Supply chain relationship management system coordinated by enterprise cluster

Abstract

The present application relates to the technical field of enterprise supply chain management, and discloses a supply chain relationship management system for enterprise cluster coordination, which comprises: a log requirement analysis and standard establishment module, which comprehensively analyzes the log record requirements of the supply chain management system, and establishes unified log standards, interface specifications and data formats; through the cooperation of the log requirement analysis and standard establishment module and the multi-layer log collection and security module, the system realizes the standardization and layered collection of full-link log records, not only ensures the comprehensive capture of key operations and interaction data of each business, service and system layer, but also introduces trusted execution environment, data encryption, multi-layer identity verification and other measures at the collection end, effectively guarantees the security and integrity of data in the collection, transmission and storage process. At the same time, after the log data is preprocessed, de-duplicated and abnormally monitored, abnormal conditions in the collection process can be found in real time, laying a solid data foundation for subsequent accurate analysis.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of enterprise supply chain management, in particular to a supply chain relationship management system for enterprise cluster coordination. BACKGROUND

[0002] The supply chain relationship management system for enterprise cluster coordination refers to optimizing and coordinating the supply chain relationship between multiple enterprises through an information-based and collaborative management system, especially when these enterprises belong to the same cluster or industry chain. The purpose of this system is to help enterprises achieve resource sharing, information flow, and win-win cooperation within the cluster, and improve the overall efficiency and response capability of the supply chain.

[0003] For example, the patent CN113077267A discloses a supply chain relationship management system for enterprise cluster coordination, which belongs to the technical field of enterprise supply chain management and includes a fixed-point layout module, a numerical positioning module, a positioning adjustment module, and a relationship analysis module. The fixed-point layout module is used to graphically layout the enterprise supply chain relationship, the numerical positioning module is used to position each component on the enterprise supply chain on the graphical layout of the fixed-point layout module, the positioning adjustment module is used to adjust the positioning position of each component on the graphical layout, and the relationship analysis module is used to analyze the correlation between the initial node and the dynamic node. This invention sets up a fixed-point layout module and a numerical positioning module, which allows for digital calculation and analysis of the relationship between each component on the supply chain, making the management of supply chain relationships more accurate and objective.

[0004] However, in the prior art, the supply chain relationship management system usually adopts a centralized or distributed log management system for log recording, mainly recording basic information such as operation time, user identity, operation type, system call, etc. In a distributed system environment, the interaction and data transmission between different subsystems are relatively complex, but the log record often only records some simple operation information, and the key data details are often not recorded in detail. Therefore, these logs usually cannot help us analyze the changes in data or discover potential abnormal behaviors, thus affecting the efficiency of fault diagnosis and system optimization.

[0005] Therefore, the present application provides a supply chain relationship management system for enterprise cluster coordination to solve the above-mentioned problems. SUMMARY

[0006] In view of the deficiencies of the prior art, the present application provides a supply chain relationship management system for enterprise cluster coordination to solve the problems mentioned in the background.

[0007] In order to achieve the above object, the application is realized by the following technical solutions: the enterprise cluster coordinated supply chain relationship management system comprises:

[0008] The log requirement analysis and standard formulation module comprehensively analyzes the log recording requirements of the supply chain management system, formulates unified log standards, interface specifications and data formats;

[0009] The multi-layer log collection and security module deploys the log collection module in multiple layers according to the log recording of the log requirement analysis and standard formulation module, records key operations and interaction processes, and introduces trusted execution environment security measures at the collection end;

[0010] The real-time intelligent monitoring module dynamically adjusts the granularity of log recording according to historical data and real-time data by introducing intelligent algorithms according to the data collected by the multi-layer log collection and security module, and monitors the system state and abnormal behavior in real time;

[0011] The distributed log storage module stores the log data collected by each layer in the distributed system according to the monitoring of the real-time intelligent monitoring module;

[0012] The full-link log big data analysis module uses big data analysis platform and intelligent algorithms to monitor and analyze the full-link log data according to the data stored by the distributed log storage module.

[0013] Preferably, the multi-layer log collection and security module comprises:

[0014] The multi-layer log collection unit is deployed in each level of the system and is responsible for real-time capture of key operations and interaction data of each layer; the data preprocessing and formatting unit cleans, removes duplicates and formats the collected raw log data; the collection exception monitoring unit monitors the abnormal conditions in the log collection process in real time.

[0015] Preferably, the real-time intelligent monitoring module comprises:

[0016] The data receiving and integration unit is responsible for receiving data from the multi-layer log collection module and performing preliminary integration and format preprocessing on the data; the real-time data analysis unit processes the received data stream at high speed, and calculates system performance indicators and state parameters in real time; the intelligent algorithm application unit integrates machine learning and other intelligent algorithms to perform deep analysis on the preprocessed data.

[0017] Preferably, the collection method of the multi-layer deployed log collection unit comprises:

[0018] Step 1.1 The business layer deploys the log module to capture key node data, and the adaptive importance weight formula is:

[0019]

[0020] where N represents the total number of business events captured within a specified time window,

[0021] α i represents the base importance coefficient of each event i,

[0022] Δt i represents the time difference from the current time for event i, represents the nonlinear decay of time, λ represents the time decay coefficient, F i represents the frequency of occurrence of event i within a set time window, and the logarithmic function ln(1+F i ) is smoothed.

[0023] Step 1.2 uses a dynamic adjustment algorithm to track cross-service calls at the service layer, and the dynamic granularity adjustment formula for service layer log collection is:

[0024]

[0025] where W 服务 represents the weight of log collection, R i represents the request volume of the i-th service, ln(1+R i ) represents the logarithmic growth of the request volume on log records, T i represents the response time of the i-th service, T max represents the maximum value of service response time, represents the relationship between the response time and the maximum value, θ i represents the system importance index related to the service;

[0026] Step 1.3 uses a dynamic weight calculation formula to collect operating system, database, and network layer data at the system layer, and the dynamic weight calculation formula is:

[0027]

[0028] where M represents the total number of system events captured within a monitoring time window,

[0029] α k represents the base importance coefficient of event k, ΔR k represents the change amplitude of resource usage caused by event k, represents the nonlinear decay of change amplitude, μ represents the sensitivity adjustment parameter, U k represents the instantaneous resource utilization at the time of event occurrence, U max represents the preset upper limit of resource utilization, which is smoothed by the tanh function.

[0030] Preferably, the acquisition anomaly monitoring unit monitors the method by accumulating small deviations to capture persistent abnormal changes:

[0031] S t = max(0, S t-1 + (X t - μ - k)),

[0032] where X t represents the current acquisition value, μ represents the target mean value, k represents the drift parameter, S t represents the cumulative deviation value at time t.

[0033] When S t exceeds the preset threshold h, it is considered that an anomaly occurs.

[0034] Preferably, the trusted execution environment includes a hardware security module and a secure computing platform, and the use method of the hardware security module is as follows:

[0035] Step 2.1 uses the hardware random source built-in HSM and the physical unclonable function to extract and generate an initial key K0;

[0036] Step 2.2 adopts a dynamic update mechanism combining chaotic mapping and time factor, and its algorithm formula is:

[0037]

[0038] where K t represents the new key generated at the current time, K t-1 represents the key at the previous time, PUF seed represents the unique hardware seed extracted by PUF,

[0039] x t is generated by chaotic mapping, and the calculation formula is: x t+1 = μx t (1-x t ),

[0040] The chaotic parameter μ takes a value in the range of 3.57 to 4.0, x t × 2 32 represents converting the chaotic output to a 32-bit integer, T represents the current timestamp, represents the bitwise XOR operation, and SHA3-256 represents generating a 256-bit output key after nonlinear mixing of the above items.

[0041] Preferably, the use method of the secure computing platform includes:

[0042] Step 3.1 distributes the key generation task to multiple independent participants using the MPC protocol and provides data to jointly generate the final key K t , the algorithm formula is:

[0043] K t =MPC(Share1,Share2,…,Share n ),

[0044] where Share represents the key fragment provided by the i-th participant, and n represents the number of participants;

[0045] Step 3.2 performs differential privacy perturbation processing on sensitive data before encryption, further protecting the privacy of log data, and the algorithm formula is:

[0046] where D t represents the original log data, represents Gaussian noise with mean 0 and standard deviation σ;

[0047] Step 3.3 encrypts the perturbed log data D t using the key K t generated by MPC: ′ uses a symmetric encryption algorithm:

[0048] L t =AES(K t ,D t ′ ),

[0049] where the key K t length is recommended to be 256 bits, and the AES encryption mode is selected as GCM mode.

[0050] Preferably, the method for data integration and preprocessing by the data receiving and integration unit comprises:

[0051] Step 4.1 uses DTW to align the slight time difference between different time series, and the algorithm formula is:

[0052] Let w be a fixed window size,

[0053]

[0054] where A=(a1,a2,…,a n ) and B=(b1,b2,…,b n ) represent two time series, and W represents an alignment path that satisfies the boundary condition;

[0055] Step 4.2 uses MinHash and LSH to detect and remove duplicate log records, and the algorithm formula is: where A and B represent the feature sets of two log records.

[0056] Step 4.3 matches the similar content in different source data by using a fuzzy matching algorithm, and the algorithm formula is:

[0057]

[0058] where f i represents the feature value of the i-th log, w i represents the weight of the feature, S fusion represents the final event score after fusion.

[0059] Preferably, the real-time data analysis unit processing method comprises the following steps:

[0060] Suppose the observation data x t at each time step is decomposed into a low-dimensional representation and a sparse error:

[0061] x t = L t w t + s t ,

[0062] where L t represents the current low-dimensional subspace basis matrix, w t represents the low-dimensional representation coefficient, and s t represents the sparse abnormal noise.

[0063] To solve w t and s t simultaneously, the following optimization problem is usually constructed:

[0064]

[0065] where λ represents the strength of the sparse regularization control.

[0066] After w t and s t are solved, the subspace basis matrix L t is updated by using gradient descent:

[0067]

[0068] η represents the learning rate, and represents the gradient calculation of L t .

[0069] Preferably, the analysis method of the intelligent algorithm application unit comprises the following steps:

[0070] An ODMD is used to find a linear operator A such that the state x tApproximately map to the next time state x t+1 :

[0071]

[0072] Wherein, A t Indicates the linear evolution operator at time t, beta indicates the forgetting factor, epsilon indicates a small positive number, and ||.||2 indicates the L2 norm.

[0073] The present application provides a supply chain relationship management system for enterprise cluster coordination. The following beneficial effects are achieved:

[0074] 1. The present application realizes the standardization and hierarchical collection of full-link log recording through log demand analysis and standard setting, multi-layer log collection and safety module cooperation, not only ensuring the comprehensive capture of key operations and interaction data of each business, service and system layer, but also introducing trusted execution environment, data encryption, multi-layer identity verification and other measures at the collection end, effectively ensuring the security and integrity of data in the collection, transmission and storage process. At the same time, after preprocessing, deduplication and abnormality monitoring, the log data can discover abnormal conditions in the collection process in real time, laying a solid data foundation for subsequent accurate analysis.

[0075] 2. The real-time intelligent monitoring module of the present application realizes dynamic monitoring and rapid response to system state and abnormal behavior by means of data receiving, integration and high-speed real-time data analysis unit, and intelligent algorithms such as machine learning and online dynamic mode decomposition (ODMD). The system can automatically adjust the granularity of log recording according to real-time and historical data, saving storage resources when the system is stable, and refining monitoring content when abnormalities occur, ensuring timely capture of problems. With distributed log storage and full-link big data analysis module, the whole scheme not only has efficient data storage and analysis capability, but also can realize dynamic optimization and scheduling of system resources, thereby improving the overall efficiency and decision support capability of supply chain management. BRIEF DESCRIPTION OF DRAWINGS

[0076] Figure 1 The flowchart of the present application. DETAILED DESCRIPTION

[0077] In order for those skilled in the art to understand the present application, the technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0078] The present application will be described in detail below with reference to the drawings:

[0079] Embodiments:

[0080] Please refer to the attached Figure 1 The embodiments of the present application provide a supply chain relationship management system for enterprise cluster coordination, comprising:

[0081] The log requirement analysis and standard formulation module comprehensively analyzes the log recording requirements of the supply chain management system, formulates unified log standards, interface specifications and data formats;

[0082] The multi-layer log collection and security module, according to the log recording of the log requirement analysis and standard formulation module, multi-layerly deploys the log collection module, records the key operations and interaction processes, and simultaneously introduces trusted execution environment security measures at the collection end;

[0083] The real-time intelligent monitoring module, according to the data collected by the multi-layer log collection and security module, dynamically adjusts the granularity of log recording according to historical data and real-time data by introducing intelligent algorithms, and monitors the system state and abnormal behavior in real time;

[0084] The distributed log storage module, according to the monitoring of the real-time intelligent monitoring module, stores the log data collected by each layer in a distributed system;

[0085] The full-link log big data analysis module, according to the data stored by the distributed log storage module, utilizes a big data analysis platform and intelligent algorithms to perform real-time monitoring and analysis on the full-link log data.

[0086] The multi-layer log collection and security module comprises:

[0087] The multi-layer log collection unit is deployed at each level of the system and is responsible for real-time capture of key operations and interaction data of each layer; the data preprocessing and formatting unit performs cleaning, deduplication and format standardization processing on the collected raw log data; the collection exception monitoring unit monitors abnormal conditions in the log collection process in real time.

[0088] The collection method of the multi-layer deployment log collection unit comprises:

[0089] Step 1.1 The business layer deploys a log module to capture key node data, and the adaptive importance weight formula is:

[0090]

[0091] Wherein, N represents the total number of business events captured in a specified time window,

[0092] α i represents the basic importance coefficient of each event i,

[0093] Δti represents the time difference between event i and the current time, represents the nonlinear decay of time, λ represents the time decay coefficient, F i represents the frequency of occurrence of event i within a set time window, and the logarithmic function ln(1+F i ) is smoothed;

[0094] Step 1.2 uses a dynamic adjustment algorithm to track cross-service calls at the service layer, and the dynamic granularity adjustment formula for service layer log collection is:

[0095]

[0096] where W 服务 represents the weight of log collection, R i represents the request volume of the i-th service, ln(1+R i ) represents the logarithmic growth of the request volume on log records, T i represents the response time of the i-th service, T max represents the maximum value of service response time, represents the relationship between the response time and the maximum value, θ i represents the system importance index related to the service;

[0097] Step 1.3 uses a dynamic weight calculation formula to collect operating system, database, and network layer data at the system layer, and the dynamic weight calculation formula is:

[0098]

[0099] where M represents the total number of system events captured within the monitoring time window,

[0100] α k represents the basic importance coefficient of event k, ΔR k represents the change amplitude of resource usage caused by event k, e -μΔRk represents the nonlinear decay of change amplitude, μ represents the sensitivity adjustment parameter, U k represents the instantaneous resource utilization at the time of event occurrence, U max represents the preset upper limit of resource utilization, which is smoothed by the tanh function.

[0101] Preferably, the abnormal monitoring unit monitoring method captures persistent abnormal changes by accumulating small deviations:

[0102] S t = max(0, S t-1 + (X t - μ - k)),

[0103] Among them, X t The value represents the current acquisition value, μ represents the target mean, k represents the drift parameter, and S represents the target mean. t This represents the cumulative deviation at time t;

[0104] When S t If the threshold h is exceeded, it is considered an abnormality.

[0105] Step S2: The trusted execution environment includes a hardware security module and a secure computing platform. The hardware security module is used as follows:

[0106] Step 2.1 Use the hardware random source and physical non-cloning function built into the HSM to extract and generate the initial key K0;

[0107] Step 2.2 employs a dynamic update mechanism combining chaotic mapping and a time factor. The algorithm formula is as follows:

[0108]

[0109] Among them, K t K represents the new key generated at the current moment. t-1 PUF represents the key from the previous time step. seed This indicates the unique hardware seed extracted by PUF.

[0110] x t Generated by chaotic mapping, the calculation formula is: x t+1 =μx t (1-x t ),

[0111] The chaotic parameter μ ranges from 3.57 to 4.0, x t ×2 32 This indicates that the chaotic output will be converted to a 32-bit integer, where T represents the current timestamp. This indicates a bitwise XOR operation. SHA3-256 means that the above terms are non-linearly mixed to generate a 256-bit output key.

[0112] Step S3, the method of using the secure computing platform includes:

[0113] Step 3.1 uses the MPC protocol to distribute the key generation task to multiple independent participants, and provides data to jointly generate the final key K. t The algorithm formula is as follows:

[0114] K t =MPC(Share1,Share2,…,Share n ),

[0115] Where Share represents the key fragment provided by the i-th participant, and n represents the number of participants;

[0116] Step 3.2 Performs differential privacy perturbation on sensitive data before encryption to further protect the privacy of log data. The algorithm formula is as follows:

[0117] Among them, D t This represents the raw log data. This represents Gaussian noise with a mean of 0 and a standard deviation of σ.

[0118] Step 3.3 Utilize the key K generated via MPC t For the perturbed log data D t ′ Encryption is performed using a symmetric encryption algorithm:

[0119] L t =AES(K t D t ′ ),

[0120] Wherein, key K t The recommended length is 256 bits, and the AES encryption mode should be set to GCM mode.

[0121] Specifically, through log requirement analysis and standardization, and the coordination of multi-layered log collection and security modules, the system achieves standardized and layered log recording across the entire chain. This not only ensures the comprehensive capture of key operations and interactions at various business, service, and system layers, but also effectively guarantees the security and integrity of data during collection, transmission, and storage by introducing trusted execution environments, data encryption, and multi-layered authentication at the collection end. Furthermore, log data undergoes preprocessing, deduplication, and anomaly monitoring, enabling real-time detection of anomalies during the collection process, laying a solid data foundation for subsequent accurate analysis.

[0122] The real-time intelligent monitoring module includes:

[0123] The data receiving and integration unit is responsible for receiving data from the multi-layer log collection module and performing preliminary integration and format preprocessing on the data; the real-time data analysis unit processes the received data stream at high speed and calculates system performance indicators and status parameters in real time; the intelligent algorithm application unit integrates machine learning and other intelligent algorithms to perform in-depth analysis on the preprocessed data.

[0124] Step S4, the data receiving and integration unit's method for data integration and preprocessing includes:

[0125] Step 4.1 uses DTW to align small temporal differences between different time series. The algorithm formula is as follows:

[0126] Let w be a fixed window size.

[0127]

[0128] Where A = (a1, a2, ..., a n ) and B = (b1, b2, ..., b n ) represents two time series, and W represents the alignment path that satisfies the boundary conditions;

[0129] Step 4.2 uses MinHash and LSH to detect and remove duplicate log records. The algorithm formula is as follows: Here, A and B represent the feature sets of two log records.

[0130] Step 4.3 uses a fuzzy matching algorithm to match similar content in different source data. The algorithm formula is as follows:

[0131]

[0132] Among them, f i Let w represent the feature value of the i-th log entry. i S represents the weight of this feature. fusion This represents the final event score after merging.

[0133] Step S5, the real-time data analysis unit processing method:

[0134] Let x be the observation data for each time period. t This is decomposed into a low-dimensional representation and sparse error:

[0135] x t =L t w t +s t ,

[0136] Among them, L t Let w represent the basis matrix of the current low-dimensional subspace. t s represents the low-dimensional coefficients. t Indicates sparse anomalous noise;

[0137] To solve w simultaneously t and s t The optimization problem is typically constructed as follows:

[0138]

[0139] Where λ represents the strength of the sparsity regularization;

[0140] After solving for w t and s tThen, gradient descent is used to update the subspace basis matrix L. t :

[0141]

[0142] η represents the learning rate. Indicates L t Gradient calculation.

[0143] Preferably, the analysis method of the intelligent algorithm application unit is as follows:

[0144] Using ODMD to find a linear operator A that makes the state x at each time step t Approximate mapping to the state x at the next time step t+1 :

[0145]

[0146] Among them, A t Let denote the linear evolution operator at time t, β denote the forgetting factor, ∈ denote a small positive number, and ||·||2 denote the L2 norm.

[0147] Specifically, the real-time intelligent monitoring module, leveraging data reception, integration, and high-speed real-time data analysis units, along with integrated intelligent algorithms such as machine learning and online dynamic pattern decomposition (ODMD), enables dynamic monitoring and rapid response to system status and abnormal behavior. The system can automatically adjust the granularity of log recording based on real-time and historical data, saving storage resources when the system is stable and refining monitoring content when anomalies occur, ensuring timely problem detection. Combined with distributed log storage and end-to-end big data analysis modules, the entire solution not only possesses efficient data storage and analysis capabilities but also enables dynamic optimization and scheduling of system resources, thereby improving the overall efficiency of supply chain management and decision support capabilities.

[0148] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A supply chain relationship management system for enterprise cluster coordination, characterized in that, include; The log requirements analysis and standardization module comprehensively analyzes the log recording requirements of the supply chain management system and formulates unified log standards, interface specifications, and data formats. The multi-layered log collection and security module records logs based on the log requirements analysis and standard setting module. The multi-layered log collection module records key operations and interaction processes, while introducing trusted execution environment security measures at the collection end. The real-time intelligent monitoring module, based on data collected from multi-layer log collection and the security module, dynamically adjusts the granularity of log recording according to historical and real-time data through the introduction of intelligent algorithms, and monitors the system status and abnormal behavior in real time. The distributed log storage module stores the log data collected from each layer in the distributed system after monitoring by the real-time intelligent monitoring module. The end-to-end log big data analysis module uses a big data analysis platform and intelligent algorithms to monitor and analyze end-to-end log data in real time, based on the data stored in the distributed log storage module. The multi-layer log collection and security module includes a multi-layer log collection unit, and the collection method of the multi-layer log collection unit includes: Step 1.1 The business layer deploys a log module to capture key node data, with its adaptive importance weight formula as follows: ， in, This indicates the total number of business events captured within the specified time window. Represent each event The basic importance coefficient, Represented as an event Time difference from the current moment, This indicates a non-linear decay over time. Indicates the time decay coefficient. Indicates an event The frequency of occurrence within a set time window is determined by a logarithmic function. Perform smoothing; Step 1.2 employs a dynamic adjustment algorithm to track cross-service calls at the service layer. The dynamic granularity adjustment formula for service layer log collection is as follows: ， in, Indicates the weight of log collection. Indicates the first The number of requests per service This indicates that the impact of request volume on log recording increases logarithmically. Indicates the first Response time of each service This indicates the maximum service response time. This indicates a measure of the relationship between response time and maximum value. This represents an index indicating the system importance of the service. Step 1.3 At the system layer, a dynamic weight calculation formula is used to collect data from the operating system, database, and network layers. The dynamic weight calculation formula is as follows: ， in, This indicates the total number of system events captured within the monitoring time window. Indicates an event The basic importance coefficient, Indicates an event The magnitude of the change in resource use caused This indicates a non-linear attenuation of the change amplitude. This is represented as a sensitivity adjustment parameter. This represents the instantaneous resource utilization rate at the time the event occurs. This indicates the preset upper limit of resource utilization, through... Function smoothing mapping.

2. The enterprise cluster coordination supply chain relationship management system according to claim 1, characterized in that, The multi-layer log collection and security module includes: The multi-layer log collection unit is deployed at various levels of the system and is responsible for capturing key operation and interaction data at each level in real time; the data preprocessing and formatting unit cleans, deduplicates, and standardizes the format of the collected raw log data; and the collection anomaly monitoring unit monitors anomalies in the log collection process in real time.

3. The supply chain relationship management system for enterprise cluster coordination according to claim 1, characterized in that, The real-time intelligent monitoring module includes: The data receiving and integration unit is responsible for receiving data from the multi-layer log collection module and performing preliminary integration and format preprocessing on the data; the real-time data analysis unit processes the received data stream at high speed and calculates system performance indicators and status parameters in real time; the intelligent algorithm application unit integrates machine learning and other intelligent algorithms to perform in-depth analysis on the preprocessed data.

4. The enterprise cluster coordination supply chain relationship management system according to claim 2, characterized in that, The monitoring method of the aforementioned anomaly monitoring unit captures continuous abnormal changes by accumulating minute deviations: ， in, Indicates the currently collected value. Indicates the target mean. Indicates the drift parameter, Indicates time The cumulative deviation value; when If the threshold h is exceeded, it is considered an abnormality.

5. The enterprise cluster coordination supply chain relationship management system according to claim 4, characterized in that, The trusted execution environment includes a hardware security module and a secure computing platform. The hardware security module is used as follows: Step 2.1 Utilize the HSM's built-in hardware random source and physical non-cloning function to extract and generate the initial key. ; Step 2.2 employs a dynamic update mechanism combining chaotic mapping and a time factor. The algorithm formula is as follows: ， in, This represents the new key generated at the current moment. This represents the key from the previous moment. This indicates the unique hardware seed extracted by PUF. Generated by chaotic mapping, the calculation formula is: , Chaos parameters The value ranges from 3.57 to 4.

0. This indicates that the chaotic output will be converted to a 32-bit integer. Indicates the current timestamp. This indicates a bitwise XOR operation. This indicates that the above nonlinear combinations are mixed to generate a 256-bit output key.

6. The enterprise cluster coordination supply chain relationship management system according to claim 5, characterized in that, The method of using the secure computing platform includes: Step 3.1 uses the MPC protocol to distribute the key generation task to multiple independent participants, and provides data to jointly generate the final key. The algorithm formula is as follows: ， in, Indicates the first Each participant provides a key fragment. Indicates the number of participants; Step 3.2 Performs differential privacy perturbation on sensitive data before encryption to further protect the privacy of log data. The algorithm formula is as follows: , in, This represents the raw log data. This indicates that the mean is 0 and the standard deviation is 0. Gaussian noise; Step 3.3 Utilize the key generated via MPC For the disturbed log data Encryption is performed using a symmetric encryption algorithm: ， Among them, key The recommended length is 256 bits, and the AES encryption mode should be set to GCM mode.

7. The enterprise cluster coordination supply chain relationship management system according to claim 3, characterized in that, The data receiving and integration unit includes the following methods for data integration and preprocessing: Step 4.1 uses DTW to align small temporal differences between different time series. The algorithm formula is as follows: set up To determine the window size, ， in, and This represents two time series. This indicates the alignment path that satisfies the boundary conditions. Step 4.2 uses MinHash and LSH to detect and remove duplicate log records. The algorithm formula is as follows: ,in, and The feature set representing two log records; Step 4.3 uses a fuzzy matching algorithm to match similar content in different source data. The algorithm formula is as follows: ， in, This represents the feature value of the i-th log entry. This represents the weight of the feature. This represents the final event score after merging.

8. The supply chain relationship management system for enterprise cluster coordination according to claim 7, characterized in that, The real-time data analysis unit processing method: Let the observation data for each time period be... This is decomposed into a low-dimensional representation and sparse error: ， in, Denotes the basis matrix of the current low-dimensional subspace. This represents the coefficients in low dimension. Indicates sparse anomalous noise; To solve simultaneously and The optimization problem is typically constructed as follows: ， in, This indicates the degree to which sparsity regularization is controlled. The solution is obtained and Then, gradient descent is used to update the subspace basis matrix. : ， Indicates the learning rate. Indicates to Gradient calculation.

9. The supply chain relationship management system for enterprise cluster coordination according to claim 8, characterized in that, The analysis method of the intelligent algorithm application unit: Using ODMD to find linear operators State at each moment Approximate mapping to the state at the next time step : ， in, Indicates time Linear evolution operators at time, Indicates the forgetting factor, Represents a small positive number. express Norm.

Images