
Threshold function table.
Optionally, which is characterized in that when sample data concentration includes that Sample video duration is identical and history plays end
When the identical sample history broadcast information of type, at least one preset duration parameters threshold function table includes at least:With PC
Hold corresponding first preset duration parameter threshold function and the second preset duration parameter threshold function corresponding with mobile terminal;
The structure submodule, is used for:
It is PC to play end type using the first sample point and corresponding history that corresponding history broadcasting end type is the ends PC
Second sample point at end carries out linear fit, obtains the first preset duration parameter threshold function;
Playing end type using the first sample point and corresponding history that corresponding history broadcasting end type is mobile terminal is
Second sample point of mobile terminal carries out linear fit, obtains the second preset duration parameter threshold function.
Optionally, which is characterized in that the property parameters are the duration of the target video;
First determining module, is used for:
If the duration of the target video is in the preset duration parameter threshold argument of function value range, by institute
The duration of target video is stated as independent variable, substitutes into the preset duration parameter threshold function, obtains the target video pair
The duration parameters threshold value answered.
Optionally, the property parameters are the duration of the target video and the target video in the play operation
In corresponding broadcasting end type, broadcasting end type include at least the ends computer PC and mobile terminal;
First determining module, is used for:
It determines the target video corresponding broadcasting end type in the play operation, obtains target and play end type;
Preset duration parameter threshold function corresponding with target broadcasting end type is determined as object function;
If the duration of the target video is in the independent variable value range of the object function, by the target video
Duration is substituted into as independent variable in the object function, obtains the corresponding duration parameters threshold value of the target video.
For first technology, the present invention has following advantage:
Duration parameters of the target user to the play operation of target video can be obtained, then according to the attribute of target video
Parameter and at least one preset duration parameter threshold function determine the corresponding duration parameters threshold value of target video, finally, can root
According to duration parameters threshold value and duration parameters, determine whether target user is satisfied with target video, compared to the prior art in it is right
All videos are all made of mode of the identical fixed duration threshold value as basis for estimation, can be according to target in the embodiment of the present invention
The property parameters of video determine the corresponding duration parameters threshold value of target video, ensure that the basis for estimation of different target videos is root
It is determined according to self attributes, and then improves the accuracy for determining video satisfaction.
Above description is only the general introduction of technical solution of the present invention, in order to better understand the technical means of the present invention,
And can be implemented in accordance with the contents of the specification, and in order to allow above and other objects of the present invention, feature and advantage can
It is clearer and more comprehensible, below the special specific implementation mode for lifting the present invention.
Description of the drawings
By reading the detailed description of hereafter preferred embodiment, various other advantages and benefit are common for this field
Technical staff will become clear.Attached drawing only for the purpose of illustrating preferred embodiments, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 is the step flow chart that a kind of video satisfaction that the embodiment of the present invention one provides determines method;
Fig. 2-1 is the step flow chart that a kind of video satisfaction provided by Embodiment 2 of the present invention determines method;
Fig. 2-2 is a kind of first curve synoptic diagram provided by Embodiment 2 of the present invention;
Fig. 2-3 is another first curve synoptic diagram provided by Embodiment 2 of the present invention;
Fig. 3 is a kind of block diagram for video satisfaction determining device that the embodiment of the present invention three provides;
Fig. 4 is a kind of block diagram for video satisfaction determining device that the embodiment of the present invention four provides.
Specific implementation mode
Exemplary embodiment of the present invention is more fully described below with reference to accompanying drawings.Although showing the present invention in attached drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the present invention without should be by embodiments set forth here
It is limited.It is to be able to be best understood from the present invention on the contrary, providing these embodiments, and can be by the scope of the present invention
Completely it is communicated to those skilled in the art.
Embodiment one
Fig. 1 is the step flow chart that a kind of video satisfaction that the embodiment of the present invention one provides determines method, such as Fig. 1 institutes
Show, this method may include:
Step 101 obtains duration parameters of the target user to the play operation of target video.
In the embodiment of the present invention, which may include target user in play operation, be broadcast to target video
It puts duration or clicks duration.Wherein, playing duration refers to the time point and target video quilt that target video is opened by target user
Duration between the time point that target user closes, it refers to the time point and mesh that target video is opened by target user to click duration
The duration between the time point of the behavior next time of user is marked, specifically, the behavior, which can be target user, clicks next knot
Fruit, either re-search for video using new keyword or exit video search, etc..
It is exemplary, it is assumed that user " Zhang San " on 2 1st, 2018 8:00 opens video A, starts to play, later, Zhang San
Again on 2 1st, 2018 8:20 open video B, while playing video A and video B, until the 8 of 2 months 1 mesh in 2018:22
Video A is closed, then can determine when the click of video A a length of 20 minutes, playing duration is 22 minutes.
Specifically, when the duration parameters are playing duration, target user can be obtained from the backstage of Video Applications and opened
When target video, the user behaviors log of generation extracts the timestamp in behavior daily record, and then obtains target video by target user
At the time point of opening, when obtaining target user's closing target video, the user behaviors log of generation extracts the time in behavior daily record
Stamp, and then obtain at the time point that target video is closed by target user, calculating between open time point and the time point of closing
Duration, and then obtain duration parameters;It correspondingly, can be from the backstage of Video Applications when the duration parameters are to click duration
When obtaining target user's opening target video, the user behaviors log of generation extracts the timestamp in behavior daily record, and then obtains mesh
At the time point that mark video is opened by target user, the behavior next time of target user is obtained, the user behaviors log of generation extracts the row
For the timestamp in daily record, and then the time point that target user executes behavior next time is obtained, open time point is calculated and is held
Duration between the time point of row behavior next time, and then duration parameters are obtained, in practical application, it can be selected according to actual demand
It selects to click duration or playing duration as duration parameters, the embodiment of the present invention is not construed as limiting this.
Step 102, the property parameters according to the target video and at least one preset duration parameter threshold function, really
Determine the corresponding duration parameters threshold value of the target video.
In the embodiment of the present invention, which includes at least the duration of target video, which can also include
Target video corresponding broadcasting end type, embodiment of the present invention in play operation are not construed as limiting this.Further, when presetting
Long parameter threshold function can be predetermined can with the function of the duration of reflecting video and duration parameters threshold value correspondence,
In the preset duration parameter threshold function, duration parameters threshold value is dependent variable, the when a length of independent variable of video.Specifically, surely belonging to
Property parameter only include target video duration when, it may be predetermined that a preset duration parameter threshold function;Work as property parameters
Duration and target video including target video are in play operation when corresponding broadcasting end type, it may be predetermined that with not
The same corresponding preset duration parameter threshold function of broadcasting end type.
Specifically, the property parameters of different target videos may be different, therefore, the corresponding duration ginseng of each target video
Number threshold value may be different, and each corresponding duration parameters threshold value of target video is determined according to the property parameters of target video
, therefore, which can indicate the duration parameters when target user is satisfied with target video.
Step 103, according to the duration parameters threshold value and the duration parameters, determine that the user regards the target
Whether frequency is satisfied with.
In the embodiment of the present invention, user can be determined to target video when duration parameters are not less than duration parameters threshold value
It is satisfied.Since duration parameters threshold value is determined according to the property parameters of target video, can indicate when target user is to target
Therefore using the duration parameters threshold value as basis for estimation, mesh can be determined more accurately out in duration parameters when video is satisfied with
Mark whether user is satisfied with target video.
In conclusion the video satisfaction that the embodiment of the present invention one provides determines method, target user can be first obtained to mesh
The duration parameters for marking the play operation of video, then according to the property parameters of target video and at least one preset duration parameter
Threshold function table determines the corresponding duration parameters threshold value of target video, finally, understands according to duration parameters threshold value and duration parameters,
Determine whether target user is satisfied with target video, compared to the prior art in identical fixed duration is all made of to all videos
Mode of the threshold value as basis for estimation in the embodiment of the present invention, can determine target video pair according to the property parameters of target video
The duration parameters threshold value answered ensures that the basis for estimation of different target videos is to be determined according to self attributes, and then improve true
Determine the accuracy of video satisfaction.
Embodiment two
Fig. 2-1 is the step flow chart that a kind of video satisfaction provided by Embodiment 2 of the present invention determines method, such as Fig. 2-1
Shown, this method may include:
Step 201, according to the corresponding sample daily record of each Sample video, determine the corresponding sample history of each Sample video
Broadcast information.
Specifically, step 201 may include:
Step 2011, according to the corresponding sample daily record of each Sample video, determine each Sample video corresponding at least one
History broadcast information.
In this step, history broadcast information can include at least the duration and history duration parameters of Sample video, this is gone through
History duration parameters may include that history playing duration or history click duration.Further, it can also be wrapped in history broadcast information
Other content is included, for example, the history including Sample video plays end type, the corresponding every history of each Sample video plays letter
Breath indicates that the primary record that the Sample video is played by user, history broadcast information can embody Sample video in this time broadcasting
Specifically which type click duration that end plays and specific or playing duration are played in.
Specifically, in the corresponding at least one history broadcast information of each Sample video of determination, it can be first flat from video
The backstage of platform obtains the corresponding daily record of the Sample video, obtains the corresponding sample daily record of the video, the Sample video corresponding day
All daily records that will, which can be the Sample video, to have added up since enter video platform can also be the Sample video at some
Between the daily record that adds up in section, the embodiment of the present invention is not construed as limiting this.It is then possible to suitable according to the time that sample daily record generates
Sequence one by one analyzes every sample daily record, generally, the daily record that user can generate for each behavior of video, daily record
It would generally include clicking time point, be clicked the ID of video, be clicked the corresponding broadcasting end type of video and this is clicked and regards
The duration of frequency, in this step, can according in every sample daily record click time point, be clicked video ID, be clicked and regard
Frequently corresponding broadcasting end type, determines the concrete behavior of the corresponding user of this daily record.It is exemplary, include with history broadcast information
The history broadcasting end type of Sample video, the duration and history duration parameters of Sample video, and history duration parameters are to play
For duration, it is assumed that indicate Sample video a in 15 purpose January in 2018 in the corresponding first sample daily record 1 of Sample video a
20:00 is opened in mobile terminal, and expression Sample video a is in January, 2018 in the corresponding Article 2 sample daily records 2 of Sample video a
The 20 of 15 mesh:02 is closed in mobile terminal, then the corresponding history broadcast information A of Sample video a can be generated, it is assumed that sample regards
The ID of frequency a be 001, when it is 40 minutes a length of, history broadcast information A can be expressed as:
Platform_id (mobile terminal) t doc_id (001) t duration (40min) t playtime (2min);
Wherein, platform_id indicates that broadcasting end type of the Sample video in this time broadcasting, doc_id indicate that sample regards
The ID of frequency, duration indicate that the duration of Sample video, playtime indicate playing duration of the Sample video in this time broadcasting.
Step 2012 obtains the corresponding at most m history broadcast information of each Sample video, obtains each Sample video pair
The sample history broadcast information answered.
In this step, m is the maximum item number of the pre-defined corresponding sample history broadcast information of each Sample video.Its
In, the concrete numerical value of m can be that developer sets according to practical experience, since some Sample videos have a large amount of click
Behavior, and then corresponding a large amount of sample daily record is had, in this way, the Sample video less compared to the behavior of click, these possess
Proportion occupied by the history broadcast information of a large amount of Sample videos for clicking behavior can be larger, causes data distribution unbalanced, into
And the preset duration function determined according to data can be caused inaccurate, in the embodiment of the present invention, by limiting each Sample video
The maximum item number of corresponding history broadcast information, can improve the harmony of data, so improve finally determine it is default when
The accuracy of long function.
Specifically when obtaining, if the item number of the corresponding all history broadcast informations of the Sample video is not more than m, obtain
The corresponding all history broadcast informations of the Sample video, obtain the corresponding sample history broadcast information of the Sample video, if should
The item number of the corresponding all history broadcast informations of Sample video is more than m, then plays letter from the corresponding all history of the Sample video
M history broadcast information is randomly choosed in breath, as the corresponding sample history broadcast information of the Sample video.It is, of course, also possible to
Other acquisition modes, the embodiment of the present invention are taken to be not construed as limiting this, as long as ensureing that the item number chosen is not more than m.
Step 202, the duration based on each Sample video draw the corresponding sample history broadcast information of each Sample video
Divide to multiple sample data sets.
Specifically, can include the duration and history duration parameters of Sample video in the sample history broadcast information
When, using dividing mode one:By comprising the identical sample history broadcast information of duration of Sample video be added to same data
Collection, obtains multiple sample data sets.Can also include the duration of Sample video, history broadcasting in the sample history broadcast information
When holding type and history duration parameters, using dividing mode two:By comprising history play that end type is identical and Sample video
The identical sample history broadcast information of duration be added to same data set, obtain multiple sample data sets.
Since the volume of video content in video platform is more huge, in this step, data set is divided according to duration
When, it can be divided using the second as the unit of the duration of Sample video.It is exemplary, it, can be with by using for dividing mode one
By comprising Sample video duration number of seconds be 10s sample history broadcast information be added in data set 1, by comprising sample
The duration number of seconds of video be 11s sample history broadcast information be added in data set 2 ... by comprising Sample video duration
Number of seconds is that the sample history broadcast information of 2700s is added in data set Z, obtains multiple sample data sets.To use division side
For formula two, can by comprising Sample video duration number of seconds be 10s and history play end type be the ends PC sample history
Broadcast information is added in data set 1 ', by comprising Sample video duration number of seconds be 11s and history play end type be PC
The sample history broadcast information at end is added in data set 2 ' ... by comprising the duration number of seconds of Sample video be 2700s and to go through
History plays the sample history broadcast information that end type is the ends PC and is added in data set Z ', obtains multiple sample data sets.
Due to when dividing data set, being to be directed to the corresponding sample history broadcast information of all Sample videos, overall data
Amount is more huge, therefore can take point bucket algorithm to realize the division of sample data set, to improve sample data set division
Efficiency.Point bucket algorithm is referred to according to the cryptographic Hash of data by data distribution to each different bucket, to complete data
Divide bucket process, bucket is sample data set.Wherein, the hash function divided employed in bucket algorithm can be selected according to data type
It selects.
Step 203, the history duration parameters for being concentrated every sample history broadcast information to include according to each sample data, really
Fixed at least one preset duration threshold function table.
Specifically, step 203 may include:
Step 2031, the sample data set that the duration of each corresponding Sample video is more than to the first duration threshold value, determine
For first sample data set, the duration of each corresponding Sample video is not more than to the sample data set of the first duration threshold value, really
It is set to the second sample data set.
In this step, which can be that developer sets according to practical experience, and exemplary, this first
Duration threshold value can be 10s.Assuming that 1~sample data set of sample data set, 10 corresponding Sample video duration is not more than 10s, it is false
If 11~sample data set of sample data set, 3000 corresponding Sample video duration is more than 10s, then can be by sample data set
11~sample data set is determined as first sample, and 3,000 1~sample data set of sample data set 10 of data set is determined as second
Sample data set.
Step 2032, the first quartile for calculating history duration parameters in each first sample data set, by described the
The duration of one quartile and the corresponding Sample video of the first sample data set obtains multiple first as first sample point
Sample point.
In this step, in the first quartile of history duration parameters in calculating first sample data set, can first by
History duration parameters in the first sample data set in every sample history broadcast information according to sequential arrangement from big to small,
It, can will be in every sample history broadcast information in the first sample data set by taking the history duration parameters are playing duration as an example
Playing duration according to sequential arrangement from small to large at an ordered series of numbers, then (n+1)/4 number in the ordered series of numbers is determined
For the first quartile of history duration parameters in the first sample data set.Further, it is assumed that first sample data set 23
The first quartile of middle history duration parameters is 10, the when a length of 30s of 23 corresponding Sample video of first sample data set, that
(20,23) can be determined as to 23 corresponding first sample point of first sample data set.
Step 2033 calculates the third quartile that each second sample data concentrates history duration parameters, by described the
The duration of three quartiles and the corresponding Sample video of second sample data set obtains multiple second as the second sample point
Sample point.
In this step, calculate the second sample data concentrate history duration parameters third quartile when, can first by
Second sample data concentrates the history duration parameters in every sample history broadcast information according to sequential arrangement from big to small,
By taking the history duration parameters are playing duration as an example, which can be concentrated in every sample history broadcast information
Playing duration according to sequential arrangement from small to large at an ordered series of numbers, then by the ordered series of numbers the 3rd (n+1)/4 number determine
The third quartile of history duration parameters is concentrated for second sample data.Further, it is assumed that in the second sample data set 9
The third quartile of history duration parameters is 3, the when a length of 9s of 9 corresponding Sample video of the second sample data set, then can
(3,9) are determined as 23 corresponding third sample point of the second sample data set.
When the duration of Sample video is shorter, if continuing to cause as sample point using first quartile follow-up
In the process, it is easy user being judged as that user is satisfied with the video for overdue hit of the Sample video, it is exemplary, for duration
For the video of 9s, its first quartile only has 3s, and the overdue of user hits the playing duration for easily reaching 3s, if with
One quartile is as standard, it is easy to which overdue hit is determined as the viewing of the once satisfaction to the video.The embodiment of the present invention
In, using third quartile as the sample point of the second sample data set, it can judge inaccuracy to avoid appearance in subsequent process
Problem
Step 2034, according to the multiple first sample point and the multiple second sample point, at least one described in structure
A preset duration threshold function table.
Specifically, when sample data concentration includes the identical sample history broadcast information of Sample video duration, step
2034 can be realized by following sub-steps (1):
Sub-step (1):Linear fit is carried out using the multiple first sample point and the multiple second sample point, is obtained
To preset duration threshold function table.
In this step, can first with Sample video when a length of reference frame horizontal axis, with the of history duration parameters
One or four scores or third quartile are the longitudinal axis of coordinate system, determined in the reference frame each first sample point and
Then each first sample point and the second sample point are sequentially connected, the first curve are obtained, then to this by each second sample point
First curve is parsed, and preset duration threshold function table is obtained, and in specific implementation, MATLAB applications may be used and solved
Analysis, the embodiment of the present invention are not construed as limiting this.
It should be noted that due in practical application scene, the negligible amounts of the long video of duration, therefore with sample
The growth of video length, the first curve is exemplary it is possible that larger fluctuation, Fig. 2-2 be second embodiment of the present invention provides
The first curve synoptic diagram of one kind, from Fig. 2-2 as can be seen that the first curve second half section part by significantly fluctuating, therefore,
It after obtaining the first curve, can be blocked larger part is fluctuated in first curve, only retain the part of normal fluctuation
It is parsed, exemplary, Fig. 2-3 is another first curve synoptic diagram provided by Embodiment 2 of the present invention, from can be in Fig. 2-3
Find out, after the part for blocking the first curve, the first curve becomes flat.
When sample data concentration includes that Sample video duration is identical and history plays the identical sample history of end type and plays
When information, step 2034 can be realized by following sub-steps (2)~sub-step (3):
Sub-step (2):The first sample point and the broadcasting of corresponding history that end type is the ends PC are played using corresponding history
It holds the second sample point that type is the ends PC to carry out linear fit, obtains the first duration parameters threshold function table.
Due to occurring mainly with mobile terminal and the ends PC for the behavior of video, other termination it is less, statistical significance is little, because
This, in the embodiment of the present invention, it may include mobile terminal and the ends PC to play end type, certainly, in another optional implementation of the present invention
In example, it can also includes other termination to play end type, for example, television, etc..
Further, the corresponding history of the corresponding first sample data set of first sample point plays end type, as this
The corresponding history of one sample point plays end type, therefore, can be determined in reference frame each based on corresponding history
The first sample point that the first sample data set that end type is the ends PC is calculated is played, and end is played based on corresponding history
Type is the second sample point that second sample data set at the ends PC is calculated, and then connects each point determined successively
It connects, obtains the second curve, then second curve is parsed, obtain the first preset duration parameter threshold corresponding with the ends PC
Function.
Sub-step (3):End type is played using corresponding history to broadcast for the first sample point of mobile terminal and corresponding history
It puts the second sample point that end type is mobile terminal and carries out linear fit, obtain the second duration parameters threshold function table.
In this step, it can determine that each corresponding history broadcasting end type that is based on is mobile terminal in reference frame
The first sample point that is calculated of first sample data set, and play that end type is mobile terminal based on corresponding history the
Then each point determined is sequentially connected, obtains third curve by the second sample point that two sample data sets are calculated,
Then the third curve is parsed, obtains the second preset duration parameter threshold function corresponding with mobile terminal.
Behavioral trait due to user at the ends PC and mobile terminal has apparent difference, it may be carried out at the same time at the ends PC
He operates, for example browses webpage, and then the duration parameters at the ends PC can be caused generally to be more than the duration parameters in mobile terminal, example
, for developer by counting in advance, it is respectively 574.91s to count the playing duration at the ends PC and click the average value of duration
And 805.29s, and 574.91, the playing duration of mobile terminal and the average value for clicking duration be respectively 515.82s and
662.35s, it can be seen that the duration parameters at the ends PC are generally more than the duration parameters in mobile terminal.Therefore, in the embodiment of the present invention,
When determining that preset duration parameter threshold function corresponding with end type is played can improve default for different broadcasting end types
The accuracy of long parameter threshold function, and then improve the accuracy for determining video satisfaction.
It should be noted that since user is during using terminal, may be browsed while the video of broadcasting
Other webpages click duration for the representative poor of the practical wish to video of user in this way, may result in, it is therefore preferable that
, using playing duration as history duration parameters, more accurately it can determine whether target user is satisfied with target video.It needs
To be illustrated, in actual application scenarios, since each video platform may be independent from each other, that is, be exactly, video platform A
All back-end datas of video platform B that possibly can not get of developer, obtain the video in other video platforms
The difficulty of playing duration is larger, therefore, in practical application, when developer can use broadcasting to the video in this video platform
It is long to be used as history duration parameters, for the video in other video platforms using click duration as history duration parameters.Into one
Step ground, when determining preset duration parameter threshold function, can be in advance based on playing duration and determine corresponding with the ends PC first
Preset duration parameter threshold function, then determine the first preset duration parameter threshold letter corresponding with the ends PC based on duration is clicked
Number determines the second preset duration parameter threshold function corresponding with mobile terminal based on playing duration, then true based on duration is clicked
The second preset duration parameter threshold function corresponding with mobile terminal is made, and then obtains four groups of preset duration parameter threshold functions,
And then convenient while determining user is to the satisfaction of the video in the video and other platforms in this platform.
Step 204 obtains duration parameters of the target user to the play operation of target video.
Specifically, the realization method of this step can refer to above-mentioned steps 101, this will not be repeated here for the embodiment of the present invention.
Step 205, the property parameters according to the target video and at least one preset duration parameter threshold function, really
Determine the corresponding duration parameters threshold value of the target video.
Specifically, when sample data concentration includes the identical sample history broadcast information of Sample video duration, that is, it is exactly,
When 201~step 203 has predefined out a preset duration parameter threshold function through the above steps, which can be with
Duration including target video, correspondingly, step 205 can be realized by following step 2051:
If the duration of step 2051, the target video is in the preset duration parameter threshold argument of function value model
In enclosing, using the duration of the target video as independent variable, substitutes into the preset duration parameter threshold function, obtain the mesh
Mark the corresponding duration parameters threshold value of video.
It is exemplary, it is assumed that the when a length of 2000s of target video, the preset duration parameter threshold argument of function value model
It encloses and it is corresponding to obtain the target video then 2000s can be substituted into the preset duration parameter threshold function for [1,2500]
Duration parameters threshold value.
When sample data concentration includes that Sample video duration is identical and history plays the identical sample history of end type and plays
When information, that is, it is exactly that 201~step 203 has predefined out the first preset duration ginseng corresponding with the ends PC through the above steps
When number threshold function table and the second preset duration parameter threshold function corresponding with mobile terminal, which may include target
The duration and target video of video corresponding broadcasting end type in this play operation, correspondingly, step 205 can pass through
Following step is realized:
Step 2052 determines the target video corresponding broadcasting end type in the play operation, obtains target and broadcasts
Put end type.
In this step, it can obtain the corresponding daily record of the play operation from the back-end data of video platform, pass through extraction
Critical field in the daily record determines target video corresponding broadcasting end type in the play operation, and then obtains target and broadcast
Put end type.
Preset duration parameter threshold function corresponding with target broadcasting end type is determined as target by step 2053
Function.
It is exemplary, it is assumed that it is the ends PC that target, which plays end type, can will the first duration parameters threshold corresponding with the ends PC
Value function is determined as object function.
If the duration of step 2054, the target video, will be described in the independent variable value range of the object function
The duration of target video is substituted into as independent variable in the object function, obtains the corresponding duration parameters threshold of the target video
Value.
It should be noted that when the duration of target video is not in preset duration parameter threshold argument of function value range
Can be exactly that maximum time parameter threshold is determined as by the dependent variable maximum value of the preset duration parameter threshold function when interior
The corresponding duration parameters threshold value of target video.
Step 206, according to the duration parameters threshold value and the duration parameters, determine the target user to the mesh
Whether mark video is satisfied with.
Specifically, the realization method of this step can refer to above-mentioned steps 103, this will not be repeated here for the embodiment of the present invention.
In another alternative embodiment of the present invention, in the satisfaction for determining user based on preset duration parameter threshold function
Later, it can also be to judge object with partial video, count these videos based on preset duration by the way of manually judging
Parameter threshold function determines under the mode of the satisfaction of user and determines expiring for user based on traditional fixation duration threshold value
Determination effect under the mode of meaning degree, in order to be further improved to the method in the present invention.Specifically, this can be counted
A little videos are when under determining the mode of satisfaction of user based on preset duration parameter threshold function and based on traditional fixation
Under mode of the long threshold value to determine the satisfaction of user, it is confirmed as accounting of unsatisfied hits in all hits,
Then, the video and the corresponding search key of the video based on the corresponding accounting difference of two ways more than 0.2, artificial judgment
Whether the quality of these videos meets corresponding search key, determines that the low method of determination of accounting is won if meeting, such as
Fruit is unsatisfactory for, and determines that the high method of determination of accounting is won, by specific experiment, it can be deduced that base provided in an embodiment of the present invention
Rate is won 92% or so in the method that preset duration parameter threshold function determines the satisfaction of user.
In conclusion video satisfaction provided by Embodiment 2 of the present invention determines method, it can be first according to each Sample video
Corresponding sample daily record determines the corresponding sample history broadcast information of each Sample video, is then based on each Sample video
The corresponding sample history broadcast information of each Sample video is divided to multiple sample data sets by duration, and true based on data set
Fixed at least one preset duration threshold function table then obtains duration parameters of the target user to the play operation of target video, so
Afterwards according to the property parameters of target video and at least one preset duration parameter threshold function, when determining that target video is corresponding
Long parameter threshold finally can determine whether target user is full to target video according to duration parameters threshold value and duration parameters
Meaning, compared to the prior art in mode of the identical fixed duration threshold value as basis for estimation, this hair are all made of to all videos
In bright embodiment, it can determine the corresponding duration parameters threshold value of target video according to the property parameters of target video, ensure different
The basis for estimation of target video is to be determined according to self attributes, and then improve the accuracy for determining video satisfaction.
Embodiment three
Fig. 3 is a kind of block diagram for video satisfaction determining device that the embodiment of the present invention three provides, as shown in figure 3, the dress
Setting 30 may include:
Acquisition module 301, the duration parameters for obtaining target user to the play operation of target video;The duration ginseng
Number includes the target user in the play operation, playing duration to the target video or clicks duration;
First determining module 302, for being joined according to the property parameters of the target video and at least one preset duration
Number threshold function table, determines the corresponding duration parameters threshold value of the target video;The property parameters are regarded including at least the target
The duration of frequency;
Second determining module 303, for according to the duration parameters threshold value and the duration parameters, determining the target
Whether user is satisfied with the target video;
Wherein, the preset duration parameter threshold function is predetermined the duration and duration parameters threshold value of reflecting video
The function of correspondence, in the preset duration parameter threshold function, duration parameters threshold value is dependent variable, video when it is a length of from
Variable.
In conclusion the video satisfaction determining device that the embodiment of the present invention three provides, acquisition module can first obtain target
User to the duration parameters of the play operation of target video, then the first determining module can according to the property parameters of target video with
And at least one preset duration parameter threshold function, determine the corresponding duration parameters threshold value of target video, finally, second determines mould
Block can determine whether target user is satisfied with target video according to duration parameters threshold value and duration parameters, compared to existing skill
Mode of the identical fixed duration threshold value as basis for estimation be all made of to all videos in art, it, can root in the embodiment of the present invention
Determine the corresponding duration parameters threshold value of target video according to the property parameters of target video, ensure the judgement of different target videos according to
It is determined according to self attributes according to being, and then improves the accuracy for determining video satisfaction.
Example IV
Fig. 4 is a kind of block diagram for video satisfaction determining device that the embodiment of the present invention three provides, as shown in figure 4, the dress
Setting 40 may include:
Acquisition module 401, the duration parameters for obtaining target user to the play operation of target video;The duration ginseng
Number includes the target user in the play operation, playing duration to the target video or clicks duration;
First determining module 402, for being joined according to the property parameters of the target video and at least one preset duration
Number threshold function table, determines the corresponding duration parameters threshold value of the target video;The property parameters are regarded including at least the target
The duration of frequency;
Second determining module 403, for according to the duration parameters threshold value and the duration parameters, determining the target
Whether user is satisfied with the target video;
Wherein, the preset duration parameter threshold function is predetermined the duration and duration parameters threshold value of reflecting video
The function of correspondence, in the preset duration parameter threshold function, duration parameters threshold value is dependent variable, video when it is a length of from
Variable.
Optionally, above-mentioned apparatus 40 further includes:
Third determining module 404, for according to the corresponding sample daily record of each Sample video, determining each Sample video pair
The sample history broadcast information answered;The sample history broadcast information includes at least the duration and history duration ginseng of Sample video
Number;
Division module 405 is used for the duration based on each Sample video, the corresponding sample history of each Sample video is broadcast
It puts information and is divided to multiple sample data sets;
4th determining module 406, for concentrating what every sample history broadcast information included to go through according to each sample data
History duration parameters determine at least one preset duration threshold function table.
Optionally, above-mentioned division module 405, is used for:
When the sample history broadcast information includes the duration and history duration parameters of Sample video, by comprising sample
The identical sample history broadcast information of duration of this video is added to same data set, obtains multiple sample data sets;
Include the duration of Sample video, history broadcasting end type and history duration ginseng in the sample history broadcast information
When number, by comprising history play that end type is identical and the identical sample history broadcast information of duration of Sample video is added to together
One data set obtains multiple sample data sets.
Optionally, above-mentioned third determining module 404, is used for:
According to the corresponding sample daily record of each Sample video, determine that corresponding at least one history of each Sample video plays
Information;
The corresponding at most m history broadcast information of each Sample video is obtained, the corresponding sample of each Sample video is obtained
History broadcast information;The m is the maximum item number of the pre-defined corresponding sample history broadcast information of each Sample video.
Optionally, above-mentioned 4th determining module 406, including:
Determination sub-module, the sample data for the duration of each corresponding Sample video to be more than to the first duration threshold value
Collection, is determined as first sample data set, and the duration of each corresponding Sample video is not more than to the sample number of the first duration threshold value
According to collection, it is determined as the second sample data set;
First computational submodule, the first quartile for calculating history duration parameters in each first sample data set
Number, using the duration of the first quartile and the corresponding Sample video of the first sample data set as first sample point,
Obtain multiple first sample points;
Second computational submodule concentrates the third quartile of history duration parameters for calculating each second sample data
Number, using the duration of the third quartile and the corresponding Sample video of second sample data set as the second sample point,
Obtain multiple second sample points;
Submodule is built, for according to the multiple first sample point and the multiple second sample point, described in structure
At least one preset duration threshold function table.
Optionally, when sample data concentration includes the identical sample history broadcast information of Sample video duration, on
Structure submodule is stated, is used for:
Linear fit is carried out using the multiple first sample point and the multiple second sample point, obtains preset duration
Threshold function table.
Optionally, when sample data concentration includes that Sample video duration is identical and history plays the identical sample of end type
When this history broadcast information, at least one preset duration parameters threshold function table includes at least:Corresponding with the ends PC first
Preset duration parameter threshold function and the second preset duration parameter threshold function corresponding with mobile terminal;
Above-mentioned structure submodule, is used for:
It is PC to play end type using the first sample point and corresponding history that corresponding history broadcasting end type is the ends PC
Second sample point at end carries out linear fit, obtains the first preset duration parameter threshold function;
Playing end type using the first sample point and corresponding history that corresponding history broadcasting end type is mobile terminal is
Second sample point of mobile terminal carries out linear fit, obtains the second preset duration parameter threshold function.
Optionally, the property parameters are the duration of the target video;
First determining module 402, is used for:
If the duration of the target video is in the preset duration parameter threshold argument of function value range, by institute
The duration of target video is stated as independent variable, substitutes into the preset duration parameter threshold function, obtains the target video pair
The duration parameters threshold value answered.
Optionally, the property parameters are the duration of the target video and the target video in the play operation
In corresponding broadcasting end type, broadcasting end type include at least the ends computer PC and mobile terminal;
First determining module 402, is used for:
It determines the target video corresponding broadcasting end type in the play operation, obtains target and play end type;
Preset duration parameter threshold function corresponding with target broadcasting end type is determined as object function;
If the duration of the target video is in the independent variable value range of the object function, by the target video
Duration is substituted into as independent variable in the object function, obtains the corresponding duration parameters threshold value of the target video.
In conclusion the video satisfaction determining device that the embodiment of the present invention four provides, third determining module can first basis
The corresponding sample daily record of each Sample video, determines the corresponding sample history broadcast information of each Sample video, then divides mould
The corresponding sample history broadcast information of each Sample video can be divided to multiple samples by block based on the duration of each Sample video
Data set, the 4th determining module can determine at least one preset duration threshold function table based on data set, and then acquisition module can obtain
Duration parameters of the target user to the play operation of target video are taken, then the first determining module can be according to the attribute of target video
Parameter and at least one preset duration parameter threshold function determine the corresponding duration parameters threshold value of target video, finally, second
Determining module can determine whether target user is satisfied with target video according to duration parameters threshold value and duration parameters, compared to
Mode of the identical fixed duration threshold value as basis for estimation, the embodiment of the present invention are all made of to all videos in the prior art
In, it can determine the corresponding duration parameters threshold value of target video according to the property parameters of target video, ensure different target videos
Basis for estimation be to be determined according to self attributes, and then improve the accuracy for determining video satisfaction.
For above-mentioned apparatus embodiment, since it is basically similar to the method embodiment, so description is fairly simple,
The relevent part can refer to the partial explaination of embodiments of method.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiment, the same or similar parts between the embodiments can be referred to each other.
It would have readily occurred to a person skilled in the art that be:The arbitrary combination application of above-mentioned each embodiment is all feasible, therefore
Arbitrary combination between above-mentioned each embodiment is all embodiment of the present invention, but this specification exists as space is limited,
This is not just detailed one by one.
Video satisfaction determines that method is not solid with any certain computer, virtual system or miscellaneous equipment provided herein
There is correlation.Various general-purpose systems can also be used together with teaching based on this.As described above, construction has this hair
Structure required by the system of bright scheme is obvious.In addition, the present invention is not also directed to any certain programmed language.It should
Understand, various programming languages can be utilized to realize the content of invention described herein, and language-specific is done above
Description is to disclose the preferred forms of the present invention.
In the instructions provided here, numerous specific details are set forth.It is to be appreciated, however, that the implementation of the present invention
Example can be put into practice without these specific details.In some instances, well known method, structure is not been shown in detail
And technology, so as not to obscure the understanding of this description.
Similarly, it should be understood that in order to simplify the present invention and help to understand one or more of each inventive aspect,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is grouped together into single implementation sometimes
In example, figure or descriptions thereof.However, the method for the disclosure should be construed to reflect following intention:It is i.e. required to protect
Shield the present invention claims the more features of feature than being expressly recited in each claim.More precisely, such as right
As claim reflects, inventive aspect is all features less than single embodiment disclosed above.Therefore, it then follows tool
Thus claims of body embodiment are expressly incorporated in the specific implementation mode, wherein each claim conduct itself
The separate embodiments of the present invention.
Those skilled in the art, which are appreciated that, to carry out adaptively the module in the equipment in embodiment
Change and they are arranged in the one or more equipment different from the embodiment.It can be the module or list in embodiment
Member or component be combined into a module or unit or component, and can be divided into addition multiple submodule or subelement or
Sub-component.Other than such feature and/or at least some of process or unit exclude each other, it may be used any
Combination is disclosed to all features disclosed in this specification (including adjoint claim, abstract and attached drawing) and so to appoint
Where all processes or unit of method or equipment are combined.Unless expressly stated otherwise, this specification (including adjoint power
Profit requires, abstract and attached drawing) disclosed in each feature can be by providing the alternative features of identical, equivalent or similar purpose come generation
It replaces.
In addition, it will be appreciated by those of skill in the art that although some embodiments described herein include other embodiments
In included certain features rather than other feature, but the combination of the feature of different embodiments means in of the invention
Within the scope of and form different embodiments.For example, in detail in the claims, embodiment claimed it is one of arbitrary
It mode can use in any combination.
The all parts embodiment of the present invention can be with hardware realization, or to run on one or more processors
Software module realize, or realized with combination thereof.It will be understood by those of skill in the art that can use in practice
Microprocessor or digital signal processor (DSP) realize the identification side of background music in video according to the ... of the embodiment of the present invention
The some or all functions of some or all components in method.The present invention is also implemented as described here for executing
Method some or all equipment or program of device (for example, computer program and computer program product).This
The program of the realization present invention of sample can may be stored on the computer-readable medium, or can be with one or more signal
Form.Such signal can be downloaded from internet website and be obtained, and either be provided on carrier signal or with any other
Form provides.
It should be noted that the present invention will be described rather than limits the invention for above-described embodiment, and ability
Field technique personnel can design alternative embodiment without departing from the scope of the appended claims.In the claims,
Any reference mark between bracket should not be configured to limitations on claims.Word "comprising" does not exclude the presence of not
Element or step listed in the claims.Word "a" or "an" before element does not exclude the presence of multiple such
Element.The present invention can be by means of including the hardware of several different elements and being come by means of properly programmed computer real
It is existing.In the unit claims listing several devices, several in these devices can be by the same hardware branch
To embody.The use of word first, second, and third does not indicate that any sequence.These words can be explained and be run after fame
Claim.
Claims (18)
1. a kind of video satisfaction determines method, which is characterized in that the method includes:
Obtain duration parameters of the target user to the play operation of target video;The duration parameters include that the target user exists
In the play operation, the playing duration to the target video or click duration;
According to the property parameters of the target video and at least one preset duration parameter threshold function, determine that the target regards
Frequently corresponding duration parameters threshold value;The property parameters include at least the duration of the target video;
According to the duration parameters threshold value and the duration parameters, determine whether the target user is full to the target video
Meaning;
Wherein, the preset duration parameter threshold function be predetermined reflecting video duration it is corresponding with duration parameters threshold value
The function of relationship, in the preset duration parameter threshold function, duration parameters threshold value is dependent variable, video when it is a length of from becoming
Amount.
2. according to the method described in claim 1, it is characterized in that, being grasped to the broadcasting of target video in the acquisition target user
Before the step of duration parameters of work, the method further includes:
According to the corresponding sample daily record of each Sample video, the corresponding sample history broadcast information of each Sample video is determined;Institute
State duration and history duration parameters that sample history broadcast information includes at least Sample video;
Based on the duration of each Sample video, the corresponding sample history broadcast information of each Sample video is divided to multiple samples
Data set;
The history duration parameters that every sample history broadcast information includes are concentrated according to each sample data, are determined at least one pre-
If duration threshold function table.
3. according to the method described in claim 2, it is characterized in that, the duration based on each Sample video, by each sample
The corresponding sample history broadcast information of this video is divided to multiple sample data sets, including:
When the sample history broadcast information includes the duration and history duration parameters of Sample video, by comprising sample regard
The identical sample history broadcast information of duration of frequency is added to same data set, obtains multiple sample data sets;
Include the duration of Sample video, history broadcasting end type and history duration parameters in the sample history broadcast information
When, by comprising history play that end type is identical and the identical sample history broadcast information of duration of Sample video be added to it is same
Data set obtains multiple sample data sets.
4. according to the method described in claim 2, it is characterized in that, the corresponding sample daily record of each Sample video of the basis,
The step of determining each Sample video corresponding sample history broadcast information, including:
According to the corresponding sample daily record of each Sample video, determine that corresponding at least one history of each Sample video plays letter
Breath;
The corresponding at most m history broadcast information of each Sample video is obtained, the corresponding sample history of each Sample video is obtained
Broadcast information;The m is the maximum item number of the pre-defined corresponding sample history broadcast information of each Sample video.
5. according to the method described in claim 2, it is characterized in that, each sample data of the basis concentrates every sample history
The history duration parameters that broadcast information includes, the step of determining at least one preset duration threshold function table, including:
The duration of each corresponding Sample video is more than to the sample data set of the first duration threshold value, is determined as first sample data
The duration of each corresponding Sample video is not more than the sample data set of the first duration threshold value, is determined as the second sample number by collection
According to collection;
The first quartile for calculating history duration parameters in each first sample data set, by the first quartile and institute
The duration of the corresponding Sample video of first sample data set is stated as first sample point, obtains multiple first sample points;
The third quartile that each second sample data concentrates history duration parameters is calculated, by the third quartile and institute
The duration of the corresponding Sample video of the second sample data set is stated as the second sample point, obtains multiple second sample points;
According to the multiple first sample point and the multiple second sample point, at least one preset duration threshold value is built
Function.
6. according to the method described in claim 5, it is characterized in that, when the sample data concentration include Sample video when appearance
With sample history broadcast information when, described according to the multiple first sample point and the multiple second sample point, structure
The step of at least one preset duration threshold function table, including:
Linear fit is carried out using the multiple first sample point and the multiple second sample point, obtains preset duration threshold value
Function.
7. according to the method described in claim 5, it is characterized in that, when the sample data concentration include Sample video when appearance
With and history play end type identical sample history broadcast information when, at least one preset duration parameters threshold function table
It includes at least:And the corresponding first preset duration parameter threshold function in the ends PC and the second preset duration parameter corresponding with mobile terminal
Threshold function table;
It is described according to the multiple first sample point and the multiple second sample point, build at least one preset duration
The step of threshold function table, including:
It is the ends PC to play end type using the first sample point and corresponding history that corresponding history broadcasting end type is the ends PC
Second sample point carries out linear fit, obtains the first preset duration parameter threshold function;
It is mobile to play end type using the first sample point and corresponding history that corresponding history broadcasting end type is mobile terminal
Second sample point at end carries out linear fit, obtains the second preset duration parameter threshold function.
8. according to the method described in claim 6, it is characterized in that, the property parameters are the duration of the target video;
The property parameters according to the target video and at least one preset duration parameter threshold function, determine the mesh
The step of marking video corresponding duration parameters threshold value, including:
If the duration of the target video is in the preset duration parameter threshold argument of function value range, by the mesh
The duration of video is marked as independent variable, substitutes into the preset duration parameter threshold function, it is corresponding to obtain the target video
Duration parameters threshold value.
9. the method according to the description of claim 7 is characterized in that the property parameters be the target video duration and
The target video corresponding broadcasting end type in the play operation, broadcasting end type include at least the ends computer PC and
Mobile terminal;
The property parameters according to the target video and at least one preset duration parameter threshold function, determine the mesh
The step of marking video corresponding duration parameters threshold value, including:
It determines the target video corresponding broadcasting end type in the play operation, obtains target and play end type;
Preset duration parameter threshold function corresponding with target broadcasting end type is determined as object function;
If the duration of the target video is in the independent variable value range of the object function, by the duration of the target video
It as independent variable, substitutes into the object function, obtains the corresponding duration parameters threshold value of the target video.
10. a kind of video satisfaction determining device, which is characterized in that described device includes:
Acquisition module, the duration parameters for obtaining target user to the play operation of target video;The duration parameters include
The target user is in the play operation, the playing duration to the target video or click duration;
First determining module is used for the property parameters according to the target video and at least one preset duration parameter threshold letter
Number, determines the corresponding duration parameters threshold value of the target video;The property parameters include at least the duration of the target video;
Second determining module, for according to the duration parameters threshold value and the duration parameters, determining the target user couple
Whether the target video is satisfied with;
Wherein, the preset duration parameter threshold function be predetermined reflecting video duration it is corresponding with duration parameters threshold value
The function of relationship, in the preset duration parameter threshold function, duration parameters threshold value is dependent variable, video when it is a length of from becoming
Amount.
11. device according to claim 10, which is characterized in that described device further includes:
Third determining module, for according to the corresponding sample daily record of each Sample video, determining the corresponding sample of each Sample video
This history broadcast information;The sample history broadcast information includes at least the duration and history duration parameters of Sample video;
Division module is used for the duration based on each Sample video, by the corresponding sample history broadcast information of each Sample video
It is divided to multiple sample data sets;
4th determining module, the history duration for concentrating every sample history broadcast information to include according to each sample data are joined
Number, determines at least one preset duration threshold function table.
12. according to the devices described in claim 11, which is characterized in that the division module is used for:
When the sample history broadcast information includes the duration and history duration parameters of Sample video, by comprising sample regard
The identical sample history broadcast information of duration of frequency is added to same data set, obtains multiple sample data sets;
Include the duration of Sample video, history broadcasting end type and history duration parameters in the sample history broadcast information
When, by comprising history play that end type is identical and the identical sample history broadcast information of duration of Sample video be added to it is same
Data set obtains multiple sample data sets.
13. according to the devices described in claim 11, which is characterized in that the third determining module is used for:
According to the corresponding sample daily record of each Sample video, determine that corresponding at least one history of each Sample video plays letter
Breath;
The corresponding at most m history broadcast information of each Sample video is obtained, the corresponding sample history of each Sample video is obtained
Broadcast information;The m is the maximum item number of the pre-defined corresponding sample history broadcast information of each Sample video.
14. according to the devices described in claim 11, which is characterized in that the 4th determining module, including:
Determination sub-module, the sample data set for the duration of each corresponding Sample video to be more than to the first duration threshold value, really
It is set to first sample data set, the duration of each corresponding Sample video is not more than to the sample data set of the first duration threshold value,
It is determined as the second sample data set;
First computational submodule, the first quartile for calculating history duration parameters in each first sample data set will
The duration of the first quartile and the corresponding Sample video of the first sample data set obtains more as first sample point
A first sample point;
Second computational submodule concentrates the third quartile of history duration parameters for calculating each second sample data, will
The duration of the third quartile and the corresponding Sample video of second sample data set obtains more as the second sample point
A second sample point;
Submodule is built, for according to the multiple first sample point and the multiple second sample point, described in structure at least
One preset duration threshold function table.
15. device according to claim 14, which is characterized in that when sample data concentration includes Sample video duration
When identical sample history broadcast information, the structure submodule is used for:
Linear fit is carried out using the multiple first sample point and the multiple second sample point, obtains preset duration threshold value
Function.
16. device according to claim 14, which is characterized in that when sample data concentration includes Sample video duration
When identical and history plays end type identical sample history broadcast information, at least one preset duration parameters threshold value letter
Number includes at least:And the corresponding first preset duration parameter threshold function in the ends PC and the second preset duration corresponding with mobile terminal are joined
Number threshold function table;
The structure submodule, is used for:
It is the ends PC to play end type using the first sample point and corresponding history that corresponding history broadcasting end type is the ends PC
Second sample point carries out linear fit, obtains the first preset duration parameter threshold function;
It is mobile to play end type using the first sample point and corresponding history that corresponding history broadcasting end type is mobile terminal
Second sample point at end carries out linear fit, obtains the second preset duration parameter threshold function.
17. device according to claim 15, which is characterized in that the property parameters are the duration of the target video;
First determining module, is used for:
If the duration of the target video is in the preset duration parameter threshold argument of function value range, by the mesh
The duration of video is marked as independent variable, substitutes into the preset duration parameter threshold function, it is corresponding to obtain the target video
Duration parameters threshold value.
18. device according to claim 16, which is characterized in that the property parameters be the target video duration with
And the target video corresponding broadcasting end type in the play operation, broadcasting end type include at least the ends computer PC
The mobile terminal and;
First determining module, is used for:
It determines the target video corresponding broadcasting end type in the play operation, obtains target and play end type;
Preset duration parameter threshold function corresponding with target broadcasting end type is determined as object function;
If the duration of the target video is in the independent variable value range of the object function, by the duration of the target video
It as independent variable, substitutes into the object function, obtains the corresponding duration parameters threshold value of the target video.
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 true CN108632670A (en) | 2018-10-09 |
CN108632670B 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) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110769286A (en) * | 2019-11-06 | 2020-02-07 | 山东科技大学 | Channel-based recommendation method and device and storage medium |
Citations (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100122291A1 (en) * | 2008-11-11 | 2010-05-13 | Samsung Electronics Co., Ltd. | Apparatus and method for processing image |
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 |
CN102769781A (en) * | 2012-07-17 | 2012-11-07 | 青岛海信传媒网络技术有限公司 | Method and device for recommending television program |
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 |
CN103747343A (en) * | 2014-01-09 | 2014-04-23 | 深圳Tcl新技术有限公司 | Method and device for resource day parting recommendation |
CN103974084A (en) * | 2014-05-07 | 2014-08-06 | 南京邮电大学 | Streaming media data block caching method, file recommendation method and streaming media server |
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 |
CN104935967A (en) * | 2015-06-19 | 2015-09-23 | 北京数码视讯科技股份有限公司 | Interest recognition method and device of video terminal user |
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 |
CN106227883A (en) * | 2016-08-05 | 2016-12-14 | 北京聚爱聊网络科技有限公司 | The temperature of a kind of content of multimedia analyzes method and apparatus |
CN106331778A (en) * | 2015-07-06 | 2017-01-11 | 腾讯科技(深圳)有限公司 | Video recommendation method 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 |
CN106604137A (en) * | 2016-12-29 | 2017-04-26 | Tcl集团股份有限公司 | Method and apparatus for predicting video viewing time length |
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 |
CN107506367A (en) * | 2017-07-03 | 2017-12-22 | 阿里巴巴集团控股有限公司 | It is determined that the method, apparatus and server of application displaying content |
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 |
-
2018
- 2018-03-15 CN CN201810215681.1A patent/CN108632670B/en active Active
Patent Citations (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100122291A1 (en) * | 2008-11-11 | 2010-05-13 | Samsung Electronics Co., Ltd. | Apparatus and method for processing image |
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 |
CN102769781A (en) * | 2012-07-17 | 2012-11-07 | 青岛海信传媒网络技术有限公司 | Method and device for recommending television program |
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 |
CN103747343A (en) * | 2014-01-09 | 2014-04-23 | 深圳Tcl新技术有限公司 | Method and device for resource day parting recommendation |
CN103974084A (en) * | 2014-05-07 | 2014-08-06 | 南京邮电大学 | Streaming media data block caching method, file recommendation method and streaming media server |
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 |
CN104935967A (en) * | 2015-06-19 | 2015-09-23 | 北京数码视讯科技股份有限公司 | Interest recognition method and device of video terminal user |
CN106331778A (en) * | 2015-07-06 | 2017-01-11 | 腾讯科技(深圳)有限公司 | Video recommendation method and device |
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 |
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 |
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 |
CN106227883A (en) * | 2016-08-05 | 2016-12-14 | 北京聚爱聊网络科技有限公司 | The temperature of a kind of content of multimedia analyzes method and apparatus |
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 |
CN106604137A (en) * | 2016-12-29 | 2017-04-26 | Tcl集团股份有限公司 | Method and apparatus for predicting video viewing time length |
CN107506367A (en) * | 2017-07-03 | 2017-12-22 | 阿里巴巴集团控股有限公司 | It is determined that the method, apparatus and server of application displaying content |
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 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110769286A (en) * | 2019-11-06 | 2020-02-07 | 山东科技大学 | Channel-based recommendation method and device and storage medium |
CN110769286B (en) * | 2019-11-06 | 2021-04-27 | 山东科技大学 | Channel-based recommendation method and device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN108632670B (en) | 2021-03-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109657138A (en) | A kind of video recommendation method, device, electronic equipment and storage medium | |
RU2636133C2 (en) | Method and device for displaying application software | |
CN104021163B (en) | Products Show system and method | |
JP5450842B2 (en) | Determination of word information entropy | |
CA3153598A1 (en) | Method of and device for predicting video playback integrity | |
CN109408665A (en) | A kind of information recommendation method and device, storage medium | |
CN103020212B (en) | Method and device for finding hot videos based on user query logs in real time | |
CN106210770B (en) | A kind of method and apparatus showing barrage information | |
CN105893390B (en) | Application processing method and electronic equipment | |
CN106600344A (en) | Method and apparatus for obtaining active user data of target product | |
US20110016111A1 (en) | Ranking search results based on word weight | |
CN105653562B (en) | The calculation method and device of correlation between a kind of content of text and inquiry request | |
CN105868256A (en) | Method and system for processing user behavior data | |
US8230039B2 (en) | Systems and methods for accelerated playback of rich internet applications | |
CN107578263A (en) | A kind of detection method, device and the electronic equipment of advertisement abnormal access | |
CN103617213B (en) | Method and system for identifying newspage attributive characters | |
CN104462554B (en) | Question and answer page relevant issues recommended method and device | |
CN113849760B (en) | Sensitive information risk assessment method, system and storage medium | |
CN107368573A (en) | Video quality evaluation method and device | |
CN104462399B (en) | The processing method and processing device of search result | |
CN110175264A (en) | Construction method, server and the computer readable storage medium of video user portrait | |
CN106874335A (en) | Behavioral data processing method, device and server | |
CN109033173B (en) | Data processing method and device for generating multidimensional index data | |
CN111061954A (en) | Search result sorting method and device and storage medium | |
CN105786910B (en) | Entry weighing computation method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |