CN110225417A - Data processing method and server, the method and server that detect Caton - Google Patents
Data processing method and server, the method and server that detect Caton Download PDFInfo
- Publication number
- CN110225417A CN110225417A CN201910383473.7A CN201910383473A CN110225417A CN 110225417 A CN110225417 A CN 110225417A CN 201910383473 A CN201910383473 A CN 201910383473A CN 110225417 A CN110225417 A CN 110225417A
- Authority
- CN
- China
- Prior art keywords
- caton
- video file
- video
- sequence
- feature vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000003672 processing method Methods 0.000 title claims abstract description 15
- 230000005540 biological transmission Effects 0.000 claims abstract description 132
- 238000001514 detection method Methods 0.000 claims abstract description 96
- 230000008569 process Effects 0.000 claims abstract description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 230000015654 memory Effects 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 7
- 238000012546 transfer Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000007812 deficiency Effects 0.000 claims 1
- 238000007637 random forest analysis Methods 0.000 description 5
- 208000001491 myopia Diseases 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 208000032369 Primary transmission Diseases 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012549 training 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]
- H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client
- H04N21/63—Control signaling related to video distribution between client, server and network components; Network processes for video distribution between server and clients or between remote clients, e.g. transmitting basic layer and enhancement layers over different transmission paths, setting up a peer-to-peer communication via Internet between remote STB's; Communication protocols; Addressing
- H04N21/647—Control signaling between network components and server or clients; Network processes for video distribution between server and clients, e.g. controlling the quality of the video stream, by dropping packets, protecting content from unauthorised alteration within the network, monitoring of network load, bridging between two different networks, e.g. between IP and wireless
- H04N21/64723—Monitoring of network processes or resources, e.g. monitoring of network load
- H04N21/6473—Monitoring network processes errors
-
- 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]
- H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client
- H04N21/63—Control signaling related to video distribution between client, server and network components; Network processes for video distribution between server and clients or between remote clients, e.g. transmitting basic layer and enhancement layers over different transmission paths, setting up a peer-to-peer communication via Internet between remote STB's; Communication protocols; Addressing
- H04N21/647—Control signaling between network components and server or clients; Network processes for video distribution between server and clients, e.g. controlling the quality of the video stream, by dropping packets, protecting content from unauthorised alteration within the network, monitoring of network load, bridging between two different networks, e.g. between IP and wireless
- H04N21/64723—Monitoring of network processes or resources, e.g. monitoring of network load
- H04N21/64738—Monitoring network characteristics, e.g. bandwidth, congestion level
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Security & Cryptography (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a kind of data processing method and servers, the method and server that detect Caton, wherein the method for the detection Caton includes: the transmission feature and video playing information for obtaining video file to be detected；According to the transmission feature of the video file and video playing information, the first input feature vector corresponding with the video file is determined；According to first input feature vector and default Caton detection model, determine whether the video file occurs Caton, wherein the default Caton detection model is to establish according to the transmission feature and playback features of sample video files.Technical solution provided by the invention can accurately detect the case where whether Caton having occurred in video display process.
Description
Technical field
The present invention relates to Internet technical field, in particular to a kind of data processing method and server detect Caton
Method and server.
Background technique
With the update of internet New Media Technology, the expansion of new media platform, the development in pluralism of new media content with
And intelligent terminal is universal, the short-sighted frequency of mobile program request applied to intelligent terminal is grown rapidly, and is increasingly becoming user more
The content circulation way of favor.For the development for adapting to short-sighted frequency, and better video playing is provided for user and is experienced, service provider
Need at any time to assess the user satisfaction of user and improve the competitiveness to promote oneself.Service provider is to user's at present
User satisfaction is assessed the subjective experience satisfaction for usually assessing user, i.e. Quality of experience (Quality of
Experience, abbreviation QoE), the competitiveness of oneself can be improved by improving user experience quality.Due to influencing user experience
The principal element of quality is the Caton occurred in video display process, so can by the way that Caton whether occurs in detection playing process
Effectively to assess user experience quality.
The method of existing detection Caton is mainly the Caton detection method based on average bit rate, can specifically include: obtaining
Take the average bit rate of video, periodically detect the transmission data accumulated in small time granularity whether be greater than or equal to average bit rate and when
Between product, if testing result be it is yes, Caton does not occur；If testing result is no, then it represents that Caton occurs.It is examined in the Caton
It,, can be by length to avoid time error caused by user's pause behavior when calculating average bit rate and the product of time in survey method
The time span that Time-Client end window mouth is 0 is considered that user suspends behavior, and removal time length.
However, the attention with people to privacy of user, more and more service providers carry out encrypted transmission to video content,
So that being difficult to be resolved to the code rate information of video in most cases, therefore, it is also difficult to obtain the average code that be used to detect Caton
Rate.Also, due to the video code rate under different playing times be it is revocable, the playback volume that each moment needs becomes with code rate
It is dynamic, therefore there may be relatively large deviations with practical Caton situation for the result based on average bit rate detection Caton, detect the knot of Caton
Fruit inaccuracy.
Therefore, a kind of method for detecting Caton is needed at present, and Caton occurs in video display process more accurately to detect
The case where, so that service provider improves Caton problem in time, improve user experience quality.
Summary of the invention
The application's is designed to provide a kind of data processing method and server, the method and server that detect Caton,
The case where whether Caton having occurred in video display process can accurately be detected.
To achieve the above object, on the one hand the application provides a kind of data processing method, comprising:
Obtain the data transmission information and video playing information of video file；The data transmission information includes: a biography
It is defeated to request corresponding transmission feature and Caton mark；The Caton mark is for characterizing whether the video file blocks
?；
The playback features of the video file are determined according to the video playing information；
The input feature vector that the video file is determined according to the transmission feature and the playback features, according to the input
The corresponding relationship that feature and the Caton of the video file identify establishes Caton detection model.
To achieve the above object, on the other hand the application also provides a kind of method for detecting Caton, comprising:
Obtain the transmission feature and video playing information of video file to be detected；
It is determining literary with the video to be detected according to the transmission feature and video playing information of the video file to be detected
Corresponding first input feature vector of part；
According to first input feature vector and default Caton detection model, determine whether the video file to be detected occurs
Caton；, wherein the default Caton detection model is to be established according to the transmission feature and playback features of sample video files.
To achieve the above object, on the other hand the application also provides a kind of data processing server, comprising: acquisition of information list
Member, playback features extraction unit and Caton detection model establish unit；
The information acquisition unit, for obtaining the data transmission information and video playing information of video file；The number
Include according to transport packet: corresponding transmission feature and Caton mark are requested in a transmission；The Caton mark is for characterizing
State whether video file occurs Caton；
The playback features extraction unit, the broadcasting for determining the video file according to the video playing information are special
Sign；
The Caton detection model establishes unit, for determining the view according to the transmission feature and the playback features
The input feature vector of frequency file establishes Caton inspection according to the corresponding relationship that the Caton of the input feature vector and the video file identifies
Survey model.
To achieve the above object, on the other hand the application also provides a kind of server for detecting Caton, comprising: the file information
Acquiring unit, input feature vector determination unit and testing result determination unit；
The file information acquiring unit, for obtaining the transmission feature and video playing information of video file to be detected；
It is described to be specifically included for obtaining video playing information: for extracting the video file to be detected according to preset time granularity
Mean Speed；The video file to be detected is to include multiple segments according to the preset time granularity division according to play time
A sequence；Correspondingly, the Mean Speed of the extraction forms a Mean Speed sequence；
The input feature vector determination unit, for being broadcast according to the data transmission information and video of the video file to be detected
Put information, determining first input feature vector corresponding with the video file to be detected；
The testing result determination unit, for determining according to first input feature vector and default Caton detection model
Whether the video file to be detected occurs Caton.
To achieve the above object, it includes memory and processor that on the other hand the application, which also provides a kind of server, described
Memory is for storing computer program, when the computer program is executed by the processor, realizes above method embodiment party
The method executed in case.
Therefore technical solution provided by the present application, Caton detection model can be established using machine learning method, built
Input feature vector needed for vertical Caton detection model is from the data transmission information and video file broadcast information of video file
The various features of acquisition, can server more fully in the transmission of reflecting video file and playing process, client and network
Situation, therefore, the Caton detection model based on the foundation of above-mentioned input feature vector is when carrying out Caton detection, it is ensured that Caton detection
Accuracy.Meanwhile the part input feature vector of extraction is determined according to the broadcast information extracted according to preset time granularity,
It is not influenced by entire video file duration, can more accurately embody the actual play situation of video.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is a kind of flow chart of data processing method in this specification embodiment；
Fig. 2 is a kind of flow chart for the method for detecting Caton in this specification embodiment；
Fig. 3 is a kind of module map of data processing server in this specification embodiment；
Fig. 4 is a kind of module map for the server for detecting Caton in this specification embodiment；
Fig. 5 is the structural schematic diagram of server in the embodiment of the present invention；
Fig. 6 is the structural schematic diagram of terminal in the embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.
The application provides a kind of data processing method.The data processing method may be implemented to establish for detecting video text
In part playing process whether the Caton detection model of Caton.The data processing method can be executed by the terminal of service provider, i.e.,
It can be executed by the transmitting terminal of video file.
Fig. 1 is a kind of flow chart of data processing method in this specification embodiment.Referring to Fig. 1, provided by the present application
Data processing method may comprise steps of.
S11: the data transmission information and video playing information of video file are obtained.
The transmitting terminal of service provider can send video file to the receiving end of user.Number can be generated in video transmitting procedure
According to transmission information.
In one embodiment, the data transmission information may include: that corresponding transmission feature is requested in a transmission
And Caton mark.
Specifically, a transmission request can correspond to a transmission log, and the transmission in available each transmission log is special
Sign and Caton mark.
The transmission feature may include one or more features, and one or more of features can be used for characterizing video
Transmission objective of the file in primary transmission request.For example, transmission feature " transmission byte number " can be used for characterizing video text
Total bytes this index that part transmits in primary transmission request.
In one embodiment, the transmission feature may include at least one of following: transmission byte number retransmits
Byte number retransmits ratio, is false when retransmitting number, initial round-trip delay, minimum round-trip delay, average RTT, maximum round trip
Prolong, minimum round-trip delay fluctuation, average RTT fluctuation, the fluctuation of maximum round trip time delay, minimum congestion window, average congestion window
Mouth, extreme congestion window, minimum window, average received window, maximum window, overall response duration, the reception window of receiving of receiving are held
Continuous duration, LOSS state duration send the limited total duration of caching, total duration of persistently giving out a contract for a project, Retransmission timeout continuous trigger most
When big number, TCP transmission state, maximum out-of-order value, head shield size of data, first screen load duration, establish connection duration, first packet
It is long, into DISORDER state number, into CWR state number, into RECOVERY state number, into LOSS state time
Number.
Above-mentioned transmission feature can effectively reflect the transmission situation of short-sighted frequency.For example, first screen size of data, first screen load
The features such as duration can reflect first screen quality, transmission speed etc.；Minimum round-trip delay fluctuation, average RTT fluctuation, maximum
The transmission features such as round-trip delay fluctuation, minimum congestion window, average congestion window, extreme congestion window can embody network congestion
Degree；Minimum receives window, average received window, maximum reception window, overall response duration, receives the features such as window duration
ISCSI receiving end window situation can be embodied；The transmission features such as transmission byte number, re-transmission byte number, re-transmission ratio, false re-transmission number can
To embody packet drop.
The transmission feature obtained is multiple features, can more fully embody the actual transmissions situation of short-sighted frequency.
Whether the Caton mark occurs Caton when can be used for characterizing video file described in client terminal playing.The Caton
Mark can be indicated using character.For example, can be indicated that Caton has occurred with character " 1 ", can indicate not send out with character " 0 "
Raw Caton.
The receiving end of the user can receive and play the video file.The user receiving end receives and plays institute
When stating video file, the available video playing information of transmitting terminal.
In one embodiment, the video playing information for obtaining the video file may include: according to default
The Mean Speed for the broadcasting video file that time granularity extracts.In this embodiment, the video file can basis
Play time is a sequence comprising multiple segments according to the preset time granularity division.Correspondingly, the extraction is flat
Equal rate can form a Mean Speed sequence.One video file can correspond to a Mean Speed sequence.
By the way that the video file is included multiple segments according to the preset time granularity division according to play time
A sequence, can make the Mean Speed extracted is the Mean Speed of preset time granularity, and Mean Speed can embody
Broadcasting situation in short time by video file total duration without being influenced.Therefore, it is averaged by what the above method extracted
Rate can more accurately embody the actual play situation of video.
For example, the play time of a video file is 10 seconds, preset time granularity is 500 milliseconds, then available
The Mean Speed of every 500 milliseconds of broadcastings, amounts to available 20 Mean Speeds.The video file of the broadcasting can be according to every
500 milliseconds are divided into 20 segments, and the video file of the broadcasting can be the sequence comprising 20 segments.In the sequence
The Mean Speed that 20 segments are extracted respectively can form a Mean Speed sequence.The Mean Speed sequence of the composition and institute
It is one-to-one for stating video file.
S12: the playback features of the video file are determined according to the video playing information.
According to the video playing information, the playback features of the video file can be determined.The video playing feature
It can be extracted from Mean Speed sequence corresponding with the video file.For example, in sequence first granularity transmission rate this
The determination method of one playback features can be with are as follows: obtains the value of first Mean Speed in the Mean Speed sequence.
In one embodiment, the video playing feature may include at least one of following: in sequence effectively
The transmission rate of first granularity in granularity number, sequence, minimum transmission rate in sequence, average transmission rate, sequence in sequence
Peak transfer rate in column, transmission rate standard deviation in sequence, each small grain size transmission rate average accumulated difference, sequence in sequence
The continuous granularity number of the maximum that client receiving window size is 0 in granularity number that middle client receiving window size is 0, sequence,
Client receiving window size is 0 in sequence total degree, the granularity number of application layer no data in sequence, in sequence application layer without
The total degree of application layer no data in the continuous granularity number of the maximum of data, sequence.
S13: the input feature vector of the video file is determined according to the transmission feature and the playback features, according to described
The corresponding relationship that the Caton of input feature vector and the video file identifies establishes Caton detection model.
The input feature vector of the video file can be determined according to the transmission feature and the playback features.
In one embodiment, feature some or all of in the transmission feature and the playback features can be made
For the input feature vector of the video file.
It in one embodiment, can according to the corresponding relationship that the Caton of the input feature vector and the video file identifies
It include: that the Caton is identified the input feature vector as output sample to as input sample to establish Caton detection model,
The input sample and output sample are trained to obtain the Caton detection model using machine learning algorithm.
In one embodiment, the machine learning algorithm includes: random forests algorithm.The random forests algorithm can
To handle a large amount of input varible, it can handle complicated input feature vector, can establish height by using random forests algorithm
The Caton detection model of accuracy.Simultaneously as trained sample, there are non-equilibrium property, for example, the video of a hour
In file, the sample size of Caton is far smaller than the sample size of not Caton, then this set for the sample of training is exactly tight
The non-equilibrium sample set of weight.Using random forests algorithm it is possible to prevente effectively from the model of foundation caused by the non-equilibrium property of sample not
Accurate problem.
In one embodiment, the input sample and output sample are being trained using machine learning algorithm
Before, the method can also include: execution pretreatment operation.
In one embodiment, the pretreatment operation may include: feature pretreatment and learning algorithm pretreatment.
The feature pretreatment can be used for pre-processing the input feature vector.It can specifically include: removal noise
Sample, removal missing values sample, sample and/or characteristic criterion of the removal comprising exceptional value.Wherein, removal noise sample can be with
It is realized using the method for outlier detection.It is pre-processed by the feature, the reliability of input sample can be improved, improve Caton
The accuracy of detection model.
The learning algorithm pretreatment can be used for presetting the parameter of the learning algorithm.It can specifically include: special
Levy dimension transformation and feature selecting.The characteristic dimension transformation can pass through principal component analysis method or linear discriminant point
Analysis method is to realize.It is converted by features described above dimension, the input feature vector can be transformed to low dimensional from high dimensional data
Data.The feature selecting can be removes redundancy or incoherent feature from one group of feature, realizes Data Dimensionality Reduction.Pass through institute
Learning algorithm pretreatment is stated, the difficulty of learning algorithm and the complexity of Caton detection model can be reduced, improve the Caton
The detection efficiency of detection model.
In one embodiment, the data transmission information can also include: not sent data original in every preset duration
Cause.If having sent data in the preset duration, the not sent data reasons can be null value.In an embodiment
In, the not sent data reasons may include: application layer no data and client receiving window size is 0.
In one embodiment, the reason of not sent data, can be identified using character.For example, can be with
Application layer no data is identified using mark "+".Mark "-" mark client receiving window size can be used for 0.
In above method embodiment, data transmission information can use TCP transmission agreement to obtain, multiple transmission of acquisition
Feature can fully and effectively embody video actual transmissions situation, from according to preset time granularity division be include multiple segments
The Mean Speed sequence extracted in the video file of one sequence can accurately reflect the actual play situation of video file, utilize
The Caton detection model that features described above is established can accurately detect whether video file occurs Caton.
The embodiment of the present application also provides a kind of method for detecting Caton.The method of the detection Caton can use this explanation
The Caton detection model established of data processing method that book embodiment provides is realized.
Fig. 2 is a kind of flow chart for the method for detecting Caton in this specification embodiment.Referring to Fig. 2, the detection card
The method paused may comprise steps of.
S21: the transmission feature and video playing information of video file to be detected are obtained.
In one embodiment, the transmission feature may include one or more features, one or more of spies
Sign can be used for characterizing the transmission objective during video file transfer to be detected.
In one embodiment, the video playing information for obtaining the video file to be detected may include: by
According to the Mean Speed for the broadcasting video file to be detected that preset time granularity is extracted.In this embodiment, described to be checked
Surveying video file can be a sequence comprising multiple segments according to the preset time granularity division according to play time.Phase
Ying Di, the Mean Speed of the extraction can form a Mean Speed sequence.One video file can correspond to one averagely
Rate sequence.
S22: according to the transmission feature and video playing information of the video file to be detected, the determining and view to be detected
Corresponding first input feature vector of frequency file.
In one embodiment, described to be believed according to the data transmission information and video playing of the video file to be detected
Breath, determining first input feature vector corresponding with the video file to be detected, may include: according to the video file to be detected
Video playing information determine corresponding with video file playback features, will the part or all of transmission feature and broadcasting
Feature is as first input feature vector.
Further, described can be with as first input feature vector using the part transmission feature and the playback features
It include: using transmission feature needed for default Caton detection model and playback features as first input feature vector；It is described default
Transmission feature needed for Caton detection model and Partial Feature can be the part or all of transmission feature and playback features.
For example, the transmission feature got may include: that " transmission byte number retransmits byte number, retransmits ratio, is false
Retransmit number, initial round-trip delay, first screen load duration ".The playback features got may include: " first in sequence
Minimum transmission rate in the transmission rate of a granularity, sequence, average transmission rate in sequence ".Assuming that needed for default Caton model
Feature include: transmission byte number, retransmit ratio, false number, initial round-trip delay, the first screen of retransmitting loads duration, the in sequence
Minimum transmission rate in the transmission rate of one granularity, sequence, average transmission rate in sequence, peak transfer rate in sequence.
It is possible to by feature " transmission byte number, retransmit ratio, false number, initial round-trip delay, the first screen of retransmitting loads duration, sequence
In the transmission rate of first granularity, minimum transmission rate in sequence, average transmission rate in sequence " it is special as the first input
Sign.
S23: according to first input feature vector and default Caton detection model, whether the video file to be detected is determined
Caton occurs.
According to first input feature vector and default Caton detection model, whether the video file to be detected can be determined
Caton occurs.Specifically, using first input feature vector as the input of the default Caton detection model, the first Caton is obtained
Mark determines whether the video file to be detected occurs Caton according to first Caton mark.
The first Caton mark can be used to indicate that whether the video file to be detected has occurred Caton.For example, working as
When first Caton is identified as " 1 ", it can indicate that Caton has occurred in the video file to be detected；When the first Caton is identified as " 0 "
When, it can indicate that there is no Catons for the video file to be detected.
Default Caton detection model can be established using random forests algorithm.
The default Caton detection model can be realized using data processing method in this specification.
In above method embodiment, it can be obtained in time and video text using the Caton detection model established in this specification
The associated transmission feature of part and playback features carry out and accurately determine whether video file occurs Caton.
In another embodiment, when the transmission rate in first input feature vector including first granularity in sequence
When, determining whether the video file to be detected occurs Caton according to first input feature vector and default Caton detection model
Before, the method can also include: the transmission rate according to first granularity in the sequence to the video text to be detected
Part carries out pre-detection, obtains pre-detection result.The pre-detection result include: there is no Caton and it is unknown whether Caton.
When the pre-detection result be it is unknown whether Caton when, the step S23 can be executed.
The transmission rate of first granularity is to the view to be detected in the sequence according in first input feature vector
Frequency file carries out pre-detection, obtains pre-detection as a result, can specifically include: will be first in the sequence in first input feature vector
The transmission rate of a granularity is compared with the first preset value；When the transmission rate that comparison result is first granularity is greater than or waits
When the first preset value, the pre-detection result can be for there is no Catons；Alternatively, when the biography that comparison result is first granularity
When defeated rate is less than the first preset value, the pre-detection result can for it is unknown whether Caton.First preset value can root
It is configured according to actual needs, such as can be set to 2000KB/s.
Due to this feature of the transmission rate of first granularity in sequence and video whether Caton relevance it is stronger, can be with
Pre-detection is carried out using this feature, it, can be with if the transmission rate of first granularity is greater than or equal to the first preset value in sequence
Think that Caton will not occur for video.Predicted detection is carried out using this feature, can greatly reduce and be carried out using Caton detection model
The data volume of Caton detection, can greatly improve the efficiency of Caton detection.
In another embodiment, when determining that Caton has occurred in the video file to be detected, the detection Caton
Method can also include: corresponding relationship according to first input feature vector and preset input feature vector and Caton factor,
Determine the reason of Caton occurs for the video file to be detected.It specifically, can be according to preset input feature vector and Caton factor
Corresponding relationship, determine corresponding with first input feature vector Caton factor, the Caton factor of the determination be described in
Detect the reason of Caton occurs for video file.
In one embodiment, the preset input feature vector and the corresponding relationship of Caton factor may include:
In input feature vector application layer no data duration account for request total duration ratio be greater than the first preset ratio value, then Caton because
Element is application layer problem；And/or
Client receiving window size is that 0 duration accounts for request total duration ratio greater than the second preset ratio in input feature vector
Value, then Caton factor is client-side issue；And/or
Average RTT is greater than time delay preset value in input feature vector, LOSS state duration is greater than preset duration, again
It passes byte number and accounts for transmission byte number ratio and be greater than third ratio value and/or Retransmission timeout duration and account for request total duration ratio and be greater than the
Four ratio values, then Caton factor is network problem.
In the above-described embodiment, when determining that Caton has occurred in the video file to be detected, pass through preset input
The corresponding relationship of feature and Caton factor can determine the reason of Caton occurs for the video file to be detected, so as to side
Just service provider takes corresponding Improving Measurements, to improve user experience.
The embodiment of the present application also provides a kind of data processing server, and the data processing server can be service provider
Server.The data processing server can be used for establishing Caton detection model.
Fig. 3 is a kind of module map of data processing server in this specification embodiment.Referring to Fig. 3, at the data
Managing server may include: that information acquisition unit, playback features extraction unit and Caton detection model establish unit.Wherein,
The information acquisition unit can be used for obtaining the data transmission information and video playing information of video file.Institute
Stating data transmission information may include: that corresponding transmission feature and Caton mark are requested in a transmission.The Caton mark can
For characterizing whether the video file occurs Caton.
The playback features extraction unit can be used for determining broadcasting for the video file according to the video playing information
Put feature.
The Caton detection model establishes unit, can be used for determining institute according to the transmission feature and the playback features
The input feature vector for stating video file is established according to the corresponding relationship that the Caton of the input feature vector and the video file identifies and is blocked
Pause detection model.
The embodiment of the present application also provides a kind of server for detecting Caton, and the server of the detection Caton can be service
The server of quotient.Whether the video file that the server of the detection Caton can be used for real-time detection broadcasting has occurred Caton.
Fig. 4 is a kind of module map for the server for detecting Caton in this specification embodiment.Referring to Fig. 4, the detection
The server of Caton may include: the file information acquiring unit, input feature vector determination unit and testing result determination unit.Its
In,
The file information acquiring unit can be used for obtaining the transmission feature and video playing letter of video file to be detected
Breath.Wherein, described to can specifically include for obtaining video playing information: described to be checked for being extracted according to preset time granularity
Survey the Mean Speed of video file；The video file to be detected can be drawn according to play time according to the preset time granularity
It is divided into a sequence comprising multiple segments；Correspondingly, the Mean Speed of the extraction can form a Mean Speed sequence.
The input feature vector determination unit can be used for data transmission information and view according to the video file to be detected
Frequency broadcast information, determining first input feature vector corresponding with the video file to be detected.
The testing result determination unit can be used for according to first input feature vector and default Caton detection model,
Determine whether the video file to be detected occurs Caton.
In one embodiment, the server of the detection Caton can also include: pre-detection unit.When the input
It include first granularity in the video file corresponding sequence to be detected in the first input feature vector that characteristics determining unit determines
When transmission rate, the pre-detection unit can be used for the transmission rate according to first granularity in the sequence to described to be checked
It surveys video file and carries out pre-detection, obtain pre-detection result.
In one embodiment, the server of the detection Caton can also include: Caton factor determination unit.Work as institute
When stating testing result determination unit and determining that Caton has occurred in the video file to be detected, the Caton factor determination unit can be with
For the corresponding relationship according to first input feature vector and preset input feature vector and Caton factor, determine described to be detected
The reason of Caton, occurs for video file.
Referring to Fig. 5, the application also provides a kind of server, the server includes memory and processor, described to deposit
Reservoir is for storing computer program, and when the computer program is executed by the processor, above method implementation may be implemented
The method that example executes.
Referring to Fig. 6, in this application, the technical solution in above-described embodiment can be applied to calculating as shown in FIG. 6
In machine terminal 10.Terminal 10 may include one or more (one is only shown in figure) (processors 102 of processor 102
Can include but is not limited to the processing unit of Micro-processor MCV or programmable logic device FPGA etc.), depositing for storing data
Reservoir 104 and transmission module 106 for communication function.It will appreciated by the skilled person that knot shown in fig. 6
Structure is only to illustrate, and does not cause to limit to the structure of above-mentioned electronic device.For example, terminal 10, which may also include, compares Fig. 6
Shown in more perhaps less component or with the configuration different from shown in Fig. 6.
Memory 104 can be used for storing the software program and module of application software, and processor 102 is stored in by operation
Software program and module in memory 104, thereby executing various function application and data processing.Memory 104 can wrap
Include high speed random access memory, may also include nonvolatile memory, as one or more magnetic storage device, flash memory or
Other non-volatile solid state memories.In some instances, memory 104 can further comprise long-range relative to processor 102
The memory of setting, these remote memories can pass through network connection to terminal 10.The example of above-mentioned network includes
But be not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Specifically, in this application, the dispositions method of above-mentioned server can be used as computer program be stored in it is above-mentioned
Memory 104 in, the memory 104 can be coupled with processor 102, then when processor 102 executes the memory
When computer program in 104, each step in the dispositions method of above-mentioned server can be realized.
Transmitting device 106 is used to that data to be received or sent via a network.Above-mentioned network specific example may include
The wireless network that the communication providers of terminal 10 provide.In an example, transmitting device 106 includes that a network is suitable
Orchestration (Network Interface Controller, NIC), can be connected by base station with other network equipments so as to
Internet is communicated.In an example, transmitting device 106 can be radio frequency (Radio Frequency, RF) module,
For wirelessly being communicated with internet.
Therefore in technical solution provided by the present application, Caton detection mould can be established using the method for machine learning
Type, input feature vector needed for the Caton detection model of foundation are to play to believe from the data transmission information and video file of video file
The various features obtained in breath, can the more fully transmission of reflecting video file and server, client and net in playing process
The case where network, therefore, the Caton detection model based on the foundation of above-mentioned input feature vector is when carrying out Caton detection, it is ensured that Caton
The accuracy of detection.Meanwhile the part input feature vector of extraction is according to the broadcast information extracted according to preset time granularity come really
Fixed, it is not influenced by entire video file duration, can more accurately embody the actual play situation of video.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to be realized by hardware.Based on such
Understand, substantially the part that contributes to existing technology can embody above-mentioned technical proposal in the form of software products in other words
Out, which may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, packet
Some instructions are included to use so that a computer equipment (can be personal computer, server or the network equipment etc.) executes
Method described in certain parts of each embodiment or embodiment.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (16)
1. a kind of data processing method characterized by comprising
Obtain the data transmission information and video playing information of video file；The data transmission information includes: that a transmission is asked
Corresponding transmission feature and Caton is asked to identify；The Caton mark is for characterizing whether the video file occurs Caton；
The playback features of the video file are determined according to the video playing information；
The input feature vector that the video file is determined according to the transmission feature and the playback features, according to the input feature vector
The corresponding relationship identified with the Caton of the video file establishes Caton detection model.
2. the method according to claim 1, wherein the video playing information for obtaining the video file includes:
According to the Mean Speed for the broadcasting video file that preset time granularity is extracted；The video file according to play time according to
The preset time granularity division is a sequence comprising multiple segments；Correspondingly, the Mean Speed composition one of the extraction
A Mean Speed sequence.
3. according to the method described in claim 2, it is characterized in that, the video playing feature includes at least one in following
Kind: effective size of grain number in sequence, the transmission rate of first granularity in sequence, minimum transmission rate in sequence are put down in sequence
Peak transfer rate in equal transmission rate, sequence, transmission rate standard deviation in sequence, each small grain size transmission rate is average in sequence
Client receiving window size is 0 most in client receiving window size is 0 in accumulated deficiency, sequence granularity number, sequence
The granularity number of application layer no data in client receiving window size is 0 in big continuous granularity number, sequence total degree, sequence,
The continuous granularity number of the maximum of application layer no data in sequence, in sequence application layer no data total degree.
4. the method according to claim 1, wherein described according to the input feature vector and the video file
It includes: using the input feature vector as input sample, by the Caton that the corresponding relationship of Caton mark, which establishes Caton detection model,
Mark is trained to obtain the Caton as output sample, using machine learning algorithm to the input sample and output sample
Detection model.
5. according to the method described in claim 4, it is characterized in that, using machine learning algorithm to the input sample and defeated
Before sample is trained out, the method also includes: execute pretreatment operation；
The pretreatment operation includes: feature pretreatment and learning algorithm pretreatment；
The feature pretreatment is for pre-processing the input feature vector, comprising: removal noise sample, removal missing values sample
Originally, removal includes the sample and/or characteristic criterion of exceptional value；
The learning algorithm pre-processes the parameter for presetting the learning algorithm, comprising: characteristic dimension transformation and spy
Sign selection.
6. a kind of method for detecting Caton characterized by comprising
Obtain the transmission feature and video playing information of video file to be detected；
According to the transmission feature and video playing information of the video file to be detected, the determining and video file pair to be detected
The first input feature vector answered；
According to first input feature vector and default Caton detection model, determine whether the video file to be detected blocks
, wherein the default Caton detection model is to be established according to the transmission feature and playback features of sample video files.
7. according to the method described in claim 6, it is characterized in that, the default Caton detection model is according to Sample video text
What the transmission feature and playback features of part were established includes:
Obtain the data transmission information and video playing information of sample video files；The data transmission information includes: a biography
It is defeated to request corresponding transmission feature and Caton mark；The Caton mark is for characterizing whether the sample video files occur
Caton；
The playback features of the sample video files are determined according to the video playing information of the sample video files；
Determine that the sample input of the sample video files is special according to the transmission feature of the sample video files and playback features
Sign establishes the default Caton according to the corresponding relationship that the Caton of the sample input feature vector and the sample video files identifies
Detection model.
8. the method according to the description of claim 7 is characterized in that the video playing for obtaining the video file to be detected
Information includes: that the Mean Speed of the video file to be detected is extracted according to preset time granularity；The video file to be detected
According to play time according to the preset time granularity division be a sequence comprising multiple segments；Correspondingly, the extraction
Mean Speed form a Mean Speed sequence.
9. according to the method described in claim 8, it is characterized in that, when first input feature vector includes first grain in sequence
When the transmission rate of degree, the video file to be detected is being determined according to first input feature vector and default Caton detection model
Before whether Caton occurring, the method also includes: according to the transmission rate of first granularity in the sequence to described to be checked
It surveys video file and carries out pre-detection, obtain pre-detection result；Whether the pre-detection result includes: there is no Caton and unknown to block
?.
10. according to the method described in claim 9, it is characterized in that, in the sequence according in first input feature vector
The transmission rate of first granularity carries out pre-detection to the video file to be detected, obtains pre-detection as a result, specifically including:
The transmission rate of first granularity in sequence in first input feature vector is compared with the first preset value；
When comparison result be more than or equal to when, the pre-detection result be there is no Catons；Alternatively, when comparison result be less than
When, the pre-detection result be it is unknown whether Caton.
11. according to the method described in claim 8, it is characterized in that, when Caton has occurred in the determining video file to be detected
When, the method for the detection Caton further include: according to first input feature vector and preset input feature vector and Caton factor
Corresponding relationship, determine the reason of Caton occurs for the video file to be detected.
12. a kind of data processing server characterized by comprising information acquisition unit, playback features extraction unit and Caton
Detection model establishes unit；
The information acquisition unit, for obtaining the data transmission information and video playing information of video file；The data pass
Defeated information includes: that corresponding transmission feature and Caton mark are requested in a transmission；The Caton mark is for characterizing the view
Whether frequency file occurs Caton；
The playback features extraction unit, for determining the playback features of the video file according to the video playing information；
The Caton detection model establishes unit, for determining the video text according to the transmission feature and the playback features
The input feature vector of part establishes Caton detection mould according to the corresponding relationship that the Caton of the input feature vector and the video file identifies
Type.
13. a kind of server for detecting Caton characterized by comprising the file information acquiring unit, input feature vector determination unit
With testing result determination unit；
The file information acquiring unit, for obtaining the transmission feature and video playing information of video file to be detected；It is described
It is specifically included for obtaining video playing information: for extracting being averaged for the video file to be detected according to preset time granularity
Rate；The video file to be detected is one comprising multiple segments according to the preset time granularity division according to play time
A sequence；Correspondingly, the Mean Speed of the extraction forms a Mean Speed sequence；
The input feature vector determination unit, for being believed according to the data transmission information and video playing of the video file to be detected
Breath, determining first input feature vector corresponding with the video file to be detected；
The testing result determination unit, described in determining according to first input feature vector and default Caton detection model
Whether video file to be detected occurs Caton.
14. server according to claim 13, which is characterized in that further include: pre-detection unit, for working as the input
It include first granularity in the video file corresponding sequence to be detected in the first input feature vector that characteristics determining unit determines
When transmission rate, pre-detection is carried out to the video file to be detected according to the transmission rate of first granularity in the sequence,
Obtain pre-detection result.
15. server according to claim 13, which is characterized in that further include: Caton factor determination unit, for working as institute
When stating testing result determination unit and determining that Caton has occurred in the video file to be detected, according to first input feature vector and
The corresponding relationship of preset input feature vector and Caton factor determines the reason of Caton occurs for the video file to be detected.
16. a kind of server, which is characterized in that the server includes memory and processor, and the memory is for storing
Computer program when the computer program is executed by the processor, is realized such as any claim in claim 1 to 11
The method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910383473.7A CN110225417B (en) | 2019-05-09 | 2019-05-09 | Data processing method and server, and method and server for detecting stuck state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910383473.7A CN110225417B (en) | 2019-05-09 | 2019-05-09 | Data processing method and server, and method and server for detecting stuck state |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110225417A true CN110225417A (en) | 2019-09-10 |
| CN110225417B CN110225417B (en) | 2022-06-10 |
Family
ID=67820711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910383473.7A Expired - Fee Related CN110225417B (en) | 2019-05-09 | 2019-05-09 | Data processing method and server, and method and server for detecting stuck state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110225417B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111010617A (en) * | 2019-11-05 | 2020-04-14 | 网宿科技股份有限公司 | Transmission quality detection method, system and equipment |
| CN111031403A (en) * | 2019-11-05 | 2020-04-17 | 网宿科技股份有限公司 | Method, system and equipment for detecting stuck |
| CN111263225A (en) * | 2020-01-08 | 2020-06-09 | 恒安嘉新（北京）科技股份公司 | Video stuck prediction method and device, computer equipment and storage medium |
| CN111405327A (en) * | 2020-04-03 | 2020-07-10 | 广州市百果园信息技术有限公司 | Network bandwidth prediction model training method, video data playing method and device |
| CN111683273A (en) * | 2020-06-02 | 2020-09-18 | 中国联合网络通信集团有限公司 | Method and device for determining video blockage information |
| CN112423096A (en) * | 2020-11-03 | 2021-02-26 | 上海哔哩哔哩科技有限公司 | Playing optimization method and system |
| CN112511818A (en) * | 2020-11-24 | 2021-03-16 | 上海哔哩哔哩科技有限公司 | Video playing quality detection method and device |
| CN112566152A (en) * | 2019-09-26 | 2021-03-26 | 华为技术有限公司 | Method for Katon prediction, method for data processing and related device |
| CN112583801A (en) * | 2020-12-02 | 2021-03-30 | 张仕文 | Network abnormal behavior detection system and method based on big data |
| CN113038163A (en) * | 2021-03-26 | 2021-06-25 | 百果园技术(新加坡)有限公司 | User experience model training method, short video user experience evaluation method and device |
| CN113055745A (en) * | 2021-03-30 | 2021-06-29 | 脸萌有限公司 | Video playing processing method, device, equipment and storage medium |
| CN113098782A (en) * | 2021-03-22 | 2021-07-09 | 武汉大学 | Network congestion control method and computer equipment |
| CN113395512A (en) * | 2021-05-27 | 2021-09-14 | 北京达佳互联信息技术有限公司 | Stuck detection method and device, stuck detection server and storage medium |
| CN114079654A (en) * | 2022-01-05 | 2022-02-22 | 荣耀终端有限公司 | Data retransmission method, system and related device |
| CN114401447A (en) * | 2021-12-20 | 2022-04-26 | 北京字节跳动网络技术有限公司 | Video stuck prediction method, device, equipment and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106803951A (en) * | 2015-11-26 | 2017-06-06 | 德科仕通信(上海)有限公司 | The live interim card method for diagnosing faults of HLS |
| CN107690077A (en) * | 2017-09-05 | 2018-02-13 | 北京京东尚科信息技术有限公司 | The method and apparatus for monitoring net cast interim card |
| CN107888579A (en) * | 2017-11-06 | 2018-04-06 | 浙江大学 | A kind of mobile video user experience quality index modeling method of non-interfering type |
| CN108696403A (en) * | 2018-03-23 | 2018-10-23 | 中国科学技术大学 | A kind of encrypted video QoE evaluating methods based on the study of network flow latent structure |
| CN109391847A (en) * | 2017-08-08 | 2019-02-26 | 中国电信股份有限公司 | The monitoring method and monitoring device of Streaming Media Caton |
-
2019
- 2019-05-09 CN CN201910383473.7A patent/CN110225417B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106803951A (en) * | 2015-11-26 | 2017-06-06 | 德科仕通信(上海)有限公司 | The live interim card method for diagnosing faults of HLS |
| CN109391847A (en) * | 2017-08-08 | 2019-02-26 | 中国电信股份有限公司 | The monitoring method and monitoring device of Streaming Media Caton |
| CN107690077A (en) * | 2017-09-05 | 2018-02-13 | 北京京东尚科信息技术有限公司 | The method and apparatus for monitoring net cast interim card |
| CN107888579A (en) * | 2017-11-06 | 2018-04-06 | 浙江大学 | A kind of mobile video user experience quality index modeling method of non-interfering type |
| CN108696403A (en) * | 2018-03-23 | 2018-10-23 | 中国科学技术大学 | A kind of encrypted video QoE evaluating methods based on the study of network flow latent structure |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112566152B (en) * | 2019-09-26 | 2022-04-29 | 华为技术有限公司 | Method for Katon prediction, method for data processing and related device |
| CN112566152A (en) * | 2019-09-26 | 2021-03-26 | 华为技术有限公司 | Method for Katon prediction, method for data processing and related device |
| CN111010617B (en) * | 2019-11-05 | 2021-07-09 | 网宿科技股份有限公司 | Transmission quality detection method, system and equipment |
| CN111031403A (en) * | 2019-11-05 | 2020-04-17 | 网宿科技股份有限公司 | Method, system and equipment for detecting stuck |
| CN111010617A (en) * | 2019-11-05 | 2020-04-14 | 网宿科技股份有限公司 | Transmission quality detection method, system and equipment |
| CN111031403B (en) * | 2019-11-05 | 2022-01-18 | 网宿科技股份有限公司 | Method, system and equipment for detecting stuck |
| WO2021088174A1 (en) * | 2019-11-05 | 2021-05-14 | 网宿科技股份有限公司 | Transmission quality testing method, system and device |
| CN111263225A (en) * | 2020-01-08 | 2020-06-09 | 恒安嘉新（北京）科技股份公司 | Video stuck prediction method and device, computer equipment and storage medium |
| CN111405327A (en) * | 2020-04-03 | 2020-07-10 | 广州市百果园信息技术有限公司 | Network bandwidth prediction model training method, video data playing method and device |
| CN111683273A (en) * | 2020-06-02 | 2020-09-18 | 中国联合网络通信集团有限公司 | Method and device for determining video blockage information |
| CN112423096A (en) * | 2020-11-03 | 2021-02-26 | 上海哔哩哔哩科技有限公司 | Playing optimization method and system |
| CN112511818A (en) * | 2020-11-24 | 2021-03-16 | 上海哔哩哔哩科技有限公司 | Video playing quality detection method and device |
| CN112583801A (en) * | 2020-12-02 | 2021-03-30 | 张仕文 | Network abnormal behavior detection system and method based on big data |
| CN113098782A (en) * | 2021-03-22 | 2021-07-09 | 武汉大学 | Network congestion control method and computer equipment |
| CN113038163A (en) * | 2021-03-26 | 2021-06-25 | 百果园技术(新加坡)有限公司 | User experience model training method, short video user experience evaluation method and device |
| CN113038163B (en) * | 2021-03-26 | 2023-06-23 | 百果园技术(新加坡)有限公司 | User experience model training method, short video user experience assessment method and device |
| CN113055745A (en) * | 2021-03-30 | 2021-06-29 | 脸萌有限公司 | Video playing processing method, device, equipment and storage medium |
| CN113055745B (en) * | 2021-03-30 | 2023-05-16 | 脸萌有限公司 | Video playing processing method, device, equipment and storage medium |
| CN113395512A (en) * | 2021-05-27 | 2021-09-14 | 北京达佳互联信息技术有限公司 | Stuck detection method and device, stuck detection server and storage medium |
| CN113395512B (en) * | 2021-05-27 | 2023-02-28 | 北京达佳互联信息技术有限公司 | Stuck detection method and device, stuck detection server and storage medium |
| CN114401447A (en) * | 2021-12-20 | 2022-04-26 | 北京字节跳动网络技术有限公司 | Video stuck prediction method, device, equipment and medium |
| CN114079654A (en) * | 2022-01-05 | 2022-02-22 | 荣耀终端有限公司 | Data retransmission method, system and related device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110225417B (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110225417A (en) | Data processing method and server, the method and server that detect Caton | |
| CN105024872B (en) | The method and device of applied in network performance test | |
| US8122124B1 (en) | Monitoring performance and operation of data exchanges | |
| CN104410692B (en) | A kind of method and system uploaded for duplicate file | |
| CN101577631B (en) | Method, system and network device for evaluating experience quality of user | |
| CN110351198B (en) | Flow regulation method, data transmission system, storage medium and equipment | |
| CN106612284B (en) | Streaming data transmission method and device | |
| CN105072139B (en) | Recommend method and apparatus | |
| CN110046794A (en) | Appraisal procedure, device, computer equipment and the storage medium of network quality | |
| US20130007274A1 (en) | Method for Analyzing Browsing and Device for Implementing the Method | |
| US8868646B2 (en) | Apparatus and method for generating virtual game clients | |
| CN103902446A (en) | Network server automated testing method and device | |
| CN106202083A (en) | Resource packaging system, method and device for web page | |
| CN104702592A (en) | Method and device for downloading stream media | |
| CN110149299A (en) | A kind of method for optimizing video, device and system, terminal and the network equipment | |
| CN103974057A (en) | Video quality user experience value evaluation method, device and system | |
| Luo et al. | Design and Implementation of TCP Data Probes for Reliable and Metric-Rich Network Path Monitoring. | |
| CN109982068A (en) | Synthetic video method for evaluating quality, device, equipment and medium | |
| US20200274909A1 (en) | Method and apparatus for adaptive streaming based on hybrid tcp and udp in multiple narrowband wireless communication environment | |
| CN109257244A (en) | Transfer control method, the apparatus and system of user behavior data | |
| CN111147330A (en) | Network quality evaluation method and device, storage medium and processor | |
| US20030081560A1 (en) | Load test system for video data distributing server | |
| CN113676926B (en) | User network sensing portrait method and device | |
| CN103580951B (en) | Output comparative approach, test migration householder method and the system of multiple information systems | |
| CN108833530A (en) | A kind of transmission method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220610 |