CN103152599A - Mobile video service user experience quality evaluation method based on ordinal regression - Google Patents
Mobile video service user experience quality evaluation method based on ordinal regression Download PDFInfo
- Publication number
- CN103152599A CN103152599A CN2013100450691A CN201310045069A CN103152599A CN 103152599 A CN103152599 A CN 103152599A CN 2013100450691 A CN2013100450691 A CN 2013100450691A CN 201310045069 A CN201310045069 A CN 201310045069A CN 103152599 A CN103152599 A CN 103152599A
- Authority
- CN
- China
- Prior art keywords
- qoe
- mobile video
- grade
- user
- video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention relates to a mobile video service user experience quality evaluation method based on ordinal regression. The method comprises the steps of firstly, regarding a mobile video service as a research object, identifying end-to-end cross-layer performance indexes which influences user experience quality, secondly, arranging network environment with the various mobile video performance indexes, recording mean opinion score (MOS) values of user view mobile video experience quality corresponding to the various indexes, then, achieving quality of experience (QoE) evaluation of the mobile video service by an ordinal regression model, and finally identifying the user experience quality by building the ordinal regression model and solving the QoE level with the largest probability. The mobile video service user experience quality evaluation method based on the ordinal regression combines the performance indexes of the mobile video service with user subjective feeling, and is capable of accurately evaluating the user experience quality based on the ordinal regression model, realistic and effective.
Description
Technical field
The present invention relates to the mobile communication technology field, relate in particular to a kind of mobile video service-user Quality of experience appraisal procedure based on ordinal regression.
Background technology
Along with developing rapidly of multimedia communication technology and video compression technology, various Video Applications are people's life extensively and profoundly.In the video traffic application popularization, the user also has higher requirement to the quality of mobile video business, and the user has become to the degree of recognition Important Problems that Virtual network operator and service provider are concerned about.Fierce market competition is recognized Virtual network operator and service provider, improves terminal use's satisfaction, be keep the user here, the scale that extends one's service and the final key point that realizes profit.Therefore, to how weighing the user to the satisfaction of mobile video business, and guaranteeing that the service that provides can access user's approval, is a problem in the urgent need to address.
Service quality (Quality of Service, QoS) is a kind of traditional business service module, and the QoS evaluation index mainly comprises throughput, time delay, delay variation, packet loss, the error rate of network etc.Although these indexs can reflect the performance of service technology aspect or Internet Transmission aspect, they have ignored the factor of user's subjective feeling, so these indexs can not reflect directly that the user is to the degree of recognition of service.Therefore, standardization body of International Telecommunications Union has defined the index of weighing user's subjective feeling, be user experience quality (Quality of Experience, QoE), it refers to " being used or the overall acceptable degree of business by terminal use institute perception a kind of ".QoE is a kind of service quality assessment method take the customer acceptance degree as standard, and it combines the influencing factor of service layer, user level, network level, environment aspect, has effectively reflected the degree of recognition of user to service.For the mobile video business, how good user experience quality is provided is the key that can business achieve success, and is also simultaneously to weigh the user to the important way of the business degree of recognition.
In order to assess better QoE and influencing factor thereof, the normal method that quantizes that adopts is weighed Quality of experience, thus the gap between the quality of reflection business and network and user's expectation.A kind of method of description user experience quality of extensive employing is international telecommunication union recommendation " average point value of evaluation " (Mean Opinion Score, MOS), and it is divided into 5 grades with the subjective feeling of QoE, be followed successively by { bad from low to high, inferior, in, good, excellent }, corresponding MOS score value is { 1,2,3,4,5}.This method is a kind of ordinal scale method, and it can describe user experience quality meticulously, and wherein the MOS value belongs to orderly variable.At present, for mobile video service-user Quality of experience, often analyze contact between QoE and influencing factor thereof by setting up model, as utilize linear regression method to set up relation between QoE and important performance indexes.But when this method was not considered the fabulous or extreme difference of mobile video business play quality, the user experienced the impression asymmetric situation that distributes.In addition, QoE and its influencing factor be linear relationship simply, so linear regression model (LRM) and not exclusively applicable.In addition, at present data service is many to be predicted user experience quality in network server end, its parameter acquisition point from user side away from, can not press close to preferably the requirement that end-to-end quality is assessed.Therefore, how to assess exactly user experience quality in conjunction with the feature of orderly variable, effective solution not yet occurs at present.
Summary of the invention
The objective of the invention is to propose a kind of mobile video service-user Quality of experience appraisal procedure based on ordinal regression in order to overcome the deficiency of existing solution.The method of the invention extracts from mobile video decoder and mobile terminal the performance index that affect user experience quality, is the feature of orderly variable in conjunction with user awareness QoE grade, sets up the model of accurate evaluation user experience quality.
To achieve these goals, the concrete steps of the technical solution adopted in the present invention are:
Step 1: take the mobile video business as research object, determine to affect the end-to-end cross-layer performance index of user experience quality.Performance index comprise: application layer index (bit rate, frame per second, video content), network layer index (packet loss), indicator terminal (resolution, terminal size).Wherein, bit rate refers to the bit number of transmission of video in the unit interval, frame per second refers to the frame number that the video per second shows, packet loss refers to that institute's lost data packets quantity accounts for the ratio of the packet that sends, resolution refers to the pixel quantity that terminal is shown, terminal size refers to the actual size of terminal screen, and video content refers to spatial information and the temporal information of video.
Step 2: different mobile video performance index (application layer, network layer, indicator terminal) network environment is set, and records the MOS value that user corresponding under different indexs watches the mobile video Quality of experience.According to the evaluation criteria of international telecommunication union recommendation, be grade with the user to the Satisfaction index of mobile video Quality of experience
,
Corresponding QoE grade is
, total
Individual grade is used respectively
Expression.Obtain sample data by repeatedly testing, sample data is divided into training set and checking collection.Mobile video service feature index is from decoder bit stream information and acquisition for mobile terminal.Wherein, by analyzing the decoder end bit stream information, can obtain packet loss, frame per second, bitrate information as RTP packet number, sampling time, RTP bag bit number; By in Video Decoder end edge calculation block message and monochrome information, can extract video content features; IMEI string by the inquiring user mobile terminal number can obtain the information of resolution, terminal size.
Step 3: will from the input as the ordinal regression model of the index of Video Decoder and acquisition for mobile terminal, record every group of subjective user corresponding to index and experience the MOS value, and statistical computation MOS value be a certain grade
(
) time probability
, to the model training and make parameter Estimation; The data detection model that the recycling checking is concentrated makes and utilizes above-mentioned performance index can estimate QoE distribution of grades situation, and utilizes the QoE assessment of ordinal regression model realization mobile video business.
QoE assessment described in step 3 is by setting up the ordinal regression model realization, and detailed process is as follows:
A) definition QoE grade
Before getting
The cumulative probability of individual value distributes:
, wherein
Expression needs the QoE grade of estimation,
For affecting the performance index of QoE.
B) work as in order to guarantee
During variation, the QoE cumulative probability satisfies all the time
, algorithm utilizes the logistic function
, guarantee
Set up, wherein
With
Parameter for estimation undetermined.
C) to the cumulative probability of model
Carry out the logit conversion
, namely
, obtain variable
About
Linear function.The QoE grade that the ordinal regression model is estimated
Belong to a certain grade
Probability be
D) utilize maximum likelihood estimate to carry out parameter Estimation, likelihood function to the ordinal regression model
,
With parameter
,
It is relevant,
It is the number of samples of required training set.Wherein when the
Individual sample belongs to
During class,
Otherwise
Carry out equation solution by iteration,
Expression the
If the result of inferior iteration is to arbitrarily
, have
, model satisfies the condition of convergence.
E) after model parameter estimation is completed, utilize Pearson came
Whether the testing model goodness of fit is estimated to occur the frequency test model by comparative observation event and model and is set up.Standard
Statistic is
, wherein
The expression checking concentrates sample data QoE to belong to grade
Frequency,
For the QoE that calculates according to the ordinal regression model belongs to grade
Frequency,
For verifying concentrated total sample number.
Step 4: the ordinal regression model that utilizes the foundation in step 3, performance index in mobile video decoder and mobile terminal collection mobile video business, comprise application layer index (bit rate, frame per second, video content), network layer index (packet loss), indicator terminal (resolution, terminal size) is as mode input
, calculate
, the user experiences grade and can realize by the QoE grade of finding the solution maximum probability, namely works as
The time, the evaluation grade of QoE is
Therefore, the MOS value that model output not only can the accurate evaluation user experience quality can also draw the MOS value and is
(
) time corresponding percentage.
The present invention is in conjunction with characteristics and user's subjective feeling of mobile video business, designed can the accurate evaluation user experience quality the method based on the ordinal regression model, its advantage applies exists:
At first, the performance index of user experience quality have been considered to affect comprehensively, the performance index of the end-to-end cross-layer of mobile video service impact user experience quality have been considered, comprise application layer index (bit rate, frame per second, video content), network layer index (packet loss), indicator terminal (resolution, terminal size).Performance index by setting up cross-layer and the corresponding relation of mobile video user experience quality can be assessed user experience quality exactly.
Secondly, utilizing user awareness QoE grade is the feature of orderly variable, has set up the mobile video service-user Quality of experience appraisal procedure based on ordinal regression.The dependent variable MOS value that this model will be assessed user's subjective feeling is mapped as orderly variable, mobile video service-user experience satisfaction and influencing factor thereof analyzed, and be a kind of realistic, effective user's experience evaluation method.
The 3rd, the present invention can be from decoder bit stream information and acquisition for mobile terminal mobile video service feature index, and does not need the source video information to make reference, and therefore specifically implements simplely, and can press close to preferably the requirement of end-to-end quality assessment.
The 4th, the present invention propose based on the mobile video service-user Quality of experience assessment models of ordinal regression not only can the accurate evaluation user experience quality the MOS value, can also draw the MOS value and be
The time corresponding percentage.These information will be improved network quality and improve the meaning that user satisfaction has directiveness operator and service provider.
Description of drawings
Fig. 1 is the end-to-end quality analysis and assessment block diagram of experiencing based on the user of the present invention.
Fig. 2 is that user experience quality model of the present invention is set up schematic diagram.
Fig. 3 is the flow chart that utilizes ordinal regression to carry out the user experience quality assessment of the present invention.
Embodiment
For making technical scheme of the present invention, purpose and advantage clearer, below in conjunction with the accompanying drawing embodiment that develops simultaneously, the present invention is described in further details.Concrete steps are:
Step 1: the end to end performance index of determining mobile video service impact user experience quality.
User experience quality QoE has reflected the whole acceptable degree of terminal use to using or serving, and its influencing factor has a lot.The present invention is directed to the mobile video business, considered to affect the performance index of the end-to-end cross-layer that the user experiences, comprise application layer index (bit rate, frame per second, video content), network layer index (packet loss), indicator terminal (resolution, terminal size).Wherein, bit rate refers to the bit number of transmission of video in the unit interval, frame per second refers to the frame number that the video per second shows, packet loss refers to that institute's lost data packets quantity accounts for the ratio of the packet that sends, resolution refers to the pixel quantity that terminal is shown, terminal size refers to the actual size of terminal screen, and video content refers to spatial information and the temporal information of video.
Step 2: different mobile video performance index are set.As shown in Figure 1, by analyzing the decoder end bit stream information, can obtain packet loss, frame per second, bitrate information as RTP packet number, sampling time, RTP bag bit number; By edge calculation block message and monochrome information, can extract video content features; IMEI string by the inquiring user mobile terminal number can obtain the information of resolution, terminal size.With These parameters as the input based on the mobile video business QoE assessment models of ordinal regression, as shown in Figure 2, wherein, the bit rate span is 18kbps-384kbps, the desirable 5fps-30fps of frame per second, the desirable QCIF of resolution, CIF, 4CIF, the desirable 0-20% of packet loss, desirable 110x50mm-250 * the 200mm of terminal size, content type is desirable at a slow speed, the video of middling speed, rapid movement.According to the evaluation criteria of International Telecommunication Union suggestion, record is user corresponding to the performance index quality of experience MOS value of watching video on the same group not, and is as shown in table 1, and calculating MOS value is a certain grade
(
) time probability
, further obtain the QoE grade
Before getting
The cumulative probability of individual value
Obtain sample data by repeatedly testing, it is training set and checking collection that sample data is divided into.The present invention is applicable to the plurality of wireless networks scene, as WCDMA, and cdma2000, TD-SCDMA,
LTE, wlan network etc.
Table 1
MOS | QoE | The extent of damage |
5 | Excellent | Can not discover |
4 | Good | Discernable but not serious |
3 | In | Slightly |
2 | Inferior | Seriously |
1 | Bad | Very serious |
Step 3: as shown in Figure 3, will from the performance index of Video Decoder and acquisition for mobile terminal as mode input, utilize training set data to carry out repetition training to model, and complete parameter Estimation; The data that the recycling checking is concentrated are come the accuracy of verification model, make utilize the mobile video business collect performance index accurately estimating user experience the distribution situation of impression, realization utilizes the process of the modeling mobile video service-user Quality of experience of ordinal regression model.Concrete steps are:
A) utilize in sample 80% data as training set, input performance index and training parameter;
B) definition QoE grade
Before getting
The probability distribution of individual value is:
, wherein
Expression needs the QoE grade of estimation,
For affecting the performance index of QoE.
C) work as in order to guarantee
During variation, QoE grade probability
All the time satisfy
, algorithm uses the logistic function
, make
Set up, wherein
With
Parameter for estimation undetermined.
D) to the cumulative probability of model
Carry out the logit conversion:
, namely
, obtained variable
About
Linear function.The QoE grade that the ordinal regression model is estimated
Belong to a certain grade
Probability be
E) utilize maximum likelihood estimate to carry out parameter Estimation, likelihood function to the ordinal regression model
,
With parameter
,
It is relevant,
It is the number of samples of required training set.Wherein when the
Individual sample belongs to
During class,
Otherwise
Carry out equation solution by iteration,
Expression the
If the result of inferior iteration is to arbitrarily
, have
, model satisfies the condition of convergence, deconditioning.
F) remaining 20% data in sample number are collected data as checking, the goodness of fit of model is tested.
G) utilize Pearson came
Whether the testing model goodness of fit is estimated to occur the frequency test model by comparative observation event and model and is set up.Standard
Statistic is
, wherein
The expression checking concentrates sample data QoE to belong to grade
Frequency,
For the QoE that calculates according to the ordinal regression model belongs to grade
Frequency,
For verifying concentrated total sample number.
H) calculate the Pearson came test statistics, if satisfy the condition of convergence, the estimation model of setting up meets the requirements.
Step 4: the ordinal regression model that utilizes the foundation in step 3, performance index in mobile video decoder and mobile terminal collection mobile video business, comprise application layer index (bit rate, frame per second, video content), network layer index (packet loss), indicator terminal (resolution, terminal size) is as mode input
Calculate
The user experiences grade and can realize by the QoE grade of finding the solution maximum probability, even
, the evaluation grade of QoE is
Therefore, the MOS value that model output not only can the accurate evaluation user experience quality can also draw the MOS value and is
The time corresponding percentage.Therefore, this model can provide more valuable network servicequality information for operator and service provider.
Claims (1)
1. based on the mobile video service-user Quality of experience appraisal procedure of ordinal regression, it is characterized in that the method comprises the following steps:
Step 1: take the mobile video business as research object, determine to affect the end-to-end cross-layer performance index of user experience quality, described performance index comprise: the application layer index: bit rate, frame per second, video content; Network layer index: packet loss; Indicator terminal: resolution, terminal size; Wherein, bit rate refers to the bit number of transmission of video in the unit interval, frame per second refers to the frame number that the video per second shows, packet loss refers to that institute's lost data packets quantity accounts for the ratio of the packet that sends, resolution refers to the pixel quantity that terminal is shown, terminal size refers to the actual size of terminal screen, and video content refers to spatial information and the temporal information of video;
Step 2: different mobile video performance index network environments is set, and records the MOS value that user corresponding under different indexs watches the mobile video Quality of experience; According to the evaluation criteria of international telecommunication union recommendation, be grade with the user to the Satisfaction index of mobile video Quality of experience
,
Corresponding QoE grade is
, total
Individual grade is used respectively
Expression; Obtain sample data by repeatedly testing, sample data is divided into training set and checking collection; Mobile video service feature index is from decoder bit stream information and acquisition for mobile terminal; Wherein, by analyzing the decoder end bit stream information, wrap bit number as RTP packet number, sampling time, RTP, obtain packet loss, frame per second, bitrate information; By in Video Decoder end edge calculation block message and monochrome information, can extract video content features; By the IMEI string number acquisition resolution of inquiring user mobile terminal, the information of terminal size;
Step 3: will from the input as the ordinal regression model of the index of Video Decoder and acquisition for mobile terminal, record every group of subjective user corresponding to index and experience the MOS value, and statistical computation MOS value be a certain grade
The time probability
, to the model training and make parameter Estimation; The data detection model that the recycling checking is concentrated makes and utilizes above-mentioned performance index can estimate QoE distribution of grades situation, and utilizes the QoE assessment of ordinal regression model realization mobile video business;
QoE assessment described in step 3 is by setting up the ordinal regression model realization, and detailed process is as follows:
A) definition QoE grade
Before getting
The cumulative probability of individual value distributes:
, wherein
Expression needs the QoE grade of estimation,
For affecting the performance index of QoE;
B) work as in order to guarantee
During variation, the QoE cumulative probability satisfies all the time
, algorithm utilizes the logistic function
, guarantee
Set up, wherein
With
Parameter for estimation undetermined;
C) to the cumulative probability of model
Carry out the logit conversion
, namely
, obtain variable
About
Linear function; The QoE grade that the ordinal regression model is estimated
Belong to a certain grade
Probability be
D) utilize maximum likelihood estimate to carry out parameter Estimation, likelihood function to the ordinal regression model
,
With parameter
,
It is relevant,
It is the number of samples of required training set; Wherein when the
Individual sample belongs to
During class,
Otherwise
Carry out equation solution by iteration,
Expression the
If the result of inferior iteration is to arbitrarily
, have
, model satisfies the condition of convergence;
E) after model parameter estimation is completed, utilize Pearson came
Whether the testing model goodness of fit is estimated to occur the frequency test model by comparative observation event and model and is set up; Standard
Statistic is
, wherein
The expression checking concentrates sample data QoE to belong to grade
Frequency,
For the QoE that calculates according to the ordinal regression model belongs to grade
Frequency,
For verifying concentrated total sample number;
Step 4: utilize the ordinal regression model of the foundation in step 3, the performance index in mobile video decoder and mobile terminal collection mobile video business comprise that bit rate, frame per second, video content, packet loss, resolution, terminal size are as mode input
, calculate
, the user experiences grade and can realize by the QoE grade of finding the solution maximum probability, namely works as
The time, the evaluation grade of QoE is
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013100450691A CN103152599A (en) | 2013-02-01 | 2013-02-01 | Mobile video service user experience quality evaluation method based on ordinal regression |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2013100450691A CN103152599A (en) | 2013-02-01 | 2013-02-01 | Mobile video service user experience quality evaluation method based on ordinal regression |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103152599A true CN103152599A (en) | 2013-06-12 |
Family
ID=48550432
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2013100450691A Pending CN103152599A (en) | 2013-02-01 | 2013-02-01 | Mobile video service user experience quality evaluation method based on ordinal regression |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103152599A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015043184A1 (en) * | 2013-09-30 | 2015-04-02 | 华为技术有限公司 | Voice quality evaluation method and apparatus |
CN104507128A (en) * | 2014-12-25 | 2015-04-08 | 北京理工大学 | QoE (quality of experience) based QoS (quality of service) mapping management method |
WO2015100560A1 (en) * | 2013-12-30 | 2015-07-09 | 华为技术有限公司 | Method for predicting quality of experience of mobile video service, and base station |
WO2016109916A1 (en) * | 2015-01-05 | 2016-07-14 | 华为技术有限公司 | Quality of experience (qoe) prediction apparatus, network device and method |
CN105828064A (en) * | 2015-01-07 | 2016-08-03 | 中国人民解放军理工大学 | No-reference video quality evaluation method integrating local and global temporal and spatial characteristics |
CN105847970A (en) * | 2016-04-06 | 2016-08-10 | 华为技术有限公司 | Video display quality calculating method and equipment |
WO2016134564A1 (en) * | 2015-02-28 | 2016-09-01 | 中兴通讯股份有限公司 | User perception estimation method and apparatus |
CN105933329A (en) * | 2016-06-12 | 2016-09-07 | 浙江大学 | Video streaming business code rate self-adaption method based on online study |
CN106656629A (en) * | 2017-01-13 | 2017-05-10 | 南京理工大学 | Prediction method for stream media playing quality |
CN106789349A (en) * | 2017-01-20 | 2017-05-31 | 南京邮电大学 | A kind of method based on Quality of experience modeling analysis and session flow point class |
CN108920455A (en) * | 2018-06-13 | 2018-11-30 | 北京信息科技大学 | A kind of Chinese automatically generates the automatic evaluation method of text |
CN109257626A (en) * | 2017-07-13 | 2019-01-22 | 大唐移动通信设备有限公司 | A kind of data processing method and device |
CN112822482A (en) * | 2020-12-31 | 2021-05-18 | 上海掌门科技有限公司 | Method and equipment for determining evaluation score of audio and video call |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080143837A1 (en) * | 2004-10-18 | 2008-06-19 | Nippon Telegraph And Telephone Corporation | Video Quality Objective Assessment Device, Assessment Method, and Program |
CN101835058A (en) * | 2009-03-11 | 2010-09-15 | 华为技术有限公司 | Method, system and equipment for detecting quality of experience of video |
CN102223262A (en) * | 2011-05-20 | 2011-10-19 | 同济大学 | Evaluation platform and method of quality of experience of video based on QoS |
-
2013
- 2013-02-01 CN CN2013100450691A patent/CN103152599A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080143837A1 (en) * | 2004-10-18 | 2008-06-19 | Nippon Telegraph And Telephone Corporation | Video Quality Objective Assessment Device, Assessment Method, and Program |
CN101835058A (en) * | 2009-03-11 | 2010-09-15 | 华为技术有限公司 | Method, system and equipment for detecting quality of experience of video |
CN102223262A (en) * | 2011-05-20 | 2011-10-19 | 同济大学 | Evaluation platform and method of quality of experience of video based on QoS |
Non-Patent Citations (1)
Title |
---|
吴吉祥等: "基于广义线性模型的QoE评估方法研究", 《计算机应用研究》 * |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104517613A (en) * | 2013-09-30 | 2015-04-15 | 华为技术有限公司 | Method and device for evaluating speech quality |
WO2015043184A1 (en) * | 2013-09-30 | 2015-04-02 | 华为技术有限公司 | Voice quality evaluation method and apparatus |
CN105264907A (en) * | 2013-12-30 | 2016-01-20 | 华为技术有限公司 | Method for predicting quality of experience of mobile video service, and base station |
CN105264907B (en) * | 2013-12-30 | 2018-08-21 | 华为技术有限公司 | The Quality of experience prediction technique of mobile video business and base station |
WO2015100560A1 (en) * | 2013-12-30 | 2015-07-09 | 华为技术有限公司 | Method for predicting quality of experience of mobile video service, and base station |
CN104507128B (en) * | 2014-12-25 | 2018-05-11 | 北京理工大学 | A kind of service class QoS mapping management process based on user experience quality QoE |
CN104507128A (en) * | 2014-12-25 | 2015-04-08 | 北京理工大学 | QoE (quality of experience) based QoS (quality of service) mapping management method |
CN106134215A (en) * | 2015-01-05 | 2016-11-16 | 华为技术有限公司 | User experience quality QoE prediction means, the network equipment and method |
WO2016109916A1 (en) * | 2015-01-05 | 2016-07-14 | 华为技术有限公司 | Quality of experience (qoe) prediction apparatus, network device and method |
CN105828064A (en) * | 2015-01-07 | 2016-08-03 | 中国人民解放军理工大学 | No-reference video quality evaluation method integrating local and global temporal and spatial characteristics |
CN105828064B (en) * | 2015-01-07 | 2017-12-12 | 中国人民解放军理工大学 | The local video quality evaluation without reference method with global space-time characterisation of fusion |
CN105991364A (en) * | 2015-02-28 | 2016-10-05 | 中兴通讯股份有限公司 | User perception evaluation method and device |
WO2016134564A1 (en) * | 2015-02-28 | 2016-09-01 | 中兴通讯股份有限公司 | User perception estimation method and apparatus |
CN105991364B (en) * | 2015-02-28 | 2020-07-17 | 中兴通讯股份有限公司 | User perception evaluation method and device |
CN105847970A (en) * | 2016-04-06 | 2016-08-10 | 华为技术有限公司 | Video display quality calculating method and equipment |
CN105933329A (en) * | 2016-06-12 | 2016-09-07 | 浙江大学 | Video streaming business code rate self-adaption method based on online study |
CN105933329B (en) * | 2016-06-12 | 2018-11-20 | 浙江大学 | Video stream traffic code rate adaptive approach based on on-line study |
CN106656629A (en) * | 2017-01-13 | 2017-05-10 | 南京理工大学 | Prediction method for stream media playing quality |
CN106656629B (en) * | 2017-01-13 | 2020-02-14 | 南京理工大学 | Method for predicting streaming media playing quality |
CN106789349B (en) * | 2017-01-20 | 2020-04-07 | 南京邮电大学 | Quality of experience modeling analysis and conversation flow classification based method |
CN106789349A (en) * | 2017-01-20 | 2017-05-31 | 南京邮电大学 | A kind of method based on Quality of experience modeling analysis and session flow point class |
CN109257626A (en) * | 2017-07-13 | 2019-01-22 | 大唐移动通信设备有限公司 | A kind of data processing method and device |
CN109257626B (en) * | 2017-07-13 | 2020-11-10 | 大唐移动通信设备有限公司 | Data processing method and device |
CN108920455A (en) * | 2018-06-13 | 2018-11-30 | 北京信息科技大学 | A kind of Chinese automatically generates the automatic evaluation method of text |
CN112822482A (en) * | 2020-12-31 | 2021-05-18 | 上海掌门科技有限公司 | Method and equipment for determining evaluation score of audio and video call |
CN112822482B (en) * | 2020-12-31 | 2022-11-08 | 上海掌门科技有限公司 | Method and equipment for determining evaluation score of audio and video call |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103152599A (en) | Mobile video service user experience quality evaluation method based on ordinal regression | |
US7936916B2 (en) | System and method for video quality measurement based on packet metric and image metric | |
CN102685790B (en) | Method for evaluating QoE (Quality of Experience) of mobile streaming media service perception experience by simulating user behaviors | |
CN104023232B (en) | Based on the mobile video method for evaluating quality of step analysis and multiple linear regression | |
WO2016101464A1 (en) | Quality of experience estimation method, device, terminal and server | |
US7768937B2 (en) | Video quality assessment | |
EP2571195A1 (en) | Method for calculating perception of the user experience of the quality of monitored integrated telecommunications operator services | |
Casas et al. | Monitoring YouTube QoE: Is your mobile network delivering the right experience to your customers? | |
CN105050125A (en) | Method and device for evaluating mobile data service quality oriented to user experience | |
CN102904773B (en) | Method and device for measuring network service quality | |
CN104113788A (en) | QoE training and assessment method and system of TCP video stream service | |
CN107027023A (en) | VoIP based on neutral net is without reference video communication quality method for objectively evaluating | |
CN105049930A (en) | Wireless video streaming service QoE estimation method based on support vector machine | |
CN102340426A (en) | Method and device for evaluating voice quality of voice over Internet protocol (VOIP) | |
Cherif et al. | A_PSQA: Efficient real-time video streaming QoE tool in a future media internet context | |
Aguiar et al. | Video quality estimator for wireless mesh networks | |
CN104796443B (en) | QoE (quality of experience) correction method and server for mobile streaming media user | |
CN103607309A (en) | Mapping method for service KQI and QOE | |
Oršolić et al. | In-network qoe and kpi monitoring of mobile youtube traffic: Insights for encrypted ios flows | |
Ghalut et al. | Content-based video quality prediction using random neural networks for video streaming over LTE networks | |
CN102572501A (en) | Video quality evaluation method and device capable of taking network performance and video self-owned characteristics into account | |
CN101895787B (en) | Method and system for subjectively evaluating video coding performance | |
Wang et al. | A new approach measuring users' QoE in the IPTV | |
CN115150901B (en) | Method, device and storage medium for determining quality difference cell in communication network | |
Hernando et al. | Evaluating quality of experience in IPTV services using MPEG frame loss rate |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130612 |