Data privacy calculation method for dynamic weight distribution in industrial internet supply chain

Abstract

The embodiment of the invention provides a data privacy calculation method for dynamic weight distribution in an industrial internet supply chain, and the method comprises the steps: building a data quality evaluation model, and monitoring the data quality of each enterprise in the supply chain in real time; determining a judgment standard of the core enterprise; designing a dynamic weight adjustment algorithm, and adjusting the calculation weight of each enterprise regularly or in real time according to the data quality evaluation result and the state change of the core enterprise; and collaborative optimization is carried out, and on the premise of privacy protection, each enterprise shares part of data feature information to jointly optimize the model. Through the scheme of the embodiment of the invention, the problem that some existing privacy calculation methods are applied in a supply chain scene of the industrial internet can be solved, so that data collaborative calculation is carried out while enterprise data privacy is protected. Part of methods try to allocate fixed weights to different enterprises, but the method cannot adapt to dynamic changes of data quality and enterprise importance in a supply chain.

Description

Technical Field

[0001] The present application relates to the field of data privacy protection technology, and specifically to a data privacy calculation method for dynamic weight distribution in an industrial Internet supply chain. Background Art

[0002] The data privacy calculation method of dynamic weight distribution in the industrial Internet supply chain refers to a method that can flexibly adjust the weight of each enterprise according to the dynamic changes of data quality and importance of different enterprises in the supply chain under the premise of protecting enterprise data privacy. This method can more effectively support data collaborative computing and improve the operational efficiency of the entire supply chain. However, in actual applications, some privacy computing methods have been able to protect enterprise data privacy, but they adopt a fixed mode in weight distribution, that is, they do not consider the dynamic changes of data quality and enterprise importance, which makes it impossible to accurately reflect the actual situation and may affect the accuracy and fairness of supply chain collaborative computing. Summary of the invention

[0003] In view of this, the embodiments of the present disclosure provide a data privacy calculation method for dynamic weight distribution in the industrial Internet supply chain, which at least partially solves the problems existing in the prior art.

[0004] The present application provides a data privacy calculation method for dynamic weight allocation in an industrial Internet supply chain, including:

[0005] Establish a data quality assessment model to monitor the data quality of each enterprise in the supply chain in real time. The assessment can be conducted from multiple dimensions such as data integrity, accuracy, and timeliness.

[0006] Determine the criteria for core enterprises, such as enterprise size, market influence, criticality to the supply chain, etc. Once the core enterprise is determined, give it an initial higher weight.

[0007] Design a dynamic weight adjustment algorithm to adjust the calculation weight of each enterprise regularly or in real time according to the data quality assessment results and the status changes of core enterprises. For example, when the data quality of a certain enterprise is significantly improved, increase its weight; if there is a problem with the core enterprise, adjust the weight allocation strategy in time.

[0008] To carry out collaborative optimization, all enterprises share some data feature information and jointly optimize the model under the premise of privacy protection. Technologies such as federated learning can be used to achieve distributed training and optimization of the model and improve the performance of the overall model.

[0009] Preferably, the data quality is evaluated by the following formula:

[0010] Assume that the set of data quality indicators is Q = {completeness Q1, accuracy Q2, timeliness Q3...};

[0011] The weight of each indicator is Wq = {Wq1, Wq2, Wq3...}, and the weight is set according to the actual situation or dynamically adjusted through machine learning algorithms;

[0012] The data quality score DQ of an enterprise is Q1*Wq1+Q2*Wq2+Q3*Wq3+…….

[0013] Preferably, the core enterprise is determined by the following formula:

[0014] Suppose the core enterprise indicator set is C = {enterprise scale C1, market influence C2, criticality to the supply chain C3...}.

[0015] The weight of each indicator is Wc = {Wc1, Wc2, Wc3...}.

[0016] The core enterprise score CC of a certain enterprise is C1*Wc1+C2*Wc2+C3*Wc3+…….

[0017] Preferably, the dynamic weight is adjusted by the following formula:

[0018] Assume that the initial weight is Wi, the data quality adjustment factor is Fdq, and the core enterprise adjustment factor is Fcc;

[0019] The dynamic weight of a certain enterprise is W = Wi*(1+Fdq*DQ+Fcc*CC);

[0020] Among them, the data quality adjustment factor Fdq and the core enterprise adjustment factor Fcc can be set according to actual conditions. For example, the data quality adjustment factor Fdq and the core enterprise adjustment factor Fcc can be adjusted according to the stability of the supply chain and the severity of data changes.

[0021] The disclosed embodiment provides a data privacy calculation method for dynamic weight allocation in an industrial Internet supply chain, including: establishing a data quality assessment model to monitor the data quality of each enterprise in the supply chain in real time. The assessment can be performed from multiple dimensions such as data integrity, accuracy, and timeliness. Determine the judgment criteria of core enterprises, such as enterprise size, market influence, and criticality to the supply chain. Once the core enterprise is determined, it is given an initial higher weight. Design a dynamic weight adjustment algorithm to adjust the calculation weight of each enterprise regularly or in real time according to the data quality assessment results and the status changes of the core enterprise. For example, when the data quality of a certain enterprise is significantly improved, its weight is increased; if there is a problem with the core enterprise, the weight allocation strategy is adjusted in time. Collaborative optimization is performed, and each enterprise shares part of the data feature information under the premise of privacy protection and jointly optimizes the model. Technologies such as federated learning can be used to achieve distributed training and optimization of the model and improve the performance of the overall model. Through the solution of the disclosed embodiment, it can be solved that in the supply chain scenario of the industrial Internet, some privacy calculation methods have been applied to protect the privacy of enterprise data while performing data collaborative calculation. Some methods try to assign fixed weights to different enterprises, but this method cannot adapt to the dynamic changes in data quality and enterprise importance in the supply chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the exemplary implementation methods of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the embodiments of the present disclosure and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 It is a flow chart of the data privacy calculation method of dynamic weight allocation in the industrial Internet supply chain;

[0024] Figure 2 is a flow chart for assessing data quality;

[0025] Figure 3 It is a flow chart for determining core enterprises;

[0026] Figure 4 It is a flowchart for adjusting dynamic weights. DETAILED DESCRIPTION

[0027] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present application. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0028] Next, refer to Figure 1 , describes the data privacy calculation method of dynamic weight allocation in the industrial Internet supply chain of the present invention. This method aims to solve the problem that in the supply chain scenario of the industrial Internet, the existing privacy calculation method assigns fixed weights to different enterprises and cannot adapt to the dynamic changes in data quality and enterprise importance. This method achieves more efficient, dynamic and secure data collaborative calculation through four steps: establishing a data quality assessment model, determining core enterprises, designing a dynamic weight adjustment algorithm, and performing collaborative optimization.

[0029] S101: Establish a data quality assessment model. This model is used to monitor the data quality of each enterprise in the supply chain in real time, so as to ensure that subsequent data processing can be based on reliable information. The assessment model can be carried out from multiple dimensions, such as data integrity, accuracy, timeliness and consistency. By combining these indicators, the assessment model can provide a comprehensive data quality score for each enterprise. For example, in a specific embodiment, a raw material supplier in the supply chain may score high in data integrity, but lack timeliness. Through model calculation, the supplier's data quality score is 85 points, indicating that its data is generally reliable, but attention needs to be paid to timeliness issues.

[0030] S102: Determine the criteria for judging core enterprises. This process aims to identify enterprises that are critical to the entire supply chain and assign higher initial weights to these core enterprises. The judgment criteria may include the size of the enterprise, its market influence, and its criticality in the supply chain. Once the core enterprises are identified, they can be given higher weights in the initial stage to make full use of their advantageous resources. For example, a large manufacturer in the supply chain is identified as a core enterprise because of its large scale, wide product line and high market share, and is given an initial weight value of 1.5 in the weight distribution. This approach helps to quickly improve the overall performance of the model in the early stage, while ensuring that the role of the core enterprises is fully utilized.

[0031] S103: Design a dynamic weight adjustment algorithm. This algorithm adjusts the calculation weight of each enterprise regularly or in real time according to the data quality assessment results and the status changes of the core enterprises. In this way, a more accurate and adaptable weight distribution can be achieved in the supply chain. For example, suppose a raw material supplier has improved its data management process and its data quality score is 95 points, which is significantly better than other suppliers. At this time, the dynamic weight adjustment algorithm will automatically increase its weight value to 1.2, so that the data of this supplier can play a greater role in the calculation process. If there is a problem with the core enterprise, such as data leakage or system failure, the algorithm will immediately reduce its weight value to prevent the spread of negative impact. Specifically, if a core enterprise has inaccurate temporary data due to system upgrade, its weight value will be reduced from 1.5 to 1.0, so that other normally operating enterprises can occupy a more reasonable proportion in the model optimization.

[0032] S104: Conduct collaborative optimization. Under the premise of privacy protection, each enterprise shares some data feature information and jointly optimizes the model. This process can be achieved through advanced technologies such as federated learning, ensuring that enterprises can still participate in the distributed training and optimization of the model while protecting their own data privacy. For example, each enterprise in the supply chain can share some information such as production parameters, logistics time, and quality inspection results of its products. Through federated learning technology, these data features can be processed locally and encrypted gradient information can be generated. Subsequently, the gradient information of each enterprise is aggregated to the central server for model update, thereby continuously optimizing the prediction ability and decision support of the entire supply chain. This collaborative approach not only improves the performance of the overall model, but also ensures that the sensitive data of each enterprise will not be directly exposed.

[0033] In summary, the data privacy calculation method with dynamic weight distribution in the industrial Internet supply chain effectively solves the problem that the fixed weight distribution in the existing method cannot adapt to the dynamic changes of the supply chain through multi-step collaborative work, and realizes more flexible, efficient and secure data collaborative calculation.

[0034] Next, refer to Figure 2 , describing the present invention, the data quality is evaluated by the following formula:

[0035] S201: Assume that the set of data quality indicators is Q = {completeness Q1, accuracy Q2, timeliness Q3...}; the weight of each indicator is Wq = {Wq1, Wq2, Wq3...}, and the weight is set according to the actual situation or dynamically adjusted through machine learning algorithms; the data quality score of an enterprise is DQ = Q1*Wq1+Q2*Wq2+Q3*Wq3+...

[0036] The evaluation process is divided into three main steps. First, determine the data quality indicators and their scope. For example, in the industrial Internet supply chain, common data quality indicators include data integrity, accuracy, and timeliness. The specific values ​​of these indicators are usually between 0 and 1, where 1 indicates the highest quality. Integrity Q1 indicates whether the data is complete, accuracy Q2 indicates the consistency of the data with the actual value, and timeliness Q3 indicates the degree of timely update of the data.

[0037] S202: Assign weights to each indicator. These weights are adjusted dynamically based on actual conditions or through machine learning algorithms. The weights are also between 0 and 1, and the sum of all weights is equal to 1. For example, if a company believes that data integrity is more important to the supply chain than other indicators, it may set Wq1 to 0.4, Wq2 and Wq3 to 0.3 and 0.3 respectively. The weights can be assigned based on expert opinions, historical data analysis, or the results of machine learning models.

[0038] S203: Calculate the enterprise's data quality score DQ. DQ is obtained by multiplying the value of each indicator by its corresponding weight and summing them up. That is, DQ = Q1*Wq1+Q2*Wq2+Q3*Wq3+……. The design of this formula ensures that the impact of each indicator on the overall data quality is proportional to its importance, thereby more objectively evaluating the overall quality of the data.

[0039] In a specific embodiment, assume that an automobile manufacturer is evaluating the quality of parts data in its supply chain. Completeness Q1 is evaluated as 0.9, accuracy Q2 is 0.85, and timeliness Q3 is 0.8. According to the importance and actual situation of the enterprise, the weight Wq1 is set to 0.4, and Wq2 and Wq3 are set to 0.3 and 0.3 respectively. According to the formula, the data quality score DQ = 0.9*0.4+0.85*0.3+0.8*0.3=0.36+0.255+0.24=0.855. This score indicates that the quality of the enterprise's supply chain data is generally good, but there is still room for improvement, especially in terms of accuracy.

[0040] Next, refer to Figure 3 , describing how the present invention determines the core enterprise.

[0041] S301: Determine the core enterprise indicator set C = {C1, C2, C3...}. In this step, the core enterprise indicator set is the core evaluation factor, covering a series of factors that have a direct impact on the core position of the enterprise in the supply chain, such as enterprise scale C1, market influence C2, and criticality to the supply chain C3. The selection of these indicators is intended to fully reflect the importance of the enterprise.

[0042] S302: Set the weight set Wc corresponding to each indicator = {Wc1, Wc2, Wc3...}. In this step, a weight needs to be assigned to each indicator, which represents the relative contribution of each indicator to the assessment of the importance of the core enterprise. Generally, the setting of weights needs to be based on a specific understanding and analysis of the supply chain to ensure that the final score can accurately reflect the position of the enterprise in the entire supply chain. For example, in the context of the industrial Internet supply chain, if a company mainly acts as a supplier, the weight of the supply chain criticality (C3) may be higher, while the weight of market influence (C2) may be relatively low.

[0043] S303: Calculate the core enterprise score CC of a specific enterprise. This step is calculated by the formula CC=C1*Wc1+C2*Wc2+C3*Wc3+…, where the right side of the formula represents the sum of each indicator multiplied by its weight. Parameter Ci (i ranges from 1 to n) represents the actual value of each indicator, and Wci corresponds to the weight of each indicator Ci. The design principle of this formula is the weighted summation method, which combines the influence of each dimension to obtain a comprehensive score to evaluate the importance of the enterprise. The advantage of this method is its high flexibility, and the weight value can be adjusted according to different industries and scenarios to ensure that the evaluation results are more in line with the actual situation.

[0044] In a specific embodiment, it is assumed that there are two industrial enterprises A and B that need to be evaluated for their core enterprise status in the industrial Internet supply chain. Among them, enterprise A has a large scale and moderate market influence, but is in a more critical position in the supply chain; while enterprise B is not large in scale, but has a large market influence and is generally important to the supply chain. By substituting a series of indicator values ​​of the two enterprises (such as enterprise scale C1 = 80, 70, market influence C2 = 60, 90, and criticality to the supply chain C3 = 90, 60) and preset weights (for example, Wc1 = 0.3, Wc2 = 0.4, Wc3 = 0.3) into the above formula, it can be calculated that the score of enterprise A CC_A = 80*0.3+60*0.4+90*0.3 = 24+24+27 = 75; the score of enterprise B CC_B = 70*0.3+90*0.4+60*0.3 = 21+36+18 = 75. Although the total scores of the two are the same, judging from the scores of each indicator, A plays a more obvious core role in the supply chain, while B has a greater market impact. Evaluators can further refine and adjust the weights or introduce more indicators according to actual needs to obtain more accurate evaluation results.

[0045] This approach can not only effectively identify key participants in the supply chain, but also help companies and managers optimize resource allocation and improve overall operational efficiency.

[0046] Next, refer to Figure 4 , describing the adjustment dynamic weight of the present invention:

[0047] S401: Assume that the initial weight is Wi, the data quality adjustment factor is Fdq, and the core enterprise adjustment factor is Fcc;

[0048] S402: The dynamic weight of an enterprise W = Wi*(1+Fdq*DQ+Fcc*CC); wherein the data quality adjustment factor Fdq and the core enterprise adjustment factor Fcc can be set according to actual conditions, for example, the data quality adjustment factor Fdq and the core enterprise adjustment factor Fcc can be adjusted according to the stability of the supply chain and the severity of data changes.

[0049] In the first step, the initial weight Wi of each participating enterprise or node is determined. The initial weight is usually set based on the basic characteristics or historical contributions of the enterprise, such as enterprise size, market share, etc. The value range of the initial weight Wi is usually (0,1], ensuring that the importance of each enterprise in the initial state is reasonably reflected.

[0050] The second step is to set the data quality adjustment factor Fdq. Fdq is adjusted according to the stability of the supply chain and the severity of data changes, and the value range is generally between [-1,1]. A positive Fdq indicates good data quality, and a negative Fdq indicates poor data quality. The optimal value of Fdq depends on the specific scenarios and requirements of the actual application, but it is usually hoped to be as close to a positive value as possible to reflect the positive impact of high data quality on the enterprise weight.

[0051] The third step is to set the core enterprise adjustment factor Fcc. Fcc is mainly adjusted based on whether the enterprise is a core enterprise and its position in the supply chain, and the value range is generally between [-1,1]. A positive Fcc indicates that the enterprise is a core enterprise, and a negative Fcc indicates that the enterprise is a non-core enterprise. The optimal value of Fcc also depends on the specific situation, but it is usually hoped that the Fcc value of the core enterprise is higher to enhance the influence of the core enterprise in the weight distribution.

[0052] The fourth step is to calculate the dynamic weight W of the enterprise based on the above parameters. The specific formula is W = Wi*(1+Fdq*DQ+Fcc*CC), where DQ is the data quality score and CC is the core enterprise rating. The value range of DQ is usually between [0,1], 1 means very good data quality, and 0 means poor data quality. The value range of CC is also between [0,1], 1 means the enterprise is a core enterprise, and 0 means the enterprise is a non-core enterprise.

[0053] For example, in one embodiment, the initial weight Wi of an industrial enterprise is set to 0.7, the data quality adjustment factor Fdq is set to 0.5, and the core enterprise adjustment factor Fcc is set to 0.6. Assuming that the data quality score DQ of the enterprise is 0.9 and the core enterprise rating CC is 0.8, its dynamic weight W is calculated as follows: W = 0.7*(1+0.5*0.9+0.6*0.8) = 0.7*(1+0.45+0.48) = 0.7*1.93 = 1.351. This means that the score of the enterprise after the dynamic weight adjustment has increased significantly, reflecting the important influence of data quality and core status on its weight.

[0054] Through the above steps and formulas, the weights of participating enterprises can be reasonably adjusted in the dynamically changing industrial Internet supply chain, optimizing resource allocation and decision-making processes. The formula setting takes into account the dual influence of data quality and core status, ensuring that the weight adjustment is both scientific and flexible, and can adapt to complex and changing actual needs.

[0055] The data privacy calculation method of dynamic weight allocation in the industrial Internet supply chain of the present invention includes:

[0056] First, a data quality assessment model is established, which can monitor the data quality of each enterprise in the supply chain in real time. A comprehensive assessment is conducted from multiple dimensions such as data integrity, accuracy, and timeliness to ensure the validity and reliability of the data. This step helps to identify potential problems in the data and provide an objective basis for subsequent weight allocation.

[0057] Secondly, determine the criteria for core enterprises, which may include enterprise size, market influence, and criticality to the supply chain. Through comprehensive consideration of multiple dimensions, ensure that the selected core enterprises have an important position in the supply chain. Once the core enterprises are determined, they will be given an initial higher weight, which will help to fully utilize the advantages of the core enterprises in data collaboration.

[0058] Third, a dynamic weight adjustment algorithm is designed, which can adjust the calculation weight of each enterprise regularly or in real time according to the data quality assessment results and the status changes of the core enterprises. For example, when the data quality of a certain enterprise is significantly improved, its weight will be increased accordingly to better reflect its actual contribution in the supply chain. If there is a problem with the core enterprise, the system will adjust the weight distribution strategy in time to ensure the robustness and fairness of the overall model.

[0059] Finally, collaborative optimization is performed, and each enterprise shares some data feature information and jointly optimizes the model under the premise of privacy protection. The present invention adopts technologies such as federated learning to achieve distributed training and optimization of the model and improve the performance of the overall model. In this way, while protecting the privacy of their own data, enterprises can still effectively participate in the overall collaboration of the supply chain and maximize the use of data.

[0060] The above method effectively solves the problem of static weight allocation in traditional methods, which cannot adapt to the dynamic changes in data quality and enterprise importance in the supply chain. Through real-time monitoring and dynamic adjustment, the present invention enables the model to respond to various situations more flexibly, improves the efficiency and accuracy of collaborative computing of supply chain data, and ensures the data security of enterprises.

[0061] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0062] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction 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 may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0063] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0064] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0065] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0066] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0067] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0068] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A data privacy calculation method for dynamic weight allocation in industrial Internet supply chain, characterized in that: include: Establish a data quality assessment model to monitor the data quality of each enterprise in the supply chain in real time; Determine the criteria for judging core enterprises; Design a dynamic weight adjustment algorithm to adjust the calculation weight of each enterprise regularly or in real time based on the data quality assessment results and the status changes of core enterprises; To conduct collaborative optimization, all enterprises share some data feature information and jointly optimize the model under the premise of privacy protection.

2. The data privacy calculation method for dynamic weight allocation in the industrial Internet supply chain according to claim 1 is characterized in that: The data quality is evaluated by the following formula: Assume that the set of data quality indicators is Q = {completeness Q1, accuracy Q2, timeliness Q3...}; The weight of each indicator is Wq = {Wq1, Wq2, Wq3...}, and the weight is set according to the actual situation or dynamically adjusted through machine learning algorithms; The data quality score DQ of a certain enterprise is Q1*Wq1+Q2*Wq2+Q3*Wq3+…….

3. The data privacy calculation method for dynamic weight allocation in the industrial Internet supply chain according to claim 1 is characterized in that: The core enterprise is determined by the following formula: Let the core enterprise index set be C = {enterprise scale C1, market influence C2, criticality to the supply chain C3...}; The weight of each indicator is Wc = {Wc1, Wc2, Wc3...}; The core enterprise score CC of a certain enterprise is C1*Wc1+C2*Wc2+C3*Wc3+…….

4. The data privacy calculation method for dynamic weight allocation in the industrial Internet supply chain according to claim 1 is characterized in that: The dynamic weight is adjusted by the following formula: Assume that the initial weight is Wi, the data quality adjustment factor is Fdq, and the core enterprise adjustment factor is Fcc; The dynamic weight of a certain enterprise is W = Wi*(1+Fdq*DQ+Fcc*CC); Among them, the data quality adjustment factor Fdq and the core enterprise adjustment factor Fcc can be set according to actual conditions.

Images