CN105264907B - The Quality of experience prediction technique of mobile video business and base station - Google Patents
The Quality of experience prediction technique of mobile video business and base station Download PDFInfo
- Publication number
- CN105264907B CN105264907B CN201380003135.7A CN201380003135A CN105264907B CN 105264907 B CN105264907 B CN 105264907B CN 201380003135 A CN201380003135 A CN 201380003135A CN 105264907 B CN105264907 B CN 105264907B
- Authority
- CN
- China
- Prior art keywords
- epsnr
- video user
- base station
- prediction models
- emos
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/004—Diagnosis, testing or measuring for television systems or their details for digital television systems
-
- 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]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/24—Monitoring of processes or resources, e.g. monitoring of server load, available bandwidth, upstream requests
- H04N21/2402—Monitoring of the downstream path of the transmission network, e.g. bandwidth available
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Mobile Radio Communication Systems (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
Abstract
The embodiment of the present invention provides a kind of Quality of experience prediction technique of mobile video business and base station, this method include：Base station obtains the sides the wireless access network RAN parameter for the video user for needing to assess, according to the sides RAN parameter and enhancing Y-PSNR ePSNR prediction models, determine the enhancing Y-PSNR ePSNR for the video user for needing to assess, according to ePSNR and enhancing subjective testing score eMOS prediction models, the enhancing subjective testing score eMOS for the video user for needing to assess is determined.In this method, base station only once maps the sides the RAN parameter for the video user that needs are assessed, you can obtains the ePSNR of characterization video user QoE, realizes the more accurate prediction to video traffic QoE.
Description
Technical field
The present embodiments relate to mobile communication field more particularly to a kind of Quality of experience prediction sides of mobile video business
Method and base station.
Background technology
With video traffic explosive growth, people to the clarity of video, the continuity of broadcasting, anywhere or anytime may be used
Access property etc. require it is higher and higher, to attract more clients, network provider and service provider more concerned about user to moving
The Quality of experience of dynamic video traffic（Quality of Experience, QoE）, the QoE is by subjective testing score（Mean
Opinion Score, MOS）It embodies, MOS values are higher, indicate that QoE is bigger, user satisfaction is good.Wherein, MOS be by people come
Video is given a mark to obtain the average of a video, this marking test needs under stringent test environment, it then follows
Specific flow as defined in standard is realized, very high to environmental requirement, and flow is complicated, will not usually use.
In the prior art, the QoE of video is predicted by way of Quadratic Map.Specifically, by wireless access network
（Radio Access Network, RAN）Some parameters, such as Signal to Interference plus Noise Ratio（Single to Interference Plus
Noise Ratio, SINR）, time delay, the mappings such as user resources obtain some discrete, objective indexs such as packet loss, bandwidth,
Then those are discrete, objective index is mapped as the QoE of video.
However, having error due to mapping each time, the QoE errors obtained above by Quadratic Map are larger, with reality
The quality of service gap that user experiences is larger.
Invention content
The embodiment of the present invention provides Quality of experience prediction technique and the base station of a kind of mobile video business, passes through direct basis
The sides RAN parameter prediction goes out the QoE of video traffic, realizes the accurate prediction to video traffic QoE.
The first aspect, the embodiment of the present invention provide a kind of Quality of experience prediction technique of mobile video business, including：
Base station obtains the sides the wireless access network RAN parameter for the video user for needing to assess, and the sides RAN parameter includes：Institute
The Signal to Interference plus Noise Ratio SINR for stating the video user for needing to assess, in the cell for needing the video user assessed to provide service
The number NU, the time delay T for needing the video user assessed on security gateway interface SGi of video user；
The base station determines that the needs are commented according to the sides RAN parameter and enhancing Y-PSNR ePSNR prediction models
The enhancing Y-PSNR ePSNR for the video user estimated；
The base station determines according to the ePSNR and enhancing subjective testing score eMOS prediction models and described needs to assess
Video user enhancing subjective testing score eMOS.
In the possible realization method of in the first aspect the first, the base station is according to the sides RAN parameter and enhancing
Y-PSNR ePSNR prediction models, before determining the enhancing Y-PSNR ePSNR of video user for needing to assess,
Further include：
The base station determines the ePSNR prediction models, the ePSNR predictions according to Sample video user and system configuration
Model is：Wherein, a, b, c, d are so that the Sample video user is according to described
One group of parameter of the ePSNR that ePSNR prediction models obtain and the actual ePSNR correlation maximums of the Sample video user.
In conjunction with the possible realization method of the first of the first aspect or the first aspect, in the first aspect second
In possible realization method, the base station is according to the ePSNR and enhances subjective testing score eMOS prediction models, described in determination
Before the enhancing subjective testing score eMOS for needing the video user assessed, further include：
The base station determines that the eMOS prediction models, the eMOS prediction models are according to Sample video user：eMOS
=e × ePSNR+f, wherein e, f are the subjective testing point of the ePSNR to the Sample video user and the Sample video user
Number MOS carries out what once linear regression fit obtained.
In conjunction with second of possible realization method of the first aspect, the third possible realization side in the first aspect
In formula, when system bandwidth is 10MHZ, a pico- base station pico is arranged in each cell of the base station, a=1.4, b=
112.25, c=6.71, d=6.70.
In conjunction with second of the first aspect or the third possible realization method, the 4th kind of possibility in the first aspect
Realization method in, e=0.34, f=4.1.
The second aspect, the embodiment of the present invention provide a kind of base station, including：
Acquisition module, the sides the wireless access network RAN parameter for obtaining the video user for needing to assess, the sides the RAN ginseng
Number includes：The Signal to Interference plus Noise Ratio SINR of the video user for needing to assess needs the video user assessed to provide service to be described
Cell in video user number NU, the time delay T for needing the video user assessed on security gateway interface SGi；
First determining module, the sides the RAN parameter for being got according to the acquisition module and enhancing peak value noise
Than ePSNR prediction model, the enhancing Y-PSNR ePSNR of the video user for needing to assess is determined；
Second determining module, the ePSNR for being determined according to first determining module and enhancing subjective testing
Score eMOS prediction models determine the enhancing subjective testing score eMOS of the video user for needing to assess.
In the possible realization method of in the second aspect the first, the base station further includes：
Third determining module, it is described for determining the ePSNR prediction models according to Sample video user and system configuration
EPSNR prediction models are：Wherein, a, b, c, d are so that the Sample video is used
The ePSNR and the one of the actual ePSNR correlation maximums of the Sample video user that family is obtained according to the ePSNR prediction models
Group parameter.
In conjunction with the possible realization method of the first of the second aspect or the second aspect, in the second aspect second
In possible realization method, the base station further includes：
4th determining module, for according to Sample video user, determining that the eMOS prediction models, the eMOS predict mould
Type is：EMOS=e × ePSNR+f, wherein e, f are to the ePSNR of the Sample video user with the Sample video user's
Subjective testing score MOS carries out what once linear regression fit obtained.
In conjunction with second of possible realization method of the second aspect, the third possible realization side in the second aspect
In formula, when system bandwidth is 10MHZ, a pico- base station pico is arranged in each cell of the base station, a=1.4, b=
112.25, c=6.71, d=6.70.
In conjunction with second of the second aspect or the third possible realization method, the 4th kind of possibility in the second aspect
Realization method in, e=0.34, f=4.1.
In terms of third, the embodiment of the present invention provides a kind of base station, including：Processor and memory, the memory are deposited
Storage executes instruction, and when the base station is run, is communicated between the processor and the memory, described in the processor execution
It executes instruction, obtains the sides the wireless access network RAN parameter for the video user for needing to assess, the sides RAN parameter includes：The need
The Signal to Interference plus Noise Ratio SINR of the video user to be assessed, for the video in the cell for needing the video user assessed to provide service
The number NU, the time delay T for needing the video user assessed on security gateway interface SGi of user；
According to the sides RAN parameter and enhancing Y-PSNR ePSNR prediction models, the video for needing to assess is determined
The enhancing Y-PSNR ePSNR of user；
According to the ePSNR and enhancing subjective testing score eMOS prediction models, determine that the video that the needs are assessed is used
The enhancing subjective testing score eMOS at family.
In the first possible realization method in terms of third, the processor is additionally operable to be used according to Sample video
Family determines that the ePSNR prediction models, the ePSNR prediction models are with system configuration：Wherein, a, b, c, d are so that the Sample video user is pre- according to the ePSNR
Survey one group of parameter of ePSNR and the actual ePSNR correlation maximums of the Sample video user that model obtains.
In conjunction with the first possible realization method in terms of third aspect or third, at second of third aspect
In possible realization method, the processor is additionally operable to, according to Sample video user, determine the eMOS prediction models, described
EMOS prediction models are：EMOS=e × ePSNR+f, wherein e, f are the ePSNR and the sample to the Sample video user
The subjective testing score MOS of video user carries out what once linear regression fit obtained.
In conjunction with second of possible realization method in terms of third, the third possible realization side in terms of third
In formula, when system bandwidth is 10MHZ, a pico- base station pico is arranged in each cell of the base station, a=1.4, b=
112.25, c=6.71, d=6.70.
In conjunction with second or the third possible realization method in terms of third, the 4th kind of possibility in terms of third
Realization method in, e=0.34, f=4.1.
The Quality of experience prediction technique of mobile video business provided in an embodiment of the present invention and base station, base station get needs
After the sides the RAN parameter of the video user of assessment, the sides RAN parameter is directly mapped as to the ePSNR of video user, then according to eMOS
Prediction model determines eMOS, so that it is determined that going out the QoE of the video user of needs assessment.The experience of the mobile video business
During prediction of quality, base station only once maps the sides the RAN parameter for the video user that needs are assessed, you can is characterized
The ePSNR of video user QoE realizes the more accurate prediction to video traffic QoE.
Description of the drawings
Fig. 1 is the flow chart of the Quality of experience prediction technique embodiment one of mobile video business of the present invention；
Fig. 2 is the structural schematic diagram of HAS videos of the present invention；
Fig. 3 is the transfer process schematic diagram of HAS videos of the present invention；
Fig. 4 be mobile video business of the present invention Quality of experience prediction technique embodiment two in subjective testing MOS points and
The matched curve figure of SINR；
Fig. 5 be mobile video business of the present invention Quality of experience prediction technique embodiment two in subjective testing MOS divide with it is small
The matched curve figure of area's number of users；
Fig. 6 be mobile video business of the present invention Quality of experience prediction technique embodiment two in subjective testing MOS divide and when
Prolong the matched curve figure of T；
Fig. 7 is the structural schematic diagram of base station embodiment one of the present invention；
Fig. 8 is the structural schematic diagram of base station embodiment two of the present invention；
Fig. 9 is the structural schematic diagram of base station embodiment three of the present invention.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
The every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Fig. 1 is the flow chart of the Quality of experience prediction technique embodiment one of mobile video business of the present invention.The present embodiment
Executive agent is base station, is applicable to the scene accurately predicted video traffic QoE.Specifically, the present embodiment includes
Following steps：
101, base station obtains the sides the wireless access network RAN parameter for the video user for needing to assess, and the sides RAN parameter includes：It needs
The Signal to Interference plus Noise Ratio SINR of the video user to be assessed, to need the video user assessed to provide the video user in the cell of service
Number NU, need time delay T of the video user assessed on security gateway interface SGi.
The base station sides RAN factor needed to be considered mainly has：Need the SINR of video user assessed, community user number, i.e.,
To need, the video user assessed provides the number NU of video user in the cell of service and the video of needs assessment is used
Time delay T of the family on security gateway interface SGi.In this step, base station can pass through user equipment（User Equipment, UE）'s
The modes such as mechanism are reported, the video user SINR for needing to assess are obtained, simultaneously as base station knows the letter of all cells of subordinate
Breath, therefore, base station can obtain for need the video user assessed provide the number NU of video user in the cell of service with
And time delay T of the video user of needs assessment on security gateway interface SGi.
102, base station determines the video for needing to assess according to the sides RAN parameter and enhancing Y-PSNR ePSNR prediction models
The enhancing Y-PSNR ePSNR of user.
In general, video be by many group of picture at, PSNR is the objective standard of image quality evaluation.Therefore,
The method of the image objective evaluation can be applied to is in video traffic, for example, in the prior art can be with by Quadratic Map
The PSNR of video user.For describe it is clear for the sake of, compared to the prior art in the PSNR that is obtained by Quadratic Map, and then obtain
Subjective testing score, the PSNR that will be directly mapped below by the sides RAN parameter in the embodiment of the present invention is referred to as to enhance
Y-PSNR ePSNR, and then be referred to as to enhance subjective testing score eMOS according to the subjective testing score that the ePSNR is obtained.
In this step, base station determines according to the sides the RAN parameter and ePSNR prediction models got and needs that assesses to regard
The ePSNR of frequency user.Wherein, ePSNR prediction models can be the subjective testing score and sample according to Sample video user in advance
What the RAN parameter fittings of video obtained, Sample video user is, for example, to be in identical or phase with the video user assessed is needed
As network environment video user, i.e. Sample video user is, for example, to be with need network residing for the video user assessed
It is under unified central planning set it is identical.The subjective testing score of each Sample video user is the essence given a mark to the Sample video by people
Really value.
103, base station determines that the video for needing to assess is used according to ePSNR and enhancing subjective testing score eMOS prediction models
The enhancing subjective testing score eMOS at family.
After the ePSNR for the video user for determining to need to assess, base station can be according to the ePSNR and enhancing subjective testing
Score eMOS prediction models determine the enhancing subjective testing score eMOS for the video user for needing to assess.Wherein, eMOS predicts mould
Type can carry out once linear by the subjective testing score MOS of ePSNR and Sample video user to Sample video user in advance
Regression fit obtains.For example, can be by next generation mobile communication network（Next Generation Mobile Netwoks, NGMN）
A certain number of video users are provided as Sample video user, determine those Sample videos user's according to step 102
EPSNR, then to subjective testing score known to those Sample videos user and the ePSNR that determines into being fitted under line, to
Determine eMOS prediction models.
The Quality of experience prediction technique of mobile video business provided in an embodiment of the present invention gets the video for needing to assess
After the sides the RAN parameter of user, the sides RAN parameter is directly mapped as to the ePSNR of video user, then according to eMOS prediction models,
EMOS is determined, so that it is determined that going out the QoE of the video user of needs assessment.The Quality of experience of the mobile video business was predicted
Cheng Zhong, base station only once map the sides the RAN parameter for the video user that needs are assessed, you can obtain characterization video user
The ePSNR of QoE realizes the more accurate prediction to video traffic QoE.
In the following, with Sample video user for HTTP adaptive stream medias（HTTP Adaptive Streaming, HAS）Depending on
For frequency is made good use of, to, how according to Sample video user and system configuration etc., determining that ePSNR is predicted in the embodiment of the present invention one
Model is described in detail with eMOS prediction models.
Fig. 2 is the structural schematic diagram of HAS videos of the present invention.HAS video traffics can be by a complete information source Video coding
At the video of several different code checks, and the video of each code check is segmented, for example, asking phase according to current channel condition
The video segmentation of code rate.
Fig. 2 is please referred to, HAS videos can be one, and there is M kinds code check, each code check to be divided into N number of segmentation
The information source video of M3U8 formats, wherein M is maximal rate.Transmitting terminal for each code check video, generate one it is corresponding
M3U8 files contain the uniform resource locator that phase code rate is each segmented in this document（Uniform Resource
The address Locator, URL）.Moreover, sender generates a total M3U8 file, which saves each
The address of the corresponding M3U8 files of code check.Receiving terminal downloads main M3U8 files and each code check pair first before playing video
Then the M3U8 files answered are downloaded the first video segment and are played out, in playing process, under receiving terminal meeting basis is current
It carries situation and determines next segmentation should ask the segmentation of what code check, and according to the M3U8 files of code check to be asked, to transmission
The corresponding segmentation of end request.Such as the time used in current one segmentation of download is very short, it was demonstrated that current channel condition is good, then under
The current code check of a ratio higher segmentation should be asked when carrying next segmentation.The video eventually received due to recipient
It is the combination of different code check segmentations, has deviation compared to original video, that is, video impairment occurs.It is specific as shown in Figure 3.
Fig. 3 is the transfer process schematic diagram of HAS videos of the present invention.It is divided into the video that maximal rate is 3, each code check
For 4 segmentations, Fig. 3 is please referred to：1st code check, as shown in the filling of figure bend；2nd code check, as shown in the filling of figure medium square；
3rd code check, as shown in vertical line filling in figure.
Fig. 3 is please referred to, direction sender is received and sends HTTP acquisition requests（HTTP GET）, sender is by network to connecing
Debit's transmission data, i.e. HAS videos.Due to by handling capacity（Throughput）Deng limitation, sender can not will be entire
Source HAS videos are sent to recipient, but only by the segmentation of request（Request Segments）, i.e., the as illustrated in the drawing the 1st
1st segmentation of code check, the 2nd, 4,5 segmentations of the 2nd code check and the 3rd segmentation of the 3rd code check are sent to recipient.Thus,
The HAS videos that recipient receives just are damaged.
In the embodiment of the present invention, base station determines ePSNR prediction models according to Sample video user and system configuration in advance,
EPSNR prediction models are：
Wherein, a, b, c, d are so that the ePSNR and Sample video that Sample video user obtains according to ePSNR prediction models
One group of parameter of the actual ePSNR correlation maximums of user.For example, in advance by next generation mobile communication network（Next
Generation Mobile Netwoks, NGMN）A certain number of video users are provided as Sample video user, according to biography
System method determines actual ePSNR, and the RAN parameters of the subjective testing score and Sample video to those Sample videos user
It is fitted obtained ePSNR prediction models.
After the prediction model for determining ePSNR, to the subjective testing of the ePSNR and Sample video user of Sample video user
Score MOS carries out once linear regression fit, obtains eMOS prediction models：
eMOS=e×ePSNR+f（2）.
Wherein, into formula is brought those coefficients in e=0.34, f=4.1（2）It can obtain：
eMOS=0.34×ePSNR+4.1（3）.
After obtaining above-mentioned ePSNR prediction models and eMOS prediction models, configures, determine for different LTE systems
Undetermined coefficient a, b, c, d.By taking system bandwidth is 10MHZ, a pico- base station pico is arranged in each cell of base station as an example, pass through
A=1.4, b=112.25, c=6.71, d=6.70 can be obtained in emulation.Bring those coefficients into formula（1）It can obtain：
By formula（5）Bring formula into（3）It can obtain：
It is 10MHZ for system bandwidth, the system configuration of one pico- base station pico of each cell setting of base station, true
Make prediction model, i.e. above-mentioned formula（6）Afterwards, for the video user of any needs assessment under the system configuration scene, base
The sides the RAN parameter for the video user for obtaining needs assessment of standing, i.e. SINR, the video user assessed for needs provide the small of service
The time delay T of the number NU of video user in area and the video user of needs assessment on security gateway interface SGi, according to
Three parameters and formula（6）QoE can accurately be evaluated.
It should be noted that above-mentioned formula（1）In undetermined coefficient, i.e. a, b, c, d have not for different system configurations
Same value, and above-mentioned formula（2）In undetermined coefficient, i.e. in general e, f are that will not occur with the difference of system configuration
Variation.
In the following, under simulated environment, by being fitted the phase relation obtained to each sides RAN parameter and subjective testing point
Number, determines the correctness of the Quality of experience prediction technique of mobile video business provided in an embodiment of the present invention.
Fig. 4 be mobile video business of the present invention Quality of experience prediction technique embodiment two in subjective testing MOS points and
The matched curve figure of SINR.
Fig. 4 is please referred to, in the present embodiment, to need the video user assessed to provide video user in the cell of service
Number NU is specially 5, and it is specially 20ms to need time delay T of the video user assessed on security gateway interface SGi, and abscissa is
SINR, ordinate are MOS points of subjective testing, and the experimental data of scatterplot is, as NU=5, T=20ms, to lead to according in the prior art
Cross MOS points of subjective testing under the different SINR that Quadratic Map mode is determined；Solid line is in the present invention, as NU=5, T=20ms
When, by this according to formula（6）MOS points of subjective testing under the different SINR determined.Through emulating it is found that experimental data and reality
The linearly dependent coefficient of line, i.e. Pearson correlation coefficients (Pearson correlation coefficient, PCC) are
0.9571.It follows that according to formula（6）QoE can accurately be evaluated.
Fig. 5 be mobile video business of the present invention Quality of experience prediction technique embodiment two in subjective testing MOS divide with it is small
The matched curve figure of area's number of users.
Please refer to Fig. 5, in the present embodiment, it is specially 7dB to need the SINR for the video user assessed, and needs the video assessed
Time delay T of the user on security gateway interface SGi is specially 20ms, and abscissa is community user number, as needs that assesses to regard
Frequency user provides the number NU of the video user in the cell of service, and ordinate is MOS points of subjective testing, the experimental data of scatterplot
In the prior art for basis, as SINR=5, T=20ms, under the different community number of users NU determined by Quadratic Map mode
Subjective testing MOS points；Solid line is in the present invention, as SINR=5, T=20ms, by this according to formula（6）It determines not
With MOS points of subjective testing under community user number NU.Through emulation it is found that the linearly dependent coefficient of experimental data and solid line, i.e. skin
Ademilson related coefficient (Pearson correlation coefficient, PCC) is 0.9535.It follows that according to formula
（6）QoE can accurately be evaluated.
Fig. 6 be mobile video business of the present invention Quality of experience prediction technique embodiment two in subjective testing MOS divide and when
Prolong the matched curve figure of T.
Fig. 6 is please referred to, in the present embodiment, to need the video user assessed to provide video user in the cell of service
Number NU is specially 5, and it is specially 7dB to need the SINR for the video user assessed, and abscissa is time delay T, is observed based on ordinate
MOS points are tried, the experimental data of scatterplot is, as NU=5, SINR=7dB, to be determined by Quadratic Map mode according in the prior art
MOS points of subjective testing under the different delay T gone out；Solid line is in the present invention, as NU=5, SINR=7dB, by this according to public affairs
Formula（6）MOS points of subjective testing under the different delay T determined.Through emulation it is found that the linearly related system of experimental data and solid line
Number, i.e. Pearson correlation coefficients (Pearson correlation coefficient, PCC) are 0.9504.It follows that root
According to formula（6）QoE can accurately be evaluated.
Fig. 7 is the structural schematic diagram of base station embodiment one of the present invention, and base station provided in this embodiment is and Fig. 1 of the present invention realities
The corresponding device embodiment of example is applied, details are not described herein for specific implementation process.Specifically, base station 100 provided in this embodiment has
Body includes：
Acquisition module 11, the sides the wireless access network RAN parameter for obtaining the video user for needing to assess, the sides RAN parameter
Including：The Signal to Interference plus Noise Ratio SINR for needing the video user assessed, to need in the cell that the video user assessed provides service
The number NU of video user needs time delay T of the video user assessed on security gateway interface SGi；
First determining module 12, the sides the RAN parameter for being got according to acquisition module 11 and enhancing Y-PSNR
EPSNR prediction models determine the enhancing Y-PSNR ePSNR for the video user for needing to assess；
Second determining module 13, the ePSNR for being determined according to the first determining module 12 and enhancing subjective testing score
EMOS prediction models determine the enhancing subjective testing score eMOS for the video user for needing to assess.
Base station provided in an embodiment of the present invention, after getting the sides the RAN parameter of video user for needing to assess, direct general
The ePSNR that the sides RAN parameter is mapped as video user determines eMOS then according to eMOS prediction models, so that it is determined that going out the need
The QoE of the video user to be assessed.During the Quality of experience prediction of the mobile video business, base station is to the video assessed of needs
The sides the RAN parameter of user is only once mapped, you can is obtained the ePSNR of characterization video user QoE, is realized to video traffic
The more accurate prediction of QoE.
Fig. 8 is the structural schematic diagram of base station embodiment two of the present invention.As shown in figure 8, the base station 200 of the present embodiment is in Fig. 9
On the basis of apparatus structure, further, further include：
Third determining module 14, for determining ePSNR prediction models, ePSNR according to Sample video user and system configuration
Prediction model is：Wherein, a, b, c, d be so that Sample video user according to
One group of parameter of ePSNR and the actual ePSNR correlation maximums of Sample video user that ePSNR prediction models obtain.
Fig. 8 is please referred to again, and base station 200 further includes：
4th determining module 15, for according to Sample video user, determining that eMOS prediction models, eMOS prediction models are：
EMOS=e × ePSNR+f, wherein e, f are the subjective testing score to the ePSNR and Sample video user of Sample video user
MOS carries out what once linear regression fit obtained.
Further, when system bandwidth is 10MHZ, a pico- base station pico is arranged in each cell of base station, a=
1.4, b=112.25, c=6.71, d=6.70.
Further, e=0.34, f=4.1.
Fig. 9 is the structural schematic diagram of base station embodiment three of the present invention.As shown in figure 9, base station 300 provided in this embodiment is wrapped
It includes：At least one bus 31, at least one processor 32 being connected with bus 31 and what is be connected with bus 31 at least one deposit
Reservoir 33, wherein processor 32 calls the code stored in memory 33 by bus 31, for：Obtain what needs were assessed
The sides the wireless access network RAN parameter of video user, the sides RAN parameter include：The Signal to Interference plus Noise Ratio SINR for the video user assessed is needed,
To need the video user assessed to provide the number NU of the video user in the cell of service, the video user assessed is needed to pacify
Time delay T on full gateway interface SGi；According to the sides RAN parameter and enhancing Y-PSNR ePSNR prediction models, determines and need to comment
The enhancing Y-PSNR ePSNR for the video user estimated；According to ePSNR and enhancing subjective testing score eMOS prediction models, really
The enhancing subjective testing score eMOS for the video user assessed is needed calmly.
In one embodiment, processor 32 are additionally operable to determine that ePSNR is predicted according to Sample video user and system configuration
Model, ePSNR prediction models are：Wherein, a, b, c, d are so that Sample video is used
The one group of parameter for the ePSNR and the actual ePSNR correlation maximums of Sample video user that family is obtained according to ePSNR prediction models.
In one embodiment, processor 32 are additionally operable to, according to Sample video user, determine eMOS prediction models, eMOS
Prediction model is：EMOS=e × ePSNR+f, wherein e, f are the master to the ePSNR and Sample video user of Sample video user
It sees test result MOS and carries out what once linear regression fit obtained.
In one embodiment, when system bandwidth is 10MHZ, a pico- base station pico is arranged in each cell of base station
When, a=1.4, b=112.25, c=6.71, d=6.70.
In one embodiment, e=0.34, f=4.1.
One of ordinary skill in the art will appreciate that：Realize that all or part of step of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer read/write memory medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed；And storage medium above-mentioned includes：ROM, RAM, magnetic disc or light
The various media that can store program code such as disk.
Finally it should be noted that：The above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Present invention has been described in detail with reference to the aforementioned embodiments for pipe, it will be understood by those of ordinary skill in the art that：Its according to
So can with technical scheme described in the above embodiments is modified, either to which part or all technical features into
Row equivalent replacement；And these modifications or replacements, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (15)
1. a kind of Quality of experience prediction technique of mobile video business, which is characterized in that including：
Base station obtains the sides the wireless access network RAN parameter for the video user for needing to assess, and the sides RAN parameter includes：The need
The Signal to Interference plus Noise Ratio SINR of the video user to be assessed, for the video in the cell for needing the video user assessed to provide service
The number NU, the time delay T for needing the video user assessed on security gateway interface SGi of user；
The base station determines what the needs were assessed according to the sides RAN parameter and enhancing Y-PSNR ePSNR prediction models
The enhancing Y-PSNR ePSNR of video user；
The base station according to the ePSNR with enhancing subjective testing score eMOS prediction models, determine it is described need assess regard
The enhancing subjective testing score eMOS of frequency user.
2. according to the method described in claim 1, it is characterized in that, the base station is according to the sides RAN parameter and enhancing peak value
Signal-to-noise ratio ePSNR prediction models also wrap before determining the enhancing Y-PSNR ePSNR of video user for needing to assess
It includes：
The base station determines the ePSNR prediction models, the ePSNR prediction models according to Sample video user and system configuration
For：Wherein, a, b, c, d are so that the Sample video user is according to the ePSNR
One group of parameter of ePSNR and the actual ePSNR correlation maximums of the Sample video user that prediction model obtains.
3. according to the method described in claim 2, it is characterized in that, the base station is according to the ePSNR and enhancing subjective testing
Score eMOS prediction models further include before determining the enhancing subjective testing score eMOS of video user for needing to assess：
The base station determines that the eMOS prediction models, the eMOS prediction models are according to Sample video user：EMOS=e
× ePSNR+f, wherein e, f are the subjective testing score to the ePSNR and the Sample video user of the Sample video user
MOS carries out what once linear regression fit obtained.
4. according to the method described in claim 3, it is characterized in that,
When system bandwidth is 10MHZ, a pico- base station pico is arranged in each cell of the base station, a=1.4, b=
112.25 c=6.71, d=6.70.
5. according to the method described in claim 4, it is characterized in that, the e=0.34, the f=4.1.
6. a kind of base station, which is characterized in that including：
Acquisition module, the sides the wireless access network RAN parameter for obtaining the video user for needing to assess, the sides the RAN parameter packet
It includes：The Signal to Interference plus Noise Ratio SINR of the video user for needing to assess needs the video user assessed to provide the small of service to be described
The number NU, the time delay T for needing the video user assessed on security gateway interface SGi of video user in area；
First determining module, the sides the RAN parameter for being got according to the acquisition module and enhancing Y-PSNR
EPSNR prediction models determine the enhancing Y-PSNR ePSNR of the video user for needing to assess；
Second determining module, the ePSNR for being determined according to first determining module and enhancing subjective testing score
EMOS prediction models determine the enhancing subjective testing score eMOS of the video user for needing to assess.
7. base station according to claim 6, which is characterized in that the base station further includes：
Third determining module, it is described for determining the ePSNR prediction models according to Sample video user and system configuration
EPSNR prediction models are：Wherein, a, b, c, d are so that the Sample video user
One group of the ePSNR and the actual ePSNR correlation maximums of the Sample video user that are obtained according to the ePSNR prediction models
Parameter.
8. base station according to claim 7, which is characterized in that the base station further includes：
4th determining module, for according to Sample video user, determining the eMOS prediction models, the eMOS prediction models
For：EMOS=e × ePSNR+f, wherein e, f are the master to the ePSNR and the Sample video user of the Sample video user
It sees test result MOS and carries out what once linear regression fit obtained.
9. base station according to claim 8, which is characterized in that
When system bandwidth is 10MHZ, a pico- base station pico is arranged in each cell of the base station, a=1.4, b=
112.25 c=6.71, d=6.70.
10. base station according to claim 9, which is characterized in that the e=0.34, the f=4.1.
11. a kind of base station, which is characterized in that including：Processor and memory, the memory storage executes instruction, when described
It when base station is run, is communicated between the processor and the memory, is executed instruction described in the processor execution, obtain and need
The sides the wireless access network RAN parameter of the video user of assessment, the sides RAN parameter include：The video user for needing to assess
Signal to Interference plus Noise Ratio SINR, for the number NU of the video user in the cell for needing the video user assessed to provide service, institute
State the time delay T for needing the video user assessed on security gateway interface SGi；
According to the sides RAN parameter and enhancing Y-PSNR ePSNR prediction models, the video user for needing to assess is determined
Enhancing Y-PSNR ePSNR；
According to the ePSNR and enhancing subjective testing score eMOS prediction models, the video user for needing to assess is determined
Enhance subjective testing score eMOS.
12. base station according to claim 11, which is characterized in that
The processor is additionally operable to determine the ePSNR prediction models according to Sample video user and system configuration, described
EPSNR prediction models are：Wherein, a, b, c, d are so that the Sample video user
One group of the ePSNR and the actual ePSNR correlation maximums of the Sample video user that are obtained according to the ePSNR prediction models
Parameter.
13. base station according to claim 12, which is characterized in that
The processor is additionally operable to, according to Sample video user, determine the eMOS prediction models, the eMOS prediction models
For：EMOS=e × ePSNR+f, wherein e, f are the master to the ePSNR and the Sample video user of the Sample video user
It sees test result MOS and carries out what once linear regression fit obtained.
14. base station according to claim 13, which is characterized in that
When system bandwidth is 10MHZ, a pico- base station pico is arranged in each cell of the base station, a=1.4, b=
112.25 c=6.71, d=6.70.
15. base station according to claim 14, which is characterized in that
The e=0.34, the f=4.1.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2013/090962 WO2015100560A1 (en) | 2013-12-30 | 2013-12-30 | Method for predicting quality of experience of mobile video service, and base station |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105264907A CN105264907A (en) | 2016-01-20 |
| CN105264907B true CN105264907B (en) | 2018-08-21 |
Family
ID=53492919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201380003135.7A Active CN105264907B (en) | 2013-12-30 | 2013-12-30 | The Quality of experience prediction technique of mobile video business and base station |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105264907B (en) |
| WO (1) | WO2015100560A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109921941A (en) * | 2019-03-18 | 2019-06-21 | 腾讯科技（深圳）有限公司 | Network servicequality evaluates and optimizes method, apparatus, medium and electronic equipment |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107509121B (en) * | 2016-06-14 | 2020-06-02 | 华为技术有限公司 | Method and device for determining video quality and method and device for positioning network fault |
| CN106998322B (en) * | 2017-02-20 | 2020-04-14 | 南京邮电大学 | Stream classification method using mean opinion averaging feature of video service |
| CN107733705B (en) * | 2017-10-10 | 2021-01-15 | 锐捷网络股份有限公司 | User experience quality assessment model establishing method and device |
| CN112383828B (en) * | 2019-12-12 | 2023-04-25 | 致讯科技(天津)有限公司 | Quality of experience prediction method, equipment and system with brain-like characteristics |
| CN112636976B (en) * | 2020-12-23 | 2022-11-22 | 武汉船舶通信研究所（中国船舶重工集团公司第七二二研究所） | Service quality determination method, device, electronic equipment and storage medium |
| CN115884195A (en) * | 2021-09-28 | 2023-03-31 | 中兴通讯股份有限公司 | Model training method, wireless resource scheduling method and device and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102638730A (en) * | 2012-04-13 | 2012-08-15 | 北京邮电大学 | User perception based cross-layer optimization method for wireless video business |
| CN103152599A (en) * | 2013-02-01 | 2013-06-12 | 浙江大学 | Mobile video service user experience quality evaluation method based on ordinal regression |
| CN103733595A (en) * | 2011-04-07 | 2014-04-16 | 交互数字专利控股公司 | Method and apparatus for local data caching |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8385221B2 (en) * | 2010-02-28 | 2013-02-26 | International Business Machines Corporation | System and method for monitoring of user quality-of-experience on a wireless network |
-
2013
- 2013-12-30 CN CN201380003135.7A patent/CN105264907B/en active Active
- 2013-12-30 WO PCT/CN2013/090962 patent/WO2015100560A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103733595A (en) * | 2011-04-07 | 2014-04-16 | 交互数字专利控股公司 | Method and apparatus for local data caching |
| CN102638730A (en) * | 2012-04-13 | 2012-08-15 | 北京邮电大学 | User perception based cross-layer optimization method for wireless video business |
| CN103152599A (en) * | 2013-02-01 | 2013-06-12 | 浙江大学 | Mobile video service user experience quality evaluation method based on ordinal regression |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109921941A (en) * | 2019-03-18 | 2019-06-21 | 腾讯科技（深圳）有限公司 | Network servicequality evaluates and optimizes method, apparatus, medium and electronic equipment |
| CN109921941B (en) * | 2019-03-18 | 2021-09-17 | 腾讯科技（深圳）有限公司 | Network service quality evaluation and optimization method, device, medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105264907A (en) | 2016-01-20 |
| WO2015100560A1 (en) | 2015-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105264907B (en) | The Quality of experience prediction technique of mobile video business and base station | |
| Wamser et al. | Modeling the YouTube stack: From packets to quality of experience | |
| CN102801690B (en) | The processing method of Streaming Media, Distributor, client and system | |
| CA2878327C (en) | Methods for quality-aware adaptive streaming over hypertext transfer protocol | |
| EP2700267B1 (en) | Full-reference computation of mobile content quality of experience in real-time | |
| US8737243B2 (en) | Methods and apparatus for monitoring network link quality | |
| CN105897769B (en) | Method and server for streaming content | |
| CN105830415B (en) | Method, Wireless Telecom Equipment and base station equipment for managing Media Stream | |
| CN101237687B (en) | Method for automatic generation of network element deployment parameters | |
| US10230590B2 (en) | Performance metric of a system conveying web content | |
| Schwind et al. | Dissecting the performance of YouTube video streaming in mobile networks | |
| Giannone et al. | Orchestrating heterogeneous MEC-based applications for connected vehicles | |
| CN103974057A (en) | Video quality user experience value evaluation method, device and system | |
| Taha et al. | An automated model for the assessment of QoE of adaptive video streaming over wireless networks | |
| KR101718127B1 (en) | Content packaging system and streaming method for context aware streaming service | |
| CN102136948B (en) | Method, terminal equipment and system for counting user experiences | |
| CN104471904A (en) | Content optimization based on real time network dynamics | |
| CN103402122A (en) | Control method and device for mobile streaming media service | |
| CN104244334B (en) | A kind of method and apparatus for determining network service quality | |
| Du et al. | Lte-emu: A high fidelity lte cellar network testbed for mobile video streaming | |
| Yetgin et al. | Quality of experience prediction model for progressive downloading over mobile broadcast networks | |
| Lopes et al. | A multi-layer probing approach for video over 5G in vehicular scenarios | |
| KR101937449B1 (en) | Method and apparatus for providing adaptively video service | |
| CN109121073B (en) | Method, device and equipment for monitoring quality of mobile communication service | |
| Baraković Husić et al. | Subjective and objective QoE measurement for H. 265/HEVC video streaming over LTE |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211224 Address after: 450046 Floor 9, building 1, Zhengshang Boya Plaza, Longzihu wisdom Island, Zhengdong New Area, Zhengzhou City, Henan Province Patentee after: Super fusion Digital Technology Co.,Ltd. Address before: 518129 Bantian HUAWEI headquarters office building, Longgang District, Guangdong, Shenzhen Patentee before: HUAWEI TECHNOLOGIES Co.,Ltd. |
|
| TR01 | Transfer of patent right |