Zero-trust network node dynamic trust degree evaluation and intelligent resource allocation method, device and medium

Abstract

The application relates to a zero-trust network node dynamic trust degree evaluation and intelligent resource allocation method, device and medium. Based on the principle of 'never trust, continuously verify', the application continuously collects and processes information of all interactive nodes in a zero-trust network environment, constructs a node trust degree calculation model based on the processed data, and dynamically optimizes weight parameters through a trust degree evaluation layer; a dynamic trust threshold is set according to the node trust degree, an access control strategy is adjusted in the decision layer, and resource hierarchical allocation is implemented. In addition, the application introduces a continuous authentication and anomaly detection mechanism, monitors node behavior in real time, dynamically adjusts the trust strategy and limits abnormal access; based on behavior, context and real-time trust evaluation, the application realizes fine access control and resource management, can effectively prevent internal threats, abuse of rights and potential attacks, meets the security requirements in a complex and dynamic environment, and further improves the trust management efficiency and the rationality of resource scheduling.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cyberspace security, and in particular to a zero-trust network node dynamic trust degree evaluation and intelligent resource allocation method, device and medium. BACKGROUND

[0002] With the development of cloud computing, big data, Internet of Things and other technologies, the number of devices and users in cyberspace has increased dramatically, and the security risks of cyberspace have also expanded. Traditional network security protection technology mainly relies on border defense and static trust model, which gradually reveals its drawbacks in complex and dynamic network environment:

[0003] (1) Limitations of border defense: The traditional border defense model assumes that nodes within the network are trusted, but devices and users within the network may also be controlled by attackers, providing a breakthrough for attacks.

[0004] (2) Static trust model: Once a user or node passes the initial verification, it is considered trusted, lacking continuous monitoring and dynamic evaluation of subsequent behavior, which can easily lead to internal threats.

[0005] (3) Attack surface expansion: Attackers can move horizontally through legitimate authenticated nodes, endangering the entire system.

[0006] (4) Unreasonable resource allocation: Lack of dynamic real-time trust evaluation mechanism, leading to rigid resource allocation, unable to regulate according to the real-time trust level of nodes, resulting in waste of resources.

[0007] In the prior art, some research attempts to introduce a dynamic trust model in network access control. For example: a trust calculation method based on device historical behavior scoring, but it cannot effectively respond to real-time changes in complex networks, and the weight allocation of trust degree is dominated by humans, lacking intelligent optimization mechanism, and it is difficult to reflect the actual scene.

[0008] In view of this, the present method is proposed in combination with the zero-trust security architecture. The zero-trust architecture is based on the principle of "never trust, always verify", and proposes to continuously and dynamically evaluate the trust degree of nodes, requiring network access control not only to rely on user identity verification, but also to continuously monitor and adjust the trust state based on behavior and real-time context evaluation, to meet the needs of complex environments that change in real time, and to achieve efficient trust management and reasonable resource allocation. SUMMARY

[0009] In view of the deficiencies of the prior art, the present application provides a zero-trust network node dynamic trust degree evaluation and intelligent resource allocation method, device and medium, solves the problem that the traditional method cannot effectively cope with real-time changes in a complex network, and the weight distribution of the trust degree is dominated by people, lacks intelligent optimization mechanism, and is difficult to reflect actual scene problems, that is, aims to solve the problem of static trust evaluation and rigid management of traditional access control. The method continuously and dynamically evaluates the trust degree of the node, requires that the network access control not only depends on user identity authentication, but also continuously and dynamically monitors and adjusts the trust state based on behavior and real-time context evaluation to meet the needs of complex environments that change in real time, and thus achieves efficient trust management and reasonable resource allocation.

[0010] To solve the above technical problems, the present application provides the following technical solutions: a zero-trust network node dynamic trust degree evaluation and intelligent resource allocation method, comprising the following steps:

[0011] S1, collecting information of all interactive nodes in a zero-trust network environment;

[0012] S2, after collecting information, performing denoising, filling and normalization cleaning processing on the data;

[0013] S3, designing a trust degree calculation formula for the node according to the collected information, and dynamically optimizing weight parameters a, b, g, h, 1, 2, 3 based on the processed data through a node trust degree evaluation layer;

[0014] S4, setting a corresponding trust threshold according to the trust degree of the node, dynamically adjusting the threshold in the decision layer, and distributing a resource hierarchical access control strategy.

[0015] Further, in step S1, in step S1, the information of all interactive nodes in the zero-trust network environment is collected, specifically including: an interaction success rate I i : a statistical proportion of whether the data transmission between nodes is successful; a response time R i : a response delay time of inter-node communication; a resource consumption rate C i : bandwidth, CPU, storage resources consumed in the node access or interaction process; historical behavior credibility A i : access history and abnormal behavior detection results of the node.

[0016] More specifically, in step S1, environmental authentication information collection is also included: using device management protocol, timestamp and IP geographical location resolution to obtain device health status, access time and geographical location information respectively, which are added to the trust evaluation, further strengthening the idea of multi-factor authentication of zero trust architecture, wherein the device health status: not only verifies the user identity, but also verifies whether the device is in a safe state, that is, whether the latest security patch is installed, whether there is malicious software; Access time and location: according to the access time and location, it is evaluated whether it belongs to the normal access mode to prevent unauthorized access after stealing user identity through phishing.

[0017] Further, in step S2, after information collection, the data is denoised, filled and normalized for cleaning processing, and the specific process includes the following steps:

[0018] S21, denoising processing is performed by using wavelet transform to decompose the signal into different frequency domains, and high-frequency sound is filtered:

[0019]

[0020] Wherein, c(m,n) is the wavelet coefficient, m is the scale parameter, which controls the stretching degree of the wavelet function, corresponding to different frequency bands in the frequency domain, n is the translation parameter, which determines the position of the wavelet function on the time axis, is the wavelet basis function;

[0021] S22, based on the statistics of similar nodes, the missing values and abnormal values in the data are filled, first define the similarity measure:

[0022]

[0023] Wherein, Node a ,Node b represent two network nodes to be compared, x a,i is the feature value of node a in the i-th feature dimension, x b,i is the feature value of node b in the i-th feature dimension;

[0024] Then according to the similarity, select the k most similar nodes from high to low, fill the missing values with the mean value of similar nodes, and then correct the abnormal values:

[0025]

[0026] Wherein, x j is the jth of the k most similar nodes, and j takes a value from 1 to k;

[0027] S23, using Min-max normalization method, all data X iThe specifications are normalized into the same scale range [0, 1] where i = 1, …, k, so as to better perform the weighted calculation, and the normalized data X is obtained i :

[0028]

[0029] where X min ,X max correspond to the minimum and maximum values of each variable.

[0030] Further, in step S3, the trust degree calculation formula of the node is designed according to the collected information, and the weight parameters α, β, γ, η, θ1, θ2, θ3 are dynamically optimized by the node trust degree evaluation layer based on the processed data, and the specific process includes the following steps:

[0031] S31, according to the collected information, the node trust degree calculation formula is designed:

[0032]

[0033] where σ(·) is a normalization function, and the trust value is normalized to the range [0, 1], T i ,I i ,R i ,C i ,A i ,E i respectively represent the trust degree, interaction success rate, response time, resource consumption rate, historical behavior credibility and current environment context variable of the node, and the non-linear mapping functions f(I i ,R i ), g(C i ,A i ) are respectively the relationship functions of interaction success rate and response time and the relationship functions of resource consumption rate and historical behavior, d(E i ) is a dynamic environment factor, and α, β, γ, η are weight parameters corresponding to each factor; γ is a basic adjustment parameter, used to balance the influence of the numerator weight and the environment factor;

[0034] In addition, the relationship function f(I i ,R i ) of interaction success rate and response time is:

[0035]

[0036] where θ1, θ2, θ3 are weight coefficients, optimized by algorithm;

[0037] The relationship function g(C i ,A i ) of resource consumption rate and historical behavior is:

[0038] g(C i ,A i )=log(1+C i )·(1-A i );

[0039] Dynamic environmental factor d(E i ):

[0040] d(E i )=α1·H i +α2·M i +α3·G i ;

[0041] wherein, H i , M i , G i ∈[0,1] are the device health status, access time and geographical location respectively, and α1, α2, α3 are the weights of H i , M i , G i respectively;

[0042] S32, the weights α, β, γ, η in the trust degree calculation formula are solved by using a particle swarm algorithm;

[0043] S33, the weight parameters θ1, θ2, θ3 in the relationship function f(I i , R i ) of the interaction success rate and the response time are solved by using a gradient descent method.

[0044] Further, in step S32, the weights α, β, γ, η in the trust degree calculation formula are solved by using a particle swarm algorithm, and the specific process includes the following steps:

[0045] S321, initialize parameters: set the number of particles N, the search range is [0, 1], and initialize the weight parameters α, β, γ, η and the speed v of each particle;

[0046] S322, fitness function evaluation design, using the accuracy of trust evaluation results and system security as the fitness evaluation standard:

[0047] Fitness(α, β, γ, η)=λ1·Accuracy(α, β, γ, η)-λ2·Risk(α, β, γ, η);

[0048] wherein, Accuracy(α, β, γ, η) is the trust degree accuracy calculated based on the optimized weights, Risk(α, β, γ, η) is the security risk of the system, which measures the influence of malicious nodes or attacks, and λ1, λ2 are adjustment coefficients;

[0049]

[0050] Risk = ∑ (Abnormal request rate + Failure rate + High-risk behavior frequency)

[0051] Where, T i True is the real trust degree of node i, T i pred is the predicted trust degree of node i, n is the total number of samples in the verification set (the number of nodes participating in the evaluation)

[0052] S323, update the global optimal solution and the local optimal solution

[0053] S324, update the particle velocity:

[0054]

[0055] Where, ω is the inertia weight, which controls the tendency of particles to maintain the original speed, c1, c2 are cognitive factors and social coefficients, which control the influence of individual experience and group experience respectively, is the local optimal solution, is the global optimal solution, x i is the position of the particle, r1, r2 are random numbers in the interval [0, 1], which are used to maintain population diversity;

[0056] Update the particle position:

[0057] x i+1 = x i + v i+1 ;

[0058] S325, when the fitness value meets the accuracy requirement or the upper limit of the number of iterations, output the optimal weight parameters α, β, γ, η.

[0059] Further, in step S33, the gradient descent method is used to solve the weight parameters θ1, θ2, θ3 in the relationship function f(I i , R i ) of interaction success rate and response time, and the specific process includes the following steps:

[0060] S331, collect data: obtain the historical data of interaction success rate I i and response time R i ;

[0061] S332, define the target loss function:

[0062] Loss = ∑ |T i True-f(I i ,R i )|;

[0063] wherein, T i True is the real trust degree of node i;

[0064] S333, initialize weight parameters θ1, θ2, θ3 and learning rate η;

[0065] S334, use gradient descent method to solve the update weight parameters θ1, θ2, θ3:

[0066]

[0067] wherein, θ k is the kth weight parameter to be optimized, k is 1 to 3;

[0068] S334, when the loss function converges or reaches the iteration limit, output the optimal weight parameters θ1, θ2, θ3.

[0069] Further, in step S4, the corresponding trust threshold is set according to the trust degree of the node, the dynamic threshold adjustment of trust is carried out in the decision layer, and the allocation of resource hierarchical access control strategy is carried out, and the specific process includes the following steps:

[0070] S41, dynamic threshold setting and access control:

[0071] T threshold = μ·avg(T) + σ·std(T);

[0072] Wherein, μ, σ are the average value and standard deviation of threshold adjustment, representing the balanced state of all nodes in the current network, avg(T), std(T) are the average value and standard deviation of trust degree, respectively, by dynamically adjusting these threshold values, it can be ensured that the system adjusts the access right and resource allocation in real time according to the network state;

[0073] S42, input the trust degree T i of each node, adjust the trust degree threshold according to the current network environment and resource allocation requirements, and carry out resource hierarchical allocation:

[0074] High trust degree node: if allow the node to access sensitive resources, and preferentially allocate high performance resources;

[0075] Medium trust degree node: if allow the node to access ordinary resources, limit part of the operation right;

[0076] Low trust degree node: if Limiting node access, and restoring when the trust value returns to a set threshold.

[0077] By the above technical solution, the application provides a zero-trust network node dynamic trust evaluation and intelligent resource allocation method, device and medium, which has at least the following beneficial effects:

[0078] 1. The application ensures the data accuracy, integrity and effectiveness in the trust evaluation process through denoising, filling and normalization of the obtained information data, so as to enhance the accuracy of trust evaluation.

[0079] 2. According to the node interaction information: interaction success rate, response time, resource consumption rate and environmental factors, a trust value calculation formula is designed, the weights of each variable are determined by using an intelligent algorithm, the weights are solved by the trust value calculation formula and the intelligent algorithm, the dynamic real-time evaluation of node trust is realized, and the defects of the static trust model are solved; the intelligent algorithm is used to solve the weights, and the intelligent algorithm is automatically adjusted with the change of the network environment, the adaptive update of the intelligent algorithm is realized, the disadvantages of human guidance are avoided, and it is ensured that the node evaluation model can adapt to the complex and changeable network environment.

[0080] 3. The application introduces a continuous authentication and anomaly detection mechanism, monitors node behavior in real time, dynamically adjusts trust strategy and limits abnormal access, sets an access control threshold based on a dynamic trust value, realizes reasonable allocation and safe transmission of resources, and efficient resource allocation and access control improve the flexibility and security of network resource management, and realize the zero-trust security principle: strictly follow the security concept of "never trust, continuous verification", continuously and dynamically evaluate all nodes, prevent potential security threats, and enhance the security protection capability of the network.

[0081] 4. Compared with the traditional static identity authentication mode, the application is based on behavior, context and real-time trust evaluation, realizes fine access control and resource management, can effectively prevent internal threats, abuse of authority and potential attacks, meets the security requirements in complex and dynamic environments, and further improves the trust management efficiency and the rationality of resource scheduling. BRIEF DESCRIPTION OF DRAWINGS

[0082] The drawings described herein are used to provide further understanding of the present application, and constitute a part of the present application, the illustrative embodiments of the present application and the description thereof are used to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0083] Figure 1 It is a zero-trust security architecture framework based on dynamic trust evaluation of the application;

[0084] Figure 2 It is a flowchart for solving parameters alpha, beta, gamma and eta by using a particle swarm algorithm;

[0085] Figure 3 Flow chart for solving parameters θ1, θ2, θ3 of the present application using gradient descent method;

[0086] Figure 4 Flow chart for dynamic threshold setting and access control of the present application. DETAILED DESCRIPTION

[0087] In order to make the above objectives, characteristics and advantages of the present application more obvious and easy to understand, the present application will be further described in detail below with reference to the drawings and specific embodiments. The implementation process of how to apply technical means to solve technical problems and achieve technical effects can be fully understood and implemented by the present application.

[0088] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment methods can be completed by programs instructing related hardware, therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0089] Please refer to Figures 1-4 , which shows a specific embodiment of the present embodiment, the present embodiment is based on the principle of "never trust, continuous verification", the present application continuously collects information of all interactive nodes in a zero trust network environment, and performs denoising, filling and normalization processing on the data to ensure the integrity of the data. Based on the processed data, a node trust degree calculation model is constructed, and the weight parameters are dynamically optimized through the trust degree evaluation layer; according to the node trust degree, a dynamic trust threshold is set, the access control strategy is adjusted in the decision layer, and the resource hierarchical allocation is implemented. In addition, the present application introduces a continuous authentication and anomaly detection mechanism, which monitors the node behavior in real time, dynamically adjusts the trust strategy and limits abnormal access, and ensures the security and flexibility of the system. Compared with the traditional mode based on static identity authentication, the present application is based on behavior, context and real-time trust evaluation, realizes fine access control and resource management, can effectively prevent internal threats, abuse of authority and potential attacks, meets the security needs in complex and dynamic environment, and further improves the efficiency of trust management and the rationality of resource scheduling.

[0090] Please refer to Figure 1 , the present embodiment proposes a zero trust network node dynamic trust degree evaluation and intelligent resource allocation method, which includes the following steps:

[0091] S1, collecting information of all interactive nodes in a zero trust network environment;

[0092] As a preferred embodiment of step S1, in step S1, the information collection of all interaction nodes in the zero trust network environment specifically includes: interaction success rate I i : statistical proportion of whether the data transmission between nodes is successful; response time R i : response delay time of inter-node communication; resource consumption rate C i : bandwidth, CPU, storage resources consumed in the node access or interaction process; historical behavior credibility A i : access history of the node, and abnormal behavior detection result;

[0093] In the zero trust network environment, the success or failure state of each interaction request is recorded by using network access logs, the resource consumption is obtained from the resource monitoring module of the node system, the delay time is extracted from the communication protocol, and the response time is recorded, so as to calculate:

[0094] ① Interaction success rate I i :

[0095]

[0096] Wherein, N total is the total number of communications between the node and other nodes, and N success is the number of successful times.

[0097] ② Response time R i :

[0098]

[0099] Wherein, T i is the response time of the ith interaction, and N t is the total number of interactions.

[0100] ③ Resource consumption rate C i :

[0101]

[0102] Wherein, U i is the resource consumed in the ith interaction process, and N t is the total number of interactions.

[0103] ④ Historical behavior credibility A i : analyze the past access logs of the node to identify abnormal behaviors such as excessive failed requests.

[0104] More specifically, step S1 also includes environmental authentication information collection: using device management protocols, timestamps, and IP geolocation resolution to obtain device health status, access time, and geolocation information, and incorporating them into the trust assessment to further strengthen the concept of multi-factor authentication in a zero-trust architecture. Among these, device health status: not only verifying the user's identity, but also verifying whether the device is in a secure state, i.e., whether the latest security patches are installed and whether there is malware; access timing and location: based on the timing and location of the access, assessing whether it belongs to a normal access pattern to prevent unauthorized access after stealing the user's identity through phishing or other means.

[0105] S2. After information collection, invalid and duplicate data are cleaned by denoising, filling and normalizing.

[0106] As a preferred embodiment of step S2, in step S2, after information collection, the data undergoes cleaning processes such as noise reduction, data filling, and normalization. The specific process includes the following steps:

[0107] S21. Denoising is achieved using wavelet transform, which decomposes the signal into different frequency domains and filters out high-frequency noise.

[0108]

[0109] Where c(m,n) are the wavelet coefficients, m is the scaling parameter, which controls the scaling degree of the wavelet function and corresponds to different frequency bands in the frequency domain, and n is the translation parameter, which determines the position of the wavelet function on the time axis. These are wavelet basis functions;

[0110] S22. Based on the statistics of similar nodes, impute missing and outlier values ​​in the data. First, define a similarity metric:

[0111]

[0112] Among them, Node a Node b Let x represent two network nodes to be compared. a,i The eigenvalue of node a in the i-th feature dimension, x b,i The feature value of node b in the i-th feature dimension;

[0113] Then, based on similarity, select the k most similar nodes from high to low. (N is the total number of nodes), missing values ​​are filled using the mean of similar nodes, thus correcting outliers:

[0114]

[0115] Where, x jFor the jth of the k most similar nodes, j ranges from 1 to k;

[0116] S23, using Min-max normalization method, all data X i (i = 1, …, k) is normalized to the same scale range, usually [0, 1], so as to better perform weighted calculation, and the normalized data X i :

[0117]

[0118] Where, X min ,X max Corresponding to the minimum, maximum value of each variable.

[0119] In this embodiment, through the cleaning processing of denoising, filling and normalization, the data accuracy and effectiveness in the trust degree calculation process are ensured, so as to enhance the accuracy of trust degree evaluation.

[0120] S3, according to the information collected, the trust degree calculation formula of the node is designed, and the weight parameters a, b, g, h, 0, 1, 0, 2, 0, 3 are dynamically optimized based on the processed data through the node trust degree evaluation layer;

[0121] As a preferred embodiment of step S3, in step S3, the trust degree calculation formula of the node is designed according to the information collected, and the weight parameters a, b, g, h, 0, 1, 0, 2, 0, 3 are dynamically optimized based on the processed data through the node trust degree evaluation layer, and the specific process includes the following steps:

[0122] S31, according to the information collected, the node trust degree calculation formula is designed:

[0123]

[0124] Where, σ(·) is a normalization function, which normalizes the trust value to the range of [0, 1], T i ,I i ,R i ,C i ,A i ,E i respectively represent the trust degree, interaction success rate, response time, resource consumption rate, historical behavior credibility and current environment context variable of the node, nonlinear mapping function f(I i ,R i ), g(C i ,A i ) are respectively the relationship functions of interaction success rate and response time and the relationship functions of resource consumption rate and historical behavior, d(E i) is a dynamic environmental factor, and a, b, g are weight parameters corresponding to each factor, and g is a basic adjustment parameter for balancing the influence of molecular weight and environmental factors;

[0125] In addition, the relationship function f(I i ,R i ) between the interaction success rate and the response time is:

[0126]

[0127] wherein, 1, 2, 3 are weight coefficients, which are optimized by an algorithm;

[0128] The relationship function g(C i ,A i ) between the resource consumption rate and the historical behavior is:

[0129] g(C i ,A i ) = log(1 + C i ) · (1 - A i );

[0130] The dynamic environmental factor d(E i ) is:

[0131] d(E i ) = a1·H i + a2·A i + a3·G i ;

[0132] wherein, H i , M i , G i ∈ [0, 1] are the device health status, access time and geographical location respectively, and a1, a2, a3 are the weights of H i , M i , G i respectively;

[0133] S32, the weights a, b, g, h in the trust degree calculation formula are solved by using a particle swarm algorithm;

[0134] More specifically, in step S32, the weights a, b, g, h in the trust degree calculation formula are solved by using a particle swarm algorithm, and the specific process includes the following steps:

[0135] S321, initialize parameters: set the number of particles N, the search range is [0, 1], initialize the weight parameters a, b, g, h and the speed v of each particle;

[0136] S322, fitness function evaluation design, using the accuracy of trust evaluation results and system security as the fitness evaluation standard:

[0137] Fitness(α,β,γ,η)=λ1·Accuracy(α,β,γ,η)-λ2·Risk(α,β,γ,η);

[0138] Where Accuracy(α,β,γ,η) is the trust accuracy calculated based on the optimized weights, Risk(α,β,γ,η) is the security risk of the system, which measures the impact of malicious nodes or attacks, and λ1 and λ2 are adjustment coefficients.

[0139]

[0140] Risk = ∑(abnormal request rate + failure rate + frequency of high-risk behavior);

[0141] Among them, T i True T represents the true trust level of node i. i pred Let n be the confidence level of the predicted node i, and n be the total number of samples in the validation set (the number of nodes participating in the evaluation).

[0142] S323, Update the global optimal solution and local optimal solution

[0143] S324, Update particle velocity:

[0144]

[0145] Where ω is the inertial weight, controlling the particle's tendency to maintain its original velocity, and c1 and c2 are cognitive factors and social coefficients, respectively controlling the influence of individual experience and group experience. For local optimal solutions, For the globally optimal solution, x i r1 and r2 are the positions of the particles, and are random numbers in the interval [0,1], used to maintain population diversity.

[0146] Update particle positions:

[0147] x i+1 =x i +v i+1 ;

[0148] S325. When the fitness value meets the accuracy requirement or the upper limit of the number of iterations, output the optimal weight parameters α, β, γ, η.

[0149] S33. Use the gradient descent method to solve the relationship function f(I) between the success rate of interaction and the response time. i ,R i The weight parameters θ1, θ2, θ3 in )

[0150] More specifically, in step S33, the weight parameters θ1, θ2, θ3 in the relationship function f(I i ,R i ) of the interaction success rate and the response time are solved by using the gradient descent method, and the specific process includes the following steps:

[0151] S331, collect data: obtain the historical data of the interaction success rate I i and the response time R i ;

[0152] S332, define the target loss function:

[0153] Loss = ∑ |T i True -f(I i ,R i ) |;

[0154] Wherein, T i True is the real trust degree of node i;

[0155] S333, initialize the weight parameters θ1, θ2, θ3 and the learning rate η;

[0156] S334, use the gradient descent method to solve the updated weight parameters θ1, θ2, θ3:

[0157]

[0158] Wherein, θ k is the kth weight parameter to be optimized, k is 1 to 3;

[0159] S334, output the optimal weight parameters θ1, θ2, θ3 when the loss function converges or reaches the iteration limit.

[0160] In this embodiment, according to the node interaction information: the interaction success rate, the response time, the resource consumption rate and the environmental factors, the trust value calculation formula is designed, the weights of each variable are determined by using the intelligent algorithm, the weights are solved by using the trust value calculation formula and the intelligent algorithm, the dynamic real-time evaluation of the node trust degree is realized, and the defects existing in the static trust model are solved; The intelligent algorithm is used to solve the weight, and is automatically adjusted with the change of the network environment, realizes the adaptive update of the intelligent algorithm, avoids the deficiency of human guidance, and ensures that the node evaluation model can adapt to the complex and changeable network environment.

[0161] S4, according to the trust degree of the node, set the corresponding trust threshold, adjust the dynamic threshold value in the decision layer, and distribute the resource hierarchical access control strategy.

[0162] As a preferred embodiment of step S4, in step S4, the corresponding trust threshold is set according to the trust degree of the node, the dynamic trust threshold adjustment is performed in the decision layer, and the allocation of the resource hierarchical access control strategy is performed, and the specific process includes the following steps:

[0163] S41, dynamic threshold setting and access control:

[0164] T threshold = mu avg (T) + sigma std (T) ;

[0165] Wherein, mu, sigma are the average value and standard deviation of threshold adjustment, respectively, representing the balanced state of all nodes in the current network, avg (T), std (T) are the average value and standard deviation of trust degree, respectively, by dynamically adjusting these thresholds, it can be ensured that the system adjusts the access right and resource allocation according to the network state in real time;

[0166] S42, input the trust degree T of each node i Adjust the trust degree threshold according to the current network environment and resource allocation requirements And carry out resource hierarchical allocation:

[0167] High trust degree node: if Allow the node to access sensitive resources, and preferentially allocate high-performance resources;

[0168] Medium trust degree node: if Allow the node to access ordinary resources and limit part of the operation right;

[0169] Low trust degree node: if Limit the node access, and restore when the trust degree value recovers to the set threshold.

[0170] In this embodiment, the access control threshold is set based on the dynamic trust value, the reasonable allocation and safe transmission of resources are realized, the efficient resource allocation and access control improve the flexibility and security of network resource management, and the implementation of the zero trust security principle: strictly follow the security concept of "never trust, continuous verification", continuously and dynamically evaluate all nodes, prevent potential security threats, and enhance the security protection ability of the network.

[0171] Specifically, the application also provides an electronic device, comprising: a memory and a processor, the memory is used for storing a computer program, and the processor runs the computer program to make the electronic device execute the zero trust network node dynamic trust degree evaluation and intelligent resource allocation method described above.

[0172] Specifically, the application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the zero-trust network node dynamic trust evaluation and intelligent resource allocation method.

[0173] To sum up, the application proposes to continuously and dynamically evaluate node trust, and requires network access control to not only rely on user identity authentication, but also continuously monitor and adjust trust status based on behavior and real-time context evaluation to meet the needs of complex environments that change in real time, thereby achieving efficient trust management and reasonable resource allocation.

[0174] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples without contradiction.

[0175] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a list of executable instructions for implementing logic functions, which can be specifically embodied in any computer readable medium for use by an instruction execution system, device or apparatus, such as a computer-based system, a system including a processor or other system that can fetch and execute instructions from the instruction execution system, device or apparatus, or in conjunction with these instructions execution system, device or apparatus.

[0176] The above embodiments have been described in detail, and the principles and embodiments of the application have been described in this paper. The above example is only used to help understand the method and core idea of the application; at the same time, for the general technical personnel in the art, according to the idea of the application, the specific embodiment and the application range will be changed; in view of the above, the content of the specification should not be understood as the limitation of the application.

Claims

1. A method for dynamic trust evaluation and intelligent resource allocation of zero trust network nodes, characterized in that, The method comprises the following steps: S1, collecting information of all interactive nodes in a zero-trust network environment; S2, after collecting information, performing denoising, filling and normalization cleaning processing on the data; S3, designing a node trust degree calculation formula according to the collected information, and dynamically optimizing weight parameters a, b, g, h, 1, 2, 3 based on the processed data through a node trust degree evaluation layer; S31, according to the collected information, a node trust degree calculation formula is designed: where σ(·) is a normalization function, which normalizes the trust value to the range of [0, 1], T i ,I i ,R i ,C i ,A i ,E i respectively represent the trust degree, interaction success rate, response time, resource consumption rate, historical behavior credibility and current environmental context variable of the node, and f(I i ,R i ), g(C i ,A i ) are respectively the relationship functions of interaction success rate and response time and resource consumption rate and historical behavior, d(E i ) is a dynamic environmental factor, and α, β, γ, η are weight parameters corresponding to each factor; γ is a basic adjustment parameter, which is used to balance the influence of the numerator weight and the environmental factor; Furthermore, the function f(I i ,R i ) of the success rate of interaction in relation to the response time is determined. Wherein, 1, 2, 3 are weight coefficients, which are optimized by algorithm; Resource consumption rate as a function of historical behavior g(C i ,A i ) : g(C i ,A i ) = log(1 + C i ) · (1 - A i ); Dynamic environmental factor d(E i ): d(E i ) = a1 · H i + a2 · M i + a3 · G i ; where H i , M i , G i ∈ [0, 1] are the device health, access time and geographical location, respectively, and a1, a2, a3 are the weights for H i , M i , G i , respectively. S32, the particle swarm algorithm is used to solve the weights a, b, g, h in the trust degree calculation formula; S33, solve the weight parameters θ1, θ2, θ3 in the relationship function f(I i ,R i ) between interaction success rate and response time by using gradient descent method; S4, according to the trust degree of the node, set the corresponding trust threshold, adjust the trust dynamic threshold in the decision layer, and allocate the resource hierarchical access control strategy.

2. The method of claim 1, wherein: In step S1, the information collection of all interaction nodes in the zero trust network environment, specifically including: interaction success rate I i : statistical proportion of whether the data transmission between nodes is successful; response time R i : response delay time of inter-node communication; resource consumption rate C i : bandwidth, CPU, storage resources consumed in the node access or interaction process; historical behavior credibility A i : access history of the node, and abnormal behavior detection result.

3. The method of claim 1, wherein: In step S1, the environment authentication information collection in the zero-trust network environment includes: using device management protocol, timestamp and IP geographical location resolution to obtain device health status, access time and geographical location information respectively, and adding them to the trust degree evaluation to further strengthen the idea of multi-factor authentication of zero-trust architecture, wherein the device health status: not only verifies the user identity, but also verifies whether the device is in a safe state, that is, whether the latest security patch is installed and whether there is malicious software; Access time and location: according to the access time and location, it is evaluated whether it belongs to the normal access mode to prevent unauthorized access after stealing user identity through phishing.

4. The method of claim 1, wherein: In step S2, after collecting information, the data is denoised, filled and normalized for cleaning processing, which includes the following steps: S21, denoising is performed by using wavelet transform to decompose the signal into different frequency domains and filter high-frequency sound: where c(m, n) is the wavelet coefficient, m is the scale parameter, which controls the stretching degree of the wavelet function, corresponding to different frequency bands in the frequency domain, n is the translation parameter, which determines the position of the wavelet function on the time axis, is a wavelet basis function; S22, based on the statistics of similar nodes, the missing values and abnormal values in the data are filled, first define the similarity measure: where Node a , Node b represent two network nodes to be compared, x a,i denotes the feature value of node a in the i-th feature dimension, x b,i denotes the feature value of node b in the i-th feature dimension; Then according to the similarity, select the k most similar nodes from high to low, fill the missing values with the mean value of similar nodes, and then correct the abnormal values: wherein x j is the jth of the k most similar nodes, j ranging from 1 to k; S23, all data X i into the same scale range [0, 1] where i = 1, …, k, in order to better perform the weighted calculation, resulting in normalized data X i ' wherein X min ,X max the minimum, maximum values corresponding to each variable.

5. The method of claim 1, wherein: In step S32, the particle swarm algorithm is used to solve the weights a, b, g, h in the trust degree calculation formula, and the specific process includes the following steps: S321, initialize parameters: set the number of particles N, the search range is [0, 1], initialize the weight parameters a, b, g, h and the velocity v of each particle; S322, fitness function evaluation design, using the accuracy of trust evaluation result and system security as the fitness evaluation standard: Fitness(a, b, g, h) = l1*Accuracy(a, b, g, h) - l2*Risk(a, b, g, h); Wherein, Accuracy(a, b, g, h) is the trust degree accuracy calculated based on the optimized weight, Risk(a, b, g, h) is the security risk of the system, which measures the influence of malicious nodes or attacks, and l1, l2 are adjustment coefficients; Risk = ∑(abnormal request rate + failure rate + high-risk behavior frequency); where T i True is the real trust degree of node i, T i pred is the predicted trust degree of node i, and n is the total number of samples of the number of nodes participating in the evaluation in the verification set. S323, updating the global optimal solution and the local optimal solution S324, update the particle velocity: where ω is the inertia weight, which controls the tendency of the particle to keep its previous velocity, and c1, c2 are cognitive and social coefficients, which control the influence of individual experience and group experience, respectively, is the local optimal solution, is the global optimal solution, x i is the position of the particle, and r1, r2 are random numbers in the interval [0, 1] and are used to maintain population diversity. Updating particle position: x i+1 = x i + v i+1 ; S325, output the optimal weight parameters a, b, g, h when the fitness value meets the accuracy requirement or the upper limit of the number of iterations.

6. The method of claim 1, wherein: In step S33, the weight parameters θ1, θ2, θ3 in the relationship function f(I i ,R i ) of the interaction success rate and the response time solved by the gradient descent method are adopted, and the specific process includes the following steps: S331, collect data: obtain historical data of interaction success rate I i and response time R i ; S332, define the target loss function: Loss =∑|T i True -f(I i ,R i )|; wherein T i True is the real trust degree of node i; S333, initialize the weight parameters θ1, θ2, θ3 and the learning rate η; S334, use the gradient descent method to solve the updated weight parameters θ1, θ2, θ3: wherein θ k is the kth weight parameter to be optimized, k taking values from 1 to 3; S334, output the optimal weight parameters θ1, θ2, θ3 when the loss function converges or reaches the iteration limit.

7. The method of claim 1, wherein: In step S4, the corresponding trust threshold is set according to the trust degree of the node, the dynamic threshold adjustment of trust is carried out in the decision layer, and the allocation of the resource hierarchical access control strategy is carried out. The specific process includes the following steps: S41, dynamic threshold setting and access control: T threshold = μ · avg(T) + σ · std(T); Wherein, μ, σ are the mean and standard deviation of threshold adjustment, respectively, representing the equilibrium state of all nodes in the current network, avg(T), std(T) are the mean and standard deviation of trust degree, respectively. By dynamically adjusting these thresholds, it can be ensured that the system adjusts access permissions and resource allocation in real time according to the network state; S42, input the trust degree T of each node i , adjust the trust degree threshold according to the current network environment and resource allocation requirements and perform resource hierarchical allocation: High-trust node: if Allow the node to access sensitive resources, and preferentially allocate high-performance resources; Medium trust node: if Allow the node to access normal resources, limit part of the operation permissions; Low trust node: if Restrict node access, which is restored when the trust value recovers to a set threshold.

8. An electronic device, comprising: Comprise: The memory is used for storing a computer program, and the processor runs the computer program to make the electronic equipment execute the zero trust network node dynamic trust degree evaluation and intelligent resource allocation method of any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to realize the zero trust network node dynamic trust degree evaluation and intelligent resource allocation method of any one of claims 1-7.

Images