Industrial intelligent change data-to-collaborative management system based on industrial internet

Abstract

The invention relates to the technical field of industrial intelligent reformation data conversion, and discloses an industrial intelligent reformation data conversion collaborative management system based on an industrial internet. The system comprises a data acquisition module, a data processing module, an intelligent evaluation module and an application service module, and the data acquisition module acquires equipment operation data, enterprise business data and industry reference data through an industrial protocol, an API interface and a web crawler; the data processing module performs missing value filling and standardized conversion on the acquired data to construct an enterprise evaluation matrix; the intelligent evaluation module dynamically calculates an index weight based on the industry knowledge base and generates an enterprise intelligent modification level score; the application service module generates an enterprise digital portrait according to the score, matches a transformation policy and outputs a supply chain cooperation scheme; according to the system, the defects of data acquisition splitting and fixed weight of an evaluation model in the prior art are overcome, scientific evaluation and collaborative management of enterprise intelligent change data conversion are realized, and the collaborative efficiency of an industrial chain is improved.

Description

Technical Field

[0001] The present invention relates to the field of industrial intelligent transformation and digital transformation technology, and in particular to an industrial intelligent transformation and digital transformation collaborative management system based on the industrial Internet. Background Art

[0002] Intelligent digital transformation refers to intelligent transformation and digital transformation. In view of the current development trend of enterprise manufacturing, promoting "intelligent digital transformation" can enhance the control capability of the industrial chain, create intelligent information recognition, and improve manufacturing efficiency, thus laying the foundation for better development of enterprises. In the field of industrial intelligent transformation and digital transformation, the existing technology system has a significant quantitative evaluation bottleneck.

[0003] The core technical challenges currently facing the industry are mainly reflected in three dimensions: First, at the data collection level, traditional evaluation systems often separate processing equipment operation data from enterprise business data; second, in terms of evaluation models, mainstream methods such as traditional TOPSIS or AHP algorithms have inherent defects. Their fixed weight mechanism cannot respond to the dynamic changes of industrial systems. It can neither automatically adjust the weight distribution based on the discreteness of indicators, nor quantify the synergistic effects between indicators such as equipment networking rate and production efficiency; this fragmented technical architecture seriously restricts the scientific decision-making of enterprises' digital transformation and the collaborative efficiency of the industrial chain; in response to the above problems, existing technologies urgently need to be improved. Summary of the Invention

[0004] The technical problem to be solved by the present invention is that there are defects in the data collection and evaluation models in the intelligent digital transformation in the existing technology. To this end, we propose an industrial intelligent transformation and digital transformation collaborative management system based on the industrial Internet.

[0005] To achieve the above objectives, this application adopts the following technical solutions: an industrial intelligent transformation and digital transformation collaborative management system based on the Industrial Internet, comprising:

[0006] Data acquisition module: used to collect equipment operation data from PLC / SCADA systems in real time through industrial protocols, obtain enterprise business data from ERP / MES systems through API interfaces, and collect industry benchmark data according to industry classification standards through web crawlers;

[0007] Data processing module: used to fill missing values ​​and perform standardization conversion on collected data, and build an enterprise evaluation matrix;

[0008] Intelligent evaluation module: used to dynamically calculate indicator weights and generate enterprise intelligent reform level scores based on indicator association rules in the industry knowledge base;

[0009] Application service module: used to generate a digital portrait of the enterprise including industry benchmarking analysis based on the scoring results, match transformation policies and output supply chain collaboration solutions.

[0010] Preferably, the data acquisition module specifically includes:

[0011] Equipment data unit: collects equipment overall efficiency (OEE), energy consumption per unit output, equipment failure rate and equipment networking rate;

[0012] Business data unit: collects enterprise size, site area, tax amount and intelligent investment funds;

[0013] Industry data unit: Build a dynamic sample database based on industry classification codes to store the average and benchmark values ​​of industry indicators.

[0014] Preferably, the data processing module performs missing value processing and data standardization; equipment data is filled with the historical mean of similar equipment, and business data is interpolated with the industry average; the original data is mapped to the [0,1] interval through linear transformation to generate a standardized evaluation matrix , , where m is the total number of enterprises and n is the total number of evaluation indicators.

[0015] Preferably, the mathematical definition of the standardized transformation is ,in is the original value of enterprise i in indicator j, is the standardized value of enterprise i in indicator j.

[0016] Preferably, the intelligent evaluation module comprises an indicator comparison strength calculation unit and an indicator correction unit, wherein the indicator comparison strength calculation unit is used to calculate the indicator dispersion. , The larger the value, the stronger the indicator's ability to distinguish enterprises; the indicator correction unit defines the collaborative relationship based on the industry knowledge base , It indicates positive synergy, such as an increase in equipment networking rate leading to an increase in OEE.

[0017] Preferably, the indicator weight calculation adopts a dynamic weighting algorithm: ,in is the indicator correlation coefficient, is the synergy intensity coefficient, and the weight is generated by integrating the indicator discrimination, conflict and synergy effect.

[0018] Preferably, the indicator correlation coefficient The calculation method is: , which is used to quantify the information overlap between indicators j and k.

[0019] Preferably, the enterprise intelligent reform level score is generated by the TOPSIS algorithm: , , , , , ; is the weighted standard image quality of enterprise i on indicator j, through the weight of indicator j Multiply by the standardized value of enterprise i in indicator j It reflects the performance of the enterprise on this indicator after comprehensive consideration of the weight; , It is a dynamic industry benchmark value; and are positive ideal solutions and negative ideal solutions, i.e., the best and worst values ​​of the industry; and is the distance between enterprise i and the positive ideal solution and the negative ideal solution, which is used to measure the gap between the enterprise and the optimal and worst levels of the industry; is the score of enterprise i’s intelligent transformation level, ranging from 0 to 1. A larger value indicates a higher intelligent transformation level of the enterprise.

[0020] Preferably, the application service module includes:

[0021] Digital Portrait Unit: Generating a Composite Score and industry rankings;

[0022] Policy matching unit: matches enterprise shortcomings with policy requirements through the cosine similarity algorithm;

[0023] Supply chain collaboration unit: Clusters enterprises based on scoring and outputs equipment sharing and technological transformation cooperation plans.

[0024] Preferably, the industry ranking is calculated as follows:

[0025] , where m is the total number of enterprises in the industry, It indicates the number of enterprises with a higher intelligent reform score than enterprise i.

[0026] The technical effects and advantages of the present invention are as follows:

[0027] In the present invention, the present invention solves the problem of fragmentation of traditional evaluation data, ensures the integrity of enterprise portraits, integrates indicator discrimination, conflict and synergy effects, breaks through the limitations of traditional fixed weights, and makes the evaluation results more in line with the complex correlation characteristics of industrial systems. It can not only generate digital portraits including industry benchmarking analysis, but also intelligently match policies and supply chain collaboration solutions to help enterprises accurately locate shortcomings and optimize resource allocation; through multi-source data collection, dynamic weight calculation and collaborative analysis of industry knowledge bases, it solves the problems of data fragmentation, weight solidification and lack of collaboration in traditional evaluation systems, and has the advantages of realizing multi-source integration of equipment operation data and enterprise business data, building a dynamic weight evaluation system and improving the collaborative efficiency of the industrial chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The disclosure of the present invention is illustrated with reference to the accompanying drawings. It should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of protection of the present invention. In the drawings, the same reference numerals are used to refer to the same components:

[0029] Figure 1 It is a schematic diagram of a module of the present invention;

[0030] Figure 2 This is a module unit diagram of the data acquisition module and the intelligent evaluation module of the present invention. DETAILED DESCRIPTION

[0031] It is easy to understand that according to the technical solution of the present invention, without changing the essential spirit of the present invention, a person skilled in the art can propose a variety of interchangeable structural modes and implementation modes. Therefore, the following specific embodiments and drawings are only exemplary descriptions of the technical solution of the present invention and should not be regarded as the entire invention or as a limitation or restriction of the technical solution of the present invention.

[0032] Reference Figure 1-Figure 2 As shown, the present invention provides a technical solution: an industrial intelligent transformation and digital transformation collaborative management system based on the industrial Internet includes a data acquisition module, a data processing module, an intelligent evaluation module and an application service module.

[0033] The data acquisition module collects equipment operation data from the PLC / SCADA system in real time through industrial protocols, obtains enterprise business data from the ERP / MES system through the API interface, and collects industry benchmark data through web crawlers according to the GB / T 4754-2017 industry classification standard; the data processing module fills in missing values ​​and standardizes the collected data to construct an enterprise evaluation matrix; the intelligent evaluation module dynamically calculates indicator weights based on the indicator association rules in the industry knowledge base and generates an enterprise intelligent transformation level score; the application service module generates an enterprise digital portrait including industry benchmarking analysis based on the scoring results, matches transformation policies and outputs supply chain collaboration plans.

[0034] Among them, the industrial protocol is a set of standardized protocols for industrial equipment communication, and OPC UA and Modbus TCP protocols are used to realize equipment data collection, solving the problem of low efficiency of traditional manual transcription; the API interface adopts RESTful architecture to connect to the enterprise business system, realizing automatic acquisition of structured data such as revenue and venues; the web crawler builds an industry data collector based on the Scrapy framework, and stores industry benchmark values ​​according to national standards; missing values ​​are filled with historical averages of similar equipment, and industry averages are used to interpolate when business data is missing to ensure the integrity of the evaluation matrix; standardized transformation is processed through data normalization, and data of different dimensions are mapped to the [0,1] interval through linear transformation to eliminate the impact of magnitude differences on the evaluation; the industry knowledge base uses a graph database to store the collaborative and conflicting relationships between indicators, providing rule support for dynamic weight calculation.

[0035] After the equipment operation data is transmitted to the data acquisition module through the industrial protocol, it is aligned with the business data of the ERP system in the time dimension; when the data processing module detects that the equipment failure rate field is missing, it automatically retrieves the historical operation average of the same model equipment for interpolation; during the standardization conversion process, negative indicators such as unit output energy consumption are reverse normalized to generate a directly comparable evaluation matrix; the intelligent evaluation module enhances the contribution of indicators with synergistic effects when calculating weights based on the positive correlation rule between equipment networking rate and OEE defined in the industry knowledge base; the application service module calculates the Euclidean distance between the enterprise score and the industry benchmark value to generate a radar chart-style digital portrait that includes strength and weakness analysis.

[0036] The data collection module includes equipment data unit, business data unit and industry data unit; the equipment data unit collects equipment comprehensive efficiency, energy consumption per unit output, equipment failure rate and equipment networking rate; the business data unit collects enterprise scale, site area, tax amount and intelligent investment funds; the industry data unit constructs a dynamic sample database according to industry classification code, and stores the average value and benchmark value of industry indicators.

[0037] The comprehensive efficiency of the equipment is calculated by multiplying the equipment operating time, performance rate and yield rate, and is used to quantify the equipment operating efficiency; the energy consumption per unit of output is achieved by collecting data through metering devices such as electricity meters and gas meters, and is used to evaluate the energy utilization efficiency of the production process; the industry classification code is the industry category identification system established by the GB / T 4754-2017 standard, and is implemented using a four-digit coding structure.

[0038] The equipment data unit establishes a communication connection with the PLC / SCADA system through the industrial protocol to obtain the equipment operating status parameters in real time; for example, the equipment networking rate can be calculated by counting the proportion of terminal devices connected to the industrial Internet of Things to the total equipment base; the business data unit connects to the enterprise ERP system through the API interface to extract the employee number field, annual revenue data in the financial module, and site area information in the fixed asset ledger; the industry data unit deploys a web crawler program to specifically capture the industry economic operation data published by the government statistical department, and stores the collected industry benchmark values ​​in the time series database according to the preset classification and coding rules to form a dynamically updateable sample data set.

[0039] The data processing module performs missing value processing and data standardization. Missing value processing includes filling in missing device data with the historical mean of similar devices and filling in missing business data with the industry average. Data standardization maps the original data to the [0,1] interval to generate a standardized evaluation matrix. , , where m is the total number of enterprises and n is the total number of evaluation indicators.

[0040] The historical mean filling of similar equipment is carried out by calculating the average value of the historical operating data of equipment of the same model or similar functions to repair the data. It is specifically implemented using a sliding window average algorithm or a time series prediction model to solve the problem of incomplete data caused by interruptions in equipment data collection; the industry average interpolation is carried out by matching the indicator benchmark value of the corresponding industry according to the industry classification standard to fill the data. It is implemented using the real-time query interface of the industry database to maintain the industry comparability of the evaluation data when business data is missing; the standardized evaluation matrix converts the original data of different dimensions into a dimensionless standardized numerical set. Specifically, the range method is used to normalize the positive and negative indicators respectively to eliminate the impact of the dimensional differences between indicators on the evaluation results.

[0041] Specifically, when abnormalities occur in the collection of equipment operation data, the historical operation records of similar equipment under the same working conditions are retrieved, and the average value of its operating parameters is calculated as the filling value. For example, when the comprehensive efficiency of the equipment is missing, the average OEE value of the same model equipment in the past 30 days can be selected for supplementation; for the case of missing enterprise business data, according to the industry classification code to which the enterprise belongs, the average value of the corresponding indicator of the industry is extracted from the dynamic sample database for interpolation. For example, when the intelligent investment funds are missing, the annual average value of the intelligent investment of enterprises in the same industry is used as a substitute; after completing the missing value processing, the range method is used to standardize the original data, the positive indicators are normalized by the difference between the maximum and minimum values, and the negative indicators are calculated by the inverse difference, and finally a standardized evaluation matrix with unified dimensions is generated to provide a data basis for subsequent dynamic weight calculations.

[0042] This application further proposes that the standardized transformation is defined as: ,in is the original value of enterprise i in indicator j, is the standardized value of enterprise i in indicator j.

[0043] The larger the value of the positive indicator, the higher the level of enterprise intelligent transformation. This is achieved by using parameters such as equipment comprehensive efficiency and equipment networking rate. The difference between the original value and the minimum value of the indicator is divided by the range to achieve the same trend processing of the positive indicator. Among them, the smaller the value of the negative indicator, the higher the level of enterprise intelligent transformation. This is achieved by using parameters such as unit output energy consumption and equipment failure rate. The reverse interference of the negative indicator on the evaluation result is eliminated. Among them, the standardized transformation is a mathematical processing method that maps raw data of different dimensions to the interval [0,1]. It is achieved through the range method and solves the comparability problem of multi-source heterogeneous data by unifying the data scale.

[0044] Specifically, the standardized transformation normalizes the original data through the range method; for positive indicators, the calculation formula with the numerator being the original value minus the minimum value of the indicator is adopted to ensure that the larger the indicator value, the closer the standardized result is to 1; for negative indicators, the calculation formula with the numerator being the maximum value of the indicator minus the original value is adopted to ensure that the smaller the indicator value, the closer the standardized result is to 1; by distinguishing the directionality of indicators, the evaluation-oriented characteristics of the original data are retained, and a standardized evaluation matrix is ​​generated to provide a data basis for subsequent dynamic weight calculations.

[0045] The intelligent evaluation module includes a contrast intensity calculation unit and a collaborative correction unit. The contrast intensity calculation unit calculates the indicator dispersion, and the indicator dispersion is calculated using the standard deviation formula. The standard deviation formula is: , It is equal to the square root of the average of the squares of the differences between the standardized values ​​of all enterprises on indicator j and their average value. The larger the value, the stronger the indicator's ability to distinguish enterprises; the collaborative correction unit defines the collaborative relationship between indicators based on the industry knowledge base belongs to -1, 0 or 1, Indicates positive collaboration, Indicates negative synergy, Indicates no correlation. Positive synergy includes an increase in the overall efficiency of equipment due to an increase in the equipment networking rate.

[0046] The indicator dispersion quantifies the degree of distribution difference of the indicator in the sample enterprises through statistical methods, which is achieved by standard deviation calculation. The effectiveness of the indicator in distinguishing the enterprise capabilities is reflected by calculating the dispersion degree of standardized data. Among them, the synergistic relationship is a logical association of mutual promotion or restriction between indicators. It is achieved by using predefined regularization parameters in the industry knowledge base. The gain or inhibition relationship between indicators is represented numerically to correct the weight calculation.

[0047] Specifically, the contrast intensity calculation unit calculates the degree of dispersion of each indicator through the standard deviation formula. Indicators with high dispersion are given higher priority in the weight calculation, thereby strengthening the distinguishing role of key indicators; the synergy correction unit introduces a synergy coefficient in the weight calculation process based on the predefined relationship between indicators. For example, when there is a positive synergy between the equipment networking rate and the equipment's comprehensive efficiency, the weight calculation of the two will produce a gain effect; the combination of dispersion calculation and synergy correction enables the weight distribution to reflect both the data distribution characteristics and conform to the industry's operating laws.

[0048] The indicator weight is calculated using the dynamic weighting formula: ,in is the indicator correlation coefficient, is the synergy intensity coefficient, the default value is 0.2, and the weight is generated by comprehensively considering the indicator discrimination, conflict and synergy effect.

[0049] Correlation coefficient The information overlap between indicators is calculated by the Pearson correlation coefficient, and the ratio of covariance to standard deviation is calculated by using standardized data to quantify the degree of redundancy between different indicators. The synergy intensity coefficient γ is used to adjust the influence of the synergy relationship between indicators on the weight, and the amplification ratio of positive and negative synergies is adjusted by preset parameters. For example, when When , the synergy effect weight increases by γ times; the indicator dispersion The distribution difference of indicator data is calculated through standard deviation, and the square root of variance is calculated using standardized data to reflect the ability of indicators to distinguish different enterprises.

[0050] The dynamic weighting formula calculates weights through three factors: First, Strengthen the weight of indicators with high differentiation; secondly, Reduce the weight redundancy of highly correlated indicators; finally combine and The weights of indicators with synergistic relationships are modified; for example, when the equipment networking rate and OEE have a positive synergistic relationship, the weights of the two will be adjusted according to During the calculation process, the numerator integrates the discrimination of a single indicator and its independence and synergy with other indicators, and the denominator is normalized to finally generate a weight distribution that dynamically adapts to the characteristics of the enterprise and the industry.

[0051] The correlation coefficient is calculated as: , used to quantify the information overlap between indicators j and k; the correlation coefficient is calculated by the ratio of the covariance of the standardized data to the product of the standard deviation, using the Pearson correlation coefficient formula, to measure the degree of linear correlation between the two indicators; the standardized value is the value of the original data after normalization, which is achieved through the range standardization method to ensure the comparability of indicators of different dimensions; the mean is the average value of all enterprises on a certain indicator, which is achieved through arithmetic mean calculation and is used to characterize the central trend of the indicator data.

[0052] The calculation of the correlation coefficient is based on the standardized enterprise evaluation data; first, the dimensional differences of different indicators are eliminated through standardization, and then the ratio of the product of the covariance and standard deviation between each indicator is calculated; for example, for the two indicators of equipment networking rate and equipment comprehensive efficiency, if their standardized data show a trend of fluctuation in the same direction, the covariance increases and the correlation coefficient approaches 1, indicating that there is a strong positive correlation between the two; conversely, if the data fluctuates in the opposite direction, the correlation coefficient approaches -1, indicating a negative correlation; by quantifying the degree of information overlap between indicators, data support is provided for the calculation of dynamic weights.

[0053] The enterprise intelligent reform level score is generated using the TOPSIS algorithm, which includes the following steps:

[0054] Step 1: Calculate the weighted normalization matrix , is the weighted standard image quality of enterprise i on indicator j, through the weight of indicator j Multiply by the standardized value of enterprise i in indicator j It reflects the performance of the enterprise on this indicator after comprehensive consideration of the weight;

[0055] Step 2: Determine the ideal solution for each indicator and negative ideal solutions ;

[0056] Step 3: Calculate the Euclidean distance between each enterprise and the positive and negative ideal solutions and ;

[0057] Step 4: Through proximity Generate a rating, is the score of enterprise i’s intelligent transformation level, ranging from 0 to 1. A larger value indicates a higher intelligent transformation level of the enterprise.

[0058] The weighted normalization matrix multiplies the normalized data by the dynamic weight to form an evaluation matrix, which is implemented using a dynamic weight formula combined with matrix multiplication. This matrix can comprehensively reflect the contribution of each indicator to the overall evaluation. The positive ideal solution is the maximum value set of each indicator in the weighted matrix, which is achieved by traversing the weighted values ​​of all enterprises and taking the maximum value, representing the theoretical optimal level. The negative ideal solution is the minimum value set of each indicator in the weighted matrix, which is achieved by traversing the weighted values ​​of all enterprises and taking the minimum value, representing the theoretical worst level. The Euclidean distance is the geometric distance between the enterprise data point and the ideal solution in multidimensional space, which is calculated by taking the square root of the sum of squared differences and is used to quantify the degree of deviation of the enterprise from the ideal state. The closeness score is a comprehensive evaluation indicator generated by the relative distance ratio, which is calculated by the proportion of the negative ideal distance to the total distance. This indicator can eliminate dimensional differences and achieve cross-industry comparability.

[0059] Specifically, the standardized evaluation matrix is ​​first linearly combined with dynamic weights to form a weighted decision matrix. This weight integrates the indicator's discrimination and synergy, dynamically reflecting the multidimensional correlation characteristics of the industrial system. Then, the positive and negative ideal solutions for each evaluation indicator are determined, where the positive ideal solution consists of the industry's optimal value, and the negative ideal solution consists of the industry's worst value. By calculating the Euclidean distance between each enterprise and these two ideal solutions in multidimensional space, a relative closeness score in the range of 0-1 is ultimately generated. The combination of dynamic weights and multidimensional spatial distance calculations overcomes the problem of lagging evaluation results caused by traditional methods relying on fixed weights. At the same time, spatial vector modeling effectively captures the complex nonlinear characteristics of industrial intelligent transformation and digital transformation.

[0060] The application service module includes a digital portrait unit that generates comprehensive scores and industry rankings, matches corporate shortcomings with policy requirements through cosine similarity, clusters companies based on scores, and outputs equipment sharing and technical transformation cooperation plans.

[0061] The comprehensive score converts the enterprise intelligent reform level closeness score into a percentage value using the linear conversion formula This conversion method can intuitively reflect the relative position of the enterprise in the industry; the industry ranking is the relative position of the enterprise's intelligent transformation level in the same industry, which is achieved by calculating the proportion of the enterprise's proximity score exceeding that of other enterprises. , where m is the total number of enterprises in the industry, It represents the number of enterprises with a higher intelligent transformation level score than enterprise i. This ranking method can eliminate the evaluation bias caused by differences in industry scale. Cosine similarity matching calculates the directional consistency between the enterprise's short board indicators and policy requirements through a vector space model. It uses the cosine value of the angle between the enterprise indicator vector and the policy keyword vector to achieve this. This method can quantify the degree of matching and screen applicable policies. Score clustering is grouped and classified according to the enterprise's intelligent transformation level score. It is achieved by using K-means or hierarchical clustering algorithms. This grouping method can identify groups of enterprises with similar transformation needs. The equipment sharing and technical transformation cooperation plan recommends resource sharing strategies based on the enterprise clustering results. It is generated by analyzing the equipment complementarity and technology demand matching of enterprises in the same group. This plan can promote the coordinated optimization of upstream and downstream of the industrial chain.

[0062] Specifically, the digital portrait unit receives the proximity score output by the intelligent assessment module, generates a comprehensive score in percentage through linear conversion, and calculates the relative ranking percentage of the current enterprise based on the total number of enterprises in the industry; the policy matching unit uses the low-scoring items in the enterprise standardization assessment matrix as short-board indicators, and vectorizes them with the required features in the policy database for modeling, and selects the policy items with the highest matching degree through cosine similarity calculation; the supply chain collaboration unit performs cluster analysis on the intelligent transformation scores of all enterprises in the industry, identifies enterprise groups with similar transformation needs, and combines equipment inventory data and technology demand maps to generate cross-enterprise equipment sharing recommendations and technology transformation cooperation paths.

[0063] The technical scope of the present invention is not limited to the contents of the above description. Those skilled in the art can make various deformations and modifications to the above embodiments without departing from the technical idea of ​​the present invention, and these deformations and modifications should all fall within the protection scope of the present invention.

Claims

1. An industrial intelligent transformation and digital transformation collaborative management system based on the industrial Internet, characterized by: include: Data acquisition module: used to collect equipment operation data from PLC / SCADA systems in real time through industrial protocols, obtain enterprise business data from ERP / MES systems through API interfaces, and collect industry benchmark data according to industry classification standards through web crawlers; Data processing module: used to fill missing values ​​and perform standardization conversion on collected data, and build an enterprise evaluation matrix; Intelligent evaluation module: used to dynamically calculate indicator weights and generate enterprise intelligent reform level scores based on indicator association rules in the industry knowledge base; Application service module: used to generate a digital portrait of the enterprise including industry benchmarking analysis based on the scoring results, match transformation policies and output supply chain collaboration solutions.

2. The industrial intelligent transformation and digital transformation collaborative management system based on the industrial Internet according to claim 1 is characterized in that: The data acquisition module specifically includes: Equipment data unit: collects equipment overall efficiency (OEE), energy consumption per unit output, equipment failure rate and equipment networking rate; Business data unit: collects enterprise size, site area, tax amount and intelligent investment funds; Industry data unit: Build a dynamic sample database based on industry classification codes to store the average and benchmark values ​​of industry indicators.

3. The industrial intelligent transformation and digital transformation collaborative management system based on the industrial Internet according to claim 1 is characterized in that: The data processing module performs missing value processing and data standardization; equipment data is filled with the historical mean of similar equipment, and business data is interpolated with the industry average; the original data is mapped to the [0,1] interval through linear transformation to generate a standardized evaluation matrix , , where m is the total number of enterprises and n is the total number of evaluation indicators.

4. The industrial intelligent transformation and digital transformation collaborative management system based on the industrial Internet according to claim 3 is characterized in that: The mathematical definition of the normalization transformation is ,in is the original value of enterprise i in indicator j, is the standardized value of enterprise i in indicator j.

5. The industrial intelligent transformation and digital transformation collaborative management system based on the industrial Internet according to claim 1 is characterized in that: The intelligent evaluation module includes an indicator comparison strength calculation unit and an indicator correction unit. The indicator comparison strength calculation unit is used to calculate the indicator dispersion. , The larger the value, the stronger the indicator's ability to distinguish enterprises; the indicator correction unit defines the collaborative relationship based on the industry knowledge base , Indicates positive collaboration.

6. The industrial intelligent transformation and digital transformation collaborative management system based on the industrial Internet according to claim 5 is characterized in that: The indicator weight calculation adopts a dynamic weighting algorithm: ,in is the indicator correlation coefficient, is the synergy intensity coefficient, and the weight is generated by integrating the indicator discrimination, conflict and synergy effect.

7. The industrial intelligent transformation and digital transformation collaborative management system based on the industrial Internet according to claim 6 is characterized in that: The correlation coefficient of the indicators The calculation method is: , which is used to quantify the information overlap between indicators j and k.

8. The industrial intelligent transformation and digital transformation collaborative management system based on the industrial Internet according to claim 1 is characterized in that: The enterprise intelligent reform level score is generated by the TOPSIS algorithm: , , , , , ; is the weighted standard image quality of enterprise i on indicator j, through the weight of indicator j Multiply by the standardized value of enterprise i in indicator j It reflects the performance of the enterprise on this indicator after comprehensive consideration of the weight; , It is a dynamic industry benchmark value; and are positive ideal solutions and negative ideal solutions, i.e., the best and worst values ​​of the industry; and is the distance between enterprise i and the positive ideal solution and the negative ideal solution, which is used to measure the gap between the enterprise and the optimal and worst levels of the industry; is the score of enterprise i’s intelligent transformation level, ranging from 0 to 1. A larger value indicates a higher intelligent transformation level of the enterprise.

9. The industrial intelligent transformation and digital transformation collaborative management system based on the industrial Internet according to claim 1 is characterized in that: The application service module includes: Digital Portrait Unit: Generating a Composite Score and industry rankings; Policy matching unit: matches enterprise shortcomings with policy requirements through the cosine similarity algorithm; Supply chain collaboration unit: Clusters enterprises based on scoring and outputs equipment sharing and technological transformation cooperation plans.

10. The industrial intelligent transformation and digital transformation collaborative management system based on the industrial Internet according to claim 9 is characterized in that: The industry ranking is calculated as follows: , where m is the total number of enterprises in the industry, It indicates the number of enterprises with a higher intelligent reform score than enterprise i.

Images