CN112884016B - Cloud platform credibility assessment model training method and cloud platform credibility assessment method - Google Patents
Cloud platform credibility assessment model training method and cloud platform credibility assessment method Download PDFInfo
- Publication number
- CN112884016B CN112884016B CN202110117542.7A CN202110117542A CN112884016B CN 112884016 B CN112884016 B CN 112884016B CN 202110117542 A CN202110117542 A CN 202110117542A CN 112884016 B CN112884016 B CN 112884016B
- Authority
- CN
- China
- Prior art keywords
- cloud platform
- evaluation
- tenant
- credible
- perception
- 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
- 238000012549 training Methods 0.000 title claims abstract description 193
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000011156 evaluation Methods 0.000 claims abstract description 286
- 230000008447 perception Effects 0.000 claims abstract description 158
- 238000013210 evaluation model Methods 0.000 claims abstract description 66
- 239000013598 vector Substances 0.000 claims description 56
- 238000012545 processing Methods 0.000 claims description 40
- 230000006870 function Effects 0.000 claims description 20
- 230000015654 memory Effects 0.000 claims description 17
- 238000000605 extraction Methods 0.000 claims description 14
- 230000007246 mechanism Effects 0.000 claims description 14
- 238000013139 quantization Methods 0.000 claims description 14
- 230000004913 activation Effects 0.000 claims description 12
- 238000012790 confirmation Methods 0.000 claims description 10
- 238000007306 functionalization reaction Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 5
- 230000006399 behavior Effects 0.000 claims description 3
- 238000002955 isolation Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 12
- 238000005259 measurement Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Educational Administration (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of cloud platform credibility measurement, and particularly discloses a cloud platform credibility evaluation model training method and a cloud platform credibility evaluation method. The training method comprises the steps of obtaining a cloud platform credible evaluation training data set, wherein the cloud platform credible evaluation training data set comprises cloud platform basic credible evaluation training data and tenant perception credible evaluation training data; inputting the cloud platform basic credible evaluation training data and the tenant perception credible evaluation training data into a network model to be trained, and training the network model to be trained until the network model to be trained meets the preset requirements, so as to obtain the cloud platform credible evaluation model. The training process comprehensively considers the cloud platform basic data and tenant perception credible evaluation data obtained by feedback after the use of the tenant, and the cloud platform credible evaluation model can truly reflect the feedback condition of the tenant to the cloud platform, so that the training process is more in line with credible evaluation of the cloud platform in a real use state, and further the accuracy and the authenticity of the cloud platform credibility evaluation result are improved.
Description
Technical Field
The invention relates to the technical field of cloud platform credibility measurement, in particular to a cloud platform credibility assessment model training method and a cloud platform credibility assessment method.
Background
With the rapid development of cloud computing, the cloud platform is widely applied to various government and enterprise services. Due to the specificity of the cloud platform service, the cloud platform service provider not only provides cloud computing resources and services for tenants, but also needs to ensure the credibility of the cloud service. Because of the particularity of cloud computing, the tenant cannot obtain the visibility and controllability of the cloud platform resources, so that the tenant lacks trust for the cloud platform.
At present, although a method for evaluating the credibility of the cloud platform exists, the method is only based on basic data of the cloud platform, is inconsistent with the real use scene of the cloud platform, cannot be evaluated by combining with the real feedback of tenants, and therefore the conventional credibility evaluation of the cloud platform cannot reflect the real situation.
Disclosure of Invention
Based on the above, it is necessary to provide a cloud platform credibility assessment model training method and a cloud platform credibility assessment method for solving the problem that the existing cloud platform credibility assessment cannot reflect the real situation.
A cloud platform trust evaluation model training method, the method comprising:
acquiring a cloud platform credible evaluation training data set, wherein the cloud platform credible evaluation training data set comprises cloud platform basic credible evaluation training data and tenant perception credible evaluation training data;
and respectively inputting the cloud platform basic credible evaluation training data and the tenant perception credible evaluation training data into a network model to be trained, and training the network model to be trained until the network model to be trained meets the preset requirement, so as to obtain the cloud platform credible evaluation model.
In one embodiment, the step of obtaining the cloud platform trust evaluation training dataset includes:
acquiring cloud platform basic class evaluation attributes and tenant perception evaluation attributes;
and carrying out quantization processing on the cloud platform basic class evaluation attribute and the tenant perception evaluation attribute to obtain cloud platform basic credible evaluation training data and tenant perception credible evaluation training data, and forming a cloud platform credible evaluation training data set.
In one embodiment, the cloud platform base class assessment attributes include reliability, security, and availability, the reliability including robustness, controllability, and failure level, the security including cloud platform cryptographic mechanisms, network security, tenant data security, security isolation, tenant authentication and access control policies, and policy enforcement, the availability including service availability and component loading;
the tenant perception evaluation attribute comprises service quality perception, self-behavior perception, integrity perception and confirmation perception, wherein the service quality perception is measured according to task resource matching degree, the self-behavior perception is measured according to behavior feasible access control, the integrity perception is measured according to credibility of cloud service provider SLA promise, and the confirmation perception is measured according to confirmation of key operation of the tenant participating in cloud service.
In one embodiment, the step of performing quantization processing on the cloud platform base class evaluation attribute and the tenant perception evaluation attribute to obtain cloud platform base trusted evaluation training data and tenant perception trusted evaluation training data, and forming a cloud platform trusted evaluation training data set includes:
determining the credibility probability of the evaluation attribute of each cloud platform basic class according to the fuzzy theory;
determining tenant perception credibility evaluation results of the tenant perception evaluation attributes according to the evaluation scores fed back by the tenants;
and forming a cloud platform credible evaluation training data set according to the cloud platform basic class evaluation attribute, the credible probability and the tenant perception credible evaluation result.
In one embodiment, the step of inputting the cloud platform basic credible evaluation training data and the tenant perception credible evaluation training data to a network model to be trained, and training the network model to be trained until the network model to be trained meets a preset requirement, and the step of obtaining the cloud platform credible evaluation model includes:
performing vectorization processing and feature extraction on the cloud platform basic credible evaluation training data through a network model to be trained to obtain a cloud platform basic feature vector;
vectorization processing and feature extraction are carried out on the tenant perception credibility assessment training data through a network model to be trained, and tenant perception feature vectors are obtained;
determining a tenant perception attention weight through an attention mechanism;
splicing the tenant perception feature vector and the cloud platform basic feature vector to obtain a new feature vector, carrying out weighted summation on the new feature vector by utilizing tenant perception attention weight, and obtaining the cloud platform credibility through nonlinear activation function and normalization processing;
and calculating the error of the cloud platform credibility according to the loss function, and obtaining a cloud platform credibility assessment model when the error of the cloud platform credibility meets a preset requirement, otherwise, adjusting parameters of the network model to be trained and retraining until the error of the cloud platform credibility meets the preset requirement.
A method of cloud platform trust evaluation, the method comprising:
acquiring a cloud platform credible evaluation data set, wherein the cloud platform credible evaluation data set comprises cloud platform basic credible evaluation data and tenant perception credible evaluation data;
and respectively inputting the cloud platform basic credible evaluation data and the tenant perception credible evaluation data into a cloud platform credible evaluation model to perform cloud platform credible evaluation to obtain a cloud platform credible evaluation result, wherein the cloud platform credible evaluation model is trained according to the training method of the cloud platform credible evaluation model.
In one embodiment, the step of inputting the cloud platform basic trusted evaluation data and the tenant perceived trusted evaluation data into a cloud platform trusted evaluation model to perform cloud platform trusted evaluation, and obtaining a cloud platform trusted evaluation result includes:
performing vectorization processing and feature extraction on the cloud platform basic credible evaluation data and the tenant perception credible evaluation data through a cloud platform credible evaluation model to obtain a cloud platform basic feature vector and a tenant perception feature vector;
determining a tenant perception attention weight through an attention mechanism;
and splicing the tenant perception feature vector and the cloud platform basic feature vector to obtain a new feature vector, carrying out weighted summation on the new feature vector by utilizing tenant perception attention weight, and obtaining the cloud platform credibility through nonlinear activation function and normalization processing.
A cloud platform trust evaluation model training apparatus, the apparatus comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a cloud platform credible evaluation training data set, and the cloud platform credible evaluation training data set comprises cloud platform basic credible evaluation training data and tenant perception credible evaluation training data;
the training module is used for respectively inputting the cloud platform basic credible evaluation training data and the tenant perception credible evaluation training data into a network model to be trained, and training the network model to be trained until the network model to be trained meets the preset requirement, so as to obtain the cloud platform credible evaluation model.
A cloud platform trust evaluation apparatus, the apparatus comprising:
the system comprises a cloud platform base trusted evaluation data set and a tenant perception trusted evaluation data set, wherein the cloud platform base trusted evaluation data set comprises a cloud platform base trusted evaluation data set and a tenant perception trusted evaluation data set;
the evaluation module is used for inputting the cloud platform basic credible evaluation data and the tenant perception credible evaluation data into a cloud platform credible evaluation model respectively to perform cloud platform credible evaluation to obtain a cloud platform credible evaluation result, and the cloud platform credible evaluation model is trained according to the training method of the cloud platform credible evaluation model.
An electronic device comprising a memory and a processor, the memory storing a computer program, the processor implementing a cloud platform trusted assessment model training method as described above or a cloud platform trusted assessment model training method as described above when executing the computer program.
A computer readable storage medium having stored therein computer instructions that when executed by a processor implement a cloud platform trusted assessment model training method as described above or a cloud platform trusted assessment model training method as described above.
According to the cloud platform credible evaluation model training method, firstly, the cloud platform credible evaluation training data set is obtained, wherein the cloud platform credible evaluation training data set comprises cloud platform basic credible evaluation training data and tenant perception credible evaluation training data, then the cloud platform basic credible evaluation training data and tenant perception credible evaluation training data are input into a network model to be trained, the network model to be trained is trained until the network model to be trained meets preset requirements, and the cloud platform credible evaluation model is obtained. Because the cloud platform basic credibility evaluation training data and the tenant perception credibility evaluation training data are contained in the training data set, the cloud platform basic data and the tenant perception credibility evaluation data fed back by the tenant after use are comprehensively considered in the training process, so that the finally trained cloud platform credibility evaluation model can truly reflect the feedback condition of the tenant to the cloud platform, more accords with credibility evaluation of the cloud platform in a real use state, and further improves the accuracy and the authenticity of the cloud platform credibility evaluation result.
Drawings
FIG. 1 is a block flow diagram of one implementation of a training method for a trusted evaluation model of a cloud platform according to an embodiment of the present application;
FIG. 2 is a block flow diagram of one implementation of step S100 in the training method of the trusted evaluation model of the cloud platform according to the first embodiment of the present application;
FIG. 3 is a block flow diagram of one implementation of step S120 in the training method of the trusted evaluation model of the cloud platform according to the first embodiment of the present application;
FIG. 4 is a block flow diagram of one implementation of step S300 in the training method of the trusted evaluation model of the cloud platform according to the first embodiment of the present application;
fig. 5 is a flow chart of an implementation manner of a cloud platform trust evaluation method provided in the second embodiment of the present application;
fig. 6 is a flow chart of an implementation manner of step S500 in the cloud platform trust evaluation method provided in the second embodiment of the present application;
fig. 7 is a schematic structural diagram of an implementation manner of a cloud platform trusted evaluation model training device provided in the third embodiment of the present application;
fig. 8 is a schematic structural diagram of an implementation manner of a cloud platform trust evaluation device provided in a fourth embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present application.
Detailed Description
In order that the invention may be readily understood, a more complete description of the invention will be rendered by reference to the appended drawings. The drawings illustrate preferred embodiments of the invention. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
In the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured," and the like are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally formed; can be mechanically or electrically connected; either directly or indirectly, through intermediaries, or both, may be in communication with each other or in interaction with each other, unless expressly defined otherwise. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
The terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Example 1
The embodiment of the application provides a cloud platform credible evaluation model training method, which is used for training and generating a cloud platform credible evaluation model.
Referring to fig. 1, the cloud platform credibility assessment model training method provided by the embodiment includes the following steps:
step S100, a cloud platform credible evaluation training data set is obtained, wherein the cloud platform credible evaluation training data set comprises cloud platform basic credible evaluation training data and tenant perception credible evaluation training data.
And step 300, respectively inputting the cloud platform basic credible evaluation training data and the tenant perception credible evaluation training data into a network model to be trained, and training the network model to be trained until the network model to be trained meets the preset requirements, so as to obtain the cloud platform credible evaluation model.
According to the cloud platform credibility assessment model training method, the cloud platform basic credibility assessment training data and the tenant perception credibility assessment training data are contained in the training data set, the cloud platform basic data and the tenant perception credibility assessment data fed back by the tenant after use are comprehensively considered in the training process, and therefore the cloud platform credibility assessment model obtained through final training can truly reflect the feedback condition of the tenant on the cloud platform, and further accuracy and authenticity of the cloud platform credibility assessment result are improved.
In step S100, a total cloud platform trust evaluation training data set may be obtained in advance, where the cloud platform trust evaluation training data set includes various training data, for example, cloud platform basic trust evaluation training data and tenant perception trust evaluation training data, and may include other data related to the trust of the cloud platform, which may be used for training a model. The cloud platform basic credibility assessment training data refers to objective basic data of the cloud platform, and the tenant perception credibility assessment training data set refers to subjective feedback data of the use effect of the tenant on the cloud platform.
Referring to fig. 2, in one embodiment, step S100, the step of acquiring a cloud platform trust evaluation training dataset, comprises the steps of:
step S110, acquiring cloud platform basic class evaluation attributes and tenant perception evaluation attributes;
and step 120, carrying out quantization processing on the cloud platform basic class evaluation attribute and the tenant perception evaluation attribute to obtain cloud platform basic credible evaluation training data and tenant perception credible evaluation training data, and forming a cloud platform credible evaluation training data set.
In step S110, first, a cloud platform base class evaluation attribute and a tenant-aware evaluation attribute are determined. The cloud platform base class assessment attribute has several seed class attributes, such as reliability, security, availability, and the like. The reliability comprises robustness, controllability, fault level and the like, the security comprises a cloud platform password mechanism, network security, tenant data security, security isolation, tenant authentication and access control strategies, strategy execution and the like, and the availability comprises service availability, component load and the like.
Likewise, tenant-aware assessment attributes also have several sub-class attributes, such as quality of service awareness, self-behavioral awareness, integrity awareness, and confirmation awareness. The Service quality perception is measured according to the task resource matching degree, the self-behavior perception is measured according to the behavior feasible access control, the integrity perception is measured according to the credibility promised by a cloud Service provider (Service-Level Agreement) and the confirmation perception is measured according to the confirmation of the participation of a tenant in the key operation in the cloud Service.
In step S120, after the cloud platform basic class evaluation attribute and the tenant perception evaluation attribute are obtained, they are quantized, so as to obtain corresponding training data. Specifically, since the evaluation attribute includes a specific quantitative attribute and an abstract qualitative attribute, in the quantization process, a quantitative and qualitative combination mode is required, for the qualitative attribute, a logic analysis method and a hierarchical analysis method can be adopted, and an expert priori knowledge is utilized to quantize the qualitative attribute, or a tenant performs subjective assignment and other human qualitative quantization methods on each evaluation attribute, and for the quantitative attribute, quantization can be directly calculated. And after the cloud platform basic credible evaluation training data and tenant perception credible evaluation training data are obtained through quantization, a cloud platform credible evaluation training data set can be formed.
Referring to fig. 3, in one embodiment, step S120, namely, performing quantization processing on the cloud platform base class evaluation attribute and the tenant perception evaluation attribute to obtain cloud platform base credible evaluation training data and tenant perception credible evaluation training data, and forming a cloud platform credible evaluation training data set, includes the following steps:
and step S121, determining the credibility probability of the evaluation attribute of each cloud platform base class according to the fuzzy theory.
For example, for a physical computing resource logically manageable by the cloud platform, the ratio of the actual value in the log file to the protocol specified value can be used as the trusted probability; for qualitative attributes which cannot be directly quantized, expert priori knowledge can be used for quantization to obtain trusted probabilities.
Step S122, determining a tenant perception credible evaluation result of each tenant perception evaluation attribute according to the evaluation score fed back by the tenant.
Specifically, for tenant notification evaluation attributes such as service quality perception, self-behavior perception, honest perception, confirmation perception and the like, evaluation scores of the evaluation attributes fed back by the tenant can be used as tenant perception credible evaluation results, namely quantification results of the tenant perception evaluation attributes.
And step 123, forming a cloud platform credible evaluation training data set according to the cloud platform basic class evaluation attribute, the credibility probability and the tenant perception credible evaluation result.
After the credibility probability of each evaluation attribute and the credibility evaluation result perceived by the tenant are determined, a cloud platform credibility evaluation training data set can be formed by a preset data template so as to serve as input data of a network model to be trained.
In step S300, when the cloud platform trust evaluation model is input into the network model to be trained, the cloud platform trust evaluation training data set may be split first, and the trust evaluation matrix form such as { cloud platform basic class evaluation attribute, trust probability, tenant perception trust evaluation } is assumed to be the original data in the cloud platform trust evaluation training data set, so that the cloud platform trust evaluation training data set may be split into { cloud platform basic class evaluation attribute, trust probability }, { tenant perception trust evaluation, trust probability } two types of data respectively as the cloud platform basic trust evaluation training data and tenant perception trust evaluation training data.
In this embodiment, the network model to be trained may be a deep neural network model, and specifically includes a convolution layer, a pooling layer, a full connection layer, an activation function, and a loss function basic component.
Referring to fig. 4, in one embodiment, step S300, namely, inputting the cloud platform basic trust evaluation training data and the tenant perception trust evaluation training data to the network model to be trained, respectively, and training the network model to be trained until the network model to be trained meets the preset requirement, the step of obtaining the cloud platform trust evaluation model includes the following steps:
and step S310, carrying out vectorization processing and feature extraction on the cloud platform basic credible evaluation training data through the network model to be trained to obtain a cloud platform basic feature vector.
Aiming at input cloud platform basic credibility evaluation training data, firstly carrying out data vectorization processing on the input cloud platform basic credibility evaluation training data, and then carrying out deep feature extraction by utilizing a convolution layer to obtain a cloud platform basic feature vector.
And step 320, performing vectorization processing and feature extraction on the tenant perception credibility evaluation training data through the network model to be trained to obtain tenant perception feature vectors.
Aiming at the input tenant perception credibility evaluation training data, firstly carrying out data vectorization processing on the training data, and then carrying out deep feature extraction by utilizing a convolution layer to obtain tenant perception feature vectors.
Step S330, determining the perception attention weight of the tenant through an attention mechanism.
After the feature vector of the lessor perception is extracted, the lessor perception can be integrated into the network feature learning process. Specifically, the tenant-aware feature vector may first be converted into a tenant-aware attention weight using an attention mechanism.
The attention mechanism is implemented as follows: from the input feature vector x= [ X ] 1 ,…,x N ]Selecting a feature z related to the tenant-aware feature vector q and passing through a scoring function alpha i To calculate the correlation between each input vector and q as a tenant perceived attention weight. The attention mechanism calculation process is shown as follows:
step S340, splicing the tenant perception feature vector and the cloud platform basic feature vector to obtain a new feature vector, carrying out weighted summation on the new feature vector by utilizing the tenant perception attention weight, and obtaining the cloud platform credibility through nonlinear activation function and normalization processing.
After new feature vectors are obtained through splicing, attention weighting is achieved through a convolution calculation mode by substituting the tenant perception attention weight as a parameter into a network full-connection layer, and the obtained weighting result S is as follows:
S＝∑a i (X,q)
and then obtaining the final cloud platform credibility through nonlinear activation function and normalization processing. The activation function adopted in this embodiment is a pralu activation function, which is defined mathematically as follows:
and when mu is updated, adopting a momentum update mode, wherein epsilon and v in the network respectively represent the momentum and the learning rate. The update process of the entrainment quantity is shown as follows:
and step 350, calculating the error of the reliability probability of the cloud platform according to the loss function, and obtaining a reliability evaluation model of the cloud platform when the error of the reliability probability of the cloud platform meets the preset requirement, otherwise, adjusting parameters of the network model to be trained and retraining until the error of the reliability probability of the cloud platform meets the preset requirement.
In this embodiment, the loss function L is defined as:
L＝E (S,H)～γ [∑||H-S||]
wherein H represents the trusted probability in the training data set, S represents the trusted probability of the cloud platform obtained by network calculation, and E (S,H)～γ Indicating the expectation of a confidence probability error in the training process.
Judging whether to end the network model training process according to the error of the cloud platform credibility of the network calculation, and if the error is larger than a threshold value, adjusting the network model updating weight and deviation parameters through an SAG random optimization algorithm, and carrying out model training again. If the error is smaller than or equal to the threshold value, the network training is stopped and the model is saved after the network training reaches the stable state.
Example two
The embodiment of the application provides a cloud platform credibility evaluation method, which is used for evaluating the credibility of a cloud platform.
Referring to fig. 5, the cloud platform trust evaluation method provided by the embodiment includes the following steps:
step S400, a cloud platform credible evaluation data set is obtained, wherein the cloud platform credible evaluation data set comprises cloud platform basic credible evaluation data and tenant perception credible evaluation data;
step 500, the cloud platform basic credibility evaluation data and tenant perception credibility evaluation data are respectively input into a cloud platform credibility evaluation model to perform cloud platform credibility evaluation, a cloud platform credibility evaluation result is obtained, and the cloud platform credibility evaluation model is trained according to the training method of the cloud platform credibility evaluation model.
According to the cloud platform credibility assessment method, the cloud platform basic data and the tenant perception credibility assessment data fed back by the tenant after use are comprehensively considered by the applied cloud platform credibility assessment model, so that the cloud platform credibility assessment model obtained through final training can truly reflect the feedback condition of the tenant on the cloud platform, and further accuracy and authenticity of the cloud platform credibility assessment result are improved.
Referring to fig. 6, in one embodiment, step S500, namely, inputting the cloud platform basic trust evaluation data and the tenant perception trust evaluation data into the cloud platform trust evaluation model to perform the cloud platform trust evaluation, and obtaining the cloud platform trust evaluation result includes the following steps:
step S510, carrying out vectorization processing and feature extraction on cloud platform basic credible evaluation data and tenant perception credible evaluation data through a cloud platform credible evaluation model to obtain a cloud platform basic feature vector and a tenant perception feature vector;
step S520, determining a tenant perception attention weight through an attention mechanism;
and step S530, splicing the tenant perception feature vector and the cloud platform basic feature vector to obtain a new feature vector, carrying out weighted summation on the new feature vector by utilizing the tenant perception attention weight, and obtaining the cloud platform credibility through nonlinear activation function and normalization processing.
The specific steps of the cloud platform credibility assessment method are similar to those of the cloud platform credibility assessment model training method provided by the first embodiment, and the difference is that the cloud platform credibility assessment method of the embodiment is to apply the model obtained by the first embodiment to carry out assessment, obtain data to be assessed, not training data, finally output the cloud platform credibility probability, and not carry out a convergence process. Therefore, specific steps of the cloud platform trust evaluation method can be referred to the corresponding descriptions in the first embodiment, and will not be repeated here.
Example III
The embodiment of the application provides a cloud platform credible evaluation model training device which is used for training and generating a cloud platform credible evaluation model.
Referring to fig. 7, the cloud platform trusted evaluation model training apparatus provided in this embodiment includes a first acquisition module 100 and a training module 200.
The first obtaining module 100 is configured to obtain a cloud platform trusted evaluation training data set, where the cloud platform trusted evaluation training data set includes cloud platform base trusted evaluation training data and tenant perception trusted evaluation training data;
the training module 200 is configured to input the cloud platform basic trust evaluation training data and the tenant perception trust evaluation training data to the network model to be trained, respectively, and train the network model to be trained until the network model to be trained meets a preset requirement, thereby obtaining the cloud platform trust evaluation model.
According to the cloud platform credibility evaluation model training device, the cloud platform basic credibility evaluation training data and the tenant perception credibility evaluation training data are contained in the training data set, the cloud platform basic data and the tenant perception credibility evaluation data fed back by the tenant after use are comprehensively considered in the training process, so that the finally trained cloud platform credibility evaluation model can truly reflect the feedback condition of the tenant to the cloud platform, and further accuracy and authenticity of the cloud platform credibility evaluation result are improved.
In one embodiment, the first acquisition module 100 includes:
the evaluation attribute acquisition unit is used for acquiring cloud platform basic class evaluation attributes and tenant perception evaluation attributes;
the training data set forming unit is used for carrying out quantization processing on the cloud platform basic class evaluation attribute and the tenant perception evaluation attribute to obtain cloud platform basic credible evaluation training data and tenant perception credible evaluation training data, and forming a cloud platform credible evaluation training data set;
in one embodiment, the training data set forming unit includes:
the first determining unit is used for determining the credibility probability of the basic class evaluation attribute of each cloud platform according to the fuzzy theory;
the second determining unit is used for determining tenant perception credible evaluation results of the tenant perception evaluation attributes according to the evaluation scores fed back by the tenants;
and the third determining unit is used for forming a cloud platform credibility evaluation training data set according to the cloud platform basic class evaluation attribute, the credibility probability and the tenant perception credibility evaluation result.
In one embodiment, training module 200 includes:
the first processing unit is used for carrying out vectorization processing and feature extraction on the cloud platform basic credible evaluation training data through the network model to be trained to obtain a cloud platform basic feature vector.
And the second processing unit is used for carrying out vectorization processing and feature extraction on the tenant perception credibility evaluation training data through the network model to be trained to obtain tenant perception feature vectors.
And the third processing unit is used for determining the perception attention weight of the tenant through an attention mechanism.
And the fourth processing unit is used for splicing the tenant perception feature vector and the cloud platform basic feature vector to obtain a new feature vector, carrying out weighted summation on the new feature vector by utilizing the tenant perception attention weight, and obtaining the cloud platform credibility through nonlinear activation function and normalization processing.
And the fifth processing unit is used for calculating the error of the reliability probability of the cloud platform according to the loss function, obtaining a reliability evaluation model of the cloud platform when the error of the reliability probability of the cloud platform meets the preset requirement, otherwise, adjusting parameters of the network model to be trained, and retraining until the error of the reliability probability of the cloud platform meets the preset requirement.
The cloud platform trusted evaluation model training device provided in the present embodiment and the cloud platform trusted evaluation model training method provided in the first embodiment belong to the same inventive concept, and specific content can be referred to the related description in the first embodiment and is not repeated here.
Example IV
The embodiment of the application provides a cloud platform credibility assessment device which is used for carrying out cloud platform credibility assessment.
Referring to fig. 8, the cloud platform trusted evaluation device provided in this embodiment includes a second obtaining module 300 and an evaluating module 400.
The second obtaining module 300 is configured to obtain a cloud platform trusted evaluation data set, where the cloud platform trusted evaluation data set includes cloud platform base trusted evaluation data and tenant-aware trusted evaluation data;
the evaluation module 400 is configured to input the cloud platform basic reliability evaluation data and the tenant perception reliability evaluation data into the cloud platform reliability evaluation model to perform the cloud platform reliability evaluation, and obtain a cloud platform reliability evaluation result, where the cloud platform reliability evaluation model is trained according to the training method of the cloud platform reliability evaluation model.
According to the cloud platform credibility assessment device, the cloud platform basic data and the tenant perception credibility assessment data fed back by the tenant after the use are comprehensively considered by the applied cloud platform credibility assessment model, so that the feedback condition of the tenant to the cloud platform can be truly reflected by the cloud platform credibility assessment model finally obtained through training, and the accuracy and the authenticity of the cloud platform credibility assessment result are improved.
In one embodiment, the assessment module 400 includes:
the first determining unit is used for carrying out vectorization processing and feature extraction on the cloud platform basic credible evaluation data and the tenant perception credible evaluation data through the cloud platform credible evaluation model to obtain a cloud platform basic feature vector and a tenant perception feature vector;
a second determining unit, configured to determine, through an attention mechanism, a tenant-perceived attention weight;
and the third determining unit is used for splicing the tenant perception feature vector and the cloud platform basic feature vector to obtain a new feature vector, carrying out weighted summation on the new feature vector by utilizing the tenant perception attention weight, and obtaining the cloud platform credibility through nonlinear activation function and normalization processing.
The cloud platform trust evaluation device provided in the present embodiment and the cloud platform trust evaluation method provided in the second embodiment belong to the same inventive concept, and specific content can be referred to the related description in the second embodiment, which is not repeated here.
Example five
The embodiment of the present application provides an electronic device, as shown in fig. 9, including a memory 500 and a processor 600, where the memory 500 and the processor 600 are communicatively connected to each other by a bus or other means, and fig. 9 is an example of a connection through a bus.
The processor 600 may be a central processing unit (Central Processing Unit, CPU). The processor 600 may also be a chip such as other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination thereof.
The memory 500 is used as a non-transitory computer readable storage medium, and can be used to store a non-transitory software program, a non-transitory computer executable program, and a module, such as a cloud platform trusted evaluation model training method or a program instruction corresponding to the cloud platform trusted evaluation method in the embodiment of the present invention. The processor 600 executes various functional applications and data processing of the processor 600, i.e., a cloud platform trust evaluation model training method or a cloud platform trust evaluation method, by running non-transitory software programs, instructions, and modules stored in the memory 500.
The memory 500 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created by the processor 600, etc. In addition, memory 500 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 500 optionally includes memory remotely located relative to processor 600, which may be connected to the processor via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
It will be appreciated by those skilled in the art that implementing all or part of the above-described embodiment method may be implemented by a computer program to instruct related hardware, where the program may be stored in a computer readable storage medium, and the program may include the above-described embodiment method when executed. Wherein the storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a Flash Memory (Flash Memory), a Hard Disk (HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the kind described above.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (9)
1. A cloud platform trust evaluation model training method, the method comprising:
acquiring cloud platform basic class evaluation attributes and tenant perception evaluation attributes;
performing quantization processing on the cloud platform basic class evaluation attribute and the tenant perception evaluation attribute to obtain cloud platform basic credible evaluation training data and tenant perception credible evaluation training data, and forming a cloud platform credible evaluation training data set; the method comprises the steps of carrying out quantization processing on the cloud platform basic class evaluation attribute and the tenant perception evaluation attribute to obtain cloud platform basic credible evaluation training data and tenant perception credible evaluation training data, and forming a cloud platform credible evaluation training data set, and comprises the following steps:
determining the credibility probability of the evaluation attribute of each cloud platform basic class according to the fuzzy theory;
determining tenant perception credibility evaluation results of the tenant perception evaluation attributes according to the evaluation scores fed back by the tenants;
forming a cloud platform credible evaluation training data set according to the cloud platform basic class evaluation attribute, the credible probability and the tenant perception credible evaluation result;
and respectively inputting the cloud platform basic credible evaluation training data and the tenant perception credible evaluation training data into a network model to be trained, and training the network model to be trained until the network model to be trained meets the preset requirement, so as to obtain the cloud platform credible evaluation model.
2. The cloud platform trust evaluation model training method of claim 1, wherein the cloud platform base class evaluation attributes comprise reliability, security and availability, the reliability comprising robustness, controllability and failure level, the security comprising cloud platform cryptographic mechanisms, network security, tenant data security, security isolation, tenant authentication and access control policies and policy enforcement, the availability comprising service availability and component loading;
the tenant perception evaluation attribute comprises service quality perception, self-behavior perception, integrity perception and confirmation perception, wherein the service quality perception is measured according to task resource matching degree, the self-behavior perception is measured according to behavior feasible access control, the integrity perception is measured according to credibility of cloud service provider SLA promise, and the confirmation perception is measured according to confirmation of key operation of the tenant participating in cloud service.
3. The method for training the cloud platform trusted evaluation model according to claim 1, wherein the step of inputting the cloud platform basic trusted evaluation training data and the tenant perceived trusted evaluation training data to a network model to be trained and training the network model to be trained until the network model to be trained meets a preset requirement, respectively, comprises the following steps:
performing vectorization processing and feature extraction on the cloud platform basic credible evaluation training data through a network model to be trained to obtain a cloud platform basic feature vector;
vectorization processing and feature extraction are carried out on the tenant perception credibility assessment training data through a network model to be trained, and tenant perception feature vectors are obtained;
determining a tenant perception attention weight through an attention mechanism;
splicing the tenant perception feature vector and the cloud platform basic feature vector to obtain a new feature vector, carrying out weighted summation on the new feature vector by utilizing tenant perception attention weight, and obtaining the cloud platform credibility through nonlinear activation function and normalization processing;
and calculating the error of the cloud platform credibility according to the loss function, and obtaining a cloud platform credibility assessment model when the error of the cloud platform credibility meets a preset requirement, otherwise, adjusting parameters of the network model to be trained and retraining until the error of the cloud platform credibility meets the preset requirement.
4. A method for evaluating trust of a cloud platform, the method comprising:
acquiring a cloud platform credible evaluation data set, wherein the cloud platform credible evaluation data set comprises cloud platform basic credible evaluation data and tenant perception credible evaluation data;
the cloud platform basic credible evaluation data and the tenant perception credible evaluation data are respectively input into a cloud platform credible evaluation model to carry out cloud platform credible evaluation, a cloud platform credible evaluation result is obtained, and the cloud platform credible evaluation model is trained according to the cloud platform credible evaluation model training method according to any one of claims 1-3.
5. The method for evaluating the trust of the cloud platform according to claim 4, wherein the step of inputting the basic trust evaluation data of the cloud platform and the tenant perception trust evaluation data of the cloud platform into a trust evaluation model of the cloud platform to evaluate the trust of the cloud platform, and obtaining the trust evaluation result of the cloud platform comprises the following steps:
performing vectorization processing and feature extraction on the cloud platform basic credible evaluation data and the tenant perception credible evaluation data through a cloud platform credible evaluation model to obtain a cloud platform basic feature vector and a tenant perception feature vector;
determining a tenant perception attention weight through an attention mechanism;
and splicing the tenant perception feature vector and the cloud platform basic feature vector to obtain a new feature vector, carrying out weighted summation on the new feature vector by utilizing tenant perception attention weight, and obtaining the cloud platform credibility through nonlinear activation function and normalization processing.
6. A cloud platform trust evaluation model training apparatus, the apparatus comprising:
the first acquisition module is used for acquiring cloud platform basic class evaluation attributes and tenant perception evaluation attributes; performing quantization processing on the cloud platform basic class evaluation attribute and the tenant perception evaluation attribute to obtain cloud platform basic credible evaluation training data and tenant perception credible evaluation training data, and forming a cloud platform credible evaluation training data set; wherein the first acquisition module is executing: acquiring cloud platform basic class evaluation attributes and tenant perception evaluation attributes; performing quantization processing on the cloud platform basic class evaluation attribute and the tenant perception evaluation attribute to obtain cloud platform basic credible evaluation training data and tenant perception credible evaluation training data, and forming a cloud platform credible evaluation training data set comprises: determining the credibility probability of the evaluation attribute of each cloud platform basic class according to the fuzzy theory; determining tenant perception credibility evaluation results of the tenant perception evaluation attributes according to the evaluation scores fed back by the tenants; forming a cloud platform credible evaluation training data set according to the cloud platform basic class evaluation attribute, the credible probability and the tenant perception credible evaluation result;
the training module is used for respectively inputting the cloud platform basic credible evaluation training data and the tenant perception credible evaluation training data into a network model to be trained, and training the network model to be trained until the network model to be trained meets the preset requirement, so as to obtain the cloud platform credible evaluation model.
7. A cloud platform trust evaluation apparatus, the apparatus comprising:
the system comprises a cloud platform base trusted evaluation data set and a tenant perception trusted evaluation data set, wherein the cloud platform base trusted evaluation data set comprises a cloud platform base trusted evaluation data set and a tenant perception trusted evaluation data set;
the evaluation module is used for inputting the cloud platform basic credible evaluation data and the tenant perception credible evaluation data into a cloud platform credible evaluation model respectively to perform cloud platform credible evaluation to obtain a cloud platform credible evaluation result, and the cloud platform credible evaluation model is trained according to the cloud platform credible evaluation model training method according to any one of claims 1-5.
8. An electronic device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the cloud platform trust evaluation model training method according to any one of claims 1-3 or the cloud platform trust evaluation method according to claim 4 or 5 when executing the computer program.
9. A computer readable storage medium, wherein computer instructions are stored in the computer readable storage medium, which when executed by a processor, implement the cloud platform trust evaluation model training method according to any one of claims 1-3 or the cloud platform trust evaluation method according to claim 4 or 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110117542.7A CN112884016B (en) | 2021-01-28 | 2021-01-28 | Cloud platform credibility assessment model training method and cloud platform credibility assessment method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110117542.7A CN112884016B (en) | 2021-01-28 | 2021-01-28 | Cloud platform credibility assessment model training method and cloud platform credibility assessment method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112884016A CN112884016A (en) | 2021-06-01 |
| CN112884016B true CN112884016B (en) | 2024-02-02 |
Family
ID=76052934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110117542.7A Active CN112884016B (en) | 2021-01-28 | 2021-01-28 | Cloud platform credibility assessment model training method and cloud platform credibility assessment method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112884016B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610225A (en) * | 2021-07-14 | 2021-11-05 | 中国银行股份有限公司 | Quality evaluation model training method and device, electronic equipment and storage medium |
| CN114154891B (en) * | 2021-12-08 | 2024-08-23 | 中国建设银行股份有限公司 | Retraining method and device for risk control model |
| CN114500048B (en) * | 2022-01-26 | 2023-10-03 | 南方电网数字电网研究院有限公司 | External threat information analysis method and system based on network security |
| CN115757273B (en) * | 2022-10-24 | 2023-09-15 | 江苏中科西北星信息科技有限公司 | Cloud platform-based pension policy data management method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105577726A (en) * | 2014-10-17 | 2016-05-11 | 青岛鑫益发工贸有限公司 | Service level protocol based trust negotiation system under cloud computing platform |
| CN106992994A (en) * | 2017-05-24 | 2017-07-28 | 腾讯科技（深圳）有限公司 | A kind of automatically-monitored method and system of cloud service |
| CN109685526A (en) * | 2018-12-12 | 2019-04-26 | 税友软件集团股份有限公司 | A kind of method for evaluating credit rating of enterprise, device and relevant device |
| WO2020168459A1 (en) * | 2019-02-19 | 2020-08-27 | Suanhua Intelligent Technology Co., Ltd. | System and method for credit assessment |
| CN111611129A (en) * | 2020-05-12 | 2020-09-01 | 中国工商银行股份有限公司 | Performance monitoring method and device of PaaS cloud platform |
-
2021
- 2021-01-28 CN CN202110117542.7A patent/CN112884016B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105577726A (en) * | 2014-10-17 | 2016-05-11 | 青岛鑫益发工贸有限公司 | Service level protocol based trust negotiation system under cloud computing platform |
| CN106992994A (en) * | 2017-05-24 | 2017-07-28 | 腾讯科技（深圳）有限公司 | A kind of automatically-monitored method and system of cloud service |
| CN109685526A (en) * | 2018-12-12 | 2019-04-26 | 税友软件集团股份有限公司 | A kind of method for evaluating credit rating of enterprise, device and relevant device |
| WO2020168459A1 (en) * | 2019-02-19 | 2020-08-27 | Suanhua Intelligent Technology Co., Ltd. | System and method for credit assessment |
| CN111611129A (en) * | 2020-05-12 | 2020-09-01 | 中国工商银行股份有限公司 | Performance monitoring method and device of PaaS cloud platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112884016A (en) | 2021-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112884016B (en) | Cloud platform credibility assessment model training method and cloud platform credibility assessment method | |
| US11651247B2 (en) | Method for verifying lack of bias of deep learning AI systems | |
| US10346782B2 (en) | Adaptive augmented decision engine | |
| CN108197652B (en) | Method and apparatus for generating information | |
| US20180268306A1 (en) | Using Different Data Sources for a Predictive Model | |
| US10067746B1 (en) | Approximate random number generator by empirical cumulative distribution function | |
| US20210117786A1 (en) | Neural networks for scalable continual learning in domains with sequentially learned tasks | |
| CN112231592B (en) | Graph-based network community discovery method, device, equipment and storage medium | |
| CN113268336B (en) | Service acquisition method, device, equipment and readable medium | |
| US11763189B2 (en) | Method for tracking lack of bias of deep learning AI systems | |
| CN110533419B (en) | Block chain-based sharing method, device and server of wind control model | |
| WO2012018574A1 (en) | System and method to measure and track trust | |
| WO2017089443A1 (en) | System and method for aiding decision | |
| US20220044109A1 (en) | Quantization-aware training of quantized neural networks | |
| US20160364810A1 (en) | Hybrid classification system | |
| CN114679341A (en) | Network intrusion attack analysis method, equipment and medium combined with ERP system | |
| CN111340245A (en) | Model training method and system | |
| JP7440984B2 (en) | Highly efficient circuit simulation methods, devices, equipment and storage media | |
| US7072795B2 (en) | Method and system for modeling a system | |
| CN112749839B (en) | Model determination method, device, equipment and storage medium | |
| CN112598241A (en) | Risk assessment method, device and system and computer readable storage medium | |
| CN114692888A (en) | System parameter processing method, device, equipment and storage medium | |
| Jiménez‐Gamero et al. | Testing for the symmetric component in skew distributions | |
| CN118171917B (en) | Risk assessment method and device for network asset, computer equipment and storage medium | |
| CN113159773B (en) | Method and device for generating quantized transaction return data |
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 |