Supply object low-carbon data processing system based on ocean engineering equipment manufacturing

Abstract

The invention provides a supply object green low-carbon data processing system based on ocean engineering equipment manufacturing, relates to the technical field of data processing, and solves the technical problem of low data processing accuracy of supply object data. The system comprises a qualification detection module used for acquiring first qualification information of supply objects, performing qualification detection on the first qualification information, and determining target supply objects with qualification; the performance evaluation module is used for acquiring historical performance data of the target supply object, identifying a target performance trend of the target supply object based on the historical performance data, and performing performance evaluation on the target supply object according to the target performance trend to obtain a performance evaluation result; and the risk management module is used for identifying and monitoring risk factor data of the target supply object according to the performance evaluation result, and performing risk evaluation on the target supply object according to the risk factor data and the state corresponding to the target supply object to obtain a risk evaluation value.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing. Background Art

[0002] Marine engineering equipment refers to various types of equipment used in the development, utilization and protection of the ocean. Marine engineering equipment is mainly divided into three categories: marine oil and gas resource development equipment, marine floating structures and other marine resource development equipment. Specific marine engineering equipment mainly includes drilling equipment manufacturing, production equipment manufacturing, auxiliary ship equipment manufacturing and supporting equipment manufacturing, etc. Its upstream links include marine engineering equipment design and raw materials and core parts supply. Among them, raw materials mainly include metals, waterproof materials, antifreeze materials, etc., and core parts mainly include electronic components, anchor chains, drilling and production systems, positioning systems, etc. For marine engineering equipment manufacturing companies, the management of suppliers and other supply objects is a very important part of corporate procurement management. However, the data processing accuracy of supply object access qualification review data and risk assessment data in the current supply object management is low, and it is difficult to obtain accurate supply object data analysis results. Summary of the invention

[0003] The object of the present invention is to provide a green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing, so as to solve the technical problem of low accuracy in data processing of supply object data.

[0004] In the first aspect, the present application provides a green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing, comprising:

[0005] A qualification detection module is used to obtain first qualification information of a supply object, and perform qualification detection on the first qualification information to determine a target supply object with qualifications;

[0006] A performance evaluation module is used to obtain the historical performance data of the target supply object, and identify the target performance trend of the target supply object based on the historical performance data through a support vector regression (SVR) model and an autoregressive integrated moving average (ARIMA) model, and perform performance evaluation on the target supply object according to the target performance trend to obtain a performance evaluation result;

[0007] A risk management module, used to identify and monitor the risk factor data of the target supply object according to the performance evaluation result, and to perform risk evaluation on the target supply object according to the risk factor data and the corresponding status of the target supply object to obtain a risk evaluation value;

[0008] The qualification detection module is also used to obtain the second qualification information of the newly introduced supply object when the risk assessment value is lower than the preset risk threshold, and perform qualification detection on the second qualification information to determine the new supply object with qualifications;

[0009] The dynamic assessment and early warning processing module is used to use a deep learning neural network to perform qualification detection, performance assessment and risk assessment on the target supply object when the risk assessment value is higher than or equal to the preset risk threshold, to obtain a comprehensive assessment result corresponding to the target supply object, and to set different levels of early warning processing mechanisms according to the comprehensive assessment results, so as to perform different levels of early warning processing on the target supply object through the early warning processing mechanism.

[0010] In a possible implementation, the qualification detection module includes:

[0011] A registration detection unit, used to receive an autonomous registration operation for the supply object through a user registration interface, obtain the qualification materials submitted by the supply object based on the autonomous registration operation, and perform multi-dimensional detection on the qualification information of the supply object automatically collected from multiple channels of the qualification materials, public information, and third-party certification agencies through big data analysis to obtain a multi-dimensional detection result; wherein the detection dimension of the multi-dimensional detection of the qualification information includes a qualification detection dimension for green and low-carbon data;

[0012] A qualification evaluation unit, configured to generate a qualification evaluation result for the supply object through a deep learning neural network according to the qualification information and the multi-dimensional detection result;

[0013] The admission unit is used to select a target supply object for admission from the multiple supply objects according to the qualification evaluation result, and enter the information of the selected target supply object.

[0014] In one possible implementation, the historical performance data acquired by the performance evaluation module includes at least one of the following dimensions: product energy consumption data, compliance data for designated green and low-carbon indicators, on-time delivery rate, product quality stability, price competitiveness, and service response speed; the performance evaluation module is also used to obtain the performance evaluation results based on the historical performance data using a deep learning neural network.

[0015] In one possible implementation, the performance evaluation module is also used to: construct a performance prediction model based on the time series of performance evaluation, and use the performance prediction model to predict future performance evaluation results at future moments, and perform weighted evaluation on historical performance evaluation results and the predicted future performance evaluation results to obtain a performance impact coefficient.

[0016] In a possible implementation, the risk management module includes:

[0017] A risk collection unit, used to collect financial status data and market dynamic data of the target supply object, and obtain natural disaster situation data within a specified range around the target supply object, and generate risk factor data based on the financial status data, the market dynamic data, and the natural disaster situation data;

[0018] A status acquisition unit, configured to acquire a first blockchain of a marine engineering equipment manufacturing object and a second blockchain of the target supply object, and determine a status corresponding to the target supply object based on the planned purchase data and production plan data in the first blockchain, and the financial data, raw material purchase data, and inventory data in the second blockchain;

[0019] The risk assessment unit is used to perform risk assessment on the target supply object by using a deep learning neural network according to an array consisting of the risk factor data and the status corresponding to the target supply object, so as to obtain a risk assessment value.

[0020] In a possible implementation, the risk management module further includes:

[0021] The judgment management unit is used to judge the relationship between the risk assessment value and the preset risk threshold. If the risk assessment value is lower than the preset risk threshold, the alternative supply objects are detected in sequence from the original supply object qualification score ranking through the qualification detection module, and the natural disaster situation data of the alternative supply objects are collected through the risk collection unit in the risk management module. When the alternative supply object does not have a natural disaster situation, the state corresponding to the alternative supply object is determined by the state acquisition unit, and the introduction of a new supply object is determined according to the state corresponding to the alternative supply object.

[0022] In a possible implementation, the dynamic evaluation and early warning processing module includes:

[0023] A dynamic evaluation unit, configured to generate a weight allocation model using a deep learning neural network based on the qualification evaluation results, the performance evaluation results, the risk evaluation value and the designated data set of weight allocation, determine weight allocation data using the weight allocation model according to the qualification evaluation results, the performance evaluation results and the risk evaluation value, and calculate a comprehensive evaluation result corresponding to the target supply object based on the weight allocation data;

[0024] The early warning processing unit is used to classify the target supply objects into supply object levels according to the comprehensive evaluation results, and to execute different early warning processing mechanisms according to different supply object levels.

[0025] In a possible implementation, the early warning processing unit is further used for:

[0026] If the comprehensive evaluation result is lower than the preset evaluation threshold, the target supply object will be determined as a risky supply object, and a rectification detection instruction will be sent to the risky supply object. The rectification detection instruction is used to control the risky supply object to complete and submit rectification report data within a preset period, so as to determine the first actual rectification effect according to the rectification report data, and when it is not detected that the first actual rectification effect reaches the preset standard rectification effect, the risky supply object will be determined as an eliminated supply object, and the newly introduced supply object will be detected through the qualification detection module.

[0027] In a possible implementation, the early warning processing unit is further used for:

[0028] If the forecast comprehensive evaluation result calculated by using the performance forecasting model is lower than the preset evaluation threshold, the target supply object will be determined as a potential risk supply object, and an inspection optimization instruction will be sent to the potential risk supply object. The inspection optimization instruction is used to control the potential risk supply object to complete and submit the optimization report data within a preset period, so as to determine the second actual rectification effect according to the optimization report data, and determine the potential risk supply object as the risk supply object when it is not detected that the second actual rectification effect reaches the preset standard rectification effect.

[0029] In a second aspect, the present application provides a green and low-carbon data processing method for supply objects based on marine engineering equipment manufacturing, the method comprising:

[0030] Acquire first qualification information of the supply object, and perform qualification detection on the first qualification information to determine the target supply object with qualifications;

[0031] Acquire historical performance data of the target supply object, and identify the target performance trend of the target supply object based on the historical performance data through a support vector regression SVR model and an autoregressive integrated moving average ARIMA model, and perform performance evaluation on the target supply object according to the target performance trend to obtain a performance evaluation result;

[0032] Identify and monitor the risk factor data of the target supply object according to the performance evaluation result, and perform risk evaluation on the target supply object according to the risk factor data and the corresponding status of the target supply object to obtain a risk evaluation value;

[0033] If the risk assessment value is lower than the preset risk threshold, the second qualification information of the newly introduced supply object is obtained, and the second qualification information is tested to determine the qualified new supply object;

[0034] If the risk assessment value is higher than or equal to the preset risk threshold, a deep learning neural network is used to perform qualification detection, performance assessment and risk assessment on the target supply object to obtain a comprehensive assessment result corresponding to the target supply object, and different levels of early warning processing mechanisms are set according to the comprehensive assessment results, so as to perform different levels of early warning processing on the target supply object through the early warning processing mechanism.

[0035] In a third aspect, the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to execute the method described in the first aspect.

[0037] This application brings the following beneficial effects:

[0038] The present application provides a green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing, which can obtain the first qualification information of the supply object, perform qualification detection on the first qualification information, determine the target supply object with qualifications, obtain the historical performance data of the target supply object, and identify the target performance trend of the target supply object based on the historical performance data through a support vector regression SVR model and an autoregressive integral moving average ARIMA model, perform performance evaluation on the target supply object according to the target performance trend, obtain the performance evaluation result, identify and monitor the risk factor data of the target supply object according to the performance evaluation result, and perform risk evaluation on the target supply object according to the risk factor data and the corresponding status of the target supply object to obtain a risk evaluation value. If the risk evaluation value is lower than the preset risk threshold, the second qualification information of the newly introduced supply object is obtained, and the second qualification information is tested to determine the new qualified supply object. If the risk evaluation value is higher than or equal to the preset risk threshold, The deep learning neural network is used to perform qualification detection, performance evaluation and risk evaluation on the target supply object, and the comprehensive evaluation results corresponding to the target supply object are obtained. Different levels of early warning processing mechanisms are set according to the comprehensive evaluation results, so as to perform different levels of early warning processing on the target supply object through the early warning processing mechanism. In this scheme, through the qualification detection module, performance evaluation module, risk management module, dynamic evaluation and early warning processing module, the system can deeply consider the risks brought by suppliers and other supply objects themselves and objective environmental factors, and formulate targeted response mechanisms, and use the qualification level, supply performance and risk response ability of the supply object in the supply process to comprehensively characterize the service ability of the supply object, and use the qualification level, supply performance and risk response ability of the supply object in the supply process to comprehensively characterize the service ability of the supply object, which can effectively improve the comprehensiveness and rationality of the evaluation, thereby improving the accuracy of data processing of supply object data, and solving the technical problem of low accuracy of data processing of supply object data.

[0039] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1A flow chart of a green and low-carbon data processing method for supply objects based on marine engineering equipment manufacturing provided in an embodiment of the present application;

[0042] Figure 2 Another schematic flow chart of the green and low-carbon data processing method for supply objects based on marine engineering equipment manufacturing provided in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of the structure of a green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing provided in an embodiment of the present application;

[0044] Figure 4 A structural diagram of a qualification review module in a green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing provided in an embodiment of the present application;

[0045] Figure 5 A structural diagram of a risk management module in a green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing provided in an embodiment of the present application;

[0046] Figure 6 A structural diagram of a dynamic scoring and early warning processing module in a green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing provided in an embodiment of the present application;

[0047] Figure 7 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0049] The terms "including" and "having" and any variations thereof mentioned in the embodiments of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0050] At present, the existing technology does not consider the identification and management of potential risk factors in the financial status, market dynamics, natural disasters, political environment and other data of suppliers and other supply objects. Risk factors may affect the stability of supplier supply, and the uncertainty of supplier supply may cause the enterprise to be unable to operate normally or the daily operation of the enterprise to be adversely affected. Furthermore, for supplier risk assessment management, it specifically includes supervising supplier risks and submitting evaluation applications, evaluating and scoring supplier risks, and managing suppliers based on risk assessment. However, it is only in daily work that the demand / responsible management department and the procurement center correspond to the risk type and evaluate and score the supplier risks according to the assessment standards, and does not involve in-depth consideration of the risks brought by the supplier itself and objective environmental factors. Therefore, the data processing accuracy of the supply object data in the current supply object management is low, it is difficult to obtain accurate analysis results, and it is impossible to realize the ability of the supplier management system to actively explore and independently respond to various risks.

[0051] Based on this, an embodiment of the present application provides a green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing. This method can solve the technical problem of low accuracy in data processing of supply object data.

[0052] The embodiments of the present invention are further described below in conjunction with the accompanying drawings.

[0053] Figure 1 A flow chart of a method for processing green and low-carbon data of supply objects based on marine engineering equipment manufacturing provided in an embodiment of the present application. Applicable to a green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing. Figure 1 As shown, the method includes:

[0054] Step S110, obtaining first qualification information of the supply object, and performing qualification detection on the first qualification information to determine the target supply object with qualifications.

[0055] As a possible implementation method, the qualification information of suppliers who register autonomously through the user registration interface is collected and analyzed, the qualification scores of the suppliers are obtained based on a deep neural network, and the suppliers are selected according to the qualification scores.

[0056] Exemplarily, a self-registration operation for the supply object is first received through the user registration interface, and the qualification materials submitted by the supply object are obtained based on the self-registration operation, and the qualification information of the supply object automatically collected from multiple channels such as the qualification materials, public information, and third-party certification agencies is subjected to multi-dimensional detection through big data analysis to obtain multi-dimensional detection results; wherein, the detection dimensions for multi-dimensional detection of qualification information include qualification detection dimensions for green and low-carbon data; then, a qualification evaluation result for the supply object is generated through a deep learning neural network based on the qualification information and the multi-dimensional detection results; thereafter, a target supply object for admission is selected from the multiple supply objects based on the qualification evaluation results, and the information of the selected target supply object is entered.

[0057] Step S120, obtain the historical performance data of the target supply object, and identify the target performance trend of the target supply object based on the historical performance data through the support vector regression SVR model and the autoregressive integrated moving average ARIMA model, and perform performance evaluation on the target supply object according to the target performance trend to obtain a performance evaluation result.

[0058] The historical performance data acquired by the performance evaluation module includes at least one of the following dimensions: product energy consumption data, data on compliance with designated green and low-carbon indicators, on-time delivery rate, product quality stability, price competitiveness, and service response speed. Exemplarily, the historical performance data of suppliers is collected and analyzed, the trend of supplier performance is automatically identified, and continuous evaluation and performance scoring are performed on them to obtain two performance scores: the current performance score and the predicted performance score.

[0059] It should be noted that the ARIMA model (autoregressive integrated moving average model) is a type of time series analysis and a time series prediction method, which is suitable for stationary time series data. It includes three parts: autoregression (AR), difference (I) and moving average (MA), and the time series data is predicted by the combination of these three parts. The SVR model (support vector regression model) is a machine learning algorithm for regression problems. It is based on the idea of ​​support vector machine (SVM) and finds an optimal function by maximizing the interval, so that the data points are as close to the function as possible, and at the same time minimizes the prediction error.

[0060] Step S130, identifying and monitoring the risk factor data of the target supply object according to the performance evaluation result, and performing risk evaluation on the target supply object according to the risk factor data and the corresponding status of the target supply object to obtain a risk evaluation value.

[0061] For example, first collect the supplier's financial status and market dynamics, and natural disaster situations in the supplier's surrounding area, obtain the company's own blockchain and the supplier's blockchain, and judge the supplier's response status based on the planned purchase data and production plan data in the company's own blockchain and the financial data, raw material purchase data and inventory data in the supplier's blockchain, and perform risk scoring based on an array of risk factors and supplier response status based on a deep neural network.

[0062] Step S140: If the risk assessment value is lower than the preset risk threshold, the second qualification information of the newly introduced supply object is obtained, and the second qualification information is tested to determine the qualified new supply object.

[0063] As an example, when the risk score is lower than the set risk threshold, the alternative suppliers are evaluated in turn from the original supplier qualification score ranking, and the natural disaster risk factors of the alternative suppliers are collected. When the alternative suppliers do not have natural disaster risk factors, the response status of the alternative suppliers is judged, and the introduction of new suppliers is determined based on the response status of the alternative suppliers.

[0064] Step S150, if the risk assessment value is higher than or equal to the preset risk threshold, the deep learning neural network is used to perform qualification detection, performance evaluation and risk evaluation on the target supply object to obtain a comprehensive evaluation result corresponding to the target supply object, and different levels of early warning processing mechanisms are set according to the comprehensive evaluation results, so as to perform different levels of early warning processing on the target supply object through the early warning processing mechanism.

[0065] As another example, when the risk score is not lower than the set risk threshold, deep learning technology is used to combine the qualification score, performance score and risk score to obtain a comprehensive score, and two comprehensive scores are obtained, one based on the current performance score and the other based on the predicted performance score. Suppliers are graded according to the comprehensive scores, and different early warning processing mechanisms are executed for the two comprehensive scores according to different supplier grades.

[0066] Among them, the process of executing different early warning processing mechanisms according to different supplier levels may specifically include the following steps: when the current performance score is used to participate in the calculation to obtain a comprehensive score, and the comprehensive score is lower than the set score threshold, the supplier is determined as a risk supplier, a rectification review is initiated for the risk supplier, and the risk supplier is required to complete and submit a rectification report within a preset period. The user determines the rectification effect based on the rectification report. If the rectification effect of the risk supplier is not detected to meet the standards, the risk supplier is determined as an eliminated supplier, and the qualification review module is started to assess and introduce new suppliers, otherwise the risk supplier is cancelled. When the predicted performance score is used to participate in the calculation to obtain a comprehensive score, if the comprehensive score is lower than the set score threshold, the supplier is determined as a potential risk supplier, an improvement self-inspection is initiated for the potential risk supplier, and the potential risk supplier is required to complete and submit an improvement report within a preset period. The user determines the rectification effect based on the rectification report. If the rectification effect of the risk supplier is not detected to meet the standards, the potential risk supplier is determined as a risk supplier, otherwise the potential risk supplier is cancelled. When the comprehensive score is not lower than the set score threshold, the supplier is determined to be a qualified supplier, and the assessment and evaluation of the current supply round ends.

[0067] Through the qualification detection module, performance evaluation module, risk management module, and dynamic evaluation and early warning processing module, the system can deeply consider the risks brought about by the supply object (supplier) itself and objective environmental factors, as well as the targeted response mechanism, and use the supply object's qualification level, supply performance and risk response ability in the supply process to comprehensively characterize the supply object's service capability. By using the supply object's qualification level, supply performance and risk response ability in the supply process to comprehensively characterize the supply object's service capability, it can effectively improve the comprehensiveness and rationality of the evaluation, thereby improving the accuracy of data processing of the supply object's data, and achieving the effect of strengthening the supplier management system's ability to actively explore and independently respond to various risks.

[0068] The embodiment of the present application also provides a green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing. The green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing includes: a qualification detection module, which is used to obtain first qualification information of the supply object, and perform qualification detection on the first qualification information to determine the target supply object with qualifications; a performance evaluation module, which is used to obtain the historical performance data of the target supply object, and identify the target performance trend of the target supply object based on the historical performance data through a support vector regression SVR model and an autoregressive integrated moving average ARIMA model, and perform performance evaluation on the target supply object according to the target performance trend to obtain a performance evaluation result; a risk management module, which is used to identify and monitor the risk factor data of the target supply object according to the performance evaluation result. And according to the risk factor data and the corresponding status of the target supply object, the target supply object is subjected to risk assessment to obtain a risk assessment value; the qualification detection module is also used to obtain the second qualification information of the newly introduced supply object when the risk assessment value is lower than the preset risk threshold, and perform qualification detection on the second qualification information to determine the new supply object with qualifications; the dynamic assessment and early warning processing module is used to perform qualification detection, performance assessment and risk assessment on the target supply object using a deep learning neural network when the risk assessment value is higher than or equal to the preset risk threshold, to obtain a comprehensive assessment result corresponding to the target supply object, and to set different levels of early warning processing mechanisms according to the comprehensive assessment results, so as to perform different levels of early warning processing on the target supply object through the early warning processing mechanism.

[0069] In some embodiments, the qualification detection module includes: a registration detection unit, which is used to receive an autonomous registration operation for the supply object through a user registration interface, obtain the qualification materials submitted by the supply object based on the autonomous registration operation, and perform multi-dimensional detection on the qualification information of the supply object automatically collected from multiple channels such as the qualification materials, public information, and third-party certification agencies through big data analysis to obtain a multi-dimensional detection result; wherein the detection dimension for multi-dimensional detection of the qualification information includes a qualification detection dimension for green and low-carbon data; a qualification evaluation unit, which is used to generate a qualification evaluation result for the supply object through a deep learning neural network based on the qualification information and the multi-dimensional detection result; an access unit, which is used to select a target supply object for access from a plurality of the supply objects based on the qualification evaluation result, and enter the information of the selected target supply object.

[0070] In some embodiments, the historical performance data acquired by the performance evaluation module includes at least one of the following dimensions: product energy consumption data, compliance data for designated green and low-carbon indicators, delivery punctuality rate, product quality stability, price competitiveness, and service response speed; the performance evaluation module is also used to obtain the performance evaluation results based on the historical performance data using a deep learning neural network.

[0071] In some embodiments, the performance evaluation module is further used to: construct a performance prediction model based on the time series of performance evaluation, and use the performance prediction model to predict future performance evaluation results at future moments, and perform weighted evaluation on historical performance evaluation results and predicted future performance evaluation results to obtain a performance impact coefficient. Through this data processing method, the supply status of the supply object at present and in the future is considered.

[0072] In some embodiments, the risk management module includes: a risk collection unit, which is used to collect the financial status data and market dynamics data of the target supply object, and obtain the natural disaster situation data within a specified range around the target supply object, and generate risk factor data based on the financial status data, the field dynamics data, and the natural disaster situation data; a status acquisition unit, which is used to obtain the first blockchain of the marine engineering equipment manufacturing object and the second blockchain of the target supply object, and determine the corresponding status of the target supply object based on the planned purchase data and production plan data in the first blockchain, and the financial data, raw material purchase data and inventory data in the second blockchain; a risk assessment unit, which is used to perform risk assessment on the target supply object according to an array composed of the risk factor data and the corresponding status of the target supply object by using a deep learning neural network to obtain a risk assessment value.

[0073] In some embodiments, the risk management module also includes: a judgment management unit, which is used to judge the relationship between the risk assessment value and a preset risk threshold. If the risk assessment value is lower than the preset risk threshold, the qualification detection module is used to detect alternative supply objects in sequence from the original supply object qualification score ranking, and the risk collection unit in the risk management module is used to collect natural disaster situation data of the alternative supply objects. When the alternative supply object does not have a natural disaster situation, the status corresponding to the alternative supply object is determined by the status acquisition unit, and the introduction of a new supply object is determined based on the status corresponding to the alternative supply object.

[0074] In some embodiments, the dynamic assessment and early warning processing module includes: a dynamic assessment unit, which is used to generate a weight allocation model using a deep learning neural network based on the qualification assessment results, the performance assessment results, the risk assessment value and the specified data set of weight allocation, and determine the weight allocation data using the weight allocation model according to the qualification assessment results, the performance assessment results and the risk assessment value, and calculate the comprehensive assessment results corresponding to the target supply object based on the weight allocation data; an early warning processing unit, which is used to divide the target supply object into supply object levels according to the comprehensive assessment results, and execute different early warning processing mechanisms according to different supply object levels.

[0075] In some embodiments, the early warning processing unit is also used to: if the comprehensive evaluation result is lower than a preset evaluation threshold, the target supply object is determined as a risky supply object, and a rectification detection instruction is sent to the risky supply object, and the rectification detection instruction is used to control the risky supply object to complete and submit the rectification report data within a preset period, so as to determine a first actual rectification effect based on the rectification report data, and when it is not detected that the first actual rectification effect reaches the preset standard rectification effect, the risky supply object is determined as an eliminated supply object, and the newly introduced supply object is detected through the qualification detection module.

[0076] In some embodiments, the early warning processing unit is also used to: if the forecast comprehensive evaluation result calculated by using the performance forecasting model is lower than the preset evaluation threshold, the target supply object is determined as a potential risk supply object, and an inspection optimization instruction is sent to the potential risk supply object, the inspection optimization instruction is used to control the potential risk supply object to complete and submit the optimization report data within a preset period, so as to determine the second actual rectification effect according to the optimization report data, and determine the potential risk supply object as the risk supply object when it is not detected that the second actual rectification effect reaches the preset standard rectification effect. Through this data processing method, it is achieved to supervise and rectify the supply object through the current performance score, and to prevent and improve the supply object based on the predicted performance score. The two are combined to further improve the early warning processing effect of multi-dimensional risks.

[0077] As a possible implementation, Figure 3As shown, the green and low-carbon data processing system for suppliers based on marine engineering equipment manufacturing includes: a qualification review module 100, which is used to collect and analyze the qualification information of suppliers to perform qualification scoring in order to assess and introduce suppliers; a performance evaluation module 200, which is used to collect and analyze the historical performance data of suppliers, automatically identify the trend of supplier performance, and conduct continuous evaluation and performance scoring; a risk management module 300, which is used to monitor and identify potential risk factors of suppliers, and perform risk scoring based on risk factors and supplier response status. When the risk score is lower than the set risk threshold, the qualification review module is started to assess and introduce new suppliers; a dynamic scoring and early warning processing module 400, which uses deep learning technology to combine qualification scoring, performance scoring and risk scoring to obtain a comprehensive score, and sets different levels of early warning processing mechanisms according to the scoring results.

[0078] Among them, Figure 4 As shown, the qualification review module 100 includes a registration review unit 101, a scoring unit 102 and an access unit 103. The registration review unit 101 implements the self-registration of suppliers based on the user registration interface, and uses big data analysis to automatically collect and analyze the qualification information of suppliers from multiple channels such as public information, qualification materials submitted by suppliers, and third-party certification agencies for multi-dimensional review. The scoring unit 102 is based on a deep neural network and obtains the qualification score of the supplier based on the supplier qualification information obtained by the registration review unit 101; the access unit 103 selects the admitted supplier according to the qualification score and enters the selected supplier information.

[0079] In the embodiment of the present application, the specific structure of the deep neural network model in the scoring unit 102 is as follows: the number of neurons in the input layer represents the number of qualification status parameters of the supplier to be verified by the scoring unit 102. Generally, the reference indicators such as the supplier's industry qualifications, financial status, production capacity and compliance can be analyzed from the qualification information collected from multiple channels such as public information, qualification materials submitted by the supplier, and third-party certification agencies. In this embodiment, the number of neurons in the input layer is selected as 4, representing industry qualifications, financial status, production capacity and compliance, respectively, and containing 16 neurons respectively. The hidden layer uses the ReLU function as the activation function, and the formula of the ReLU function is f(x)=max(0,x). The output layer is 1 neuron, representing the supplier's qualification score. The activation function uses the linear function f(x)=wx+b, and the loss function is the smooth L1 loss L1=(1 / n)∑|yy′|, where y is the true value, y′ is the predicted value, and n is the number of samples. The optimizer uses a stochastic gradient descent optimizer, and the initial learning rate is 0.001, and it is decayed according to the change of the loss function, and the gradient is calculated using back propagation.

[0080] In a possible implementation, the industry qualifications, financial status, production capacity and compliance of the supplier are transformed, and the above-mentioned qualification information after the transformation is scored by experts. The industry qualifications, financial status, production capacity and compliance of the supplier and the corresponding expert scores are combined to obtain an array, so that the training data can be expanded to make the training data more diverse. The deep neural network model is trained and tested based on the above training data, and the model parameters are adjusted so that the performance of the model meets the requirements. Then, the newly collected industry qualifications, financial status, production capacity and compliance data of the supplier are input into the trained deep neural network model to obtain the supplier's qualification score Q1.

[0081] As a possible implementation method, the admission unit 103 ranks suppliers from high to low according to their qualification scores, selects the admitted suppliers in order, generally selects the supplier ranked first, and enters the selected supplier information. For the performance evaluation module 200, the historical performance data collected by the performance evaluation module 200 includes but is not limited to multiple dimensions such as delivery punctuality, product quality stability, price competitiveness, and service response speed. A deep neural network is used to obtain a performance score based on the historical performance data. The deep neural network model structure is similar to that in the scoring unit 102. The number of neurons in its input layer is 4, representing the delivery punctuality, product quality stability, price competitiveness, and service response speed, respectively. The output layer is 1 neuron, representing the performance score of the supplier. The collected supplier historical performance data is input into the deep neural network model to obtain the supplier's performance score Q2.

[0082] In an optional implementation, a performance prediction model is constructed based on the time series of performance scores, and the constructed performance prediction model is used to predict the performance scores at future moments to automatically identify the development trend of supplier performance scores. For example, an LSTM model is used to predict the performance scores at future moments, and the time series of performance scores is used as training data to obtain a performance prediction model that can be used to predict the performance scores at future moments. The influence coefficient is determined based on the predicted performance scores. The influence coefficient is obtained by weighting the predicted performance scores and the historical performance scores. The influence coefficient is generally determined by the coefficient formula vi=βqi+1+(1-β)qavg, where qi+1 is the predicted performance score at future moments, qavg is the historical average performance score, and β∈[0,1]. When using the predicted performance score to calculate the subsequent comprehensive score, viQ2 is generally considered.

[0083] For the risk management module 300, if Figure 5As shown, it includes a risk collection unit 301, a state acquisition unit 302, a risk scoring unit 303 and a judgment management module 304, wherein the risk collection unit 301 is used to collect the financial status and market dynamics of suppliers, and obtain the natural disaster situation within the supplier's surrounding area, the state acquisition unit 302 is used to obtain the enterprise's own blockchain and the supplier's blockchain, and perform assimilation management to determine the supplier's response status, and the risk scoring unit 303 is based on a deep neural network and performs risk scoring according to an array composed of risk factors and supplier response status. A risk threshold is set in the judgment management module 304 to determine the relationship between the risk score and the set risk threshold. When the risk score is lower than the set risk threshold, the qualification review module 100 is started to assess the alternative suppliers in turn from the original supplier qualification score ranking, and the risk collection unit 301 in the risk management module 300 is started to collect the natural disaster risk factors of the alternative suppliers. When the alternative supplier does not have natural disaster risk factors, the state acquisition unit 302 is started to determine the response status of the alternative supplier, and the introduction of a new supplier is determined based on the response status of the alternative supplier.

[0084] In the embodiment of the present application, the financial status, market dynamics, and natural disasters of the supplier collected by the risk collection unit 301 constitute risk factors. The status acquisition unit 302 is based on the planned purchase data and production plan data in the enterprise's own blockchain and the financial data, raw material purchase data, and inventory data in the supplier's blockchain, and at the same time, it is based on the data in the enterprise's own blockchain and the supplier's blockchain to judge the supplier's response status. The structure of the deep neural network model in the risk scoring unit 303 is similar to that in the scoring unit 102. The number of neurons in its input layer is 4, representing the supplier's financial status, the supplier's market dynamics, natural disasters, and the supplier's response status, respectively. The output layer is 1 neuron, representing the supplier's risk score. The collected supplier's financial status, supplier's market dynamics, natural disaster data, and the supplier's response status data are input into the deep neural network model to obtain the supplier's risk score Q3.

[0085] In the embodiment of the present application, in order to quickly respond to risk factors and strive to minimize the impact, the risk threshold Q3 threshold is set by the judgment management module 304. When Q3 < Q3 threshold, the judgment management module 304 issues a control instruction to start the qualification review module 100, and the alternative suppliers are evaluated in turn from the last supplier qualification score ranking given by the access unit 103, and the risk collection unit 301 is started to collect the natural disaster risk factors of the alternative suppliers. When the alternative supplier does not have natural disaster risk factors, the status acquisition unit 302 is started to judge the response status of the alternative supplier, and the introduction of a new supplier is determined based on the response status of the alternative supplier to replace the current supplier. When the current supplier's ability to cope with risks is low, the alternative supplier that is not affected by natural disasters and has a higher risk response ability score is immediately selected from the original registered supplier list ranking, and the alternative supplier is determined as the admitted supplier. It is particularly suitable for situations where the current supplier is facing natural disasters and is difficult to cope with. It should be noted that the operation of replacing suppliers generally needs to be reviewed and approved by the user, and the current supplier is notified to stop supplying.

[0086] In general, if the risk score Q3 is not lower than the set risk threshold Q3, the dynamic scoring and warning processing module 400 is started to obtain a comprehensive score Q by combining the qualification score Q1, the performance score Q2 (viQ2) and the risk score Q3, and different levels of warning processing mechanisms are set according to the scoring results. Figure 6 As shown, the dynamic scoring and early warning processing module 400 includes a dynamic scoring unit 401 and an early warning processing unit 402, wherein the dynamic scoring unit 401 uses a deep neural network to obtain a weight distribution model based on a data set of qualification score Q1, performance score Q2 (viQ2), risk score Q3 and weight distribution, and uses the weight distribution model to obtain weight distribution based on the real-time qualification score Q1, performance score Q2 (viQ2), and risk score Q3 to calculate the comprehensive score Q; the early warning processing unit 402 divides the supplier level according to the comprehensive score Q, and executes different early warning processing mechanisms according to different supplier levels.

[0087] In an embodiment of the present application, based on the different scoring conditions of different suppliers, a deep neural network is used to build a weight distribution model to determine the weights corresponding to the qualification score Q1, the performance score Q2 (viQ2) and the risk score Q3, so as to calculate the comprehensive score Q. The network structure of the model is as follows: the input layer contains 3 neurons, representing the qualification score Q1, the performance score Q2 (viQ2) and the risk score Q3 respectively. The hidden layer is two layers, each containing 16 neurons. The hidden layer uses the ReLU function as the activation function. The formula of the ReLU function is f(x)=max(0,x). The output layer is 3 neurons, representing the weights corresponding to the qualification score Q1, the performance score Q2 (viQ2) and the risk score Q3 respectively. The activation function uses the linear function f(x)=wx+b. The loss function is the smooth L1 loss L1=(1 / n)∑|yy′|, where y is the true value, y′ is the predicted value, and n is the number of samples. The optimizer uses a stochastic gradient descent optimizer with an initial learning rate of 0.001, which is decayed according to the change of the loss function, and the gradient is calculated using back propagation. For the qualification score Q1, performance score Q2 (viQ2) and risk score Q3 under different scoring conditions of different suppliers, the corresponding weights of the three are determined, and the comprehensive score is calculated according to Q=∑ni=1ωiQi, where Qi represents the qualification score, performance score and risk score respectively, and ωi is the weight corresponding to Qi.

[0088] After obtaining the comprehensive score of the supplier, the early warning processing unit 402 divides the supplier level according to the comprehensive score Q, and implements different early warning processing mechanisms according to different supplier levels. On this basis, it is divided into two situations: current performance score Q2 and predicted performance score viQ2. Considering the supply status of the supplier at the current and future moments, the supplier is supervised and rectified based on the current performance score, and the supplier is prevented and improved based on the predicted performance score. The combination of the two can further improve the early warning processing effect of multi-dimensional risks. Specifically, different early warning processing mechanisms are implemented according to different supplier levels, including:

[0089] (1) When the current performance score is used to calculate the comprehensive score, and the comprehensive score is lower than the set score threshold, the supplier is identified as a risk supplier, and a rectification review is initiated for the risk supplier. The risk supplier is required to complete and submit a rectification report within a preset period. The user determines the rectification effect based on the rectification report. If the risk supplier's rectification effect does not meet the standards, the risk supplier is identified as an eliminated supplier, the qualification review module is initiated for assessment, and a new supplier is introduced. Otherwise, the risk supplier is cancelled.

[0090] (2) When the predicted performance score is used to calculate the comprehensive score, if the comprehensive score is lower than the set score threshold, the supplier will be identified as a potential risk supplier, and a self-inspection for improvement will be initiated for the potential risk supplier. The potential risk supplier will be required to complete and submit an improvement report within a preset period. The user will determine the rectification effect based on the rectification report. If the risk supplier's rectification effect does not meet the standards, the potential risk supplier will be identified as a risk supplier. Otherwise, the identification of the potential risk supplier will be cancelled.

[0091] The supplier's service capability is characterized by the supplier's qualification level, supply performance and risk response capability in the supply process, and the influence of qualification level, supply performance and risk response capability on supplier's service capability is comprehensively evaluated through deep neural network, so as to achieve a comprehensive evaluation of supplier's service capability and effectively improve the comprehensiveness and rationality of the evaluation. At the same time, the supplier's current and future supply status is considered from the supplier's supply performance at the current and future moments, and different reasonable early warning measures are taken for current risks and expected potential risks in the future, so as to improve the supplier management system's ability to actively explore and independently respond to various risks.

[0092] Through modular design and the application of advanced technologies, comprehensive management of supplier qualifications, performance and risks is achieved, effectively improving the reliability and overall efficiency of the supply chain.

[0093] In an optional implementation, the green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing may also include:

[0094] The data visualization and reporting module integrates the analysis results of various modules and intuitively displays various data of supplier management through charts, dashboards and reports. It can provide a customized data display interface so that managers can quickly obtain the required information and support the generation of detailed analysis reports.

[0095] The integrated interface module is responsible for the seamless connection and data exchange between the system and other information systems within the enterprise (such as ERP, CRM, MES, etc.) and external data sources. It supports multiple data interface standards and protocols to ensure that the system can efficiently interact with various information systems to form an integrated information management platform.

[0096] The user rights and security management module is responsible for the system's enterprise user identity authentication and rights management, ensuring the security of the system and the confidentiality of data. It supports multiple authentication methods, such as passwords, fingerprints, facial recognition, etc., and sets different permission levels according to enterprise user roles to ensure that each type of user can only access data and functions within their authority. At the same time, the module also has comprehensive logging and auditing functions, which can track user operations and ensure the safe operation of the system.

[0097] In this embodiment, by providing visualization tools through the data visualization and reporting module, the enterprise management can fully understand the qualifications, performance and risk status of suppliers, so as to make scientific supply chain management decisions; through the integrated interface module, the enterprise can achieve real-time synchronization and sharing of data, further improving the coordination and overall efficiency of supply chain management.

[0098] It should be noted that the system provided in the above embodiment only uses the division of the above functional modules as an example to implement its functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0099] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0100] The green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing provided in the embodiment of the present application has the same technical features as the green and low-carbon data processing method for supply objects based on marine engineering equipment manufacturing provided in the above-mentioned embodiment, so it can also solve the same technical problems and achieve the same technical effects.

[0101] An electronic device provided in an embodiment of the present application is Figure 7 As shown, the electronic device 700 includes a processor 702 and a memory 701, wherein the memory stores a computer program that can be run on the processor, and the processor implements the steps of the method provided in the above embodiment when executing the computer program.

[0102] See also Figure 7 The electronic device further includes: a bus 703 and a communication interface 704, a processor 702, a communication interface 704 and a memory 701 are connected via the bus 703; the processor 702 is used to execute an executable module stored in the memory 701, such as a computer program.

[0103] The memory 701 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 704 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0104] The bus 703 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0105] Among them, the memory 701 is used to store programs, and the processor 702 executes the program after receiving the execution instruction. The method executed by the device defined by the process disclosed in any embodiment of the present application can be applied to the processor 702 or implemented by the processor 702.

[0106] The processor 702 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 702. The above processor 702 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software modules in the decoding processor can be combined to execute. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 701, and the processor 702 reads the information in the memory 701 and completes the steps of the above method in combination with its hardware.

[0107] Corresponding to the above-mentioned green and low-carbon data processing method for supply objects based on marine engineering equipment manufacturing, an embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by the processor, the computer-executable instructions prompt the processor to execute the steps of the above-mentioned green and low-carbon data processing method for supply objects based on marine engineering equipment manufacturing.

[0108] The green and low-carbon data processing device for supply objects based on marine engineering equipment manufacturing provided in the embodiments of the present application can be specific hardware on the equipment or software or firmware installed on the equipment. The device provided in the embodiments of the present application, its implementation principle and the technical effect produced are the same as those in the aforementioned method embodiments. For the sake of brief description, the parts not mentioned in the device embodiment can refer to the corresponding contents in the aforementioned method embodiments. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.

[0109] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0110] For another example, the flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the device, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or the flowchart, and the combination of the boxes in the block diagram and / or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0113] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the green and low-carbon data processing method for supply objects based on marine engineering equipment manufacturing described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., and other media that can store program codes.

[0114] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0115] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solution of the present application, rather than to limit it. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the aforementioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solution recorded in the aforementioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of the embodiment of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing, characterized in that: include: A qualification detection module is used to obtain first qualification information of a supply object, and perform qualification detection on the first qualification information to determine a target supply object with qualifications; A performance evaluation module is used to obtain the historical performance data of the target supply object, and identify the target performance trend of the target supply object based on the historical performance data through a support vector regression SVR model and an autoregressive integrated moving average ARIMA model, and perform performance evaluation on the target supply object according to the target performance trend to obtain a performance evaluation result; A risk management module, used to identify and monitor the risk factor data of the target supply object according to the performance evaluation result, and to perform risk evaluation on the target supply object according to the risk factor data and the corresponding status of the target supply object to obtain a risk evaluation value; The qualification detection module is also used to obtain the second qualification information of the newly introduced supply object when the risk assessment value is lower than the preset risk threshold, and perform qualification detection on the second qualification information to determine the new supply object with qualifications; The dynamic assessment and early warning processing module is used to use a deep learning neural network to perform qualification detection, performance assessment and risk assessment on the target supply object when the risk assessment value is higher than or equal to the preset risk threshold, to obtain a comprehensive assessment result corresponding to the target supply object, and to set different levels of early warning processing mechanisms according to the comprehensive assessment results, so as to perform different levels of early warning processing on the target supply object through the early warning processing mechanism.

2. The green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing according to claim 1 is characterized in that: The qualification detection module includes: A registration detection unit, used to receive an autonomous registration operation for the supply object through a user registration interface, obtain the qualification materials submitted by the supply object based on the autonomous registration operation, and perform multi-dimensional detection on the qualification information of the supply object automatically collected from multiple channels of the qualification materials, public information, and third-party certification agencies through big data analysis to obtain a multi-dimensional detection result; wherein the detection dimension of the multi-dimensional detection of the qualification information includes a qualification detection dimension for green and low-carbon data; A qualification evaluation unit, configured to generate a qualification evaluation result for the supply object through a deep learning neural network according to the qualification information and the multi-dimensional detection result; The admission unit is used to select a target supply object for admission from the multiple supply objects according to the qualification evaluation result, and enter the information of the selected target supply object.

3. The green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing according to claim 2 is characterized in that: The historical performance data acquired by the performance evaluation module includes at least one of the following dimensions: product energy consumption data, compliance data for designated green and low-carbon indicators, delivery punctuality rate, product quality stability, price competitiveness, and service response speed; the performance evaluation module is also used to obtain the performance evaluation results based on the historical performance data using a deep learning neural network.

4. The green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing according to claim 3 is characterized in that: The performance evaluation module is also used to: build a performance prediction model based on the time series of performance evaluation, and use the performance prediction model to predict future performance evaluation results at future moments, and perform weighted evaluation on historical performance evaluation results and predicted future performance evaluation results to obtain a performance impact coefficient.

5. The green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing according to claim 1 is characterized in that: The risk management module includes: A risk collection unit, used to collect financial status data and market dynamic data of the target supply object, and obtain natural disaster situation data within a specified range around the target supply object, and generate risk factor data based on the financial status data, the market dynamic data, and the natural disaster situation data; A status acquisition unit, configured to acquire a first blockchain of a marine engineering equipment manufacturing object and a second blockchain of the target supply object, and determine a status corresponding to the target supply object based on the planned purchase data and production plan data in the first blockchain, and the financial data, raw material purchase data, and inventory data in the second blockchain; The risk assessment unit is used to perform risk assessment on the target supply object by using a deep learning neural network according to an array consisting of the risk factor data and the status corresponding to the target supply object, so as to obtain a risk assessment value.

6. The green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing according to claim 5 is characterized in that: The risk management module also includes: The judgment management unit is used to judge the relationship between the risk assessment value and the preset risk threshold. If the risk assessment value is lower than the preset risk threshold, the alternative supply objects are detected in sequence from the original supply object qualification score ranking through the qualification detection module, and the natural disaster situation data of the alternative supply objects are collected through the risk collection unit in the risk management module. When the alternative supply object does not have a natural disaster situation, the state corresponding to the alternative supply object is determined by the state acquisition unit, and the introduction of a new supply object is determined according to the state corresponding to the alternative supply object.

7. The green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing according to claim 4 is characterized in that: The dynamic evaluation and early warning processing module includes: A dynamic evaluation unit, configured to generate a weight allocation model using a deep learning neural network based on the qualification evaluation results, the performance evaluation results, the risk evaluation value and the designated data set of weight allocation, determine weight allocation data using the weight allocation model according to the qualification evaluation results, the performance evaluation results and the risk evaluation value, and calculate a comprehensive evaluation result corresponding to the target supply object based on the weight allocation data; The early warning processing unit is used to classify the target supply objects into supply object levels according to the comprehensive evaluation results, and to execute different early warning processing mechanisms according to different supply object levels.

8. The green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing according to claim 7 is characterized in that: The early warning processing unit is also used for: If the comprehensive evaluation result is lower than the preset evaluation threshold, the target supply object will be determined as a risky supply object, and a rectification detection instruction will be sent to the risky supply object. The rectification detection instruction is used to control the risky supply object to complete and submit rectification report data within a preset period, so as to determine the first actual rectification effect according to the rectification report data, and when it is not detected that the first actual rectification effect reaches the preset standard rectification effect, the risky supply object will be determined as an eliminated supply object, and the newly introduced supply object will be detected through the qualification detection module.

9. The green and low-carbon data processing system for supply objects based on marine engineering equipment manufacturing according to claim 8 is characterized in that: The early warning processing unit is also used for: If the forecast comprehensive evaluation result calculated by using the performance forecasting model is lower than the preset evaluation threshold, the target supply object will be determined as a potential risk supply object, and an inspection optimization instruction will be sent to the potential risk supply object. The inspection optimization instruction is used to control the potential risk supply object to complete and submit the optimization report data within a preset period, so as to determine the second actual rectification effect according to the optimization report data, and determine the potential risk supply object as the risk supply object when it is not detected that the second actual rectification effect reaches the preset standard rectification effect.

10. A green and low-carbon data processing method for supply objects based on marine engineering equipment manufacturing, characterized in that: The method comprises: Acquire first qualification information of the supply object, and perform qualification detection on the first qualification information to determine the target supply object with qualifications; Acquire historical performance data of the target supply object, and identify the target performance trend of the target supply object based on the historical performance data through a support vector regression SVR model and an autoregressive integrated moving average ARIMA model, and perform performance evaluation on the target supply object according to the target performance trend to obtain a performance evaluation result; Identify and monitor the risk factor data of the target supply object according to the performance evaluation result, and perform risk evaluation on the target supply object according to the risk factor data and the corresponding status of the target supply object to obtain a risk evaluation value; If the risk assessment value is lower than the preset risk threshold, the second qualification information of the newly introduced supply object is obtained, and the second qualification information is tested to determine the qualified new supply object; If the risk assessment value is higher than or equal to the preset risk threshold, a deep learning neural network is used to perform qualification detection, performance assessment and risk assessment on the target supply object to obtain a comprehensive assessment result corresponding to the target supply object, and different levels of early warning processing mechanisms are set according to the comprehensive assessment results, so as to perform different levels of early warning processing on the target supply object through the early warning processing mechanism.

Images