CN103974096A - Video file assessment method, device and system - Google Patents
Video file assessment method, device and system Download PDFInfo
- Publication number
- CN103974096A CN103974096A CN201310042552.4A CN201310042552A CN103974096A CN 103974096 A CN103974096 A CN 103974096A CN 201310042552 A CN201310042552 A CN 201310042552A CN 103974096 A CN103974096 A CN 103974096A
- Authority
- CN
- China
- Prior art keywords
- video file
- user
- historical
- time span
- behavior
- 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
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
Embodiments of the invention provide a video file assessment method, device and system. The method includes: playing a video file and acquiring attribute information of the video file; acquiring user historical operational behaviors for the video file, and acquiring user historical behavioral data on the basis of the acquired user historical operational behaviors; calculating historical user viscosity parameter of the video file according to the user historical behavioral data and the attribute information of the video file, and determining results of video file assessment according to the historical viscosity parameter. The video file assessment method, device and system has the advantages that on the basis of objective behaviors of users watching video files, popularity of the video files is automatically reflected through mass data, video watchers need not actively make objective assessment results, and efficiency of assessing the video files is improved.
Description
Technical field
Embodiment of the present invention relates to technical field of information processing, more specifically, relates to a kind of video file appraisal procedure, device and system.
Background technology
Along with the develop rapidly of computer technology and network technology, the effect that the Internet (Internet) and instant messaging are brought into play in daily life, study and work is also increasing.And along with the development of mobile Internet, the Internet is also developing to mobile.In the current information age, various information equipments arise at the historic moment: the landline telephone, the mobile phone that are useful on Tone Via; Be useful on server and PC that information resources are shared, processed; Be useful on various television sets of video data demonstration etc.These equipment are all to produce for solving actual demand in specific area.Along with the arrival that E-consumer, computer, communication (3C) merge, people have been put into attentiveness in the research that the information equipment of each different field is fully utilized more and more, better serve as people to make full use of existing resource equipment.
Internet video is a kind of typical integrated application.That Internet video refers to is that provided by Web Video Service business, taking Streaming Media as broadcast format, can be online the audio video interleaved of live or program request.Internet video generally needs independently player, and file format is mainly to take the less FLV stream media format of client resource based on P2P technology, etc., also can comprise the dynamic image of propagating with video file formats such as WMV, RM, RMVB and MOV.
In various Video Applications, often have the demand that video file is assessed, thereby can reasonable arrangement video file put in order, initiatively push to user the video file that assessment result is higher, etc.In current video evaluating system, after generally having browsed video file by video audient, initiatively video file is assessed.
But because video audient's number is limited, and the video audient number of being ready initiatively to provide assessment still less, therefore this video file assessment mode efficiency is very low.And, because video audient may be with subjective colo(u)r, even there is malice comment, therefore the accuracy of this video file assessment mode is not high yet.
Summary of the invention
Embodiment of the present invention proposes a kind of video file appraisal procedure, to improve assess effectiveness.
Embodiment of the present invention has also proposed a kind of video file apparatus for evaluating, to improve assess effectiveness.
Embodiment of the present invention has also proposed a kind of video file evaluating system, to improve assess effectiveness.
The concrete scheme of embodiment of the present invention is as follows:
A kind of video file appraisal procedure, the method comprises:
Playing video file, and obtain the attribute information of this video file;
Gather for user's historical operation behavior of this video file, and user's historical behavior data are obtained in user's historical operation behavior based on gathered;
Calculate the historical viscosity parameter of this video file based on these user's historical behavior data and video file attribute information, and determine the assessment result of this video file according to this history viscosity parameter.
A kind of video file apparatus for evaluating, this device comprises video file broadcast unit, user's historical behavior data capture unit and assessment result determining unit, wherein:
Video file broadcast unit, for playing video file, and obtains the attribute information of this video file;
User's historical behavior data capture unit, for gathering the user's historical operation behavior for this video file, and user's historical behavior data are obtained in user's historical operation behavior based on gathered;
Assessment result determining unit, for calculating the historical viscosity parameter of this video file based on these user's historical behavior data and video file attribute information, and determines the assessment result of this video file according to this history viscosity parameter.
A kind of video file evaluating system, comprises client and video archive server, wherein:
Video archive server, for providing video file to client, obtains the attribute information of this video file; The user's historical behavior data that provide based on client and video file attribute information calculate the historical viscosity parameter of this video file, and determine the assessment result of this video file according to this history viscosity parameter;
Client, for playing video file, gathers for user's historical operation behavior of this video file, and user's historical operation behavior based on gathered obtains user's historical behavior data, and described user's historical behavior data are sent to video archive server.
Can find out from technique scheme, in embodiment of the present invention, playing video file, and obtain the attribute information of this video file; Gather for user's historical operation behavior of this video file, and user's historical behavior data are obtained in user's historical operation behavior based on gathered; Calculate the historical viscosity parameter of this video file based on these user's historical behavior data and video file attribute information, and determine the assessment result of this video file according to this history viscosity parameter.As can be seen here, after application embodiment of the present invention, can watch based on user the objective behavior of video file, by the pouplarity of the automatic reflecting video file of mass data, and initiatively provide subjective evaluation result without video audient, thereby improve video file assess effectiveness.
Brief description of the drawings
Fig. 1 is the video file appraisal procedure flow chart according to embodiment of the present invention;
Fig. 2 is the video file apparatus for evaluating structure chart according to embodiment of the present invention;
Fig. 3 is the video file evaluating system structure chart according to embodiment of the present invention.
Embodiment
For making the object, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing, the present invention is described in further detail.
In embodiment of the present invention, a kind of video file assessment technology based on user behavior is proposed, can watch based on user the objective behavior of video file, by the pouplarity of the automatic reflecting video file of mass data, initiatively provide subjective evaluation result without video audient, thereby improve video file assess effectiveness.
Fig. 1 is the video file appraisal procedure flow chart according to embodiment of the present invention.
As shown in Figure 1, the method comprises:
Step 101: playing video file, and obtain the attribute information of this video file.
Here, can be both local video at the video file of client terminal playing, can be also the Internet video that comes from network side.Internet video can be the dynamic image of propagating with video file formats such as WMV, RM, RMVB, FLV, MOV on network, comprises all kinds of movie and video programs, news, advertisement, FLASH animation, auto heterodyne DV, chat video, game video, monitor video etc.
Under normal circumstances, video file format has different classification, as Microsoft's video: wmv, asf, asx, etc.; Real Player video: rm, rmvb; MPEG video: mpg, mpeg, mpe; Mobile video: 3gp, etc.; Apple video: mov; Sony video: mp4, m4v, etc.; Other common video: avi, dat, mkv, flv, vob, etc.
When lacking the decoder of corresponding format in video playback client, or some external played devices (such as mobile phone, MP4 etc.) can only be play set form, therefore the phenomenon that just there will be video to play, needs using form transducer software to change in advance in this case conventionally.
The attribute information of video file has specifically described the respective attributes of video file, such as the time span of video file, the storage size of video file, the name of video file, etc.
Step 102: gather for user's historical operation behavior of this video file, and user's historical behavior data are obtained in user's historical operation behavior based on gathered.
Here, when the attribute information of the video file gathering in step 101 time span that is this video file, can gather user and watch video file behavior, and user based on gathered watches video file behavior to obtain user watching video file time span.
In one embodiment, when the attribute information of the video file gathering in step 101 time span that is this video file, can gather the surrounding time point that user drags the behavior of playback video file, the difference that user based on gathered drags the surrounding time point of playback video file behavior is obtained user and is dragged playback and watch video file time span, and user based on gathering within a predetermined period of time drags video file behavior number of times and determines the drag and drop frequency of reversing.Such as: this predetermined amount of time can be the complete overall time span of watching this video file of user, can be also the part period in this overall time span.In the time that predetermined amount of time is overall time span, the drag and drop frequency of reversing is in this overall time span, to reverse the behavior number of times of drag and drop video file divided by this overall time span; In the time that predetermined amount of time is the part period in overall time span, the drag and drop frequency of reversing is in this part period, to reverse the behavior number of times of drag and drop video file divided by the time span of this part period.In one embodiment, when the attribute information of the video file gathering in step 101 time span that is this video file, can gather user and watch video file behavior, the user based on gathered watches video file behavior to obtain user and watches video file time span; Can also gather the surrounding time point that user drags the behavior of playback video file, the difference that user based on gathered drags the surrounding time point of playback video file behavior is obtained user and is dragged playback and watch video file time span, and user based on gathering within a predetermined period of time drags video file behavior number of times and determines the drag and drop frequency of reversing.
Step 103: calculate the historical viscosity parameter of this video file based on these user's historical behavior data and video file attribute information, and determine the assessment result of this video file according to this history viscosity parameter.
In one embodiment, can watch video file time span and video file time span to calculate historical viscosity parameter based on user, and determine the assessment result of this video file according to this history viscosity parameter; Wherein historical viscosity parameter watches video file time span to be directly proportional to user, is inversely proportional to video file time span, and the assessment result of this video file is directly proportional to historical viscosity parameter.
In one embodiment, can drag that video file time span is watched in playback based on user, the drag and drop frequency of reversing and video file time span calculate historical viscosity parameter, and determine the assessment result of this video file according to this history viscosity parameter; Wherein historical viscosity parameter watches video file time span and the drag and drop frequency of reversing to be directly proportional to dragging playback, is inversely proportional to video file time span, and the assessment result of this video file is directly proportional to historical viscosity parameter.
In one embodiment, can watch that video file time span, user drag that video file time span is watched in playback based on user, the drag and drop frequency of reversing and video file time span calculate historical viscosity parameter, and determine the assessment result of this video file according to this history viscosity parameter; Wherein historical viscosity parameter is watched video file time span to user, is dragged that video file time span is watched in playback and the drag and drop frequency of reversing is directly proportional, be inversely proportional to video file time span, the assessment result of this video file is directly proportional to historical viscosity parameter.
Preferably, obtain in the process of user's historical behavior data in the user's historical operation behavior based on gathered, further remove the behavior of inactive users historical operation according to video file Internet Transmission historical record.
And after determining the assessment result of this video file, the method further comprises: the assessment result for each video file is carried out denoising; For the video file after denoising, sort according to assessment result.Such as: can be for the assessment result of each video file, the average assessment result of calculating each user and watching same video file according to Bayes's mean value algorithm.
Describe denoising mode taking Bayes's mean value algorithm as example above, it will be appreciated by those of skill in the art that embodiment of the present invention is not limited to this, but be applicable to any denoising algorithm.
In fact, can specifically implement the present invention by numerous embodiments.Such as, can be watched by the collection of video playback client the user behavior data of each video frequency program, then screen the watch data relevant to video content interest, filter out due to the not good behavioral data that affects user behavior of network condition.
Calculating in the historical viscosity parameter of this video file and the process of assessment result based on user's historical behavior data and video file attribute information, can, according to average the watching completion rate and watch the playback in process to drag behavior of video frequency program, map to ten point system score value result by setting in advance weight (such as 8:2).Wherein:
Watch completion rate=effectively the watch total duration of duration/this video;
Drag behavior score value=(playback drags duration/video duration) * playback and drag frequency * a, a is the threshold parameter setting in advance.
And, can adopt Bayes's qualitative modeling to converge the assessment result score for each each user of video file.In fact, sequence with Bayes's average out to foundation more can be reacted real situation, marking often and scoring higher product can be more forward, marking scoring after lower product also can lean on more often, compared with sorting with the average mark of the each product of simple foundation, adopt the result of Bayes's qualitative modeling more accurate.
Illustrate:
If need to be that three films sort, film A be according to 3 people's user behavior assessment, average mark 5.0; Film B is according to 10 people's user behavior assessment, average mark 4.8; Film C is according to 50 people's user behavior assessment, and average mark only has 4.5.If according to general average mark sequence, film A is optimal selection.
But, in fact say that more multi-user's behavioral data participates in marking, the scoring of this film is just more credible, just should obtain higher weight, and Bayes's mean value (Bayesian average) is exactly the method for a kind of calculating mean value of providing according to bayesian theory.Bayes's Mean Value Formulas is as follows:
C is constant, is directly proportional to the size of data set, and x
iit is concrete scoring once; M is the arithmetic mean of data set, and n is the sum of data set.
Taking film ABC as a data acquisition system is as example.Constant C=(3+10+50)/3=21, m=(3*5+10*4.8+50*4.5)/63=4.571
Table 1 is the marking contrast table of film ABC.As shown in table 1: although film A has high average, to be optimal selection in conjunction with film B after user behavior marking number of times.
Table 1
| Movie name | Marking number of times | Average marking | Total score | Bayes is average |
| A | 3 | 5.0 | 15 | 4.625 |
| B | 10 | 4.8 | 48 | 4.645 |
| C | 50 | 4.5 | 225 | 4.521 |
In above-mentioned flow process, user can utilize video player to carry out playing video file in various terminals, these terminals can include, but are not limited to: functional mobile phone, smart mobile phone, palmtop PC, PC (PC), panel computer or PDA(Personal Digital Assistant), etc.
Although enumerated in detail above the instantiation of terminal, those skilled in the art can recognize, these are enumerated is only purposes of illustration, is not intended to limit the present invention the protection range of execution mode.
When the browser of mobile terminal that is built-in with video player when employing carrys out playing video file, go for intelligent terminal operating system arbitrarily, the operating system that specifically can adopt includes, but are not limited to: Android (Andorid), Palm OS, Symbian(Saipan), Windows mobile, Linux, Android(Android), iPhone(apple) OS, Black Berry(blackberry, blueberry) OS6.0, Windows Phone series, etc.
When the browser of mobile terminal that is built-in with video player when employing carrys out playing video file, mobile terminal specifically can adopt Android operating system, and mobile terminal can use among each version of Andorid, include, but are not limited to: A Tongmu (Android Beta), clockwork spring robot (Android1.0), cup cake (Android1.5), baked donut (Android1.6), muffin (Android2.0/2.1), frozen yogurt (Android2.2), gingerbread (Android2.3), honeycomb (Android3.0), ice cream sandwich (Android4.0), jelly beans (Jelly Bean, the version such as Android4.1).
Below enumerated in detail the concrete version of Android platform, it will be appreciated by those of skill in the art that embodiment of the present invention is not limited to the above-mentioned version of enumerating, and can also be applicable among other any versions based on Android software architecture.
The browser of mobile terminal that is built-in with video player specifically can comprise the Firefox of InternetExplorer, the Mozilla of Microsoft, the Safari of Apple, the browsers such as Opera, Google Chrome, GreenBrowser.
Although listed in detail above some and be built-in with the browser of mobile terminal of video player, those skilled in the art can recognize, embodiment of the present invention is not limited to these browsers, but go for can be used for arbitrarily the file in display web page server or archives economy and allow the application (App) of user and file interaction, these application can be current common various browsers, can be also other the application programs arbitrarily with web page browsing function.
Based on foregoing detailed description, embodiment of the present invention has also proposed a kind of video file apparatus for evaluating.
Fig. 2 is the video file apparatus for evaluating structure chart according to embodiment of the present invention.
As shown in Figure 2, this device comprises video file broadcast unit 201, user's historical behavior data capture unit 202 and assessment result determining unit 203, wherein:
Video file broadcast unit 201, for playing video file, and obtains the attribute information of this video file;
User's historical behavior data capture unit 202, for gathering the user's historical operation behavior for this video file, and user's historical behavior data are obtained in user's historical operation behavior based on gathered;
Assessment result determining unit 203, for calculating the historical viscosity parameter of this video file based on these user's historical behavior data and video file attribute information, and determines the assessment result of this video file according to this history viscosity parameter.
In one embodiment, the time span that the attribute information of described video file is this video file;
User's historical behavior data capture unit 202, watches video file behavior for gathering user, and user based on gathered watches video file behavior to obtain user watching video file time span;
Assessment result determining unit 203, for watch video file time span and video file time span to calculate historical viscosity parameter based on user, and determines the assessment result of this video file according to this history viscosity parameter; Wherein historical viscosity parameter watches video file time span to be directly proportional to user, is inversely proportional to video file time span, and the assessment result of this video file is directly proportional to historical viscosity parameter.
In one embodiment, the time span that the attribute information of described video file is this video file;
User's historical behavior data capture unit 202, drag the surrounding time point of playback video file behavior for gathering user, the difference that user based on gathered drags the surrounding time point of playback video file behavior is obtained user and is dragged playback and watch video file time span, and user based on gathering within a predetermined period of time drags video file behavior number of times and determines the drag and drop frequency of reversing;
Assessment result determining unit 203, watches video file time span for drag playback based on user, the drag and drop frequency of reversing and video file time span calculate historical viscosity parameter, and determine the assessment result of this video file according to this history viscosity parameter; Wherein historical viscosity parameter watches video file time span and the drag and drop frequency of reversing to be directly proportional to dragging playback, is inversely proportional to video file time span, and the assessment result of this video file is directly proportional to historical viscosity parameter.
In one embodiment, the time span that the attribute information of described video file is this video file;
User's historical behavior data capture unit 202, watches video file behavior for gathering user, and the user based on gathered watches video file behavior to obtain user and watches video file time span; Gather the surrounding time point that user drags the behavior of playback video file, the difference that user based on gathered drags the surrounding time point of playback video file behavior is obtained user and is dragged playback and watch video file time span, and user based on gathering within a predetermined period of time drags video file behavior number of times and determines the drag and drop frequency of reversing;
Assessment result determining unit 203, for watching based on user, video file time span, user drag that video file time span is watched in playback, the drag and drop frequency of reversing and video file time span are calculated historical viscosity parameter, and determine the assessment result of this video file according to this history viscosity parameter; Wherein historical viscosity parameter is watched video file time span to user, is dragged that video file time span is watched in playback and the drag and drop frequency of reversing is directly proportional, be inversely proportional to video file time span, the assessment result of this video file is directly proportional to historical viscosity parameter.
Preferably, this device further comprises invalid data removal unit 204;
Invalid data removal unit 204, obtains the process of user's historical behavior data for the user's historical operation behavior based on gathered, do not meet the time period of predetermined threshold according to video file Internet Transmission historical record retrieval network transmission rate; Remove this and retrieve the user's historical operation behavior in the time period.
In one embodiment, this device further comprises sequencing unit 205;
Sequencing unit 205, carries out denoising for the assessment result for each video file, and for the video file after denoising, sorts according to assessment result.
Preferably, sequencing unit 205, is further used for according to assessment result, video file being sorted, according to the video file of ranking results active push predetermined number, or according to the passive video file that predetermined number is provided of ranking results.
Based on above-mentioned labor, embodiment of the present invention has also proposed a kind of video file evaluating system.
Fig. 3 is the video file evaluating system structure chart according to embodiment of the present invention.
As shown in Figure 3, this system client 301 and video archive server 302, wherein:
Video archive server 302, for providing video file to client, obtains the attribute information of this video file; The user's historical behavior data that provide based on client and video file attribute information calculate the historical viscosity parameter of this video file, and determine the assessment result of this video file according to this history viscosity parameter;
Client 301, for playing video file, gather for user's historical operation behavior of this video file, and user's historical operation behavior based on gathered obtains user's historical behavior data, and described user's historical behavior data are sent to video archive server.
In one embodiment, video archive server 302, be further used for according to assessment result, video file being sorted, initiatively push the video file of predetermined number to client 301 according to ranking results, or the video file of predetermined number is provided by trend client 301 according to ranking results.
In one embodiment, client 301, watches video file behavior for gathering user, and the user based on gathered watches video file behavior to obtain user and watches video file time span; Gather the surrounding time point that user drags the behavior of playback video file, the difference that user based on gathered drags the surrounding time point of playback video file behavior is obtained user and is dragged playback and watch video file time span, and user based on gathering within a predetermined period of time drags video file behavior number of times and determines the drag and drop frequency of reversing;
Video archive server 302, for watching based on user, video file time span, user drag that video file time span is watched in playback, the drag and drop frequency of reversing and video file time span are calculated historical viscosity parameter, and determine the assessment result of this video file according to this history viscosity parameter; Wherein historical viscosity parameter is watched video file time span to user, is dragged that video file time span is watched in playback and the drag and drop frequency of reversing is directly proportional, and is inversely proportional to video file time span, and the assessment result of this video file is directly proportional to historical viscosity parameter.
Between client 301 and video archive server 302, can communicate connection by multiple wireline communication network or cordless communication network.
The direction and the time relationship that transmit by information, the communication mode between client 301 and video archive server 302 can be divided into simplex, half-duplex operation and full-duplex communication, etc.
In embodiment of the present invention, between client 301 and video archive server 302, can arrange concrete communication protocol, in these communication protocols, define the form that data cell is used, the information that information unit should comprise and implication, connected mode, the sequential of information sending and receiving, thus guarantee that in network, data are successfully sent to definite place.
Such as, but the communication protocol that client 301 and video archive server 302 can adopt comprises and being not limited to: the 3rd version (POP3) of TCP/IP (TCP/IP), HTTP(Hypertext Transport Protocol), Simple Mail Transfer protocol (SMTP), post office protocol, etc.
And client 301 can be carried out information interaction by multiple communication standard and video file 302 in embodiment of the present invention.Such as: can adopt the various communication standards such as global system for mobile communications (GSM), Wideband Code Division Multiple Access (WCDMA) (WCDMA), CDMA 2000 (CDMA-2000), TD SDMA (TD-SCDMA).
Information interaction form between client 301 and video archive server 302 can have various ways.Such as, information format can include, but are not limited to: short message (SMS), Email, instant messaging (IM) information, multimedia messages (MMS) or voice messaging, etc.
Preferably, before video file stream is sent to client 301 by video archive server 302, whether video archive server 302 is can checking client 301 identity legal, and and if only if client 301 identity just send video file stream to client 301 when legal.Wherein: whether checking client 301 identity legal comprises for video archive server 302: checking client 301 user fingerprints whether with authorize that fingerprint matches, checking client 301 users' iris whether with authorize that iris matches, whether the international Mobile Equipment identification code of checking client 301 (IEMI) legal; or the screen protection of checking client 301 whether password is set correct, etc.
Although enumerate out in detail above some concrete forms of the information interaction form between client 301 and video archive server 302, it will be appreciated by those of skill in the art that this enumerating is only exemplary, and be not used in, embodiment of the present invention is limited.
In fact, can specifically implement video file appraisal procedure and the device that embodiment of the present invention proposes by various ways.Such as, can follow the application programming interfaces of certain specification, video file appraisal procedure is written as to the plug-in card program being installed in PC, mobile terminal etc., also can be encapsulated as application program and be downloaded voluntarily use for user.In the time being written as plug-in card program, can be implemented as the multiple card format such as ocx, dll, cab.Also can implement the video file appraisal procedure that embodiment of the present invention proposes by the concrete technology such as Flash plug-in unit, RealPlayer plug-in unit, MMS plug-in unit, MIDI staff plug-in unit, ActiveX plug-in unit.
The video file appraisal procedure that can embodiment of the present invention be proposed by the storing mode of instruction or instruction set storage is stored on various storage mediums.These storage mediums include, but are not limited to: floppy disk, CD, DVD, hard disk, flash memory, USB flash disk, CF card, SD card, mmc card, SM card, memory stick (Memory Stick), xD card etc.
In addition, the video file appraisal procedure that embodiment of the present invention can also be proposed is applied in the storage medium based on flash memory (Nand flash), such as USB flash disk, CF card, SD card, SDHC card, mmc card, SM card, memory stick, xD card etc.
In sum, in embodiment of the present invention, playing video file, and obtain the attribute information of this video file; Gather for user's historical operation behavior of this video file, and user's historical behavior data are obtained in user's historical operation behavior based on gathered; Calculate the historical viscosity parameter of this video file based on these user's historical behavior data and video file attribute information, and determine the assessment result of this video file according to this history viscosity parameter.As can be seen here, after application embodiment of the present invention, can watch based on user the objective behavior of video file, by the pouplarity of the automatic reflecting video file of mass data, initiatively provide subjective evaluation result without video audient, thereby improve video file assess effectiveness.
The above, be only preferred embodiment of the present invention, is not intended to limit protection scope of the present invention.Within the spirit and principles in the present invention all, any amendment of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (18)
1. a video file appraisal procedure, is characterized in that, the method comprises:
Playing video file, and obtain the attribute information of this video file;
Gather for user's historical operation behavior of this video file, and user's historical behavior data are obtained in user's historical operation behavior based on gathered;
Determine the historical viscosity parameter of this video file based on these user's historical behavior data and video file attribute information, and determine the assessment result of this video file according to this history viscosity parameter.
2. video file appraisal procedure according to claim 1, is characterized in that, the time span that the attribute information of described video file is this video file; Described collection is for user's historical operation behavior of this video file, and user's historical operation behavior based on gathered is obtained user's historical behavior data and comprised:
Gather user and watch video file behavior, and user based on gathered watches video file behavior to obtain user watching video file time span;
Describedly determine the historical viscosity parameter of this video file based on these user's historical behavior data and video file attribute information, and determine that according to this history viscosity parameter the assessment result of this video file comprises:
Watch video file time span and video file time span to determine historical viscosity parameter based on user, and determine the assessment result of this video file according to this history viscosity parameter; Wherein historical viscosity parameter watches video file time span to be directly proportional to user, is inversely proportional to video file time span, and the assessment result of this video file is directly proportional to historical viscosity parameter.
3. video file appraisal procedure according to claim 1, is characterized in that, the time span that the attribute information of described video file is this video file; Described collection is for user's historical operation behavior of this video file, and user's historical operation behavior based on gathered is obtained user's historical behavior data and comprised:
Gather the surrounding time point that user drags the behavior of playback video file, the difference that user based on gathered drags the surrounding time point of playback video file behavior is obtained user and is dragged playback and watch video file time span, and user based on gathering within a predetermined period of time drags video file behavior number of times and determines the drag and drop frequency of reversing;
Describedly determine the historical viscosity parameter of this video file based on these user's historical behavior data and video file attribute information, and determine that according to this history viscosity parameter the assessment result of this video file comprises:
Based on user drag that video file time span is watched in playback, the drag and drop frequency of reversing and video file time span determine historical viscosity parameter, and determine the assessment result of this video file according to this history viscosity parameter; Wherein historical viscosity parameter watches video file time span and the drag and drop frequency of reversing to be directly proportional to dragging playback, is inversely proportional to video file time span, and the assessment result of this video file is directly proportional to historical viscosity parameter.
4. video file appraisal procedure according to claim 1, is characterized in that, the time span that the attribute information of described video file is this video file; Described collection is for user's historical operation behavior of this video file, and user's historical operation behavior based on gathered is obtained user's historical behavior data and comprised:
Gather user and watch video file behavior, the user based on gathered watches video file behavior to obtain user and watches video file time span; Gather the surrounding time point that user drags the behavior of playback video file, the difference that user based on gathered drags the surrounding time point of playback video file behavior is obtained user and is dragged playback and watch video file time span, and user based on gathering within a predetermined period of time drags video file behavior number of times and determines the drag and drop frequency of reversing;
Describedly determine the historical viscosity parameter of this video file based on these user's historical behavior data and video file attribute information, and determine that according to this history viscosity parameter the assessment result of this video file comprises:
Based on user watch that video file time span, user drag that video file time span is watched in playback, the drag and drop frequency of reversing and video file time span determine historical viscosity parameter, and determine the assessment result of this video file according to this history viscosity parameter; Wherein historical viscosity parameter is watched video file time span to user, is dragged that video file time span is watched in playback and the drag and drop frequency of reversing is directly proportional, be inversely proportional to video file time span, the assessment result of this video file is directly proportional to historical viscosity parameter.
5. video file appraisal procedure according to claim 1, is characterized in that, the method further comprises:
Obtain in the process of user's historical behavior data in the user's historical operation behavior based on gathered, do not meet the time period of predetermined threshold according to video file Internet Transmission historical record retrieval network transmission rate;
Remove this and retrieve the user's historical operation behavior in the time period.
6. video file appraisal procedure according to claim 1, is characterized in that, after determining the assessment result of this video file, the method further comprises:
Assessment result for each video file is carried out denoising;
For the video file after denoising, sort according to assessment result.
7. video file appraisal procedure according to claim 6, is characterized in that, the described assessment result for each video file is carried out denoising and comprised:
For the assessment result of each video file, the average assessment result of calculating each user and watching same video file according to Bayes's mean value algorithm.
8. video file appraisal procedure according to claim 6, is characterized in that, the method further comprises:
According to assessment result, video file is sorted, and according to the video file of ranking results active push predetermined number, or according to the passive video file that predetermined number is provided of ranking results.
9. a video file apparatus for evaluating, is characterized in that, this device comprises video file broadcast unit, user's historical behavior data capture unit and assessment result determining unit, wherein:
Video file broadcast unit, for playing video file, and obtains the attribute information of this video file;
User's historical behavior data capture unit, for gathering the user's historical operation behavior for this video file, and user's historical behavior data are obtained in user's historical operation behavior based on gathered;
Assessment result determining unit, for determining the historical viscosity parameter of this video file based on these user's historical behavior data and video file attribute information, and determines the assessment result of this video file according to this history viscosity parameter.
10. video file apparatus for evaluating according to claim 9, is characterized in that, the time span that the attribute information of described video file is this video file;
User's historical behavior data capture unit, watches video file behavior for gathering user, and user based on gathered watches video file behavior to obtain user watching video file time span;
Assessment result determining unit, for watch video file time span and video file time span to determine historical viscosity parameter based on user, and determines the assessment result of this video file according to this history viscosity parameter; Wherein historical viscosity parameter watches video file time span to be directly proportional to user, is inversely proportional to video file time span, and the assessment result of this video file is directly proportional to historical viscosity parameter.
11. video file apparatus for evaluating according to claim 9, is characterized in that the time span that the attribute information of described video file is this video file;
User's historical behavior data capture unit, drag the surrounding time point of playback video file behavior for gathering user, the difference that user based on gathered drags the surrounding time point of playback video file behavior is obtained user and is dragged playback and watch video file time span, and user based on gathering within a predetermined period of time drags video file behavior number of times and determines the drag and drop frequency of reversing;
Assessment result determining unit, watches video file time span for drag playback based on user, the drag and drop frequency of reversing and video file time span determine historical viscosity parameter, and determine the assessment result of this video file according to this history viscosity parameter; Wherein historical viscosity parameter watches video file time span and the drag and drop frequency of reversing to be directly proportional to dragging playback, is inversely proportional to video file time span, and the assessment result of this video file is directly proportional to historical viscosity parameter.
12. video file apparatus for evaluating according to claim 9, is characterized in that the time span that the attribute information of described video file is this video file;
User's historical behavior data capture unit, watches video file behavior for gathering user, and the user based on gathered watches video file behavior to obtain user and watches video file time span; Gather the surrounding time point that user drags the behavior of playback video file, the difference that user based on gathered drags the surrounding time point of playback video file behavior is obtained user and is dragged playback and watch video file time span, and user based on gathering within a predetermined period of time drags video file behavior number of times and determines the drag and drop frequency of reversing;
Assessment result determining unit, for watching based on user, video file time span, user drag that video file time span is watched in playback, the drag and drop frequency of reversing and video file time span are determined historical viscosity parameter, and determine the assessment result of this video file according to this history viscosity parameter; Wherein historical viscosity parameter is watched video file time span to user, is dragged that video file time span is watched in playback and the drag and drop frequency of reversing is directly proportional, be inversely proportional to video file time span, the assessment result of this video file is directly proportional to historical viscosity parameter.
13. video file apparatus for evaluating according to claim 9, is characterized in that, this device further comprises invalid data removal unit;
Invalid data removal unit, obtains the process of user's historical behavior data for the user's historical operation behavior based on gathered, further do not meet the time period of predetermined threshold according to video file Internet Transmission historical record retrieval network transmission rate; Remove this and retrieve the user's historical operation behavior in the time period.
14. video file apparatus for evaluating according to claim 9, is characterized in that, this device further comprises sequencing unit;
Sequencing unit, carries out denoising for the assessment result for each video file, and for the video file after denoising, sorts according to assessment result.
15. video file apparatus for evaluating according to claim 14, is characterized in that,
Sequencing unit, after being further used for sorting video file being sorted according to assessment result, according to the video file of ranking results active push predetermined number, or according to the passive video file that predetermined number is provided of ranking results.
16. 1 kinds of video file evaluating systems, is characterized in that, comprise client and video archive server, wherein:
Video archive server, for providing video file to client, obtains the attribute information of this video file; The user's historical behavior data that provide based on client and video file attribute information calculate the historical viscosity parameter of this video file, and determine the assessment result of this video file according to this history viscosity parameter;
Client, for playing video file, gathers for user's historical operation behavior of this video file, and user's historical operation behavior based on gathered obtains user's historical behavior data, and described user's historical behavior data are sent to video archive server.
17. video file evaluating systems according to claim 16, is characterized in that,
Video archive server, is further used for according to assessment result, video file being sorted, and initiatively to the video file of client push predetermined number, or is provided the video file of predetermined number by trend client according to ranking results according to ranking results.
18. video file evaluating systems according to claim 16, is characterized in that,
Client, watches video file behavior for gathering user, and the user based on gathered watches video file behavior to obtain user and watches video file time span; Gather the surrounding time point that user drags the behavior of playback video file, the difference that user based on gathered drags the surrounding time point of playback video file behavior is obtained user and is dragged playback and watch video file time span, and user based on gathering within a predetermined period of time drags video file behavior number of times and determines the drag and drop frequency of reversing;
Video archive server, for watching based on user, video file time span, user drag that video file time span is watched in playback, the drag and drop frequency of reversing and video file time span are calculated historical viscosity parameter, and determine the assessment result of this video file according to this history viscosity parameter; Wherein historical viscosity parameter is watched video file time span to user, is dragged that video file time span is watched in playback and the drag and drop frequency of reversing is directly proportional, be inversely proportional to video file time span, the assessment result of this video file is directly proportional to historical viscosity parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310042552.4A CN103974096B (en) | 2013-02-01 | 2013-02-01 | A kind of video file appraisal procedure, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310042552.4A CN103974096B (en) | 2013-02-01 | 2013-02-01 | A kind of video file appraisal procedure, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103974096A true CN103974096A (en) | 2014-08-06 |
| CN103974096B CN103974096B (en) | 2018-10-26 |
Family
ID=51243061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310042552.4A Active CN103974096B (en) | 2013-02-01 | 2013-02-01 | A kind of video file appraisal procedure, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103974096B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104410874A (en) * | 2014-11-19 | 2015-03-11 | 北京国双科技有限公司 | A method, a device, and a system for detecting video viscosity information |
| CN106658083A (en) * | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Watching channel path counting method and watching channel path counting device |
| CN107079199A (en) * | 2014-10-17 | 2017-08-18 | 汤森路透全球资源公司 | Order video news program |
| CN107147957A (en) * | 2017-04-19 | 2017-09-08 | 北京小米移动软件有限公司 | Video broadcasting method and device |
| CN107302552A (en) * | 2016-04-15 | 2017-10-27 | 福建华渔未来教育科技有限公司 | A kind of file migration method and system |
| CN107613289A (en) * | 2017-10-19 | 2018-01-19 | 何翔 | A kind of video content analysis method and device based on blink detection |
| CN108495150A (en) * | 2018-01-24 | 2018-09-04 | 北京奇艺世纪科技有限公司 | A kind of video clicks the determination method and device of satisfaction |
| CN109218770A (en) * | 2018-10-19 | 2019-01-15 | 深圳市轱辘汽车维修技术有限公司 | A kind of appraisal procedure, device and the equipment of Automobile Service video |
| CN110069714A (en) * | 2019-04-25 | 2019-07-30 | 北京酷我科技有限公司 | A kind of video recommendation system |
| CN111565335A (en) * | 2020-06-01 | 2020-08-21 | 中国联合网络通信集团有限公司 | Video quality evaluation method and device, computer equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030208754A1 (en) * | 2002-05-01 | 2003-11-06 | G. Sridhar | System and method for selective transmission of multimedia based on subscriber behavioral model |
| US20080120650A1 (en) * | 2006-11-21 | 2008-05-22 | Kabushiki Kaisha Toshiba | Program information providing system |
| CN101415085A (en) * | 2007-10-19 | 2009-04-22 | 株式会社东芝 | Viewing behavior learning apparatus |
| US20090282439A1 (en) * | 2008-05-06 | 2009-11-12 | Microsoft Corporation | Digital tv scanning optimization |
| CN102487456A (en) * | 2009-11-30 | 2012-06-06 | 国际商业机器公司 | Method for providing visit rate of online video and device thereof |
| CN102486796A (en) * | 2010-12-03 | 2012-06-06 | 腾讯科技（深圳）有限公司 | Method and device for acquiring video information |
-
2013
- 2013-02-01 CN CN201310042552.4A patent/CN103974096B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030208754A1 (en) * | 2002-05-01 | 2003-11-06 | G. Sridhar | System and method for selective transmission of multimedia based on subscriber behavioral model |
| US20080120650A1 (en) * | 2006-11-21 | 2008-05-22 | Kabushiki Kaisha Toshiba | Program information providing system |
| CN101415085A (en) * | 2007-10-19 | 2009-04-22 | 株式会社东芝 | Viewing behavior learning apparatus |
| US20090282439A1 (en) * | 2008-05-06 | 2009-11-12 | Microsoft Corporation | Digital tv scanning optimization |
| CN102487456A (en) * | 2009-11-30 | 2012-06-06 | 国际商业机器公司 | Method for providing visit rate of online video and device thereof |
| CN102486796A (en) * | 2010-12-03 | 2012-06-06 | 腾讯科技（深圳）有限公司 | Method and device for acquiring video information |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107079199A (en) * | 2014-10-17 | 2017-08-18 | 汤森路透全球资源公司 | Order video news program |
| CN104410874A (en) * | 2014-11-19 | 2015-03-11 | 北京国双科技有限公司 | A method, a device, and a system for detecting video viscosity information |
| CN106658083A (en) * | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Watching channel path counting method and watching channel path counting device |
| CN106658083B (en) * | 2015-10-30 | 2019-09-17 | 北京国双科技有限公司 | A kind of statistical method and device for watching channel path |
| CN107302552A (en) * | 2016-04-15 | 2017-10-27 | 福建华渔未来教育科技有限公司 | A kind of file migration method and system |
| CN107147957B (en) * | 2017-04-19 | 2019-09-10 | 北京小米移动软件有限公司 | Video broadcasting method and device |
| CN107147957A (en) * | 2017-04-19 | 2017-09-08 | 北京小米移动软件有限公司 | Video broadcasting method and device |
| CN107613289A (en) * | 2017-10-19 | 2018-01-19 | 何翔 | A kind of video content analysis method and device based on blink detection |
| CN108495150A (en) * | 2018-01-24 | 2018-09-04 | 北京奇艺世纪科技有限公司 | A kind of video clicks the determination method and device of satisfaction |
| CN108495150B (en) * | 2018-01-24 | 2020-09-15 | 北京奇艺世纪科技有限公司 | Method and device for determining video click satisfaction |
| CN109218770A (en) * | 2018-10-19 | 2019-01-15 | 深圳市轱辘汽车维修技术有限公司 | A kind of appraisal procedure, device and the equipment of Automobile Service video |
| CN109218770B (en) * | 2018-10-19 | 2021-08-10 | 深圳市轱辘车联数据技术有限公司 | Method, device and equipment for evaluating automobile repair video |
| CN110069714A (en) * | 2019-04-25 | 2019-07-30 | 北京酷我科技有限公司 | A kind of video recommendation system |
| CN111565335A (en) * | 2020-06-01 | 2020-08-21 | 中国联合网络通信集团有限公司 | Video quality evaluation method and device, computer equipment and storage medium |
| CN111565335B (en) * | 2020-06-01 | 2021-09-03 | 中国联合网络通信集团有限公司 | Video quality evaluation method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103974096B (en) | 2018-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103974096A (en) | Video file assessment method, device and system | |
| CN107087235B (en) | Media content recommendation method, server and client | |
| US9256826B2 (en) | Predicting reactions to short-text posts | |
| US10454889B2 (en) | Automatic anomaly detection framework for grid resources | |
| CN110941738B (en) | Recommendation method and device, electronic equipment and computer-readable storage medium | |
| CN110598157B (en) | Target information identification method, device, equipment and storage medium | |
| US20120136714A1 (en) | User intent analysis engine | |
| CN106970949A (en) | A kind of information recommendation method and device | |
| Chan et al. | Review of evaluation metrics used in digital and traditional tobacco control campaigns | |
| CN103905835A (en) | Progress preview method, device and system for video player | |
| TW201543238A (en) | Method and system for evaluating user satisfaction with respect to a user session | |
| CN102929938A (en) | Playable network resource ordering method and device | |
| CN104935651A (en) | Content recommending method and terminal | |
| CN112215238B (en) | Method, system and device for constructing general feature extraction model | |
| US20170127132A1 (en) | Channel Preference Scoring For Users Based On Channel Watching and Browsing Behavior | |
| CN107301585A (en) | A kind of recommendation method, system and equipment applied based on real-time dynamic interactive scene | |
| US20170168660A1 (en) | Voice bullet screen generation method and electronic device | |
| WO2016165414A1 (en) | Method and device for push information | |
| CN113988954A (en) | Financing product marketing method and device | |
| CN106682054B (en) | Terminal application recommendation method, device and system | |
| CN110121088B (en) | User attribute information determination method and device and electronic equipment | |
| WO2022225927A1 (en) | System for audience sentiment feedback and analysis | |
| CN103942247A (en) | Information providing method and device for multimedia resources | |
| CN109408723A (en) | A kind of method for pushing and device | |
| CN105956061A (en) | Method and device for determining similarity between users |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |