CN108390775A - A kind of user experience quality evaluation method and system based on SPICE - Google Patents
A kind of user experience quality evaluation method and system based on SPICE Download PDFInfo
- Publication number
- CN108390775A CN108390775A CN201810111479.4A CN201810111479A CN108390775A CN 108390775 A CN108390775 A CN 108390775A CN 201810111479 A CN201810111479 A CN 201810111479A CN 108390775 A CN108390775 A CN 108390775A
- Authority
- CN
- China
- Prior art keywords
- quality
- user
- experience
- user experience
- mapping relations
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/5003—Managing SLA; Interaction between SLA and QoS
- H04L41/5009—Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/50—Testing arrangements
- H04L43/55—Testing of service level quality, e.g. simulating service usage
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The present invention relates to computer virtualized fields, a kind of user experience quality evaluation method and system based on SPICE are disclosed, to enhance adaptive ability, reduce error, for the user experience demand and feedback of different user different scenes, improves service quality, improve the utilization benefit of user；This method includes：The average subjective scores difference of relevant user experience is acquired as actual user's Quality of experience；Server-side, network layer and client the related data index corresponding with actual user's Quality of experience in different scenes are acquired by SPICE protocol；Establish the mapping relations between related data index and actual user's Quality of experience, prediction user experience quality is obtained according to mapping relations, the loss function between prediction user experience quality and actual user's Quality of experience is calculated using DBN and BP neural network, based on loss function, mapping relations are optimized, the automatic Evaluation to user experience quality is further completed.
Description
Technical field
The present invention relates to computer virtualized field more particularly to a kind of user experience quality evaluation sides based on SPICE
Method and system.
Background technology
With the development of computer network and virtualization technology, desktop virtualization solution is increasingly mature, is done in enterprise
The numerous areas such as public affairs, on-line study are widely applied, and have provided efficient, safety to the user and efficiently user interacts body
It tests.The virtual desktop solution that SPICE increases income as one provides long-range display and equipment for client access, as keyboard,
The support of mouse, audio etc., and the attempting to share part CPU and GPU intensity of the task gives full play to client to client
Performance improves the usage experience situation of user.Due to complexity of the virtual desktop based on network access procedure, be related to server-side,
The multiple data of client and virtual machine transmits, and considers the different actual use scene of user, this respect is to user experience at present
Quality (QoE, Quality of Experience) evaluation is not also very perfect, in addition, when using virtual desktop, user's body
The amount of checking the quality is not only related to objective network quality, server-side or client performance, also has with the environment scene residing for user
Certain relationship.
Therefore, it now needs to provide that a kind of adaptive ability is strong, and error is small, the user's body of different user different scenes can be directed to
Demand and feedback are tested, improves service quality, improves the user experience quality evaluation method based on SPICE of the utilization benefit of user
And system.
Invention content
Present invention aims at a kind of user experience quality evaluation method and system based on SPICE is provided, certainly with enhancing
Adaptability, reduce error makes virtual desktop serve quotient change for the user experience demand and feedback of different user different scenes
It is apt to the service quality of itself, improves the utilization benefit of user.
To achieve the above object, the present invention provides a kind of average subjective scores differences of acquisition relevant user experience as real
Border user experience quality；
By SPICE protocol acquire server-side, network layer and client in different scenes with actual user's body
The corresponding related data index of the amount of checking the quality；
The mapping relations between the related data index and actual user's Quality of experience are established, according to the mapping
Relationship obtains prediction user experience quality, and the prediction user experience quality and the reality are calculated using DBN and BP neural network
Loss function between the user experience quality of border is：
In formula, m indicates that input data group number, i indicate i-th group of input data, yiIndicate actual user's Quality of experience, uiTable
Show prediction user experience quality；
Based on the loss function, the mapping relations are optimized, then obtain real-time related data index, by institute
It states real-time related data index and carries out map analysis by the mapping relations after optimization to automatically generate commenting for user experience quality
Valence result.
Preferably, the related data index includes that network bandwidth, time delay, packet loss, client CPU, server-side are virtual
Cpu busy percentage, memory usage and the bandwidth availability ratio of machine.
The technical concept total as one, the user experience quality evaluation system based on SPICE that the present invention also provides a kind of,
Including：
First unit：For acquiring the average subjective scores difference of relevant user experience as actual user's Quality of experience；
Second unit：For by SPICE protocol acquire server-side, network layer and client in different scenes with institute
State the corresponding related data index of actual user's Quality of experience；
Third unit：It is closed for establishing the mapping between the related data index and actual user's Quality of experience
System obtains prediction user experience quality according to the mapping relations, the prediction user's body is calculated using DBN and BP neural network
Loss function between the amount of checking the quality and actual user's Quality of experience is：
In formula, m indicates that input data group number, i indicate i-th group of input data, yiIndicate actual user's Quality of experience, uiTable
Show prediction user experience quality；
Unit the 4th：For being based on the loss function, the mapping relations are optimized, are then obtained related in real time
The real-time related data index is carried out map analysis to automatically generate user by data target by the mapping relations after optimization
The evaluation result of Quality of experience.
Preferably, the related data index in the second unit includes network bandwidth, time delay, packet loss, client
CPU, the cpu busy percentage of server-side virtual machine, memory usage and bandwidth availability ratio.
The invention has the advantages that：
The present invention provides a kind of user experience quality evaluation method and system based on SPICE, preliminary first to establish reality
Mapping relations between user experience quality and server-side, the related data of network layer and client, then pass through DBN and BP
The Neural Network Optimization mapping relations complete automatic Evaluation to user experience quality to integrate related data and the mapping relations,
This method and system enhance the adaptive ability used, reduce error, reach the user that can be directed to different user different scenes
Demand for experience and feedback make virtual desktop serve quotient improve the service quality of itself, preferably optimize the various aspects of virtual desktop
Performance indicator improves the purpose of the utilization benefit of user.
Below with reference to accompanying drawings, the present invention is described in further detail.
Description of the drawings
The attached drawing constituted part of this application is used to provide further understanding of the present invention, schematic reality of the invention
Example and its explanation are applied for explaining the present invention, is not constituted improper limitations of the present invention.In the accompanying drawings：
Fig. 1 is the method flow diagram of the preferred embodiment of the present invention；
Fig. 2 is the mapping relations figure of the preferred embodiment of the present invention；
Fig. 3 is the neural network schematic diagram of the preferred embodiment of the present invention；
Fig. 4 is the normalization result schematic diagram of the preferred embodiment of the present invention.
Specific implementation mode
The embodiment of the present invention is described in detail below in conjunction with attached drawing, but the present invention can be defined by the claims
Implement with the multitude of different ways of covering.
Embodiment 1
Referring to Fig. 1, the user experience quality evaluation method based on SPICE that the present embodiment provides a kind of includes the following steps：
The average subjective scores difference of relevant user experience is acquired as actual user's Quality of experience；
By SPICE protocol acquisition server-side, network layer and client matter is experienced with actual user in different scenes
Measure corresponding related data index；
The mapping relations between related data index and actual user's Quality of experience are established, are predicted according to mapping relations
User experience quality is calculated using DBN and BP neural network between prediction user experience quality and actual user's Quality of experience
Loss function is：
In formula, m indicates that input data group number, i indicate i-th group of input data, yiIndicate actual user's Quality of experience, uiTable
Show prediction user experience quality；
Based on loss function, mapping relations are optimized, then obtain real-time related data index, by real-time dependency number
Map analysis is carried out to automatically generate the evaluation result of user experience quality by the mapping relations after optimization according to index.
As the present embodiment preferred embodiment, related data index includes network bandwidth, time delay, packet loss, client
Hold CPU, the cpu busy percentage of server-side virtual machine, memory usage and bandwidth availability ratio.
In the case where no network factors limit, i.e., without bandwidth limitation, zero time delay, zero packet loss, user is in difference for acquisition
The MOS values of SPICE clients are used under usage scenario, as shown in table 1 below：
1 user experience quality table of table
By above-mentioned table 1 it is found that the bigger expression user experience quality of MOS values is better.Since user is actually by SPICE
Client uses virtual machine desktop, while acquiring the utilization rate of the CPU of virtual machine, memory and bandwidth in server-side.It needs to illustrate
, above-mentioned difference usage scenarios refer to word read, web page browsing, document office and video playing etc. it is different use shape
State, since related data index such as bandwidth utilization rate of the network in above-mentioned different usage scenarios is different, i.e., in video
There is very strong dependence to the CPU of server-side and client, bandwidth when playing scene, and in web page browsing, to client CPU
Dependence it is very faint.Specifically, in different scenes related data acquisition the specific steps are：
1, the flow entrance of SPICE clients is monitored to obtain network bandwidth, packet loss data using iptraf.
2, the input channels events such as mouse click/release, keyboard click are monitored based on SPICE, work as monitor event
When being sent out from client package, a PING packet is retransmited, PING packet interior elements include test data bag serial number (ID) and time
It stabs (Timestamp).
It should be noted that ID is self-propagation attribute, timestamp is g_get_monotonic_time functions, wherein
G_get_monotonic_time functions are t1, i.e., existed by the function of inquiry system clock calculation time, precision in the libraries glib
Microsecond rank, and not by the NTP times correct with Tong Bu influenced, can better time of measuring.
3, when server-side receives the processing of such input channel event, immediately to the identical ID of client feedback and
The data packet of timestamp is labeled as PONG, when client receives the PONG packets of server-side, with connecing for current computer
T between time receiving2With t1Make the difference method, the round-trip time delay RTT of as one transmission：RTT=t2-t1。
It is worth noting that in numerous indexs, time delay is a most important factor, i.e. measuring customer end mouse each time
The actual response time of mark, keyboard input operation in the virtual machine of server-side.The measurement of ability third party's packet capturing software is generally all deposited
In external error it cannot be guaranteed that accuracy, it is preferable that the present embodiment calculates essence by changing measurement of the SPICE realizations to time delay
It is accurate effective.
4, client cpu data is acquired, since SPICE server-sides with client when establishing the link for the first time, can actively be supervised
Performance and the state of client are surveyed to distribute different render modes, if client supports Cairo and OpenGL and network is good,
Then allow to carry out polar plot rendering in client and partial graphical is hardware-accelerated, that is, is defined as the mould that client undertakes partial task
Formula is opened；If client does not support Cairo, OpenGL or network bad, it is not turned on, this is 0.It is then weighed when unlatching and is
Cpu busy percentage.
5, the CPU, memory and bandwidth availability ratio of virtual machine are acquired respectively by virtual platform Libvirt-API.
Through the above steps, the utilization power that can get related data index in different usage scenarios is as shown in table 2 below：
The utilization power of related data index in the different usage scenarios of table 2
It is different by the index for influencing user experience quality known to above-mentioned table 2 in different scenes, it therefore, can be according to clothes
The resource utilization at business end deduces different usage scenarios, and, use DBN (depth belief network) and BP neural network can be with
By this kind of feature black box, i.e., can be obtained between usage scenario and user experience quality by the repetition learning of neural network
The mapping relations between related data index and user experience quality are further analyzed and established to relationship, as shown in Figure 2.It needs
Illustrate, by the mapping relations, can reflect user experience quality and from server-side, network layer and client
Contact between related data index can promote virtual desktop serve quotient to improve the service quality of itself to a certain extent, more
Optimize the various aspects of performance index of virtual desktop well.
Further, the user experience quality of acquisition and related data index are arranged, foundation refers to from related data
Mark the mapping relations between actual user's Quality of experience.That is, first according under the limitation of no network factors and heterogeneous networks control
The DMOS values for finding out the user under this usage scenario are made the difference to MOS values.
DMOS=MOSorigial-MOSdistory,
In formula, MOSorigialIndicate the user experience value under no network factors limitation, MOSdistoryIndicate various condition limitations
Under user experience value, the wherein bigger expression user experience of DMOS values is poorer.
Then, as shown in figure 3, it is acquisition bandwidth corresponding to above-mentioned user experience quality, time delay, packet loss etc. is related
Data target carries out multilayer as input vector, by DBN and connects entirely, and unsupervised learning repeatedly is carried out to the mapping relations, and
BP neural network study is carried out using the learning outcome as the input of BP neural network, with autoadapted learning rate gradient descent algorithm
Optimize training process, weights are corrected in settingWherein, η indicates learning rate,Indicate k-1 layers i-th
Connection weight w of the neuron to k j-th of neuron of layer.And use Sigmoid by the output DMOS result normalizings of BP neural network
Change to the sections 0-1, that can analyze more quickly output result.As shown in Figure 4, wherein 0 to represent user experience splendid,
The lower numerical value the better.
Further, after by the repetition learning and calculating of DBN and BP neural network, obtain prediction user experience quality with
Loss function between actual user's Quality of experience is：
In formula, m indicates that input data group number, i indicate i-th group of input data, yiIndicate actual user's Quality of experience, uiTable
Show prediction user experience quality.
Finally, it is considered as learning success when loss function is less than preset threshold value, and is optimized based on the loss function
Above-mentioned mapping relations, user experience quality can be automatically generated according to the mapping relations after real-time related data index and the optimization
Evaluation result.It should be noted that the mapping relations can reflect influence of the related data index to user experience quality, institute
The evaluation result of user experience quality can be automatically generated so that real-time related data is carried out map analysis by mapping relations, together
When, moreover it is possible to it is further influenced caused by the related data index in analysis different scenes, can facilitate service provider that can be directed to not
With the user experience demand and feedback of user's different scenes, preferably network performance is provided, reaches improvement service quality, improves and uses
The purpose of the utilization benefit at family.
Embodiment 2
With above method embodiment correspondingly, the user experience quality evaluation that the present embodiment provides a kind of based on SPICE
System, including：
First unit：For acquiring the average subjective scores difference of relevant user experience as actual user's Quality of experience；
Second unit：For by SPICE protocol acquire server-side, network layer and client in different scenes with reality
The corresponding related data index of border user experience quality；
Third unit：For establishing the mapping relations between related data index and actual user's Quality of experience, according to reflecting
The relationship of penetrating obtains prediction user experience quality, and prediction user experience quality and actual user are calculated using DBN and BP neural network
Loss function between Quality of experience is：
In formula, m indicates that input data group number, i indicate i-th group of input data, yiIndicate actual user's Quality of experience, uiTable
Show prediction user experience quality；
Unit the 4th：For being based on loss function, mapping relations are optimized, real-time related data is then obtained and refers to
Real-time related data index is carried out map analysis to automatically generate user experience quality by mark by the mapping relations after optimization
Evaluation result.
As the present embodiment preferred embodiment, the related data index in second unit include network bandwidth, time delay,
Packet loss, client CPU, the cpu busy percentage of server-side virtual machine, memory usage and bandwidth availability ratio.
The concrete processing procedure of above-mentioned each unit can refer to above method embodiment, repeat no more.
As described above, the present invention provides a kind of user experience quality evaluation method and system based on SPICE, first tentatively
The mapping relations between actual user's Quality of experience and server-side, the related data of network layer and client are established, are then led to
It crosses DBN and optimizes the mapping relations with BP neural network to integrate related data and mapping relations completion to user experience quality
Automatic Evaluation, this method and system enhance the adaptive ability used, reduce error, different user difference field can be directed to by reaching
The user experience demand and feedback of scape, make virtual desktop serve quotient improve the service quality of itself, preferably optimize virtual desktop
Various aspects of performance index, improve the purpose of the utilization benefit of user.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, any made by repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (4)
1. a kind of user experience quality evaluation method based on SPICE, which is characterized in that include the following steps：
The average subjective scores difference of relevant user experience is acquired as actual user's Quality of experience；
By SPICE protocol acquisition server-side, network layer and client matter is experienced with the actual user in different scenes
Measure corresponding related data index；
The mapping relations between the related data index and actual user's Quality of experience are established, according to the mapping relations
Prediction user experience quality is obtained, calculate the prediction user experience quality using DBN and BP neural network uses with the reality
Loss function between the Quality of experience of family is：
In formula, m indicates that input data group number, i indicate i-th group of input data, yiIndicate actual user's Quality of experience, uiIndicate pre-
Survey user experience quality；
Based on the loss function, the mapping relations are optimized, then obtain real-time related data index, by the reality
Shi Xiangguan data targets carry out map analysis to automatically generate the evaluation knot of user experience quality by the mapping relations after optimization
Fruit.
2. the user experience quality evaluation method according to claim 1 based on SPICE, which is characterized in that the correlation
Data target includes network bandwidth, time delay, packet loss, client CPU, the cpu busy percentage of server-side virtual machine, memory usage
And bandwidth availability ratio.
3. a kind of user experience quality evaluation system based on SPICE, which is characterized in that including：
First unit：For acquiring the average subjective scores difference of relevant user experience as actual user's Quality of experience；
Second unit：For by SPICE protocol acquire server-side, network layer and client in different scenes with the reality
The corresponding related data index of border user experience quality；
Third unit：For establishing the mapping relations between the related data index and actual user's Quality of experience, root
Prediction user experience quality is obtained according to the mapping relations, calculating the prediction user's body with BP neural network using DBN checks the quality
Measure actual user's Quality of experience between loss function be：
In formula, m indicates that input data group number, i indicate i-th group of input data, yiIndicate actual user's Quality of experience, uiIndicate pre-
Survey user experience quality；
Unit the 4th：Based on the loss function, the mapping relations are optimized, real-time related data is then obtained and refers to
The real-time related data index is carried out map analysis by the mapping relations after optimization and is checked the quality with automatically generating user's body by mark
The evaluation result of amount.
4. the user experience quality evaluation system according to claim 3 based on SPICE, which is characterized in that described second
Related data index in unit includes the CPU utilizations of network bandwidth, time delay, packet loss, client CPU, server-side virtual machine
Rate, memory usage and bandwidth availability ratio.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810111479.4A CN108390775B (en) | 2018-02-05 | 2018-02-05 | User experience quality evaluation method and system based on SPICE |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810111479.4A CN108390775B (en) | 2018-02-05 | 2018-02-05 | User experience quality evaluation method and system based on SPICE |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108390775A true CN108390775A (en) | 2018-08-10 |
| CN108390775B CN108390775B (en) | 2021-03-30 |
Family
ID=63074463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810111479.4A Active CN108390775B (en) | 2018-02-05 | 2018-02-05 | User experience quality evaluation method and system based on SPICE |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108390775B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255160A (en) * | 2018-08-17 | 2019-01-22 | 东南大学 | Unit time delay prediction method and unit time-delay sensitivity calculation method neural network based |
| CN110855669A (en) * | 2019-11-14 | 2020-02-28 | 北京理工大学 | Video QoE index prediction method suitable for encrypted flow based on neural network |
| WO2021196968A1 (en) * | 2020-03-31 | 2021-10-07 | 华为技术有限公司 | Method and apparatus for distributed processing of ux element |
| CN114077469A (en) * | 2020-08-19 | 2022-02-22 | 中国电信股份有限公司 | Method, system and apparatus for optimizing virtual desktop management |
| US11520692B1 (en) | 2021-09-08 | 2022-12-06 | International Business Machines Corporation | Performing software testing with best possible user experience |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130219043A1 (en) * | 2012-02-20 | 2013-08-22 | Moritz M. Steiner | Method and apparatus for automatic migration of application service |
| CN104144349A (en) * | 2014-07-09 | 2014-11-12 | 中电科华云信息技术有限公司 | SPICE video coding and decoding expansion method and system based on H264 |
| CN105828069A (en) * | 2016-04-06 | 2016-08-03 | 上海交通大学 | Encoder adaptive adjustment method based on subjective quality evaluation |
-
2018
- 2018-02-05 CN CN201810111479.4A patent/CN108390775B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130219043A1 (en) * | 2012-02-20 | 2013-08-22 | Moritz M. Steiner | Method and apparatus for automatic migration of application service |
| CN104144349A (en) * | 2014-07-09 | 2014-11-12 | 中电科华云信息技术有限公司 | SPICE video coding and decoding expansion method and system based on H264 |
| CN105828069A (en) * | 2016-04-06 | 2016-08-03 | 上海交通大学 | Encoder adaptive adjustment method based on subjective quality evaluation |
Non-Patent Citations (3)
| Title |
|---|
| 徐浩 等: "《基于SPICE协议的桌面虚拟化技术研究与改进方案》", 《计算机工程与科学》 * |
| 李伟民等: "《The optimization of Transparent-Desktop service mechanism based on SPICE》", 《CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE》 * |
| 王斌 等: "《SPICE在透明桌面服务机制中的应用及优化研究》", 《计算机科学》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255160A (en) * | 2018-08-17 | 2019-01-22 | 东南大学 | Unit time delay prediction method and unit time-delay sensitivity calculation method neural network based |
| CN109255160B (en) * | 2018-08-17 | 2020-10-16 | 东南大学 | Neural network-based unit delay prediction method and unit delay sensitivity calculation method |
| CN110855669A (en) * | 2019-11-14 | 2020-02-28 | 北京理工大学 | Video QoE index prediction method suitable for encrypted flow based on neural network |
| WO2021196968A1 (en) * | 2020-03-31 | 2021-10-07 | 华为技术有限公司 | Method and apparatus for distributed processing of ux element |
| CN114077469A (en) * | 2020-08-19 | 2022-02-22 | 中国电信股份有限公司 | Method, system and apparatus for optimizing virtual desktop management |
| US11520692B1 (en) | 2021-09-08 | 2022-12-06 | International Business Machines Corporation | Performing software testing with best possible user experience |
| US11775419B2 (en) | 2021-09-08 | 2023-10-03 | International Business Machines Corporation | Performing software testing with best possible user experience |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108390775B (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108390775A (en) | A kind of user experience quality evaluation method and system based on SPICE | |
| CN106470133B (en) | System pressure testing method and device | |
| CN104618924B (en) | User experience quality index system and measurement method based on wireless ubiquitous network | |
| US11057787B2 (en) | Method and test system for mobile network testing as well as prediction system | |
| Anchuen et al. | QOE model in cellular networks based on QOS measurements using Neural Network approach | |
| KR20110096488A (en) | Collaborative networking with optimized inter-domain information quality assessment | |
| JP5957419B2 (en) | QoE estimation apparatus, QoE estimation method and program | |
| CN109194545B (en) | Network test platform flow generation system, method and device and electronic equipment | |
| JP2022000775A (en) | Test method, device and apparatus for traffic flow monitoring measurement system | |
| Jahromi et al. | Establishing waiting time thresholds in interactive web mapping applications for network QoE management | |
| Uhlir et al. | Latency-based benchmarking of cloud service providers | |
| Adegboyega | Time-series models for cloud workload prediction: A comparison | |
| Mostacero-Agama et al. | Analysis of Internet Service Latency and its Impact on Internet of Things (IoT) Applications | |
| Habbal et al. | Design and assessment of an experimental SDN-enabled private cloud using Openstack | |
| CN111314690A (en) | Video user perception evaluation method and device | |
| García et al. | Probabilistic analysis and interdependence discovery in the user interactions of a video news on demand service | |
| CN111598390B (en) | Method, device, equipment and readable storage medium for evaluating high availability of server | |
| Khairy et al. | ACM MMSys 2024 Bandwidth Estimation in Real Time Communications Challenge | |
| CN111010312B (en) | Network quality evaluation method and server | |
| Kniazieva et al. | Method of assessment and improvement the quality of multimedia services | |
| He et al. | PNN-based QoE measuring model for video applications over LTE system | |
| Boguhn | Benchmarking the scalability of distributed stream processing engines in case of load peaks | |
| Veeraragavan et al. | QoE estimation models for tele-immersive applications | |
| Liu et al. | Choquet integral based QoS-to-QoE mapping for mobile VoD applications | |
| Louati et al. | Enhancing QoE based on Machine Learning in Cloud infrastructure |
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 |