Risk monitoring and early warning grading and classification management and control method and device based on distribution network supply chain, medium and product

Abstract

The invention discloses a risk monitoring and early warning grading and classification management and control method and device based on a distribution network supply chain, a medium and a product, and relates to the field of distribution network supply chain risk prediction.The method comprises the steps that potential risk factors of all links of the distribution network supply chain are determined based on risk associated data, and a risk factor library is constructed; establishing a risk assessment index system based on the risk factor library; determining the weight of each risk assessment index by adopting an analytic hierarchy process; constructing a fuzzy set and a comment set based on a fuzzy comprehensive evaluation theory; constructing a fuzzy comprehensive evaluation matrix according to the membership degree of the risk level corresponding to the risk evaluation index; determining an overall risk assessment value of the distribution network supply chain based on the fuzzy comprehensive evaluation matrix; determining a corresponding early warning mechanism by combining real-time monitoring data and a multi-dimensional prediction model, and performing early warning; according to the invention, the accuracy of risk identification can be improved, the real-time performance of risk early warning can be enhanced, the accuracy of risk management and control can be optimized, and the systematic risk of the distribution network supply chain can be reduced.

Description

Technical Field

[0001] This application relates to the field of risk prediction in the power distribution network supply chain, and in particular to a method, equipment, medium and product for risk monitoring, early warning and hierarchical classification and control based on the power distribution network supply chain. Background Technology

[0002] With the accelerated construction of new power systems, the scale of the power distribution network supply chain is growing rapidly, and its structure is becoming increasingly complex. The power distribution network supply chain encompasses multiple stages, from raw material procurement, equipment production, material transportation, and warehousing management to power equipment installation and operation and maintenance. These stages are interconnected and mutually influential. This process faces numerous risks, such as supplier credit risk, raw material price fluctuation risk, transportation delay risk, the impact of natural disasters on material supply, equipment quality risk, and the risk of unforeseen failures during operation and maintenance.

[0003] Currently, existing risk management methods for power distribution network supply chains have many shortcomings. On the one hand, risk identification is not comprehensive or accurate enough, often focusing only on some common risks and failing to identify potential and emerging risk factors. On the other hand, there is a lack of a scientific and reasonable risk assessment and classification system, making it impossible to take precise and effective control measures for different types and levels of risks. Furthermore, existing risk monitoring and early warning mechanisms have slow response times, failing to detect changes in risks and issue warnings in a timely manner. This makes it difficult to take rapid countermeasures when risks occur or escalate, significantly impacting the stable operation of the power distribution network supply chain and potentially causing serious consequences such as power supply interruptions, economic losses, and adverse social impacts.

[0004] To address the aforementioned issues, there is an urgent need for a method that can comprehensively and accurately identify risks, scientifically and rationally assess and classify risks, and achieve timely and effective monitoring, early warning, and precise control. Summary of the Invention

[0005] The purpose of this application is to provide a method, equipment, medium, and product for risk monitoring, early warning, hierarchical classification, and control based on the distribution network supply chain, which can improve the accuracy of risk identification, enhance the real-time nature of risk early warning, optimize the precision of risk control, and reduce systemic risks in the distribution network supply chain.

[0006] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a risk monitoring, early warning, hierarchical classification, and control method based on the distribution network supply chain, the method comprising: Construct a full-domain data acquisition network for the power distribution network supply chain; the full-domain data acquisition network is used to acquire risk-related data in real time; the risk-related data includes: supplier cooperation history data, credit data, operational stability data, raw material market data, production process data, logistics timeliness data, warehousing operation data, external environmental impact data, equipment operation and maintenance data, and market demand data; Based on the risk correlation data obtained from the full-domain data acquisition network, potential risk factors in each link of the power distribution network supply chain are identified, and a risk factor database is constructed. A risk assessment indicator system is established based on a risk factor database. The risk assessment indicator system includes: a target layer, a criterion layer, and an indicator layer. The target layer is a comprehensive quantitative assessment value of risk. The criterion layer includes: supply risk, production risk, logistics risk, and warehouse management risk. The indicator layer consists of quantified risk assessment indicators under the criterion layer. Based on the risk assessment index system, the weight of each risk assessment index is determined by the analytic hierarchy process (AHP); and a fuzzy set and a comment set are constructed based on the fuzzy comprehensive assessment theory; the comment set includes multiple risk levels. Based on the membership degree of the risk level corresponding to the risk assessment indicators, a fuzzy comprehensive evaluation matrix is ​​constructed; and based on the fuzzy comprehensive evaluation matrix, the overall risk assessment value of the power distribution network supply chain is determined. Based on the overall risk assessment value of the power distribution network supply chain, combined with real-time monitoring data and multi-dimensional prediction models, a corresponding early warning mechanism is determined and an early warning is issued; the multi-dimensional prediction models include: Long Short-Term Memory Network and Random Forest Model.

[0007] Optionally, the construction of the full-domain data collection network for the power distribution network supply chain specifically includes: Deploy IoT sensors in the supplier's production facility and connect them to the supplier management system via industrial Ethernet; Install machine vision inspection devices and equipment status sensors on the power distribution equipment production line; The transport vehicles are equipped with BeiDou positioning terminals and temperature and humidity sensors; radio frequency identification reading and writing equipment is deployed at transit hubs; and the vehicles are connected to the transport management system via a 5G network. Infrared thermal imagers, temperature and humidity sensors, smoke detectors, and intelligent shelf weighing devices are deployed in the warehouse area; and the warehouse management system is connected to the inbound and outbound barcode scanning equipment.

[0008] Optionally, the step of determining potential risk factors in each link of the power distribution network supply chain based on risk-related data acquired through a comprehensive data acquisition network, and constructing a risk factor database, specifically includes: Standardize the processing of risk-related data; Based on the standardized risk correlation data, potential risk factors in each link of the power distribution network supply chain are identified. A risk factor database is constructed based on the potential risk factors in each link of the power distribution network supply chain.

[0009] Optionally, the step of determining the weight of each risk assessment indicator based on the risk assessment indicator system using the analytic hierarchy process (AHP) specifically includes: Using formula Determine the weight of the i-th risk assessment indicator ; in, Let represent the importance of the i-th risk assessment indicator, and n be the number of risk assessment indicators.

[0010] Optionally, the step of constructing a fuzzy comprehensive evaluation matrix based on the membership degree of the risk level corresponding to the risk assessment indicator specifically includes: Using formula Determine the fuzzy comprehensive evaluation matrix ; in, This indicates the impact of the i-th risk assessment indicator on the k-th level rating. The membership degree is defined as follows: k=1 represents the criterion layer, k=2 represents the indicator layer, m represents the m evaluation results, and p is the number of risk levels. , For the i-th risk assessment indicator, the k-level comments are... The quantitative value of the evaluation results.

[0011] Optionally, based on the overall risk assessment value of the power distribution network supply chain, combined with real-time monitoring data and a multi-dimensional prediction model, a corresponding early warning mechanism is determined and issued, specifically including: When the overall risk assessment value of the power distribution network supply chain exceeds the warning threshold, a multi-channel warning will be issued; Based on real-time monitoring data and multi-dimensional prediction models, the risk level is predicted; and warnings are issued based on the predicted risk level.

[0012] Optionally, the step of predicting the risk level based on real-time monitoring data and a multi-dimensional prediction model, and issuing an early warning based on the predicted risk level, specifically includes: Using formula Determine the risk level ; in, For time-series risk weights, For multi-factor risk weighting, , This is the output of the random forest model. This is the output of the Long Short-Term Memory network.

[0013] Secondly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the aforementioned risk monitoring, early warning, hierarchical classification and control method based on the power distribution network supply chain.

[0014] Thirdly, this application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the aforementioned risk monitoring, early warning, hierarchical classification and control method based on the power distribution network supply chain.

[0015] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned risk monitoring, early warning, hierarchical classification and control method based on the power distribution network supply chain.

[0016] According to the specific embodiments provided in this application, this application has the following technical effects: This application provides a method, equipment, medium, and product for risk monitoring, early warning, hierarchical classification, and control of power distribution network supply chains. It determines the weights of each risk assessment indicator using the Analytic Hierarchy Process (AHP) based on a risk assessment indicator system. Furthermore, it constructs fuzzy sets and comment sets based on fuzzy comprehensive evaluation theory. Specifically, it transforms fuzzy qualitative descriptions (such as "low risk," "medium risk," and "high risk") into calculable quantitative data (e.g., a membership degree of 0.7 for an indicator to "high risk"), accurately capturing the fuzzy attributes of the evaluation object and avoiding evaluation bias caused by forced "precision," thus better meeting actual evaluation needs. It supports multi-factor and multi-dimensional comprehensive evaluation, balancing comprehensiveness and hierarchy. It can achieve multi-dimensional system analysis through hierarchical fuzzy evaluation. The hierarchical logic of this application covers all key influencing factors and clearly reflects the importance of each factor, avoiding the one-sidedness of single-factor evaluation. In addition, the weight allocation mechanism of the fuzzy comprehensive evaluation theory in this application is highly flexible. It can be combined with historical data and actual business needs, and supports optimization of weight calculation using tools such as the Analytic Hierarchy Process (AHP) and entropy weight method, ensuring the scientific and reasonable nature of the weights. This application presents a risk early warning system for the distribution network supply chain based on the coupling of LSTM and random forest. Through a standardized process of "LSTM time series prediction → feature fusion → random forest multi-factor coupling," it achieves complementary advantages between the two algorithms. This solves the challenge of trend prediction for long-term nonlinear risks and quantifies the risk intensity of multiple superimposed factors, filling a gap in existing technologies. This application can improve the accuracy of risk identification, enhance the real-time performance of risk early warning, optimize the precision of risk management, and reduce systemic risks in the distribution network supply chain. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of a risk monitoring, early warning, hierarchical classification and control method based on a power distribution network supply chain according to one embodiment of this application; Figure 2 This is a schematic diagram of the risk assessment indicator system structure. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] In one exemplary embodiment, such as Figure 1 As shown, a risk monitoring, early warning, and hierarchical classification management method based on the power distribution network supply chain is provided. This method includes the following steps S101 to S106. Wherein: S101, Construct a full-domain data acquisition network for the power distribution network supply chain; the full-domain data acquisition network is used to acquire risk-related data in real time; the risk-related data includes: supplier cooperation history data, credit data, operational stability data, raw material market data, production process data, logistics timeliness data, warehousing operation data, external environmental impact data, equipment operation and maintenance data, and market demand data. S101 specifically includes: (1) In the supply chain, IoT sensors are deployed in the supplier’s production plant to collect data on raw material inventory, production progress and quality inspection in real time; and the supplier management system is accessed through industrial Ethernet to automatically capture structured data such as the validity period of the supplier’s qualification certificate, historical performance records and financial credit rating. The sampling frequency is set to once per hour, and second-level collection is triggered in abnormal conditions. (2) In the production and manufacturing process, machine vision inspection devices and equipment status sensors are installed on the power distribution equipment production line to monitor the process parameters (temperature, pressure, time), equipment operating status (vibration frequency, current load) and finished product sampling data (power frequency withstand voltage value, partial discharge amount) of key processes in real time. After the data is collected by the production execution system, it is preprocessed through edge computing nodes, and abnormal data is uploaded to the cloud platform in real time. (3) In the logistics and transportation process, Beidou positioning terminals and temperature and humidity sensors are installed on the transport vehicles to collect the real-time location of the materials, driving trajectory, environmental parameters inside the carriage (0-40℃ temperature threshold and 30%-70% humidity threshold are set for precision equipment) and transportation status (such as whether there is severe bumping and the number of times the box is opened); Radio frequency identification reading and writing equipment is deployed at the transit hub to automatically record the loading and unloading time of materials and the information of the handover personnel. All data is pushed to the transportation management system in real time through the 5G network. The location information is updated once every 30 seconds and the status parameters are collected once every 5 minutes. (4) In the warehouse management process, infrared thermal imagers, temperature and humidity sensors, smoke alarms and intelligent shelf weighing devices are deployed in the warehouse area to monitor the inventory environment (temperature, humidity, open flame hazard) and the storage status of materials (such as stacking height and changes in inventory weight) in real time. The warehouse management system is connected to the inbound and outbound barcode scanning equipment to automatically collect the material inbound acceptance data (quantity, specifications, batch number) and outbound requisition records, so as to realize the real-time update of inventory data. Environmental parameters are collected once every 10 minutes, and inbound and outbound operations trigger immediate data recording.

[0022] S102, Based on the risk correlation data obtained from the full-domain data acquisition network, identify the potential risk factors in each link of the power distribution network supply chain and construct a risk factor database; S102 specifically includes: S21 involves standardizing risk-related data, transforming data from different dimensions into comparable indicators. Further, the transformed data undergoes "risk-oriented preprocessing" to filter out valid data related to "cost, delivery, quality, safety, and compliance," while eliminating irrelevant and distracting items. The frequency and percentage of various abnormal data in this stage are then statistically analyzed, and the causes of these abnormal data are attributed.

[0023] S22, Based on the standardized risk correlation data, identify the potential risk factors in each link of the power distribution network supply chain; S23, construct a risk factor database based on the potential risk factors in each link of the power distribution network supply chain.

[0024] S103, Establish a risk assessment indicator system based on a risk factor database; such as Figure 2As shown, the risk assessment indicator system includes: a target layer, a criterion layer, and an indicator layer; the target layer is a comprehensive quantitative assessment value of risk; the criterion layer includes: supply risk, production risk, logistics risk, and warehouse management risk; the indicator layer consists of quantified risk assessment indicators under the criterion layer. Specifically, the raw material delivery delay rate is calculated as "number of delayed delivery orders / total number of orders". The raw material sampling failure rate is calculated as "number of batches failing sampling / total number of batches sampled". The core supplier supply disruption warning days are determined by assessing supply risks through "supplier inventory, capacity, and performance records". The equipment mean time between failures (MTBF) is calculated as "continuous trouble-free operation time of equipment". The production cycle time achievement rate is recorded as the achievement rate of "actual cycle time / planned cycle time". The finished product first-pass yield rate is calculated as "number of first-pass qualified finished products / total number of finished products". The logistics and distribution delay rate is calculated as "number of delayed delivery orders / total number of delivery orders". The goods damage rate in transit is calculated as "number of damaged goods / total number of transported goods". The number of logistics chain interruption warnings is calculated as "historical number of interruptions + real-time road conditions / capacity warnings". The raw material delivery delay rate is calculated as "outbound quantity / average inventory". The raw material storage damage rate is calculated as "number of damaged storage items / total inventory quantity". The number of warehouse safety hazards is calculated as "number of problems identified in safety hazard investigations".

[0025] S104, Based on the risk assessment index system, the weight of each risk assessment index is determined by the analytic hierarchy process; and a fuzzy set and a comment set are constructed based on the fuzzy comprehensive assessment theory; the comment set includes multiple risk levels. S104 specifically includes: S41, Calculate the importance of risk assessment indicators at each criterion level. ; S42, using the formula Importance The weights of the i-th risk assessment indicator are obtained by weighting. n represents the number of risk assessment indicators.

[0026] S43, Importance After weighting each risk assessment indicator, a fuzzy set is established. Essentially, the importance of a higher-level risk is weighted and aggregated by the importance of lower-level indicators. That is, the overall importance of a risk factor at the criterion level is the weighted sum of the weights of all its subordinate assessment indicators multiplied by the "contribution" of each indicator to that risk. This is further illustrated using the weight transfer formula of the Analytic Hierarchy Process (AHP). Let... Let i represent the set of risk factors in the criteria layer of the distribution network supply chain, where i = 1, 2, ..., n, and n is the number of risk factors in the criteria layer. The number of; Let j = 1, 2, ..., m, where m is the set of risk assessment indicators in the indicator layer. The number of.

[0027] set up This represents a collection of comments, in which, The evaluation results are defined as follows, where k = 1, 2, ..., p, and p represents the number of risk levels. Risk levels are primarily categorized into five types: low risk, relatively low risk, medium risk, relatively high risk, and high risk. The evaluation results are derived from the supplier's historical cooperation data, credit data, operational stability data, raw material market data, production process data, logistics timeliness data, warehousing operation data, external environmental impact data, equipment maintenance data, market demand data, as well as historical economic losses caused by risks, the frequency of historical risks, and the importance of historical risks. The membership intervals corresponding to the risk levels are: (0, 0.2], (0.2, 0.4], (0.4, 0.6], (0.6, 0.8], and (0.8, 1).

[0028] S105. Based on the membership degree of the risk level corresponding to the risk assessment indicators, a fuzzy comprehensive evaluation matrix is ​​constructed; and based on the fuzzy comprehensive evaluation matrix, the overall risk assessment value of the power distribution network supply chain is determined. From the set arrive A fuzzy mapping f: ,beg Fuzzy comprehensive evaluation matrix Specifically: ; in, This indicates the impact of the i-th risk assessment indicator on the k-th level rating. The membership degree is defined as follows: k=1 represents the criterion layer, k=2 represents the indicator layer, m represents the m evaluation results, and p is the number of risk levels. , For the i-th risk assessment indicator, the k-level comments are... The quantitative value of the evaluation result, with a numerical range of (0,1).

[0029] S106. Based on the overall risk assessment value of the power distribution network supply chain, combined with real-time monitoring data and multi-dimensional prediction models, determine the corresponding early warning mechanism and issue early warnings; the multi-dimensional prediction models include: long short-term memory network and random forest model.

[0030] S106 specifically includes: S61, when the overall risk assessment value of the power distribution network supply chain exceeds the early warning threshold, early warning will be issued through multiple channels; S62 predicts the risk level based on real-time monitoring data and a multi-dimensional prediction model, and issues an early warning based on the predicted risk level.

[0031] As shown in S61 and S62, this application sets corresponding early warning mechanisms for risks of different evaluation levels, taking into account the actual operation and management requirements of the distribution network supply chain. First, a "threshold-triggered" early warning mechanism based on real-time data monitoring is established. This involves deploying sensing devices to collect key operational indicators from each link of the distribution network supply chain, setting industry / enterprise-level risk thresholds, and automatically triggering an early warning when an indicator exceeds the threshold, achieving a real-time "anomaly-based alarm" response. Simultaneously, a "proactive" early warning mechanism based on multi-dimensional model prediction is adopted. This mechanism uses mathematical models to quantitatively predict potential risks in the distribution network supply chain, rather than relying solely on real-time data thresholds. It can identify risk trends days to months in advance and is suitable for "slow-variable risks" (such as material shortages and cost fluctuations).

[0032] Among them, the "proactive" early warning mechanism based on multi-dimensional model prediction mainly uses Long Short-Term Memory (LSTM) networks to process long-period nonlinear time-series data, random forests to quantify the coupling effects of multiple factors, and constructs a collaborative logic between the two to achieve proactive identification of risks in the power distribution network supply chain. LTM networks address the vanishing gradient problem in long sequences of traditional recurrent neural networks through "input gates, forget gates, output gates" and "cell states." The core formula revolves around the "gating mechanism" and "cell state updates." The input gate determines how much new information is updated; its core formula is: ; ; In the formula, ∈[0,1] is used to control the weight of new information. ∈[-1,1] represents the candidate cell state, such as the predicted price trend increment. The forget gate determines how much historical data to retain, and its core formula is: ; In the formula: ∈[0,1], the closer the value is to 1, the more historical inventory / price data is retained; This represents the output at time t-1. The input at time t (e.g., the current price of raw materials). The output gate represents the output at the current time, and its core formula is: ; In the formula: It is the LSTM output at time t. By controlling the output weights, the tanh function compresses the output to [-1, 1], which can then be mapped to actual physical quantities. Cellular states are the core memory units, and their core formula is: ; In the above formula, It is the activation function (outputs 0-1, simulating a "gated switch"), tanh is the hyperbolic tangent function, controlling the numerical range), and ⊙ is element-wise multiplication. / / / It is a weight matrix. / / / It is the bias vector.

[0033] The early warning process based on multi-dimensional model prediction is as follows: A feature fusion matrix is ​​constructed to integrate LSTM predictions with static / quasi-static class factors into random forest input features. Qualitative factors are quantified using the rank mapping method, and a feature fusion matrix X is constructed. The row dimension of the matrix is ​​the number of samples (one sample corresponds to one decision tree), and the column dimension is "the number of time-series risk predictions + the number of static / quasi-static class factors". ; In the formula: Let m be the predicted time-series risks output by the LSTM. These are k quantized static / quasi-static class factors. Total output of the random forest: (M represents the number of decision trees, and the average score of all trees is taken to reflect the risk of multi-factor association; y) k This typically represents the target value at time k in a time-series prediction task. LSTM, as a time-series modeling system, directly generates y in its output layer when used for time-series prediction. k (Estimated value). Formula for the final risk level after coupling: ; In the formula, the time series risk weight is: (In distribution network scenarios) Take a value of 0.4-0.5 (because time series trends are equally important as multiple factors), and the risk weight of multiple factors is... .

[0034] When a risk assessment value reaches or exceeds the warning threshold, a multi-channel warning release mechanism automatically sends warning information to relevant managers and responsible departments through automated system warnings and manual-assisted warnings. Automated system warnings integrate with Internet of Things (IoT) terminals (such as supply chain monitoring dashboards, mobile apps, and industrial tablets) to display the risk status in real time through audio-visual alerts, push notifications, and five-color (red / orange / yellow / green / blue) warning indicators on large screens. The warning information includes detailed information such as the risk level, category, location, potential impact range, and recommended initial response measures, enabling relevant personnel to quickly understand the risk situation and respond appropriately.

[0035] This application achieves complementary advantages of two types of algorithms through a standardized process of "LSTM time series prediction → feature fusion → random forest multi-factor coupling". It not only solves the problem of trend prediction of long-term nonlinear risks, but also quantifies the risk intensity of multiple factors superimposed, filling the gap in existing technology. LSTM retains long-term data features through a gating mechanism, with a prediction error MSE ≤ 0.05. Random forest, through the integration of multiple decision trees and the information gain splitting criterion, achieves a risk level prediction accuracy of ≥ 92%, which is significantly better than a single algorithm. By analyzing the importance of features output by random forest, the core driving factors of risks can be located, providing the distribution network supply chain management department with a basis for "precise response" (such as initiating price-locked procurement in response to price increase risks, and transferring production capacity in response to policy-related production restrictions), avoiding blind control.

[0036] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a risk monitoring, early warning, hierarchical classification, and control method based on a power distribution network supply chain.

[0037] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0038] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0039] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0040] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0041] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0042] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0043] In this application, all actions to acquire signals, information, or data are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with the authorization granted by the owner of the relevant device.

[0044] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0045] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A risk monitoring, early warning, hierarchical classification, and control method based on power distribution network supply chain, characterized in that, The risk monitoring, early warning, hierarchical and classified management method based on the power distribution network supply chain includes: Construct a full-domain data acquisition network for the power distribution network supply chain; the full-domain data acquisition network is used to acquire risk-related data in real time; the risk-related data includes: supplier cooperation history data, credit data, operational stability data, raw material market data, production process data, logistics timeliness data, warehousing operation data, external environmental impact data, equipment operation and maintenance data, and market demand data; Based on the risk correlation data obtained from the full-domain data acquisition network, potential risk factors in each link of the power distribution network supply chain are identified, and a risk factor database is constructed. A risk assessment indicator system is established based on a risk factor database. The risk assessment indicator system includes: a target layer, a criterion layer, and an indicator layer. The target layer is a comprehensive quantitative assessment value of risk. The criterion layer includes: supply risk, production risk, logistics risk, and warehouse management risk. The indicator layer consists of quantified risk assessment indicators under the criterion layer. Based on the risk assessment index system, the weight of each risk assessment index is determined by the analytic hierarchy process (AHP); and a fuzzy set and a comment set are constructed based on the fuzzy comprehensive assessment theory; the comment set includes multiple risk levels. Based on the membership degree of the risk level corresponding to the risk assessment indicators, a fuzzy comprehensive evaluation matrix is ​​constructed; and based on the fuzzy comprehensive evaluation matrix, the overall risk assessment value of the power distribution network supply chain is determined. Based on the overall risk assessment value of the power distribution network supply chain, combined with real-time monitoring data and multi-dimensional prediction models, a corresponding early warning mechanism is determined and an early warning is issued; the multi-dimensional prediction models include: Long Short-Term Memory Network and Random Forest Model.

2. The risk monitoring, early warning, hierarchical classification and control method based on the power distribution network supply chain according to claim 1, characterized in that, The aforementioned comprehensive data collection network for constructing the power distribution network supply chain specifically includes: Deploy IoT sensors in the supplier's production facility and connect them to the supplier management system via industrial Ethernet; Install machine vision inspection devices and equipment status sensors on the power distribution equipment production line; The transport vehicles are equipped with BeiDou positioning terminals and temperature and humidity sensors; radio frequency identification reading and writing equipment is deployed at transit hubs; and the vehicles are connected to the transport management system via a 5G network. Infrared thermal imagers, temperature and humidity sensors, smoke detectors, and intelligent shelf weighing devices are deployed in the warehouse area; and the warehouse management system is connected to the inbound and outbound barcode scanning equipment.

3. The risk monitoring, early warning, hierarchical classification and control method based on the power distribution network supply chain according to claim 1, characterized in that, The risk correlation data obtained based on the full-domain data acquisition network is used to determine the potential risk factors in each link of the power distribution network supply chain and to construct a risk factor database, specifically including: Standardize the processing of risk-related data; Based on the standardized risk correlation data, potential risk factors in each link of the power distribution network supply chain are identified. A risk factor database is constructed based on the potential risk factors in each link of the power distribution network supply chain.

4. The risk monitoring, early warning, hierarchical classification and control method based on the power distribution network supply chain according to claim 1, characterized in that, The risk assessment indicator system is based on an analytic hierarchy process (AHP) method to determine the weights of each risk assessment indicator, specifically including: Using formula Determine the weight of the i-th risk assessment indicator ; in, Let represent the importance of the i-th risk assessment indicator, and n be the number of risk assessment indicators.

5. The risk monitoring, early warning, hierarchical classification and control method based on the power distribution network supply chain according to claim 1, characterized in that, The step of constructing a fuzzy comprehensive evaluation matrix based on the membership degree of the risk level corresponding to the risk assessment indicators specifically includes: Using formula Determine the fuzzy comprehensive evaluation matrix ; in, This indicates the impact of the i-th risk assessment indicator on the k-th level rating. The membership degree is defined as follows: k=1 represents the criterion layer, k=2 represents the indicator layer, m represents the m evaluation results, and p is the number of risk levels. , For the i-th risk assessment indicator, the k-level comments are... The quantitative value of the evaluation results.

6. The risk monitoring, early warning, hierarchical classification and control method based on the power distribution network supply chain according to claim 1, characterized in that, Based on the overall risk assessment value of the power distribution network supply chain, combined with real-time monitoring data and multi-dimensional prediction models, a corresponding early warning mechanism is determined and issued, specifically including: When the overall risk assessment value of the power distribution network supply chain exceeds the warning threshold, a multi-channel warning will be issued; Based on real-time monitoring data and multi-dimensional prediction models, the risk level is predicted; and warnings are issued based on the predicted risk level.

7. The risk monitoring, early warning, hierarchical classification and control method based on the power distribution network supply chain according to claim 6, characterized in that, The risk level is predicted based on real-time monitoring data and a multi-dimensional prediction model. And issue early warnings based on the predicted risk level, specifically including: Using formula Determine the risk level ; in, For time-series risk weights, For multi-factor risk weighting, , This is the output of the random forest model. This is the output of the Long Short-Term Memory network.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the risk monitoring, early warning, hierarchical classification and control method based on the power distribution network supply chain as described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the risk monitoring, early warning, hierarchical classification and control method based on the power distribution network supply chain as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the risk monitoring, early warning, hierarchical classification and control method based on the power distribution network supply chain as described in any one of claims 1-7.

Images