CN107707964A - The method and apparatus for predicting video content temperature - Google Patents
The method and apparatus for predicting video content temperature Download PDFInfo
- Publication number
- CN107707964A CN107707964A CN201610644027.3A CN201610644027A CN107707964A CN 107707964 A CN107707964 A CN 107707964A CN 201610644027 A CN201610644027 A CN 201610644027A CN 107707964 A CN107707964 A CN 107707964A
- Authority
- CN
- China
- Prior art keywords
- temperature
- video content
- predicted
- day
- standard grade
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 77
- 238000012217 deletion Methods 0.000 claims description 28
- 230000037430 deletion Effects 0.000 claims description 28
- 238000009826 distribution Methods 0.000 claims description 8
- 230000001154 acute effect Effects 0.000 claims description 4
- 230000006870 function Effects 0.000 description 15
- 238000003860 storage Methods 0.000 description 12
- 239000000344 soap Substances 0.000 description 10
- 230000008859 change Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 239000000306 component Substances 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 4
- 238000005859 coupling reaction Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010438 heat treatment Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 239000003795 chemical substances by application Substances 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000013016 damping Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000005055 memory storage Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000001373 regressive effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 241001123248 Arma Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 208000021760 high fever Diseases 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004549 pulsed laser deposition Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
- H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
- H04N21/4314—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations for fitting data in a restricted space on the screen, e.g. EPG data in a rectangular grid
-
- 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
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
- H04N21/4756—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Human Computer Interaction (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The embodiment of the invention discloses a kind of method and apparatus for predicting video content temperature, this method includes:The temperature information of forecasting of video content to be predicted is obtained, temperature information of forecasting includes at least one of following:The temperature of female collection of drama of video content to be predicted, the temperature of the video content in Electronic Program Guide EPG residing for video content to be predicted in region, the fitting temperature of video content to be predicted, wherein, fitting temperature includes decay temperature and random temperature;The temperature that video content to be predicted reaches the standard grade i-th day is determined according to temperature information of forecasting, i is the integer more than or equal to 1.Pass through the temperature of female collection of drama of video content to be predicted, temperature, the fitting temperature of video content to be predicted of video content in Electronic Program Guide EPG residing for video content to be predicted in region, can predict video content to be predicted reach the standard grade after the temperature of following any day, forecasting accuracy is low when solving the problems, such as to be predicted as granularity using day in the prior art.
Description
Technical field
The present invention relates to Video service field, and more particularly, to it is a kind of predict video content temperature method and
Device.
Background technology
At present, video file transfer occupies the flow of internet more than 60%.Because the transmission of video file is to bandwidth
It is much higher with the requirement ratio webpage (Web) of time delay, so the source server that user directly arrives content provider obtains the side serviced
Formula can not only make poor user experience, and huge bandwidth pressure can be also brought to bearer network.So content provider would generally use
Content distributing network (Content Distribution Network, CDN) carries out the service of content distribution.
CDN is a kind of covering (Overlay) network on bearer network.The classification deployment of CDN system generally use
Mode:Centroid preserves full dose content close to the source station of content provider;Fringe node preserves part close to terminal user
Content.Due to the limited storage space of fringe node, in order to utilize storage and the distribution capability of fringe node to greatest extent, need
Fringe node is allowed to preserve the high fever content that user's future most probable accesses as much as possible.At this time, it may be necessary to video content future
Temperature be predicted.
CDN is when predicting video content future temperature, two kinds of approach of generally use:One kind is to pull the side of (PULL)
Formula, another kind are the modes for pushing (PUSH).PULL modes carry out work by the way of video content future temperature is calculated in real time
Make.And because requirement of real-time is higher, history temperature progress of the PULL modes generally only with video content is simple pre-
Survey.For example, minimum use the video content that (Least Recently Used, LRU) algorithm is thought to be accessed recently not recently
It is bigger than the video content possibility not accessed for a long time the possibility that is accessed, therefore temperature is higher.The minimum frequency uses
(Least Frequently Used, LFU) algorithm thinks the possibility that the video content of historical requests often will be accessed in future
The property video content possibility fewer than historical requests number is bigger, therefore temperature is higher.Although this Forecasting Methodology can be every
Individual user asks to carry out real-time cache decision when arrival, but its information of forecasting relied on is less, and precision of prediction is poor,
It is unable to reach very high cache hit rate.PUSH modes are very low (for example, once daily) to requirement of real-time, it will usually using more
More dimensions carries out the prediction of video content future temperature, therefore can obtain higher video content future temperature prediction essence
Degree and cache hit rate.
The mode that prior art is weighted according to the temperature association attributes of video resource is following to predict video content
Temperature.Wherein, temperature association attributes includes performer, director, subject matter etc..For example, the temperature characteristic information of video resource is Weir
Smith and science fiction, history hot value corresponding to the two features are 80 and 90, temperature weight difference corresponding to performer and type
For 0.6 and 0.4, then the prediction hot value of the video resource is 80*0.6+90*0.4=84.
Prior art simply carries out temperature prediction by the way of the temperature of different temperature association attributeses is added by weight,
Because the period of change of temperature association attributes is very long (in units of the moon), and it is very short (in units of day) therefore right to push away the cycle in advance
The precision of following one day temperature prediction of video content is relatively low.
The content of the invention
The embodiments of the invention provide a kind of method for predicting video content temperature, it is possible to increase video content future temperature
The precision of prediction.
First aspect, there is provided a kind of method for predicting video content temperature, including:Obtain the heat of video content to be predicted
Information of forecasting is spent, temperature information of forecasting includes at least one of following:The temperature of female collection of drama of video content to be predicted, in electricity
The fitting of the temperature, video content to be predicted of video content in sub- program navigating EPG residing for video content to be predicted in region
Temperature, wherein, fitting temperature includes decay temperature and random temperature, and decay temperature is the day of reaching the standard grade according to video content to be predicted
Number and reach the standard grade what the corresponding history temperature of number of days determined with video content to be predicted, random temperature is according to decay temperature and with declining
What history temperature corresponding to reduction of heat degree determined;The temperature that video content to be predicted reaches the standard grade i-th day is determined according to temperature information of forecasting,
I is the integer more than or equal to 1.
In the prior art in the temperature after predicting that video content to be predicted is reached the standard grade according to temperature association attributes, due to temperature
The period of change of association attributes is very long (in units of the moon), thus video content to be predicted reach the standard grade after the temperature of following any day
Prediction result is essentially identical.And the method for the prediction video content temperature of the embodiment of the present invention, pass through video content to be predicted
The temperature of female collection of drama, the temperature of video content in Electronic Program Guide EPG residing for video content to be predicted in region, treat it is pre-
Survey video content fitting temperature, can predict video content to be predicted reach the standard grade after the temperature of following any day, solve show
There is the problem of forecasting accuracy is low when being predicted in technology using day as granularity.
In a kind of possible implementation, the temperature of female collection of drama of video content to be predicted includes video content to be predicted
The temperature reached the standard grade i-th day of part or all of female collection of drama, determine that video content to be predicted is reached the standard grade i-th day according to temperature information of forecasting
Temperature, including:The temperature that part or all of female collection of drama in female collection of drama of video content to be predicted is reached the standard grade i-th day, really
The temperature that fixed video content to be predicted is reached the standard grade i-th day.
In the embodiment of the present invention, because the temperature information of forecasting used is the mother using day as the video content to be predicted of granularity
The temperature that collection of drama is reached the standard grade i-th day, to predict the i-th of video content to be predicted day temperature.Accordingly, with respect in the prior art with change
Change cycle very long temperature association attributes to predict the i-th of video content to be predicted day temperature, precision of prediction is higher.
In a kind of possible implementation, part or all of female collection of drama in female collection of drama of video content to be predicted
The temperature reached the standard grade i-th day, the temperature that video content to be predicted is reached the standard grade i-th day is determined, including:Determined according to below equation to be predicted
The temperature that video content is reached the standard grade i-th day:
Wherein, hiThe temperature reached the standard grade for video content to be predicted i-th day,For m female collection of dramas of video content to be predicted
In the temperatures reached the standard grade i-th day of female collection of drama j, ajThe temperature weight reached the standard grade for female collection of drama j i-th day, m of video content to be predicted
Female collection of drama is part or all of female collection of drama in female collection of drama of video content to be predicted, and m is the integer more than or equal to 1, and j is big
In or equal to 1 integer.
In a kind of possible implementation, the temperature of the video content in region residing for video content to be predicted includes
The average temperature that video content residing for video content to be predicted in region is reached the standard grade the i-th -1 day, determined according to temperature information of forecasting
The temperature that video content to be predicted is reached the standard grade i-th day, including:Reached the standard grade according to the video content residing for video content to be predicted in region
The average temperature of the i-th -1 day, determine the temperature that video content to be predicted is reached the standard grade i-th day.
The method of the prediction video content temperature of the embodiment of the present invention, in the region according to residing for video content to be predicted
The temperature of content the previous day predicts the temperature in one day future of content to be predicted, it is possible to increase precision of prediction.
In a kind of possible implementation, believed according to the temperature of the video content residing for video content to be predicted in region
The average temperature that the video content that ceasing is included residing for video content to be predicted in region is reached the standard grade the i-th -1 day, determines video to be predicted
The temperature that content is reached the standard grade i-th day, including:The temperature that video content to be predicted reaches the standard grade i-th day is determined according to below equation:
Wherein, hiThe temperature reached the standard grade for video content to be predicted i-th day,For n region residing for video content to be predicted
The average temperature that video content in j-th interior of region is reached the standard grade the i-th -1 day, ajReached the standard grade for the video content in j-th of region
The temperature weight of the i-th -1 day, n are the part or all of region in the region residing for video content to be predicted, and n is to be more than or wait
In 1 integer, j is the integer more than or equal to 1.
In a kind of possible implementation, determine that video content to be predicted is reached the standard grade i-th day according to temperature information of forecasting
Temperature, including:The temperature that video content to be predicted reaches the standard grade i-th day is determined according to below equation:
hi=b1g1+b2g2+b3g3
Wherein, hiThe temperature reached the standard grade for video content to be predicted i-th day, g1、b1、g2、b2、g3And b3It is nonnegative real number, g1
The first temperature that the video content to be predicted determined for the temperature of female collection of drama according to video content to be predicted is reached the standard grade i-th day, b1
For temperature weight corresponding with the first temperature, g2According in Electronic Program Guide EPG region residing for video content to be predicted
The second temperature that the video content to be predicted that the temperature of interior video content determines is reached the standard grade i-th day, b2To be corresponding with the second temperature
Temperature weight, g3Video content to be predicted to be determined according to the fitting temperature of video content to be predicted reach the standard grade i-th day
Three temperatures, b3For temperature weight corresponding with the 3rd temperature.
In a kind of possible implementation, this method can also include:Reached the standard grade i-th day according to video content to be predicted
Temperature and the pre- magnitude relationship pushed away between threshold value, it is determined whether pushed to the fringe node of video content distribution network CDN system
Video content to be predicted;And/or
The temperature and the pre- magnitude relationship deleted between threshold value reached the standard grade i-th day according to video content to be predicted, it is determined whether
Video content to be predicted is deleted from fringe node, wherein, threshold value is pushed away in advance is more than or equal to pre- deletion threshold value.
The method of the prediction video content temperature of the embodiment of the present invention, passes through the heat of female collection of drama of video content to be predicted
Degree, the temperature of video content in Electronic Program Guide EPG residing for video content to be predicted in region, video content to be predicted
Fitting temperature, can predict video content to be predicted reach the standard grade after the temperature of following any day, solve in the prior art with
The problem of forecasting accuracy is low when it is predicted for granularity.On the other hand, because in prediction video according to embodiments of the present invention
Hold temperature method obtain it is higher as the prediction result accuracy of granularity using day, therefore carry out video content it is pre- push away when,
Cache hit rate can be improved, and Consumer's Experience can be lifted.
Second aspect, there is provided a kind of device for predicting video content temperature, for performing first aspect or first aspect
Any possible implementation in method.Specifically, device includes being used for times for performing first aspect or first aspect
The unit of method in possible implementation of anticipating.
The third aspect, there is provided a kind of device for predicting video content temperature, the device include receiver, transmitter, place
Manage device, memory and bus system.Wherein, receiver, transmitter, processor and memory are connected by bus system, storage
Device is used for store instruction, and processor is used for the instruction for performing memory storage, to control receiver reception signal and control to send
Device sends signal.And when the instruction of computing device memory storage, perform and cause computing device first aspect or the
Method in any possible implementation of one side.
Fourth aspect, the application provide a kind of computer-readable medium, for storing computer program, the computer program
Include the instruction of the method in any possible implementation for performing first aspect or first aspect.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, it will make below to required in the embodiment of the present invention
Accompanying drawing is briefly described, it should be apparent that, drawings described below is only some embodiments of the present invention, for
For those of ordinary skill in the art, on the premise of not paying creative work, other can also be obtained according to these accompanying drawings
Accompanying drawing.
Fig. 1 is the system architecture schematic diagram of the method for prediction video content temperature according to embodiments of the present invention.
The indicative flowchart of the method for prediction video content temperature according to embodiments of the present invention Fig. 2.
The indicative flowchart of the method for Fig. 3 prediction video content temperatures according to an embodiment of the invention.
The indicative flowchart of the method for Fig. 4 prediction video content temperatures according to another embodiment of the present invention.
The indicative flowchart of the method for Fig. 5 prediction video content temperatures according to another embodiment of the present invention.
Fig. 6 is the schematic block diagram of the device of prediction video content temperature according to embodiments of the present invention.
Fig. 7 is the schematic diagram of the device of prediction video content temperature according to embodiments of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is part of the embodiment of the present invention, rather than whole embodiments.Based on this hair
Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example, belongs to the scope of protection of the invention.
Fig. 1 is the system architecture diagram of the method for the prediction video content temperature that can be applied to the embodiment of the present invention.Shown in Fig. 1
System can include CDN system 110 and video platform system 120.Wherein, CDN system 110 is responsible for the distribution of video content,
Video platform system 120 preserves video content metadata and Electronic Program Guide (Electronic Program Guide, EPG)
Etc. information.Pass through content-management interface (Content Management between CDN system 110 and video platform system 120
Interface, CMI) 15 interact.
The generally use of CDN system 110 classification deployment, for example, two level CDN system includes Centroid 111 and fringe node
112.Media push away engine 10 and are located at Centroid 111 in advance, and its media generated pushes away the caching that list is sent to fringe node 112 in advance
Management module 17, the pre- Huawei matchmaker for pushing away task and pre- deletion task, and being sent to fringe node is generated by caching management module 17
Body server (Huawei Media Server, HMS) 18 performs.The HMS 18 of fringe node can be from center when being pushed away in advance
The HMS 16 of node obtains the pre- video content pushed away in list.
Each part in the system architecture shown in Fig. 1 is simply introduced below.
Media push away engine 10 in advance:The core component that video content pushes away in advance is realized, by pushing away the related letter of trigger module 11, temperature in advance
Cease acquisition module 12, content temperature prediction module 13 and push away List Generating Module 14 in advance and form.Below to the work(of this four modules
It can be briefly described.
Trigger module 11 is pushed away in advance, task is pushed away in advance for clocked flip.
Temperature relevant information acquisition module 12, for from HMS 16, Media Entertainment Middleware (Media
Entertainment Middleware, MEM) 19, Content Management System (Content Management System, CMS) 20
Deng the related information of component retrieval temperature prediction.In order to reduce the coupling of CDN system 110 and other systems, in video platform
The part such as MEM 19, CMS 20 be required for interacting by CMI 15 when interacting with CDN system 110.
Content temperature prediction module 13, the history temperature information prediction video content for the video content according to acquisition is not
The temperature come.
Push away List Generating Module 14 in advance, for obtained according to default threshold value or study threshold value (for example, it is pre- push away threshold value and
It is pre- to delete threshold value), the prediction temperature of video content is converted into 0/1 and pushes away list in advance.
Caching management module 17, can be a module in some HMS 18, for entering to the video content on the HMS
Row management.Caching management module 17 can also dispose on stand-alone computers, to multiple HMS in a fringe node 112
Video content on 18 is managed.
HMS 18:For providing the streaming media server of Video service, available for obtain video content history temperature and
On-line time information.HMS 18 can ask to push away regarding in list in advance when execution pushes away task in advance to the HMS 16 of Centroid 111
Frequency content, when performing pre- deletion task, the video content in pre- delete list in the machine can be deleted.
CMI 15:It is CDN system 110 and interface that video platform system 120 interacts.Matchmaker in CDN system 110
Body pushes away engine 10 and wants to obtain the relevant information in video platform 120 in MEM 19 and CMS 20 in advance, it is necessary to passes through CMI 15
Interact therewith.
MEM 19:It is responsible for EPG generation and management in video platform 120, can manages and preserve video content in EPG
In positional information.
CMS 20:It is responsible for the management of video content metadata in video platform 120, can manages and preserve video content
Female episode information.
The function of each primary interface in system architecture shown in Fig. 1 is briefly discussed below.
IF1:Push away history temperature information from video content to HMS 18 and on-line time letter that engine 10 obtains in advance for media
Breath.
IF2:Push away female episode information and video content that engine 10 obtains video content to video platform 120 in advance for media
Positional information.
IF3:The positional information of video content is obtained to video platform 120 for CMI 15.
IF4:Female episode information of video content is obtained to video platform 120 for CMI 15.
IF5:Engine 10 is pushed away in advance for media by pushing away list is sent to caching management module 17 in advance.
IF6:The pre- of generation is pushed away task and pre- deletion task is sent to HMS 18 for caching management module 17.
IF7:For HMS 18 video content is obtained to HMS 16.
Below, the method that prediction video content temperature according to embodiments of the present invention will be described in detail.
Fig. 2 is the indicative flowchart of the method for the prediction video content temperature of the embodiment of the present invention.Prediction shown in Fig. 2
The method of video content temperature can be as shown in Figure 1 CDN system 110 perform.
S210, obtain the temperature information of forecasting of video content to be predicted.
Specifically, temperature information of forecasting can include the temperature, to be predicted in the epg of female collection of drama of video content to be predicted
The temperature of video content residing for video content in region, the fitting temperature of video content to be predicted.
Female collection of drama of video content to be predicted can be more early than video content on-line time to be predicted, and with video to be predicted
The related video content of content.For example, when video content to be predicted collects for the 5th of TV play A, the mother of video content to be predicted is acute
Collection can be TV play A the 1st the~the 4 collection of collection.Or video content to be predicted is when being variety show B 20160801 phase,
Female collection of drama of video content so to be predicted can be the phase before variety show B all phases video content.
Region can have one or more residing for video content to be predicted in the epg.For example, video content to be predicted is
During TV play A the 5th collection, TV play A the 5th collection has two positions in the epg, and one is homepage recommendation list, and another is
TV play A columns page 1.In region, there can be multiple video contents residing for video content to be predicted.For example, homepage is recommended
List can also have the TV play B video content such as the 2nd collection, TV play C the 3rd collection in addition to TV play A the 5th collection.For another example,
TV play A columns page 1 can also have TV play A the 1st the~the 4 collection of collection in addition to TV play A the 5th collection.
Being fitted temperature includes decay temperature and random temperature.The temperature that decays and the number of days phase of reaching the standard grade of video content to be predicted
Close, random temperature is unrelated with the number of days of reaching the standard grade of video content to be predicted.The temperature that decays is according to the upper of video content to be predicted
Line number of days and reach the standard grade what the corresponding history temperature of number of days determined with video content to be predicted, random temperature be according to decay temperature and
What history temperature corresponding with decay temperature determined.
S220, the temperature that video content to be predicted reaches the standard grade i-th day is determined according to temperature information of forecasting, i is more than or equal to 1
Integer.
It should be understood that determining the temperature that video content to be predicted reaches the standard grade i-th day according to temperature information of forecasting, refer to according to heat
Spend information of forecasting and predict the temperature of following any day of the video content to be predicted after reaching the standard grade.
In embodiments of the present invention, can be determined according to the temperature of female collection of drama of video content to be predicted in video to be predicted
Hold the temperature reached the standard grade i-th day.For example, i=5, when video content to be predicted is TV play A the 5th collection, believes being predicted according to temperature
When breath determines the temperature that video content to be predicted is reached the standard grade the 5th day, it can be reached the standard grade the 1st day according to the 1st of TV play A the~the 4 collection of collection
The temperature of~the 5 day predicts the 5th of TV play A the temperature reached the standard grade the 5th day of collection.Or can also be only according to the of TV play A
2 the~the 4 temperatures for reaching the standard grade the 1st day~the 5th day of collection of collection predict temperature that the 5th of TV play A the collection is reached the standard grade the 5th day.Or also may be used
Only to reach the standard grade the according to the 2nd of TV play A the~the 4 temperature for reaching the standard grade the 2nd day~the 5th day of collection of collection to predict the 5th of TV play A the collection
The temperature of 5 days
Furthermore it is also possible to the temperature of the video content according to residing for video content to be predicted in the epg in region, it is determined that treating
The temperature that prediction video content is reached the standard grade i-th day.Similarly, with i=5, exemplified by the 5th collection that video content to be predicted is TV play A.
Region residing for TV play A the 5th collection has two, is homepage recommendation list and TV play A columns page 1 respectively.At this point it is possible to root
The the 1st day~the 4th is reached the standard grade according to the 5th collection of the TV play A in homepage recommendation list, TV play B the 2nd collection, TV play C the 3rd collection
It temperature, and TV play A columns TV play A of page 1 the 5th collection, TV play A the 1st collection~the 4 collection reach the standard grade the 1st day~
The temperature of the 4th day predicts the 5th of TV play A the temperature reached the standard grade the 5th day of collection.Or can be only according in homepage recommendation list
TV play A the 5th collection, TV play B the 2nd collection, TV play C the 3rd temperature reached the standard grade the 2nd day~the 4th day of collection, and TV
Acute A columns TV play A of page 1 the 5th collection, TV play A the 1st the~the 4 temperature for reaching the standard grade the 2nd day~the 4th day of collection of collection are predicted
The temperature that TV play A the 5th collection is reached the standard grade the 5th day.
In addition, in the fitting temperature according to video content to be predicted, the temperature that video content to be predicted is reached the standard grade i-th day is determined
When, decay temperature can be predicted by the anticipation function f that decays (number of days of reaching the standard grade), and random temperature can pass through stochastic prediction letter
Number f (history temperature) is predicted.Decay anticipation function can pass through the history temperature to video content to be predicted and day of reaching the standard grade
Number is fitted to obtain.For example, to predict the temperature that TV play A the 5th collection is reached the standard grade the 5th day, the 5th of TV play A the can be passed through
Collect the temperature (that is, history temperature) reached the standard grade the 1st day~the 4th day and number of days of reaching the standard grade is fitted to obtain decay anticipation function.Decay prediction
Function can be fitted using decaying exponential function, can also use SVMs (Support Vector Machine,
) etc. SVM machine learning method is fitted.Random temperature is predicted by stochastic prediction function f (history temperature), random pre-
Survey function can be by predicting that the difference of temperature is fitted to obtain to video content history temperature to be predicted and decay.Random temperature
Autoregression (Auto Regressive, AR) model, autoregressive moving average (Auto Regressive Moving can be used
Average, ARMA) the stochastic prediction model such as model is fitted.The temperature that video content to be predicted is reached the standard grade i-th day can be declined
Reduction of heat degree prediction result and random temperature prediction result sum.
It should be understood that the method for the prediction video content temperature of the embodiment of the present invention, can also combine video content to be predicted
The temperature of female collection of drama, the temperature of video content in Electronic Program Guide EPG residing for video content to be predicted in region, treat
Any two in the fitting temperature three of video content, or joint three are predicted to enter to the temperature of video content to be predicted
Row prediction, the embodiment of the present invention are not construed as limiting to this.
In the prior art in the temperature after predicting that video content to be predicted is reached the standard grade according to temperature association attributes, due to temperature
The period of change of association attributes is very long (in units of the moon), thus video content to be predicted reach the standard grade after the temperature of following any day
Prediction result is essentially identical.And the method for the prediction video content temperature of the embodiment of the present invention, pass through video content to be predicted
The temperature of female collection of drama, the temperature of video content in Electronic Program Guide EPG residing for video content to be predicted in region, treat it is pre-
Survey video content fitting temperature, can predict video content to be predicted reach the standard grade after the temperature of following any day, solve show
There is the problem of forecasting accuracy is low when being predicted in technology using day as granularity.
Alternatively, the temperature of female collection of drama of video content to be predicted can include the part or all of of video content to be predicted
The temperature that female collection of drama is reached the standard grade i-th day.Now, in S220, determine that video content to be predicted reaches the standard grade i-th according to temperature information of forecasting
During it temperature, the temperature that can be reached the standard grade i-th day according to part or all of female collection of drama in female collection of drama of video content to be predicted,
Determine the temperature that video content to be predicted is reached the standard grade i-th day.
Specifically, can to predict the temperature reached the standard grade the 5th day of the 5th of video content TV play A to be predicted the collection for example
To collect the temperature reached the standard grade the 5th day according to the 1st of TV play A the collection~the 4 to predict that the 5th of TV play A the collects the heat reached the standard grade the 5th day
Degree.Or the temperature reached the standard grade the 5th day of part collection of drama concentrated according to the 1st of TV play A the collection~the 4 predicts the of TV play A
The temperature that 5 collection are reached the standard grade the 5th day.
Further, part or all of female collection of drama in female collection of drama according to video content to be predicted is reached the standard grade i-th day
Temperature, when determining the temperature that video content to be predicted is reached the standard grade i-th day, it can be determined according to formula (1) on video content to be predicted
The line temperature of i-th day:
Wherein, hiThe temperature reached the standard grade for video content to be predicted i-th day,For m female collection of dramas of video content to be predicted
In the temperatures reached the standard grade i-th day of female collection of drama j, ajThe temperature weight reached the standard grade for female collection of drama j i-th day, m of video content to be predicted
Female collection of drama is part or all of female collection of drama in female collection of drama of the video content to be predicted, and m is integer more than or equal to 1, j
For the integer more than or equal to 1.
With i=5, exemplified by m=4, if the 5th collection that video content to be predicted is TV play A, then now hiFor TV play A
The 5th temperature h that reaches the standard grade the 5th day of collection5.Also, h5The temperature that the 1st collection equal to TV play A is reached the standard grade the 5th day2nd collection is reached the standard grade
The temperature of the 5th dayThe temperature that 3rd collection is reached the standard grade the 5th dayThe temperature that 4th collection is reached the standard grade the 5th dayRespectively with a1、a2、a3、a4
The sum of products.For example, the temperature that TV play A the 1st the~the 4 collection of collection is reached the standard grade the 5th day is respectively 70,65,60,60, it is corresponding
Temperature weight is respectively 0.2,0.3,0.5,0.5.So, TV play A the 5th temperature reached the standard grade the 5th day of collection is:70*0.2+65*
0.3+60*0.3+60*0.2=63.5.
In the embodiment of the present invention, because the temperature information of forecasting used is the mother using day as the video content to be predicted of granularity
The temperature that collection of drama is reached the standard grade i-th day, to predict the i-th of video content to be predicted day temperature.Accordingly, with respect in the prior art with change
Change cycle very long temperature association attributes to predict the i-th of video content to be predicted day temperature, precision of prediction is higher.
Alternatively, the temperature of the video content residing for video content to be predicted in region can include video content to be predicted
The average temperature that video content in residing region is reached the standard grade the i-th -1 day.Now, video to be predicted is determined according to temperature information of forecasting
During the temperature that content is reached the standard grade i-th day, video content that can be according to residing for video content to be predicted in region is reached the standard grade the i-th -1 day
Average temperature, determines the temperature that video content to be predicted is reached the standard grade i-th day.
Specifically, the temperature of the video content residing for video content to be predicted in region can include in video to be predicted
The average temperature that video content residing for appearance in all or part of region is reached the standard grade the i-th -1 day.Further, video content to be predicted
The temperature of video content on location can be included on all or part of video content in this all or part of region
The line average temperature of the i-th -1 day.Here the i-th -1 day refers to i-th day the previous day.That is, it can use to be predicted
Video content residing for video content in region is reached the standard grade the average temperature of the previous day, to predict reaching the standard grade not for video content to be predicted
Carry out the temperature of one day.
To predict the temperature reached the standard grade the 5th day of the 5th of video content TV play A to be predicted the collection for example, TV play A's
Region residing for 5th collection has two, is homepage recommendation list and TV play A columns page 1 respectively.At this point it is possible to pushed away according to homepage
The average temperature that the 5th collection of the TV play A in list, TV play B the 2nd collection, TV play C the 3rd collection are reached the standard grade the 4th day is recommended, with
And the average temperature that TV play A columns TV play A of page 1 the 5th collection, TV play A the 1st the~the 4 collection of collection are reached the standard grade the 4th day is come in advance
Survey the temperature that TV play A the 5th collection is reached the standard grade the 5th day.Or the 5th collection, electricity according only to the TV play A in homepage recommendation list
Collect depending on the 2nd of acute B, the 3rd of TV play C the collects the average temperature reached the standard grade the 4th day to predict that the 5th of TV play A the collection is reached the standard grade the 5th day
Temperature.Or reached the standard grade the 4th day according only to TV play A columns TV play A of page 1 the 5th collection, TV play A the 1st the~the 4 collection of collection
Average temperature predict the 5th of TV play A the temperature reached the standard grade the 5th day of collection, the embodiment of the present invention is not construed as limiting to this.
Further, the video content according to residing for video content to be predicted in region temperature information include it is to be predicted
The average temperature that video content residing for video content in region is reached the standard grade the i-th -1 day, determine that video content to be predicted is reached the standard grade i-th day
Temperature when, the temperature that video content to be predicted is reached the standard grade i-th day can be determined according to formula (2):
Wherein, hiThe temperature reached the standard grade for video content to be predicted i-th day,For n region residing for video content to be predicted
The average temperature that video content in j-th interior of region is reached the standard grade the i-th -1 day, ajReached the standard grade for the video content in j-th of region
The temperature weight of the i-th -1 day, n be video content to be predicted residing for region in part or all of region, n be more than or equal to
1 integer, j are the integer more than or equal to 1.
To predict the temperature reached the standard grade the 5th day of the 5th of video content TV play A to be predicted the collection, n=2 is for example.Homepage
The 5th collection of TV play A in recommendation list, TV play B the 2nd collection, the 3rd of TV play C the collect the average temperature reached the standard grade the 4th day and are
50, TV play A column TV play A of page 1 the 5th collection, TV play A the 1st collection~the 4 collect the average temperature reached the standard grade the 4th day and are
70.Rule of thumb or the temperature weight reached the standard grade the 4th day of video content of homepage recommendation list that obtains of study is 0.4, TV play A
The temperature weight that the video content that column is page 1 is reached the standard grade the 4th day is 0.6.So, what the 5th of TV play A collected reaches the standard grade the 5th day
The prediction result of temperature is:50*0.4+70*0.6=62.
The method of the prediction video content temperature of the embodiment of the present invention, in the region according to residing for video content to be predicted
The temperature of content the previous day predicts the temperature in one day future of content to be predicted, it is possible to increase precision of prediction.
Alternatively, in S220, when determining the temperature that video content to be predicted is reached the standard grade i-th day according to temperature information of forecasting,
The temperature that video content to be predicted is reached the standard grade i-th day can also be determined according to formula (3):
hi(t=i)=f1(t)+f2(hist) (3)
Wherein, hi(t=i) temperature reached the standard grade i-th day for video content to be predicted, f1And f (t)2(hist) it is referred to as to be predicted
The fitting temperature of video content.Specifically, f1(t) it is referred to as the decay temperature of video content to be predicted, f2(hist) it is referred to as to be predicted
The random temperature of video content.f1(t)=a*e-λtFor exponential damping forecast model, wherein t is that video content to be predicted is reached the standard grade day
Number, a and λ are the relevant parameter of exponential decay model, and the parameter can train to obtain by prior arts such as least squares.For AR stochastic prediction models, pass through the history heat to video content to be predicted
Degree is fitted to the residual error of exponential damping forecast model prediction result can obtain related parameter, and approximating method belongs to existing
Technology, for sake of simplicity, here is omitted.
Similarly, to predict the temperature reached the standard grade the 5th day of the 5th of video content TV play A to be predicted the collection, i.e. exemplified by i=5
Illustrate.The attenuation model for being fitted to obtain by history temperature and number of days of reaching the standard grade is f1(t)=100*e-0.1*t, using true
The stochastic prediction model that history temperature and attenuation model prediction result residual error obtain is f2(hist)=0.5+0.3Xt-1+
0.2Xt-2, Xt-1And Xt-2Value be respectively 0.8 and -0.6.So, using the prediction video content temperature of the embodiment of the present invention
Method prediction TV play A the 5th collection the temperature reached the standard grade the 5th day be:
f1(5)+f2(hist)=100*e-0.1*5+ (0.5+0.3*0.8-0.2*0.6)=60.7+0.62=61.32
Alternatively, in S220, when determining the temperature that video content to be predicted is reached the standard grade i-th day according to temperature information of forecasting,
The temperature that video content to be predicted is reached the standard grade i-th day can also be determined according to formula (4):
hi=b1g1+b2g2+b3g3 (4)
Wherein, hiThe temperature reached the standard grade for video content to be predicted i-th day, g1、b1、g2、b2、g3And b3It is nonnegative real number.g1
The first temperature that the video content to be predicted determined for the temperature of female collection of drama according to video content to be predicted is reached the standard grade i-th day, b1
For temperature weight corresponding with the first temperature;g2For according to the video content residing for video content to be predicted in region in the epg
The second temperature for reaching the standard grade i-th day of video content to be predicted for determining of temperature, b2For temperature weight corresponding with the second temperature;g3
The 3rd temperature reached the standard grade i-th day for the video content to be predicted determined according to the fitting temperature of video content to be predicted, b3For with
Temperature weight corresponding to 3rd temperature.
Specifically, can by the prediction result that is obtained to the temperature of female collection of drama based on video content to be predicted, be based on
The temperature of the video content on video content location to be predicted obtains in the epg prediction result, regarded based on to be predicted
The method that the temperature prediction result that the fitting temperature of frequency content obtains is weighted predicts that video content to be predicted is reached the standard grade i-th day
Temperature.That is, by predicting video to be predicted to the method being weighted based on the first temperature, the second temperature and the 3rd temperature
The temperature that content is reached the standard grade i-th day.
As one, the first temperature can obtain according to formula (1), and the second temperature can be obtained according to formula (2)
Arrive, the 3rd temperature can obtain according to formula (3).Further, with hereinbefore for specific embodiment, the first temperature
For 63.5, the second temperature is 62, and the 3rd temperature is 61.32.Now, the 5th of the TV play A obtained according to formula (4) collects upper
The line temperature of the 5th day is:63.5*0.3+62*0.4+61.32*0.3=62.25.
It should be understood that in embodiments of the present invention, b1、b2And b3In one of them can be 0.That is, the present invention is real
Applying example can also be by the method to being weighted based on any two temperature in the first temperature, the second temperature and the 3rd temperature
To predict temperature that video content to be predicted is reached the standard grade i-th day.In other words, the embodiment of the present invention can also be according to video to be predicted
The temperature of female collection of drama of content, video content in Electronic Program Guide EPG on video content location to be predicted
Any two aspect in temperature, the fitting temperature of video content to be predicted predicts video content temperature.
Alternatively, this method can also include:The temperature reached the standard grade i-th day according to video content to be predicted pushes away between threshold value in advance
Magnitude relationship determine whether that the fringe node of video content distribution network CDN system pushes video content to be predicted;And/or
The temperature and the pre- magnitude relationship deleted between threshold value reached the standard grade i-th day according to video content to be predicted, it is determined whether
Video content to be predicted is deleted from fringe node, wherein, threshold value is pushed away in advance is more than or equal to pre- deletion threshold value.
Specifically, it is determined that after the temperature that video content to be predicted is reached the standard grade i-th day, video more to be predicted can also be passed through
The temperature and push away threshold value and the pre- magnitude relationship for deleting threshold value in advance that content is reached the standard grade i-th day, it is determined that being the fringe node to CDN system
Video content to be predicted is pushed, or video content to be predicted is deleted from fringe node, or not in the video of fringe node
Hold and carry out any operation.
For example, it can be 63 to push away threshold value in advance, and pre- threshold value of deleting can be 62, if video content to be predicted reaches the standard grade the
The temperature of i days is 63.5, then can push video content to be predicted to the fringe node of CDN system;If video to be predicted
The temperature that content is reached the standard grade i-th day is 61.5, then can delete video content to be predicted from fringe node;If video to be predicted
The temperature that content is reached the standard grade i-th day is 62.5, then does not make any processing to the video content stored in fringe node.
Therefore, the method for the prediction video content temperature of the embodiment of the present invention, passes through female collection of drama of video content to be predicted
Temperature, the temperature of video content in Electronic Program Guide EPG residing for video content to be predicted in region, video to be predicted
The fitting temperature of content, can predict video content to be predicted reach the standard grade after the temperature of following any day, solve prior art
In the problem of forecasting accuracy is low when being predicted using day as granularity.On the other hand, because prediction according to embodiments of the present invention regards
The method of frequency content temperature obtains higher as the prediction result accuracy of granularity using day, therefore is pushed away carrying out the pre- of video content
When, it is possible to increase cache hit rate, and Consumer's Experience can be lifted.
With reference to the system architecture shown in Fig. 1, to the method for prediction video content temperature according to embodiments of the present invention
It is described in detail.System architecture with reference to shown in Fig. 1, the prediction video content temperature according to embodiments of the present invention shown
The indicative flowchart of method can be found in Fig. 3 to Fig. 5.
It should be understood that the CND systems shown in Fig. 3 to Fig. 5 can be the CDN system 110 shown in Fig. 1, video platform system can
To be the video platform 120 shown in Fig. 1.Each module in CND systems and video platform system shown in Fig. 3 to Fig. 5 can phase
Answer each module in the corresponding CDN system 110 and video platform 120 with shown in Fig. 1 in ground.It should be noted that Fig. 3 to Fig. 5 institutes
HMS in the CND systems shown can be corresponded to and the HMS 16 shown in Fig. 1.
It is the schematic flow for the method according to an embodiment of the invention for predicting video content temperature that Fig. 3, which shows,
Figure.Fig. 3 has shown that temperature of the shown method based on female collection of drama according to video content to be predicted predicts video to be predicted
The method of content future temperature.
301, trigger module is pushed away in advance sends triggering information to temperature relevant information acquisition module.Triggering information can be used for touching
Heating degree relevant information acquisition module obtain video content to be predicted female collection of drama mark (Identification, ID) information and
History temperature information.
In the embodiment of the present invention, history temperature information can be the temperature of female collection of drama of content to be measured.Specifically, history heat
Degree information can be the temperature of the corresponding number of days of reaching the standard grade of all female collection of dramas of video content to be predicted, can also be video to be predicted
Part mother's collection of drama of content is accordingly reached the standard grade the temperature of number of days.
302, temperature relevant information acquisition module sends the first request message to CMI.
First request message can include the id information of video content to be predicted, please for the CMS to video platform system
Seek female collection of drama id information.
Here, temperature relevant information acquisition module can use Simple Object Access Protocol (Simple Object
Access Protocol, SOAP) to CMI the first request messages of transmission, but the embodiment of the present invention is not construed as limiting to this.
303, CMI send the first request message to CMS.
Specifically, temperature relevant information acquisition module can ask video content to be predicted by CMI to video platform
Female collection of drama id information.When CMI receives the first request message for asking female collection of drama id information, CMI forward this first please
Seek message.
Here, CMI can use SOAP to send the first request message to CMS.
304, CMS send female collection of drama id information to CMI.
Specifically, CMS can return to female collection of drama id information according to the first request message received to CMI.
Here, CMS can send female collection of drama id information using SOAP to CMI.
305, CMI send female collection of drama id information to temperature relevant information acquisition module.
By CMI forwarding, female collection of drama id information that temperature relevant information acquisition module can be asked.
Here, CMI can use SOAP to send female collection of drama id information to temperature relevant information acquisition module.
306, temperature relevant information acquisition module sends the second request message to HMS.Second request message can be used for please
Seek history temperature information.
Specifically, the second request message can carry female collection of drama id information that temperature relevant information acquisition module is got.
So, HMS can obtain according to female collection of drama id information it is determined that after female collection of drama of video content to be predicted to temperature relevant information
Module returns to the temperature of female collection of drama of its video content to be predicted asked.
An agency (Agent) can be set to count video content from HMS daily records in the embodiment of the present invention, in HMS
History temperature information.The statistical information that the agency counts to obtain can include female collection of drama ID and female correspondingly with female collection of drama ID
The history temperature of collection of drama.
307, HMS send history temperature information to temperature relevant information acquisition module.
History temperature information is the response message to the second request message in 306.Here, HMS can use SOAP to
Temperature relevant information acquisition module sends history temperature information.
308, temperature relevant information acquisition module sends female collection of drama id information and history temperature to content temperature prediction module
Information.
309, content temperature prediction module is true according to the temperature of female collection of drama id information and female collection of drama of video content to be predicted
Fixed video content temperature to be predicted.
Specifically, content temperature prediction module can be according to female collection of drama of female collection of drama id information and video content to be predicted
Temperature predicts video content future temperature to be predicted, i.e., video content to be predicted is reached the standard grade following some day the temperature of (i-th day).Example
Such as, the temperature that the 5th collection of formula (1) prediction TV play A above can be used to reach the standard grade the 5th day.
310, temperature prediction result is sent to and pre- pushes away List Generating Module by content temperature prediction module.
311, push away in advance List Generating Module according to prediction result, it is pre- push away threshold value and delete threshold value in advance, generation is pre- push away list and
Pre- delete list.
For example, the temperature that the TV play A predicted using formula (1) above the 1st the~the 4 collection of collection is reached the standard grade the 6th day
Respectively 60,66,64,63.When the pre- threshold value that pushes away rule of thumb obtained is 60, when pre- deletion threshold value is 50, the pre- of generation pushes away row
Table and pre- delete list are following (wherein 1 represents to push away in advance, and 0, which represents pre-, deletes):
dianshijuA01 1
dianshijuA 02 1
dianshijuA 03 0
dianshijuA 04 0
312, push away that List Generating Module pre- will push away list and pre- delete list is sent to caching management module in advance.
313, caching management module generation pushes away task and pre- deletion task in advance.
Specifically, the video content that has been stored in HMS of the caching management module according to fringe node and it is pre- push away list and
Video content in pre- delete list, it is determined that finally pre- pushes away task and pre- deletion task.If protected in the HMS of fringe node
There is the pre- video content pushed away in list, then will not generate the pre- of the video content and push away task;If in the HMS of fringe node not
The pre- video content pushed away in list is preserved, the pre- of the video content can be generated and push away task.
For example caching management module pushes away list and pre- delete list according to pre- in step 311, generation it is pre- push away task and
Pre- deletion task is respectively:
wget http://www.example.com/dianshijuA 01.mp4
wget http://www.example.com/dianshijuA 02.mp4
rm-rf/var/videos/dianshijuA 03.mp4
rm-rf/var/videos/dianshijuA 04.mp4
314, caching management module sends to HMS and pushes away task and pre- deletion task in advance.
315, HMS execution push away task and pre- deletion task in advance.
Specifically, the HMS of fringe node deletes the video content in pre- deletion task;Obtained from the HMS of Centroid
The pre- video content for pushing away task.The HMS of fringe node deletes TV play A the 3rd collection and the video content of the 4th collection, and from center
The HMS of node obtains TV play A the 1st collection and the video content of the 2nd collection.
The method of the prediction video content temperature of the embodiment of the present invention, passes through the temperature of female collection of drama of video content to be predicted
Can predict video content to be predicted reach the standard grade after the temperature of following any day, solve in the prior art using day as granularity carry out
The problem of forecasting accuracy is low during prediction.On the other hand, because of the method for prediction video content temperature according to embodiments of the present invention
What is obtained is higher as the prediction result accuracy of granularity using day, thus carry out video content it is pre- push away when, it is possible to increase caching
Hit rate, and Consumer's Experience can be lifted.
Fig. 4 is the indicative flowchart of the method for prediction video content temperature according to another embodiment of the present invention.Fig. 4 shows
Gone out the temperature of the video content according to residing for the video content to be predicted in Electronic Program Guide EPG in region predict treat it is pre-
The method for surveying video content future temperature.
401, trigger module is pushed away in advance sends triggering information to temperature relevant information acquisition module.Triggering information can be used for touching
Heating degree relevant information acquisition module obtains video content positional information of the video content to be predicted in Electronic Program Guide EPG
With history temperature information.
In the embodiment of the present invention, video content positional information can include video content to be predicted in Electronic Program Guide
Residing region in EPG, and the id information of all video contents in the region.Video content positional information can be with
Including to respective regions corresponding to corresponding number of days of reaching the standard grade temperature weight.History temperature information can be that prediction video content exists
Video content in EPG in residing all regions is accordingly reached the standard grade the temperature of number of days, or can also be that prediction video content exists
Video content in EPG in the region of residing part is accordingly reached the standard grade the temperature of number of days.
402, temperature relevant information acquisition module sends the first request message to CMI.
First request message can include the id information of video content to be predicted, please for the CMS to video platform system
Seek the video content positional information.
Here, temperature relevant information acquisition module can use SOAP to send the first request message to CMI, but the present invention is real
Example is applied to be not construed as limiting this.
403, CMI send the first request message to MEM.
Specifically, temperature relevant information acquisition module can ask video content positional information by CMI to video platform.
When CMI receives the first request message for asking video content positional information, CMI forwards first request message.This
In, CMI can use SOAP to send the first request message to MEM.
404, MEM send video content positional information to CMI.
Specifically, MEM can return to video content positional information according to the first request message received to CMI.
Here, MEM can send the video content positional information using SOAP to CMI.
405, CMI send video content positional information to temperature relevant information acquisition module.
By CMI forwarding, video content positional information that temperature relevant information acquisition module can be asked.This
In, CMI can use SOAP to send video content positional information to temperature relevant information acquisition module.
406, temperature relevant information acquisition module sends the second request message to HMS.Second request message can be used for please
Seek history temperature information.
Specifically, the second request message can carry the video content position letter that temperature relevant information acquisition module is got
Breath.So, HMS can according to the id information in video content positional information it is determined that after video content corresponding with the ID, to
The video content that temperature relevant information acquisition module returns to residing for the video content to be predicted that it is asked in region is accordingly reached the standard grade
The temperature of number of days.
An agency (Agent) can be set to count video content from HMS daily records in the embodiment of the present invention, in HMS
History temperature information.The statistical information that the agency counts to obtain can include video content ID and be corresponded with video content ID
Video content history temperature.
407, HMS send video content positional information and history temperature information to temperature relevant information acquisition module.
History temperature information is the response message to the second request message in 406.Here, HMS can use SOAP to
Temperature relevant information acquisition module sends video content positional information and history temperature information.
408, temperature relevant information acquisition module sends video content positional information and history to content temperature prediction module
Temperature information.
409, content temperature prediction module determines video to be predicted according to video content positional information and history temperature information
The temperature of content.
Specifically, content temperature prediction module can be according to residing for video content positional information and video content to be predicted
The temperature of video content in region predicts video content future temperature to be predicted, i.e., video content to be predicted is reached the standard grade following a certain
My god (i-th day) temperature.It is for instance possible to use the heat that the 5th collection of formula (2) prediction TV play A above is reached the standard grade the 5th day
Degree.
410, temperature prediction result is sent to and pre- pushes away List Generating Module by content temperature prediction module.
411, push away in advance List Generating Module according to prediction result, it is pre- push away threshold value and delete threshold value in advance, generation is pre- push away list and
Pre- delete list.
For example, the temperature that the TV play A predicted using formula (2) above the 1st the~the 4 collection of collection is reached the standard grade the 6th day
Respectively 60,66,64,63.When the pre- threshold value that pushes away rule of thumb obtained is 60, when pre- deletion threshold value is 50, the pre- of generation pushes away row
Table and pre- delete list are following (wherein 1 represents to push away in advance, and 0, which represents pre-, deletes):
dianshijuA01 1
dianshijuA 02 1
dianshijuA 03 0
dianshijuA 04 0
412, push away that List Generating Module pre- will push away list and pre- delete list is sent to caching management module in advance.
413, caching management module generation pushes away task and pre- deletion task in advance.
Specifically, the video content that has been stored in HMS of the caching management module according to fringe node and it is pre- push away list and
Video content in pre- delete list, it is determined that finally pre- pushes away task and pre- deletion task.If protected in the HMS of fringe node
There is the pre- video content pushed away in list, then will not generate the pre- of the video content and push away task;If in the HMS of fringe node not
The pre- video content pushed away in list is preserved, the pre- of the video content can be generated and push away task.
For example caching management module pushes away list and pre- delete list according to pre- in step 411, generation it is pre- push away task and
Pre- deletion task is respectively:
wget http://www.example.com/dianshijuA 01.mp4
wget http://www.example.com/dianshijuA 02.mp4
rm-rf/var/videos/dianshijuA 03.mp4
rm-rf/var/videos/dianshijuA 04.mp4
414, caching management module sends to HMS and pushes away task and pre- deletion task in advance.
415, HMS execution push away task and pre- deletion task in advance.
Specifically, the HMS of fringe node deletes the video content in pre- deletion task, is obtained from the HMS of Centroid
The pre- video content for pushing away task.For example the HMS of fringe node deletes TV play A the 3rd collection and the video content of the 4th collection, and
TV play A the 1st collection and the video content of the 2nd collection are obtained from the HMS of Centroid.
Therefore, the method for the prediction video content temperature of the embodiment of the present invention, it is pre- by being treated in Electronic Program Guide EPG
Survey the temperature of the video content residing for video content in region, can predict video content to be predicted reach the standard grade after following any day
Temperature, forecasting accuracy is low when solving the problems, such as to be predicted as granularity using day in the prior art.On the other hand, because of basis
The method of the prediction video content temperature of the embodiment of the present invention obtains higher as the prediction result accuracy of granularity using day, therefore
Carry out video content it is pre- push away when, it is possible to increase cache hit rate, and Consumer's Experience can be lifted.
It is schematic stream according to the method for the prediction video content temperature of one another embodiment of the present invention that Fig. 5, which is shown,
Cheng Tu.Method shown in Fig. 5 predicts video content to be predicted based on the fitting temperature according to video content to be predicted is shown
The method of following temperature.
501, trigger module is pushed away in advance sends triggering information to temperature relevant information acquisition module.Triggering information can be used for touching
Heating degree relevant information acquisition module obtains history temperature information and the number of days information of reaching the standard grade of video content to be predicted.Going through here
History temperature information can be used for obtaining decay temperature and random temperature.
502, temperature relevant information acquisition module sends request message to HMS.Request message can include video to be predicted
The id information of content, for asking the number of days information of reaching the standard grade of history temperature information and video content to be predicted.
503, HMS send the day of reaching the standard grade of history temperature information and video content to be predicted to temperature relevant information acquisition module
Number information
504, temperature relevant information acquisition module sends history temperature information to content temperature prediction module and to be predicted regarded
The number of days information of reaching the standard grade of frequency content
505, content temperature prediction module is true according to the number of days information of reaching the standard grade of history temperature information and video content to be predicted
Fixed video content temperature to be predicted.
Specifically, content temperature prediction module can be according to history temperature information and the number of days of reaching the standard grade of video content to be predicted
Information determines fitting temperature, and video content future temperature to be predicted is predicted according to fitting temperature, i.e., on video content to be predicted
The temperature of line some day in future (i-th day).It is for instance possible to use the 5th collection of formula (3) prediction TV play A above is reached the standard grade
The temperature of the 5th day.
506, content temperature prediction module sends temperature prediction result to pushing away List Generating Module in advance.
507, push away in advance List Generating Module according to prediction result, it is pre- push away threshold value and delete threshold value in advance, generation is pre- push away list and
Pre- delete list.
For example, the temperature that the TV play A predicted using formula (2) above the 1st the~the 4 collection of collection is reached the standard grade the 6th day
Respectively 60,66,64,63.When the pre- threshold value that pushes away rule of thumb obtained is 60, when pre- deletion threshold value is 50, the pre- of generation pushes away row
Table and pre- delete list are following (wherein 1 represents to push away in advance, and 0, which represents pre-, deletes):
dianshijuA01 1
dianshijuA 02 1
dianshijuA 03 0
dianshijuA 04 0
508, push away that List Generating Module pre- will push away list and pre- delete list is sent to caching management module in advance.
509, caching management module generation pushes away task and pre- deletion task in advance.
Specifically, the video content that has been stored in HMS of the caching management module according to fringe node and it is pre- push away list and
Video content in pre- delete list, it is determined that finally pre- pushes away task and pre- deletion task.If protected in the HMS of fringe node
There is the pre- video content pushed away in list, then will not generate the pre- of the video content and push away task;If in the HMS of fringe node not
The pre- video content pushed away in list is preserved, the pre- of the video content can be generated and push away task.
For example caching management module pushes away list and pre- delete list according to pre- in step 507, generation it is pre- push away task and
Pre- deletion task is respectively:
wget http://www.example.com/dianshijuA 01.mp4
wget http://www.example.com/dianshijuA 02.mp4
rm-rf/var/videos/dianshijuA 03.mp4
rm-rf/var/videos/dianshijuA04.mp4
510, caching management module sends to HMS and pushes away task and pre- deletion task in advance.
511, HMS execution push away task and pre- deletion task in advance.
Specifically, the HMS of fringe node deletes the video content in pre- deletion task, is obtained from the HMS of Centroid
The pre- video content for pushing away task.The HMS of fringe node deletes TV play A the 3rd collection and the video content of the 4th collection, and from center
The HMS of node obtains TV play A the 1st collection and the video content of the 2nd collection.
Therefore, the method for the prediction video content temperature of the embodiment of the present invention, the fitting heat of video content to be predicted is passed through
Degree, can predict video content to be predicted reach the standard grade after the temperature of following any day, solve in the prior art using day as granularity
The problem of forecasting accuracy is low when being predicted.On the other hand, because of prediction video content temperature according to embodiments of the present invention
Method obtains higher as the prediction result accuracy of granularity using day, thus carry out video content it is pre- push away when, it is possible to increase
Cache hit rate, and Consumer's Experience can be lifted.
Above in conjunction with Fig. 2 to Fig. 5, the method for prediction video content temperature according to embodiments of the present invention has been carried out in detail
Describe in detail bright.Hereinafter, with reference to Fig. 6 and Fig. 7, the device of prediction video content temperature according to embodiments of the present invention is illustrated.
Fig. 6 shows the schematic block diagram of the device 600 of prediction video content temperature according to embodiments of the present invention.Such as figure
Shown in 3, the device 600 includes:Acquiring unit 610 and determining unit 620.
Acquiring unit 610, for obtaining the temperature information of forecasting of video content to be predicted, the temperature information of forecasting includes
At least one of below:The temperature of female collection of drama of the video content to be predicted, treat described in Electronic Program Guide EPG it is pre-
Temperature, the fitting temperature of the video content to be predicted of the video content residing for video content in region are surveyed,
Wherein, the fitting temperature includes decay temperature and random temperature, and the decay temperature is according to described to be predicted
Reaching the standard grade for video content and reaches the standard grade what the corresponding history temperature of number of days determined at number of days with the video content to be predicted, described random
Temperature is to be determined according to the decay temperature and history temperature corresponding with the decay temperature.
Determining unit 620, the temperature information of forecasting for being obtained according to the acquiring unit determine described to be predicted
The temperature that video content is reached the standard grade i-th day, i are the integer more than or equal to 1.
The each unit of device 600 according to embodiments of the present invention and above-mentioned other operations or function are above-mentioned in order to realize respectively
The corresponding flow that method is performed by CDN system.For sake of simplicity, here is omitted.
The device of the prediction video content temperature of the embodiment of the present invention, passes through the heat of female collection of drama of video content to be predicted
Degree, the temperature of video content in Electronic Program Guide EPG residing for video content to be predicted in region, video content to be predicted
Fitting temperature, can predict video content to be predicted reach the standard grade after the temperature of following any day, solve in the prior art with
The problem of forecasting accuracy is low when it is predicted for granularity.On the other hand, because in prediction video according to embodiments of the present invention
Hold temperature device obtain it is higher as the prediction result accuracy of granularity using day, therefore carry out video content it is pre- push away when,
Cache hit rate can be improved, and Consumer's Experience can be lifted.
Fig. 7 is the schematic diagram of the device 700 of prediction video content temperature according to embodiments of the present invention.Such as Fig. 7
Shown, the device 700 includes:Receiver 710, transmitter 720, processor 730, memory 740 and bus system 750.Wherein,
Receiver 710, transmitter 720, processor 730 and memory 740 are connected by bus system 750, and the memory 740 is used to deposit
Storage instruction, the processor 730 are used for the instruction for performing the memory 740 storage, to control the reception signal of receiver 710, and controlled
Transmitter 720 processed sends signal.
Processor 730, for obtaining the temperature information of forecasting of video content to be predicted, the temperature information of forecasting include with
It is at least one of lower:It is the temperature of female collection of drama of the video content to be predicted, to be predicted described in Electronic Program Guide EPG
The fitting temperature of the temperature of video content residing for video content in region, the video content to be predicted.Wherein, the fitting
Temperature includes decay temperature and random temperature, the decay temperature be according to the video content to be predicted reach the standard grade number of days and with
The video content to be predicted reaches the standard grade what history temperature corresponding to number of days determined, and the random temperature is according to the decay temperature
Corresponding history temperature determines with the decay temperature.
Processor 730 is additionally operable to, and the temperature information of forecasting obtained according to the acquiring unit determines described to be predicted
The temperature that video content is reached the standard grade i-th day, i are the integer more than or equal to 1.
It should be understood that in embodiments of the present invention, the processor 730 can be CPU (central
Processing unit, referred to as " CPU "), the processor 730 can also be other general processors, digital signal processor
(DSP), application specific integrated circuit (ASIC), ready-made programmable gate array (FPGA) or other PLDs, discrete gate
Or transistor logic, discrete hardware components etc..General processor can be that microprocessor or the processor can also
It is any conventional processor etc..
The memory 740 can include read-only storage and random access memory, and to processor 730 provide instruction and
Data.The a part of of memory 740 can also include nonvolatile RAM.For example, memory 740 can also be deposited
Store up the information of device type.
The bus system 750 can also include power bus, controlling bus and status signal in addition to including data/address bus
Bus etc..But for the sake of clear explanation, various buses are all designated as bus system 750 in figure.
In implementation process, each step of the above method can pass through the integrated logic circuit of the hardware in processor 730
Or the instruction of software form is completed.With reference to the prediction video content temperature of the embodiment of the present invention method the step of can be direct
It is presented as that hardware processor performs completion, or completion is performed with the hardware in processor and software module combination.Software module
It can be located at random access memory, flash memory, read-only storage, programmable read only memory or electrically erasable programmable memory,
In the ripe storage medium in this areas such as register.The storage medium is located at memory 740, and processor 730 reads memory 740
In information, with reference to its hardware complete the above method the step of.To avoid repeating, it is not detailed herein.
Device 700 according to embodiments of the present invention and above-mentioned other operations or function respectively in order to perform in the above method by
The corresponding flow that CND systems perform.For sake of simplicity, here is omitted.
The device of the prediction video content temperature of the embodiment of the present invention, passes through the heat of female collection of drama of video content to be predicted
Degree, the temperature of video content in Electronic Program Guide EPG residing for video content to be predicted in region, in video to be predicted
The fitting temperature of appearance, can predict video content to be predicted reach the standard grade after the temperature of following any day, solve in the prior art
The problem of forecasting accuracy is low when being predicted using day as granularity.On the other hand, because of prediction video according to embodiments of the present invention
The device of content temperature obtains higher as the prediction result accuracy of granularity using day, therefore is pushed away carrying out the pre- of video content
When, it is possible to increase cache hit rate, and Consumer's Experience can be lifted.
It should be understood that the terms "and/or", only a kind of incidence relation for describing affiliated partner, expression can deposit
In three kinds of relations, for example, A and/or B, can be represented:Individualism A, while A and B be present, these three situations of individualism B.
In addition, character "/" herein, it is a kind of relation of "or" to typically represent forward-backward correlation object.
It should be understood that in various embodiments of the present invention, the size of the sequence number of above-mentioned each process is not meant to perform suitable
The priority of sequence, the execution sequence of each process should be determined with its function and internal logic, without the implementation of the reply embodiment of the present invention
Process forms any restriction.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Member and algorithm steps, it can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, application-specific and design constraint depending on technical scheme.Professional and technical personnel
Described function can be realized using distinct methods to each specific application, but this realization is it is not considered that exceed
The scope of the present invention.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, the corresponding process in preceding method embodiment is may be referred to, will not be repeated here.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, can be with
Realize by another way.For example, device embodiment described above is only schematical, for example, the unit
Division, only a kind of division of logic function, can there is other dividing mode, such as multiple units or component when actually realizing
Another system can be combined or be desirably integrated into, or some features can be ignored, or do not perform.It is another, it is shown or
The mutual coupling discussed or direct-coupling or communication connection can be the indirect couplings by some interfaces, device or unit
Close or communicate to connect, can be electrical, mechanical or other forms.
The unit illustrated as separating component can be or may not be physically separate, show as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.
If the function is realized in the form of SFU software functional unit and is used as independent production marketing or in use, can be with
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words
The part to be contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter
Calculation machine software product is stored in a storage medium, including some instructions are causing a computer equipment (can be
People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the present invention.
And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (14)
- A kind of 1. method for predicting video content temperature, it is characterised in that including:The temperature information of forecasting of video content to be predicted is obtained, the temperature information of forecasting includes at least one of following:Institute State the temperature of female collection of drama of video content to be predicted, the region residing for video content to be predicted described in Electronic Program Guide EPG The fitting temperature of the temperature of interior video content, the video content to be predicted,Wherein, the fitting temperature includes decay temperature and random temperature, and the decay temperature is according to the video to be predicted Reaching the standard grade for content and reaches the standard grade what the corresponding history temperature of number of days determined at number of days with the video content to be predicted, the random temperature For what is determined according to the decay temperature and history temperature corresponding with the decay temperature;The temperature that the video content to be predicted reaches the standard grade i-th day is determined according to the temperature information of forecasting, i is more than or equal to 1 Integer.
- 2. the method as described in claim 1, it is characterised in that the temperature of female collection of drama of the video content to be predicted includes institute The temperature that part or all of female collection of drama of video content to be predicted is reached the standard grade i-th day is stated,The temperature for determining that the video content to be predicted reaches the standard grade i-th day according to the temperature information of forecasting, including:The temperature that part or all of female collection of drama in female collection of drama of the video content to be predicted is reached the standard grade i-th day, determines institute State the temperature that video content to be predicted is reached the standard grade i-th day.
- 3. method as claimed in claim 2, it is characterised in that in female collection of drama according to the video content to be predicted The temperature that part or all of female collection of drama is reached the standard grade i-th day, determines the temperature that the video content to be predicted is reached the standard grade i-th day, including:The temperature that the video content to be predicted reaches the standard grade i-th day is determined according to below equation:<mrow> <msub> <mi>h</mi> <mi>i</mi> </msub> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>m</mi> </munderover> <msub> <mi>a</mi> <mi>j</mi> </msub> <msubsup> <mi>h</mi> <mi>j</mi> <mi>i</mi> </msubsup> </mrow>Wherein, hiThe temperature reached the standard grade i-th day for the video content to be predicted,M for the video content to be predicted is female The temperature that female collection of drama j in collection of drama reaches the standard grade i-th day, ajThe temperature weight reached the standard grade i-th day for female collection of drama j, it is described to be predicted The m of video content female collection of dramas are part or all of female collection of drama in female collection of drama of the video content to be predicted, m to be more than or Integer equal to 1, j are the integer more than or equal to 1.
- 4. the method as described in claim 1, it is characterised in that in the video in region residing for the video content to be predicted The temperature of appearance includes the average temperature that the video content residing for the video content to be predicted in region is reached the standard grade the i-th -1 day,The temperature for determining that the video content to be predicted reaches the standard grade i-th day according to the temperature information of forecasting, including:The average temperature reached the standard grade according to the video content residing for the video content to be predicted in region the i-th -1 day, it is determined that described The temperature that video content to be predicted is reached the standard grade i-th day.
- 5. method as claimed in claim 4, it is characterised in that described according to residing for the video content to be predicted in region The temperature information of video content, which includes video content residing for the video content to be predicted in region, reaches the standard grade the i-th -1 day and is averaged Temperature, the temperature that the video content to be predicted is reached the standard grade i-th day is determined, including:The temperature that the video content to be predicted reaches the standard grade i-th day is determined according to below equation:<mrow> <msub> <mi>h</mi> <mi>i</mi> </msub> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>a</mi> <mi>j</mi> </msub> <msubsup> <mi>h</mi> <mi>j</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msubsup> </mrow>Wherein, the hiThe temperature reached the standard grade i-th day for the video content to be predicted,For residing for the video content to be predicted The average temperature that the video content in j-th of region in n region is reached the standard grade the i-th -1 day, ajFor regarding in j-th of region The temperature weight that frequency content is reached the standard grade the i-th -1 day, n are the part or all of area in the region residing for the video content to be predicted Domain, n are the integer more than or equal to 1, and j is the integer more than or equal to 1.
- 6. the method as described in claim 1, it is characterised in that it is described determined according to the temperature information of forecasting it is described to be predicted The temperature that video content is reached the standard grade i-th day, including:The temperature that the video content to be predicted reaches the standard grade i-th day is determined according to below equation:hi=b1g1+b2g2+b3g3Wherein, the hiThe temperature reached the standard grade i-th day for the video content to be predicted, g1、b1、g2、b2、g3And b3It is non-negative reality Number,g1The video content to be predicted determined for the temperature of female collection of drama according to the video content to be predicted is reached the standard grade i-th day The first temperature, b1For temperature weight corresponding with first temperature,g2According to video content described in Electronic Program Guide EPG residing for video content to be predicted in region temperature it is true The second temperature that the fixed video content to be predicted is reached the standard grade i-th day, b2For temperature weight corresponding with second temperature,g3The video content to be predicted to be determined according to the fitting temperature of the video content to be predicted reach the standard grade i-th day Three temperatures, b3For temperature weight corresponding with the 3rd temperature.
- 7. the method as any one of claim 1 to 6, it is characterised in that methods described also includes:The temperature and the pre- magnitude relationship pushed away between threshold value reached the standard grade i-th day according to the video content to be predicted, it is determined whether to The fringe node of video content distribution network CDN system pushes the video content to be predicted;And/orThe temperature and the pre- magnitude relationship deleted between threshold value reached the standard grade i-th day according to the video content to be predicted, it is determined whether The video content to be predicted is deleted from the fringe node, wherein, the pre- threshold value that pushes away is more than or equal to the pre- deletion threshold Value.
- A kind of 8. device for predicting video content temperature, it is characterised in that including:Acquiring unit, for obtaining the temperature information of forecasting of video content to be predicted, the temperature information of forecasting include it is following in At least one:The temperature of female collection of drama of the video content to be predicted, the video to be predicted described in Electronic Program Guide EPG The fitting temperature of the temperature of video content residing for content in region, the video content to be predicted,Wherein, the fitting temperature includes decay temperature and random temperature, and the decay temperature is according to the video to be predicted Reaching the standard grade for content and reaches the standard grade what the corresponding history temperature of number of days determined at number of days with the video content to be predicted, the random temperature For what is determined according to the decay temperature and history temperature corresponding with the decay temperature;Determining unit, the temperature information of forecasting for being obtained according to the acquiring unit determine the video content to be predicted The temperature reached the standard grade i-th day, i are the integer more than or equal to 1.
- 9. device as claimed in claim 8, it is characterised in that the temperature of female collection of drama of the video content to be predicted includes institute The temperature that part or all of female collection of drama of video content to be predicted is reached the standard grade i-th day is stated,The determining unit is specifically used for:The temperature that part or all of female collection of drama in female collection of drama of the video content to be predicted is reached the standard grade i-th day, determines institute State the temperature that video content to be predicted is reached the standard grade i-th day.
- 10. device as claimed in claim 9, it is characterised in that the determining unit is specifically used for:The temperature that the video content to be predicted reaches the standard grade i-th day is determined according to below equation:<mrow> <msub> <mi>h</mi> <mi>i</mi> </msub> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>m</mi> </munderover> <msub> <mi>a</mi> <mi>j</mi> </msub> <msubsup> <mi>h</mi> <mi>j</mi> <mi>i</mi> </msubsup> </mrow>Wherein, hiThe temperature reached the standard grade i-th day for the video content to be predicted,M for the video content to be predicted is female acute The temperature that female collection of drama j of concentration reaches the standard grade i-th day, ajThe temperature weight reached the standard grade i-th day for female collection of drama j, it is described to be predicted to regard M female collection of dramas of frequency content are part or all of female collection of drama in female collection of drama of the video content to be predicted, and m is to be more than or wait In 1 integer, j is the integer more than or equal to 1.
- 11. device as claimed in claim 8, it is characterised in that the video in region residing for the video content to be predicted The temperature of content includes the average temperature that the video content residing for the video content to be predicted in region is reached the standard grade the i-th -1 day,The determining unit is specifically used for:The average temperature reached the standard grade according to the video content residing for the video content to be predicted in region the i-th -1 day, it is determined that described The temperature that video content to be predicted is reached the standard grade i-th day.
- 12. device as claimed in claim 11, it is characterised in that the determining unit is specifically used for:The temperature that the video content to be predicted reaches the standard grade i-th day is determined according to below equation:<mrow> <msub> <mi>h</mi> <mi>i</mi> </msub> <mo>=</mo> <munderover> <mo>&Sigma;</mo> <mrow> <mi>j</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>a</mi> <mi>j</mi> </msub> <msubsup> <mi>h</mi> <mi>j</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> </msubsup> </mrow>Wherein, the hiThe temperature reached the standard grade i-th day for the video content to be predicted,For residing for the video content to be predicted The average temperature that the video content in j-th of region in n region is reached the standard grade the i-th -1 day, ajFor regarding in j-th of region The temperature weight that frequency content is reached the standard grade the i-th -1 day, n are the part or all of area in the region residing for the video content to be predicted Domain, n are the integer more than or equal to 1, and j is the integer more than or equal to 1.
- 13. device as claimed in claim 8, it is characterised in that the determining unit is specifically used for:The temperature that the video content to be predicted reaches the standard grade i-th day is determined according to below equation:hi=b1g1+b2g2+b3g3Wherein, the hiThe temperature reached the standard grade i-th day for the video content to be predicted, g1、b1、g2、b2、g3And b3It is non-negative reality Number,g1The video content to be predicted determined for the temperature of female collection of drama according to the video content to be predicted is reached the standard grade i-th day The first temperature, b1For temperature weight corresponding with first temperature,g2According to video content described in Electronic Program Guide EPG residing for video content to be predicted in region temperature it is true The second temperature that the fixed video content to be predicted is reached the standard grade i-th day, b2For temperature weight corresponding with second temperature,g3The video content to be predicted to be determined according to the fitting temperature of the video content to be predicted reach the standard grade i-th day Three temperatures, b3For temperature weight corresponding with the 3rd temperature.
- 14. the device as any one of claim 8 to 13, it is characterised in that the determining unit is additionally operable to:The temperature and the pre- magnitude relationship pushed away between threshold value reached the standard grade i-th day according to the video content to be predicted, it is determined whether to The fringe node of video content distribution network CDN system pushes the video content to be predicted;And/orThe temperature and the pre- magnitude relationship deleted between threshold value reached the standard grade i-th day according to the video content to be predicted, it is determined whether The video content to be predicted is deleted from the fringe node, wherein, the pre- threshold value that pushes away is more than or equal to the pre- deletion threshold Value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610644027.3A CN107707964A (en) | 2016-08-08 | 2016-08-08 | The method and apparatus for predicting video content temperature |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610644027.3A CN107707964A (en) | 2016-08-08 | 2016-08-08 | The method and apparatus for predicting video content temperature |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107707964A true CN107707964A (en) | 2018-02-16 |
Family
ID=61168653
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610644027.3A Pending CN107707964A (en) | 2016-08-08 | 2016-08-08 | The method and apparatus for predicting video content temperature |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107707964A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108769730A (en) * | 2018-05-21 | 2018-11-06 | 腾讯科技(深圳)有限公司 | Playback method, device, computing device and the storage medium of video |
CN108898415A (en) * | 2018-05-29 | 2018-11-27 | 北京奇艺世纪科技有限公司 | A kind of the flow index of correlation prediction technique and device of video collection of drama |
CN109040844A (en) * | 2018-09-25 | 2018-12-18 | 有米科技股份有限公司 | A kind of method, apparatus and electronic equipment obtaining video temperature |
CN109327710A (en) * | 2018-12-10 | 2019-02-12 | 网宿科技股份有限公司 | A kind of method and device that the cold and hot situation of the video flowing of live broadcast system determines |
CN109963174A (en) * | 2019-01-28 | 2019-07-02 | 北京奇艺世纪科技有限公司 | Flow index of correlation predictor method, device and computer readable storage medium |
CN110225407A (en) * | 2019-04-23 | 2019-09-10 | 北京奇艺世纪科技有限公司 | The acquisition methods and device and computer readable storage medium of a kind of played data |
CN111062527A (en) * | 2019-12-10 | 2020-04-24 | 北京爱奇艺科技有限公司 | Video collection flow prediction method and device |
CN111090774A (en) * | 2019-11-07 | 2020-05-01 | 北京科技大学 | Video heat prediction method under edge computing environment |
CN111225267A (en) * | 2018-11-26 | 2020-06-02 | 中国电信股份有限公司 | Content cache scheduling method, device and system and content distribution network node |
CN111597383A (en) * | 2020-04-24 | 2020-08-28 | 北京奇艺世纪科技有限公司 | Video heat level prediction method and device |
CN112004120A (en) * | 2019-05-27 | 2020-11-27 | 广州虎牙信息科技有限公司 | Method, device, equipment and storage medium for predicting platform network resource playing amount |
CN113347464A (en) * | 2021-04-30 | 2021-09-03 | 北京奇艺世纪科技有限公司 | Video playing flow prediction method and device, electronic equipment and storage medium |
CN114297156A (en) * | 2021-12-27 | 2022-04-08 | 北京达佳互联信息技术有限公司 | Multimedia file cleaning method and device, electronic equipment and storage medium |
CN114615525A (en) * | 2022-03-18 | 2022-06-10 | 北京字节跳动网络技术有限公司 | Video pushing method, device, equipment and storage medium |
CN115250368A (en) * | 2021-04-26 | 2022-10-28 | 北京字跳网络技术有限公司 | Video preheating method, device, equipment and storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101477556A (en) * | 2009-01-22 | 2009-07-08 | 苏州智讯科技有限公司 | Method for discovering hot sport in internet mass information |
CN102790915A (en) * | 2012-07-09 | 2012-11-21 | 上海聚力传媒技术有限公司 | Method and device for pre-pushing video resource to P2P (peer-to-peer) nodes |
WO2013033869A1 (en) * | 2011-09-09 | 2013-03-14 | Nokia Siemens Networks Oy | Method, device and system for providing and selecting candidate nodes for live streaming services |
CN103312776A (en) * | 2013-05-08 | 2013-09-18 | 青岛海信传媒网络技术有限公司 | Method and device for caching contents of videos by edge node server |
CN103986977A (en) * | 2014-04-15 | 2014-08-13 | 上海聚力传媒技术有限公司 | Method and device for preloading video in content distribution network |
CN104065981A (en) * | 2014-06-20 | 2014-09-24 | 海信集团有限公司 | Method and device for recommending videos |
CN104469434A (en) * | 2014-12-23 | 2015-03-25 | 合一网络技术(北京)有限公司 | Intelligent router hotspot video distribution method |
CN105302890A (en) * | 2015-10-16 | 2016-02-03 | 海信集团有限公司 | Multimedia content online recommendation method and multimedia content online recommendation auxiliary method and apparatus |
CN105323602A (en) * | 2014-07-23 | 2016-02-10 | 中兴通讯股份有限公司 | Program ordering method and device |
CN105335517A (en) * | 2015-11-06 | 2016-02-17 | 努比亚技术有限公司 | Method and terminal for selecting heat multimedia |
CN105787049A (en) * | 2016-02-26 | 2016-07-20 | 浙江大学 | Network video hotspot event finding method based on multi-source information fusion analysis |
-
2016
- 2016-08-08 CN CN201610644027.3A patent/CN107707964A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101477556A (en) * | 2009-01-22 | 2009-07-08 | 苏州智讯科技有限公司 | Method for discovering hot sport in internet mass information |
WO2013033869A1 (en) * | 2011-09-09 | 2013-03-14 | Nokia Siemens Networks Oy | Method, device and system for providing and selecting candidate nodes for live streaming services |
CN102790915A (en) * | 2012-07-09 | 2012-11-21 | 上海聚力传媒技术有限公司 | Method and device for pre-pushing video resource to P2P (peer-to-peer) nodes |
CN103312776A (en) * | 2013-05-08 | 2013-09-18 | 青岛海信传媒网络技术有限公司 | Method and device for caching contents of videos by edge node server |
CN103986977A (en) * | 2014-04-15 | 2014-08-13 | 上海聚力传媒技术有限公司 | Method and device for preloading video in content distribution network |
CN104065981A (en) * | 2014-06-20 | 2014-09-24 | 海信集团有限公司 | Method and device for recommending videos |
CN105323602A (en) * | 2014-07-23 | 2016-02-10 | 中兴通讯股份有限公司 | Program ordering method and device |
CN104469434A (en) * | 2014-12-23 | 2015-03-25 | 合一网络技术(北京)有限公司 | Intelligent router hotspot video distribution method |
CN105302890A (en) * | 2015-10-16 | 2016-02-03 | 海信集团有限公司 | Multimedia content online recommendation method and multimedia content online recommendation auxiliary method and apparatus |
CN105335517A (en) * | 2015-11-06 | 2016-02-17 | 努比亚技术有限公司 | Method and terminal for selecting heat multimedia |
CN105787049A (en) * | 2016-02-26 | 2016-07-20 | 浙江大学 | Network video hotspot event finding method based on multi-source information fusion analysis |
Non-Patent Citations (2)
Title |
---|
张超: "基于k均值的监控视频热度云存储研究", 《计算机与现代化》 * |
顾梁: "一种播存网络环境下的UCL协同过滤推荐方法", 《计算机研究与发展》 * |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108769730A (en) * | 2018-05-21 | 2018-11-06 | 腾讯科技(深圳)有限公司 | Playback method, device, computing device and the storage medium of video |
CN108898415A (en) * | 2018-05-29 | 2018-11-27 | 北京奇艺世纪科技有限公司 | A kind of the flow index of correlation prediction technique and device of video collection of drama |
CN109040844A (en) * | 2018-09-25 | 2018-12-18 | 有米科技股份有限公司 | A kind of method, apparatus and electronic equipment obtaining video temperature |
CN111225267A (en) * | 2018-11-26 | 2020-06-02 | 中国电信股份有限公司 | Content cache scheduling method, device and system and content distribution network node |
CN109327710A (en) * | 2018-12-10 | 2019-02-12 | 网宿科技股份有限公司 | A kind of method and device that the cold and hot situation of the video flowing of live broadcast system determines |
CN109963174A (en) * | 2019-01-28 | 2019-07-02 | 北京奇艺世纪科技有限公司 | Flow index of correlation predictor method, device and computer readable storage medium |
CN109963174B (en) * | 2019-01-28 | 2021-06-22 | 北京奇艺世纪科技有限公司 | Flow related index estimation method and device and computer readable storage medium |
CN110225407A (en) * | 2019-04-23 | 2019-09-10 | 北京奇艺世纪科技有限公司 | The acquisition methods and device and computer readable storage medium of a kind of played data |
CN110225407B (en) * | 2019-04-23 | 2021-09-03 | 北京奇艺世纪科技有限公司 | Method and device for acquiring playing data and computer readable storage medium |
CN112004120A (en) * | 2019-05-27 | 2020-11-27 | 广州虎牙信息科技有限公司 | Method, device, equipment and storage medium for predicting platform network resource playing amount |
CN112004120B (en) * | 2019-05-27 | 2023-10-13 | 广州虎牙信息科技有限公司 | Method, device, equipment and storage medium for predicting playing amount of platform network resources |
CN111090774A (en) * | 2019-11-07 | 2020-05-01 | 北京科技大学 | Video heat prediction method under edge computing environment |
CN111090774B (en) * | 2019-11-07 | 2023-06-27 | 北京科技大学 | Video heat prediction method in edge computing environment |
CN111062527A (en) * | 2019-12-10 | 2020-04-24 | 北京爱奇艺科技有限公司 | Video collection flow prediction method and device |
CN111062527B (en) * | 2019-12-10 | 2023-12-05 | 北京爱奇艺科技有限公司 | Video traffic collection prediction method and device |
CN111597383A (en) * | 2020-04-24 | 2020-08-28 | 北京奇艺世纪科技有限公司 | Video heat level prediction method and device |
CN115250368A (en) * | 2021-04-26 | 2022-10-28 | 北京字跳网络技术有限公司 | Video preheating method, device, equipment and storage medium |
WO2022228411A1 (en) * | 2021-04-26 | 2022-11-03 | 北京字跳网络技术有限公司 | Video warmup method and apparatus, and device and storage medium |
CN113347464A (en) * | 2021-04-30 | 2021-09-03 | 北京奇艺世纪科技有限公司 | Video playing flow prediction method and device, electronic equipment and storage medium |
CN114297156A (en) * | 2021-12-27 | 2022-04-08 | 北京达佳互联信息技术有限公司 | Multimedia file cleaning method and device, electronic equipment and storage medium |
CN114615525A (en) * | 2022-03-18 | 2022-06-10 | 北京字节跳动网络技术有限公司 | Video pushing method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107707964A (en) | The method and apparatus for predicting video content temperature | |
Wang et al. | Multi-agent imitation learning for pervasive edge computing: A decentralized computation offloading algorithm | |
CN103716251B (en) | For the load-balancing method and equipment of content distributing network | |
Du et al. | Enabling AI-generated content (AIGC) services in wireless edge networks | |
CN107306355B (en) | A kind of content recommendation method and server | |
CN105450579B (en) | Internet resources pre-add support method, client and middleware server | |
CN110083334A (en) | The online method and device of model | |
Misra et al. | Optimal gateway selection in sensor–cloud framework for health monitoring | |
CN104796449A (en) | Content delivery method, device and equipment | |
Bashar | Autonomic scaling of cloud computing resources using BN-based prediction models | |
CN104769550B (en) | The method and system of bandwidth allocation in system for cloud computing | |
CN112491964B (en) | Mobile assisted edge calculation method, apparatus, medium, and device | |
CN105068755B (en) | A kind of data trnascription storage method towards cloud computing content distributing network | |
CN108604194A (en) | Probability adjusting | |
CN104641355B (en) | Adaptive service time-out | |
CN109348264A (en) | Video resource sharing method, device, storage medium and electronic equipment | |
CN109891839A (en) | System and method for the incoming network flow request that throttles | |
Li et al. | Human in the loop: distributed deep model for mobile crowdsensing | |
CN104991935B (en) | A kind for the treatment of method and apparatus of website attention rate | |
Li et al. | Efficient cooperative cache management for latency-aware data intelligent processing in edge environment | |
CN106209731A (en) | Session service processing method and processing device | |
CN109639813A (en) | Video file transfer processing method and processing device, electronic equipment and storage medium | |
CN110191362B (en) | Data transmission method and device, storage medium and electronic equipment | |
CN105139326A (en) | Subway traffic information query method and system | |
US9330181B2 (en) | Methods and apparatuses for document processing at distributed processing nodes |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200206 Address after: 518129 Bantian HUAWEI headquarters office building, Longgang District, Guangdong, Shenzhen Applicant after: HUAWEI TECHNOLOGIES Co.,Ltd. Address before: 210012 Ande Gate No. 94, Yuhuatai District, Jiangsu, Nanjing Applicant before: Huawei Technologies Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180216 |
|
RJ01 | Rejection of invention patent application after publication |