Purchase efficiency optimization management method and system based on artificial intelligence

Abstract

The invention discloses a purchase efficiency optimization management method and system based on artificial intelligence. The method comprises the steps of data sub-item collection, data preprocessing, supply chain relation modeling, purchase strategy optimization and purchase efficiency optimization. The invention relates to the technical field of power fuel purchase management, in particular to a purchase efficiency optimization management method and system based on artificial intelligence, and adopts a comprehensive intelligent method combining cross-domain data fusion with supply chain modeling and purchase strategy optimization to realize real-time and dynamically optimized purchase efficiency optimization and management. A dynamic heterogeneous improved graph neural network method is adopted to carry out supply chain relation modeling, so that the state updating of the supply chain and the quantitative calculation of risk conduction are optimized, and the intelligent dimension of purchasing efficiency management is improved; and purchasing strategy optimization is carried out by adopting a multi-objective reward improved multi-layer strategy reinforcement learning method.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power fuel procurement management, and specifically to an artificial intelligence-based procurement efficiency optimization management method and system. Background Art

[0002] The AI-based procurement efficiency optimization management method refers to the use of AI technologies such as machine learning and deep learning to intelligently analyze, model and make decisions on the entire procurement process data in order to achieve a modern management method of reducing procurement costs, improving supply stability and automating processes. Its core function is to automatically identify procurement rules, predict market changes, optimize supplier selection and procurement strategies through intelligent algorithms, thereby significantly improving the accuracy and timeliness of procurement decisions, reducing the impact of human factors, and being able to dynamically adapt to market fluctuations and supply chain risks. In key areas such as the power industry, this method can also effectively balance multiple goals such as economy, reliability and environmental protection, creating significant cost reduction and efficiency improvement value for enterprises. Compared with traditional methods, AI-driven procurement optimization has outstanding advantages such as real-time response, continuous learning and multi-objective collaboration, and has become an important direction for the digital transformation of corporate supply chains.

[0003] However, in the existing procurement efficiency optimization management methods, there is a problem that the existing power industry fuel procurement mostly adopts a static evaluation system, and the static system is inevitably out of touch with the dynamic market, which leads to decision lags and lacks effective application in extreme scenarios. Therefore, the traditional method relies on fixed-cycle evaluation and cannot adapt to the sharp fluctuations in fuel prices in the power industry. At the same time, production data and supply chain data are separated, emergency procurement delays are long, and manual simulation tests are difficult to cover complex risk scenarios. Technical problems; in the existing supply chain relationship modeling methods, there are existing supplier evaluations, which are mainly based on historical transaction data, but the relevant data of the real-time coal consumption rate changes of the units are not reflected in the traditional methods. At the same time, the traditional graph model cannot quantify the impact of risk events on procurement demand, and the physical relationship between coal quality and power generation efficiency is difficult to represent. Technical problems; in the existing procurement strategy optimization methods, there is the traditional reinforcement learning procurement strategy optimization, which fails to make a comprehensive decision analysis for complex procurement processes and various procurement risks, carbon emission indicators and market fluctuations, which leads to the technical problem that the existing methods are difficult to combine the results of supply chain relationship modeling for multi-directional comprehensive procurement decisions. Summary of the invention

[0004] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a procurement efficiency optimization management method and system based on artificial intelligence. In the existing procurement efficiency optimization management method, the existing power industry fuel procurement mostly adopts a static evaluation system, and the static system is inevitably easily out of touch with the dynamic market, which leads to decision-making lags and lacks effective application in extreme scenarios. Therefore, the traditional method relies on fixed-cycle evaluation and cannot adapt to the drastic fluctuations in fuel prices in the power industry. At the same time, production data and supply chain data are separated, emergency procurement delays are long, and manual simulation tests are difficult to cover technical problems in complex risk scenarios. This solution creatively adopts a comprehensive intelligent method of cross-domain data fusion combined with supply chain modeling and procurement strategy optimization to achieve real-time dynamic optimization of procurement efficiency optimization and management; in the existing supply chain relationship modeling method, there is an existing supplier evaluation, which is mainly based on historical transaction data, but the relevant data of the real-time coal consumption rate changes of the unit is not reflected in the traditional method. At the same time, the traditional graph The model cannot quantify the impact of risk events on procurement demand, and the physical relationship between coal quality and power generation efficiency is difficult to characterize. This solution creatively adopts a dynamic heterogeneous improved graph neural network method to model supply chain relationships, optimizes the supply chain state update and the quantitative calculation of risk transmission, and improves the intelligent dimension of procurement efficiency management. In the existing procurement strategy optimization methods, there is a traditional reinforcement learning procurement strategy optimization, which fails to make a comprehensive decision analysis for the complex procurement process and various procurement risks, carbon emission indicators and market fluctuations, which leads to the technical problem that the existing methods are difficult to combine the results of supply chain relationship modeling for multi-directional comprehensive procurement decisions. This solution creatively adopts a multi-layer strategy reinforcement learning method with multi-objective reward improvement to optimize the procurement strategy. By combining state parameter improvement, reward improvement and disturbance control improvement, a multi-layer reinforcement learning basic model is built, which improves the analysis efficiency of the procurement strategy and the overall usability and intelligence of procurement efficiency management.

[0005] The technical solution adopted by the present invention is as follows: The procurement efficiency optimization management method based on artificial intelligence provided by the present invention comprises the following steps:

[0006] Step S1: data collection by item;

[0007] Step S2: data preprocessing;

[0008] Step S3: Supply chain relationship modeling;

[0009] Step S4: Procurement strategy optimization;

[0010] Step S5: Optimize procurement efficiency.

[0011] Furthermore, in step S1, the data is collected by item, and is used to collect the original data set required for optimizing procurement efficiency, specifically, by collecting classified data to obtain the original data for optimizing procurement efficiency management;

[0012] The classified data collection includes production data collection, supply chain data collection and market data collection;

[0013] The procurement efficiency optimization manages raw data, including production data, supply chain data and market data.

[0014] Further, in step S2, the data preprocessing is used to preprocess the original data, specifically, according to the procurement efficiency optimization management of the original data, through data enhancement and conversion, data preprocessing is performed to obtain procurement efficiency optimization data, including the following steps:

[0015] Step S21: original data mapping, specifically, performing data mapping on the data in the procurement efficiency optimization management original data to obtain classified mapping data; the classified mapping data includes production mapping data, supply chain mapping data and market mapping data;

[0016] Step S22: preprocessing the production data, specifically, performing feature enhancement processing on the production mapping data, performing feature enhancement on the load rate and coal consumption rate data in the production mapping data through a sliding window feature enhancement operation, obtaining load efficiency features and coal consumption trend features, and obtaining fault risk score features by performing fault frequency statistics on the fault event feature data;

[0017] Step S23: preprocessing the supply chain data, specifically, performing feature enhancement processing on the supply chain mapping data, constructing supplier quality fluctuation characteristics by reconstructing the time series structure of the coal calorific value detection information in the basic characteristics of the supplier, and obtaining the default probability distribution characteristics by calculating the default probability of the supplier's historical default record information in the basic characteristics of the supplier, and obtaining the supply transportation efficiency characteristics by calculating the transportation efficiency of the supply coal transportation sensor information in the basic characteristics of the supplier;

[0018] Step S24: market data preprocessing, specifically, performing feature enhancement processing on the market mapping data, obtaining coal price trend features by performing trend decomposition and volatility calculation on the futures price data, and performing linear regression calculation on the carbon price data to obtain a carbon price weight factor, and using the carbon price weight factor as a carbon price feature;

[0019] Step S25: feature fusion, specifically, obtaining enhanced feature data through the production data preprocessing, the supply chain data preprocessing and the market data preprocessing, and obtaining procurement efficiency optimization data by sequentially performing missing value filling, outlier processing, timestamp synchronization, high-dimensional feature compression and feature labeling;

[0020] The procurement efficiency optimization data includes optimizing load efficiency characteristics, optimizing coal consumption trend characteristics, optimizing fault risk score characteristics, optimizing supplier quality fluctuation characteristics, optimizing default probability distribution characteristics, optimizing supply and transportation efficiency characteristics, optimizing coal price trend characteristics and optimizing carbon price characteristics.

[0021] Further, in step S3, the supply chain relationship modeling is used to perform digital modeling analysis and risk assessment on the supply chain relationship of the materials to be purchased, specifically, based on the procurement efficiency optimization data, a dynamic heterogeneous improved graph neural network method is used to perform supply chain relationship modeling to obtain supply chain relationship analysis reference data, including the following steps:

[0022] Step S31: constructing a heterogeneous graph of a supply chain, specifically constructing a heterogeneous graph of a procurement supply chain according to the procurement efficiency optimization data, and obtaining heterogeneous graph data of the supply chain by defining node types, node attributes and edge types;

[0023] The node types include supplier nodes, material nodes and logistics nodes;

[0024] The node attributes include production capacity attributes, supplier credit rating attributes, coal inventory attributes, logistics node throughput capacity attributes, and transportation delay rate attributes;

[0025] The edge types include supply relationship edges, logistics path edges and risk transmission edges;

[0026] The supply relationship edge is specifically established based on the historical transaction frequency; the logistics path edge is specifically established based on the actual transportation path and real-time transportation capacity; the risk transmission edge is specifically used to simulate the risk cascading effect between nodes, including default and delay effects;

[0027] Step S32: Dynamic evolution reconstruction of the graph structure, specifically building a dynamic evolution mechanism to reconstruct the graph structure, specifically updating the node status once an hour and reconstructing the graph structure topology once a day to reflect the real-time changes in entity status and the impact and changes of supply relationships;

[0028] Step S33: hierarchical attention improvement, specifically, constructing a three-layer hierarchical attention mechanism, including a cross-modal feature fusion attention layer, a spatiotemporal attention layer, and a risk transmission attention layer, to extract graph information, and through the risk transmission attention layer, to model the risk cascade transmission of the procurement process, and calculate the risk transmission probability reference data;

[0029] The cross-modal feature fusion attention layer is used to integrate node data and edge data, and to obtain the associative attention weight by constructing a standard long short-term memory neural network to process the time series node features;

[0030] The spatiotemporal attention layer is used to introduce a time window attention weight function to analyze the timing characteristics of the supply chain, and obtain the spatiotemporal attention weight through weighted calculation;

[0031] The risk transmission attention layer is used to calculate the risk transmission probability by integrating the relevance attention weight and the spatiotemporal attention weight to obtain the risk transmission probability reference data. The calculation formula is:

[0032] ;

[0033] Where P risk is the reference data of risk propagation probability, is the risk source node, is the transmission target node, sig(·) is the S-type activation function, K is the total number of intermediate nodes, k is the intermediate node index, which is used to represent the intermediate nodes between the risk source node and the transmission target node. is the associative attention weight between the risk source node and the kth intermediate node, is the spatiotemporal attention weight between the kth intermediate node and the target node, t is the time index, is the disturbance influence function, and the standard Gaussian function is used to simulate the disturbance influence. It is the material quality deviation reference value;

[0034] Step S34: risk propagation modeling, specifically, performing supply chain node risk simulation modeling based on the risk propagation probability reference data and the supply chain heterogeneous graph data to obtain procurement risk modeling reference data;

[0035] Step S35: coal quality decomposition modeling, specifically, performing coal quality decomposition modeling according to the coal consumption trend characteristics and load efficiency characteristics in the procurement efficiency optimization data, and constructing coal quality three-dimensional tensor modeling data and coal quality optimization reference data;

[0036] Step S36: supply chain relationship modeling, specifically, supply chain relationship modeling is performed through the supply chain heterogeneous graph construction, the graph structure dynamic evolution reconstruction, the hierarchical attention improvement, the risk propagation modeling and the coal quality decomposition modeling to obtain supply chain relationship analysis reference data;

[0037] The supply chain relationship analysis reference data includes a supplier procurement risk assessment tensor, a supplier risk transmission probability matrix, and a supplier comprehensive assessment value;

[0038] The supplier procurement risk assessment tensor includes credit risk assessment, delivery risk assessment, combustion quality risk assessment, price assessment and emergency procurement quality assessment.

[0039] Further, in step S4, the procurement strategy optimization is used to calculate the optimal procurement strategy, specifically, based on the supply chain relationship analysis reference data and the procurement efficiency optimization data, a multi-layer strategy reinforcement learning method improved by multi-objective rewards is used to optimize the procurement strategy to obtain the procurement optimal strategy reference data, including the following steps:

[0040] Step S41: improving the state parameter space, specifically constructing a state parameter space for reinforcement learning and improving the system state vector to obtain improved state parameter space data, including coal inventory status, unit operation status, and carbon emission quota balance status;

[0041] Step S42: multi-layer strategy network modeling, specifically constructing a meta-strategy layer, a procurement dynamic optimization layer, and an intelligent allocation execution layer in sequence, and performing multi-layer strategy reinforcement learning through the multi-layer strategy network modeling to obtain an initial procurement strategy;

[0042] The meta-strategy layer is used to process the formulation of annual framework agreements and optimize long-term resource allocation, and specifically adopts a meta-strategy generator based on a transformer structure to generate meta-procurement strategies;

[0043] The procurement dynamic optimization layer is used to control the dynamic optimization of the monthly procurement rhythm and supply structure, and specifically adopts a double-delayed deep deterministic policy gradient algorithm for optimization calculation;

[0044] The intelligent allocation execution layer is used to intelligently allocate daily or real-time orders and balance procurement costs and inventory pressure;

[0045] Step S43: Improvement of the multi-objective reward function, specifically, by introducing procurement cost, delivery deviation, emission index and emergency procurement indicator function, the multi-objective reward function is improved to obtain an improved multi-objective reward function, and the calculation formula is:

[0046] ;

[0047] In the formula, R t is an improved multi-objective reward function, is the purchase cost weight, C t is the purchase cost value, C max is the maximum purchase budget value, is the delivery bias weight, is the delivery deviation time, is the mean delivery deviation, is the emission index weight, m ​​is the emission element index, including sulfur dioxide emission, nitrogen oxide emission and dust emission, E m is the emission index parameter, is the maximum emission limit, is the emergency purchase instruction weight, is the emergency purchase indicator function value, which is used to indicate whether it is an emergency purchase;

[0048] Step S44: disturbance injection improvement, specifically, by introducing a disturbance factor control function, disturbance injection improvement is performed to obtain a disturbance injection function, the calculation formula of which is:

[0049] ;

[0050] Where roll(·) is the disturbance injection function, t is the time index, and g is the disturbance control parameter, which is used to control the degree of disturbance injection. By controlling the value of the disturbance injection function, disturbance simulation is performed, including market price fluctuation disturbance, transportation congestion disturbance, and supply chain disruption disturbance.

[0051] The specific calculation formula of the market price fluctuation disturbance is: ,in, is the historical statistical parameter of market volatility; the specific calculation formula of the transportation congestion disturbance is: ; The specific calculation formula for the supply chain disruption disturbance is: ,in, is the Bernoulli distribution function;

[0052] Step S45: Procurement strategy optimization, specifically, performing phased optimization of procurement strategy optimization through the state parameter space improvement, the multi-layer strategy network modeling, the multi-objective reward function improvement and the disturbance injection improvement, to obtain the optimal procurement strategy reference data;

[0053] The optimal procurement strategy reference data includes a multi-objective procurement strategy vector, a strategy enhancement reference function, and an emergency procurement plan reference data;

[0054] The phased optimization includes an initial stabilization phase, a disturbance introduction phase, and a multi-objective optimization phase;

[0055] The initial stabilization stage is specifically to optimize the standard reinforcement learning procurement strategy based on the state parameter space improvement and multi-layer strategy network modeling to obtain an initial procurement plan;

[0056] The disturbance introduction stage is specifically to introduce price fluctuations, transportation congestion and supply interruption simulations based on the disturbance injection improvement on the basis of the initial procurement plan, and optimize the procurement strategy for disturbance introduction improvement to obtain an anti-disturbance procurement plan;

[0057] The multi-objective optimization stage is specifically to optimize the procurement strategy of multi-objective optimization based on the anti-disturbance procurement plan and the multi-objective reward function, so as to obtain the reference data of the optimal procurement strategy.

[0058] Further, in step S5, the procurement efficiency optimization is used to construct an intelligent evaluation method to verify the optimization of procurement strategy and improve procurement efficiency. Specifically, based on the optimal procurement strategy reference data, a multi-dimensional procurement strategy evaluation index is constructed and a procurement strategy effect evaluation is performed. By selecting the procurement strategy with the best evaluation effect, procurement efficiency is optimized to obtain a comprehensive optimization reference plan for procurement efficiency.

[0059] The multi-dimensional procurement strategy evaluation indicators include economic indicators, reliability indicators, environmental indicators and agility indicators;

[0060] The economic index specifically refers to the deviation rate between actual cost and budgeted cost; the reliability index specifically refers to the frequency of emergency procurement; the environmental index specifically refers to the utilization rate of emission quotas; the agility index specifically refers to the time consumption of procurement strategy response.

[0061] The artificial intelligence-based procurement efficiency optimization management system provided by the present invention includes a data source processing module, a supply relationship modeling module, a procurement strategy optimization module and a comprehensive efficiency optimization module;

[0062] The data source processing module is used for data item collection and data preprocessing, and obtains procurement efficiency optimization data through data item collection and data preprocessing, and sends the procurement efficiency optimization data to the supply relationship modeling module and the procurement strategy optimization module;

[0063] The supply relationship modeling module is used for supply chain relationship modeling, obtains supply chain relationship analysis reference data through supply chain relationship modeling, and sends the supply chain relationship analysis reference data to the procurement strategy optimization module;

[0064] The procurement strategy optimization module is used for procurement strategy optimization, obtains procurement optimal strategy reference data through procurement strategy optimization, and sends the procurement optimal strategy reference data to the comprehensive efficiency optimization module;

[0065] The comprehensive efficiency optimization module is used for optimizing procurement efficiency, and through optimizing procurement efficiency, a comprehensive optimization reference plan for procurement efficiency is obtained.

[0066] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0067] (1) In view of the existing procurement efficiency optimization management methods, the existing power industry fuel procurement mostly adopts a static evaluation system, which is inevitably out of touch with the dynamic market, resulting in decision-making lags and lack of effective application in extreme scenarios. Therefore, the traditional method relies on fixed-cycle evaluation and cannot adapt to the sharp fluctuations in fuel prices in the power industry. At the same time, production data and supply chain data are separated, emergency procurement delays are long, and manual simulation tests are difficult to cover complex risk scenarios. Technical problems, this solution creatively adopts a comprehensive intelligent method of cross-domain data fusion combined with supply chain modeling and procurement strategy optimization to achieve real-time dynamic optimization of procurement efficiency optimization and management;

[0068] (2) In the existing supply chain relationship modeling methods, there are existing supplier evaluations that are mainly based on historical transaction data, but the relevant data on the real-time coal consumption rate changes of the units are not reflected in the traditional methods. At the same time, the traditional graph model cannot quantify the impact of risk events on procurement demand, and the physical relationship between coal quality and power generation efficiency is difficult to characterize. This solution creatively adopts a dynamic heterogeneous improved graph neural network method to model the supply chain relationship, optimizes the supply chain status update and the quantitative calculation of risk transmission, and improves the intelligent dimension of procurement efficiency management;

[0069] (3) In the existing procurement strategy optimization methods, there is a problem that the traditional reinforcement learning procurement strategy optimization fails to make comprehensive decision analysis for complex procurement processes and various procurement risks, carbon emission indicators and market fluctuations, which leads to the technical problem that the existing methods are difficult to combine the results of supply chain relationship modeling to make multi-directional comprehensive procurement decisions. This scheme creatively adopts a multi-layer strategy reinforcement learning method with multi-objective reward improvement to optimize the procurement strategy. By combining state parameter improvement, reward improvement and disturbance control improvement, a multi-layer reinforcement learning basic model is built, which improves the analysis efficiency of the procurement strategy and also improves the overall usability and intelligence of procurement efficiency management. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 A flow chart of the artificial intelligence-based procurement efficiency optimization management method provided by the present invention;

[0071] Figure 2 A schematic diagram of the artificial intelligence-based procurement efficiency optimization management system provided by the present invention;

[0072] Figure 3 This is a schematic diagram of the process of data preprocessing in step S2;

[0073] Figure 4 Schematic diagram of the process of modeling the supply chain relationship in step S3;

[0074] Figure 5 Schematic diagram of the process of optimizing the procurement strategy in step S4.

[0075] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0076] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0077] In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0078] Example 1, see Figure 1 The present invention provides a procurement efficiency optimization management method based on artificial intelligence, which includes the following steps:

[0079] Step S1: data collection by item;

[0080] Step S2: data preprocessing;

[0081] Step S3: Supply chain relationship modeling;

[0082] Step S4: Procurement strategy optimization;

[0083] Step S5: Optimize procurement efficiency.

[0084] By performing the above operations, in the existing procurement efficiency optimization management methods, there is a problem that the existing power industry fuel procurement mostly adopts a static evaluation system, and the static system is inevitably easily out of touch with the dynamic market, which leads to decision-making lags and lacks effective application in extreme scenarios. Therefore, the traditional method relies on fixed-cycle evaluation and cannot adapt to the sharp fluctuations in fuel prices in the power industry. At the same time, production data and supply chain data are separated, emergency procurement delays are long, and manual simulation tests are difficult to cover technical problems in complex risk scenarios. This solution creatively adopts a comprehensive intelligent method of cross-domain data fusion combined with supply chain modeling and procurement strategy optimization to achieve real-time dynamic optimization of procurement efficiency optimization and management.

[0085] Example 2, see Figure 1 and Figure 2 In step S1, the data is collected item by item to collect the original data set required for optimizing procurement efficiency, specifically, by collecting classified data to obtain the original data for optimizing procurement efficiency management;

[0086] The classified data collection includes production data collection, supply chain data collection and market data collection;

[0087] The production data collection includes unit load rate collection, coal consumption rate collection and equipment fault log collection;

[0088] The supply chain data collection includes coal inventory collection, spare parts supplier basic information collection and transportation scheduling data collection;

[0089] The basic information collection of the spare parts supplier includes the collection of coal calorific value test reports, the collection of supplier's historical breach records and the collection of coal supply and transportation sensor data;

[0090] The market data collection includes thermal coal futures price collection and carbon emission rights trading data collection;

[0091] The procurement efficiency optimization management raw data includes production data, supply chain data and market data;

[0092] The production data is collected at a frequency of minutes, including time series data and event log data;

[0093] The supply chain data is collected at an hourly frequency and includes supplier information text, structured tables, and transportation geographic information;

[0094] The market data is collected at a daily frequency, including multivariate time series data.

[0095] Example 3, see Figure 1 , Figure 2 and Figure 3This embodiment is based on the above embodiment. In step S2, the data preprocessing is used to preprocess the original data. Specifically, the original data is managed according to the procurement efficiency optimization, and the data is preprocessed through data enhancement and conversion to obtain procurement efficiency optimization data, including the following steps:

[0096] Step S21: original data mapping, specifically, performing data mapping on the data in the procurement efficiency optimization management original data to obtain classified mapping data; the classified mapping data includes production mapping data, supply chain mapping data and market mapping data;

[0097] The production mapping data includes load rate, coal consumption rate, and fault event characteristic data; the fault event characteristic data includes timestamp, equipment number, and fault type;

[0098] The supply chain mapping data includes inventory volume, supply transportation track and basic characteristics of suppliers;

[0099] The basic characteristics of the supplier include coal calorific value detection information, supplier historical breach record information and coal supply sensor information;

[0100] The market mapping data includes futures price data and carbon price data;

[0101] Step S22: preprocessing the production data, specifically, performing feature enhancement processing on the production mapping data, performing feature enhancement on the load rate and coal consumption rate data in the production mapping data through a sliding window feature enhancement operation, obtaining load efficiency features and coal consumption trend features, and obtaining fault risk score features by performing fault frequency statistics on the fault event feature data;

[0102] Step S23: preprocessing the supply chain data, specifically, performing feature enhancement processing on the supply chain mapping data, constructing supplier quality fluctuation characteristics by reconstructing the time series structure of the coal calorific value detection information in the basic characteristics of the supplier, and obtaining the default probability distribution characteristics by calculating the default probability of the supplier's historical default record information in the basic characteristics of the supplier, and obtaining the supply transportation efficiency characteristics by calculating the transportation efficiency of the supply coal transportation sensor information in the basic characteristics of the supplier;

[0103] The supplier's quality fluctuation characteristics, including the calorific value, sulfur content and ash content of the coal;

[0104] The supply transportation efficiency characteristic is specifically calculated by dividing the actual transportation volume by the actual transportation capacity;

[0105] Step S24: market data preprocessing, specifically, performing feature enhancement processing on the market mapping data, obtaining coal price trend features by performing trend decomposition and volatility calculation on the futures price data, and performing linear regression calculation on the carbon price data to obtain a carbon price weight factor, and using the carbon price weight factor as a carbon price feature;

[0106] Step S25: feature fusion, specifically, obtaining enhanced feature data through the production data preprocessing, the supply chain data preprocessing and the market data preprocessing, and obtaining procurement efficiency optimization data by sequentially performing missing value filling, outlier processing, timestamp synchronization, high-dimensional feature compression and feature labeling;

[0107] The procurement efficiency optimization data includes optimizing load efficiency characteristics, optimizing coal consumption trend characteristics, optimizing fault risk score characteristics, optimizing supplier quality fluctuation characteristics, optimizing default probability distribution characteristics, optimizing supply and transportation efficiency characteristics, optimizing coal price trend characteristics and optimizing carbon price characteristics, and the calculation formula is:

[0108] ;

[0109] In the formula, X is the purchasing efficiency optimization data, e load is the optimized load efficiency characteristic, y coal is the optimization of coal consumption trend characteristics, p fault is the fault risk scoring feature, Q t is to optimize the supplier quality fluctuation characteristics, P de is the optimized default probability distribution characteristic, n tr is the characteristic of optimizing supply and transportation efficiency, S coal is to optimize the coal price trend characteristics, C car It is to optimize the carbon price characteristics.

[0110] Example 4, see Figure 1 , Figure 2 and Figure 4 This embodiment is based on the above embodiment. In step S3, the supply chain relationship modeling is used to perform digital modeling analysis and risk assessment on the supply chain relationship of the materials to be purchased. Specifically, based on the procurement efficiency optimization data, a dynamic heterogeneous improved graph neural network method is used to perform supply chain relationship modeling to obtain supply chain relationship analysis reference data, including the following steps:

[0111] Step S31: constructing a heterogeneous graph of the supply chain, specifically constructing a heterogeneous graph of the procurement supply chain based on the procurement efficiency optimization data, and obtaining heterogeneous graph data of the supply chain by defining node types, node attributes and edge types. The calculation formula is:

[0112] ;

[0113] In the formula, G t is the heterogeneous graph data of the supply chain, V t is a node set used to represent coal suppliers, spare parts manufacturers and coal hub locations. t is an edge set used to represent the supply, transportation, and procurement relationships. t is the coal carbon price trend vector, used to represent the coal price trend and carbon price weight;

[0114] The node types include supplier nodes, material nodes and logistics nodes;

[0115] The node attributes include production capacity attributes, supplier credit rating attributes, coal inventory attributes, logistics node throughput capacity attributes, and transportation delay rate attributes;

[0116] The edge types include supply relationship edges, logistics path edges and risk transmission edges;

[0117] The supply relationship edge is specifically established based on the historical transaction frequency; the logistics path edge is specifically established based on the actual transportation path and real-time transportation capacity; the risk transmission edge is specifically used to simulate the risk cascading effect between nodes, including default and delay effects;

[0118] Step S32: Dynamic evolution reconstruction of the graph structure, specifically building a dynamic evolution mechanism to reconstruct the graph structure, specifically updating the node status once an hour and reconstructing the graph structure topology once a day to reflect the real-time changes in entity status and the impact and changes of supply relationships;

[0119] Step S33: hierarchical attention improvement, specifically, constructing a three-layer hierarchical attention mechanism, including a cross-modal feature fusion attention layer, a spatiotemporal attention layer, and a risk transmission attention layer, to extract graph information, and through the risk transmission attention layer, to model the risk cascade transmission of the procurement process, and calculate the risk transmission probability reference data;

[0120] The cross-modal feature fusion attention layer is used to integrate node data and edge data, and to construct a standard long short-term memory neural network to process the time series node features and obtain the associative attention weight. The calculation formula is:

[0121] ;

[0122] In the formula, a ij is the associative attention weight, softmax(·) is the classifier function, sig(·) is the S-type activation function, W l is the cross-modal feature fusion attention layer weight, h i is the hidden state of the node data output by the standard long short-term memory neural network, i is the node index, hj is the hidden state of the edge data output by the standard long short-term memory neural network, j is the edge index, a l is the learnability coefficient;

[0123] The spatiotemporal attention layer is used to introduce the time window attention weight function to analyze the timing characteristics of the supply chain, and obtain the spatiotemporal attention weight through weighted calculation. The calculation formula is:

[0124] ;

[0125] Where b t is the spatiotemporal attention weight, exp(·) is the natural base function, and f(·) is the time window attention weight function. The specific calculation formula is: ,in, is the time period variable, w1 is the attention weight of the first time window, w2 is the attention weight of the second time window, t0 is the time series fluctuation time index, which is used to indicate the occurrence time of abnormal events or risk events in the time series data, t is the time index, T is the total number of time series fluctuations, and t1 is the time index of the second time series fluctuations;

[0126] The risk transmission attention layer is used to calculate the risk transmission probability by integrating the relevance attention weight and the spatiotemporal attention weight to obtain the risk transmission probability reference data. The calculation formula is:

[0127] ;

[0128] Where P risk is the reference data of risk propagation probability, is the risk source node, is the transmission target node, sig(·) is the S-type activation function, K is the total number of intermediate nodes, k is the intermediate node index, which is used to represent the intermediate nodes between the risk source node and the transmission target node. is the associative attention weight between the risk source node and the kth intermediate node, is the spatiotemporal attention weight between the kth intermediate node and the target node, t is the time index, is the disturbance influence function, and the standard Gaussian function is used to simulate the disturbance influence. It is the material quality deviation reference value;

[0129] Step S34: risk propagation modeling, specifically, performing supply chain node risk simulation modeling based on the risk propagation probability reference data and the supply chain heterogeneous graph data to obtain procurement risk modeling reference data;

[0130] Step S35: coal quality decomposition modeling, specifically, coal quality decomposition modeling is performed based on the coal consumption trend characteristics and load efficiency characteristics in the procurement efficiency optimization data, and coal quality three-dimensional tensor modeling data and coal quality optimization reference data are constructed. The calculation formula is:

[0131] ;

[0132] Where, X c is the three-dimensional tensor modeling data of coal quality, P f It is the combustion efficiency reference data, which is specifically weighted by coal consumption trend characteristics and load efficiency characteristics. 1U is the supplier dimension data, 2V is the mining area source dimension data, and 3W is the transportation mode dimension data. The coal quality optimization reference data is obtained by performing target optimization decomposition on the three-dimensional tensor modeling data of the coal quality.

[0133] The target optimization decomposition is specifically calculated by using Tucker decomposition, and the calculation formula is:

[0134] ;

[0135] In the formula, F target is the objective function of the target optimization decomposition, min is the minimization function, X c is the three-dimensional tensor modeling data of coal quality, Core is the core vector of coal quality obtained by Tucker decomposition, U is the characteristic factor matrix of supplier dimension, V is the characteristic factor matrix of mining area source dimension, and W is the characteristic factor matrix of transportation mode dimension. is the Frobenius norm operator, which is used to measure the tensor error after decomposition. is the regularization coefficient, tr(·) is the regularization control function, Core T is the transpose of the coal mass core vector;

[0136] Step S36: supply chain relationship modeling, specifically, supply chain relationship modeling is performed through the supply chain heterogeneous graph construction, the graph structure dynamic evolution reconstruction, the hierarchical attention improvement, the risk propagation modeling and the coal quality decomposition modeling to obtain supply chain relationship analysis reference data;

[0137] The supply chain relationship analysis reference data includes a supplier procurement risk assessment tensor, a supplier risk transmission probability matrix, and a supplier comprehensive assessment value;

[0138] The supplier procurement risk assessment tensor includes credit risk assessment, delivery risk assessment, combustion quality risk assessment, price assessment and emergency procurement quality assessment.

[0139] By performing the above operations, in order to solve the technical problems that in the existing supply chain relationship modeling methods, the existing supplier evaluation is mainly based on historical transaction data, but the relevant data on the real-time coal consumption rate changes of the units are not reflected in the traditional methods, and the traditional graph model cannot quantify the impact of risk events on procurement demand, and the physical relationship between coal quality and power generation efficiency is difficult to characterize, this solution creatively adopts a dynamic heterogeneous improved graph neural network method to model the supply chain relationship, optimizes the supply chain status update and the quantitative calculation of risk transmission, and improves the intelligent dimension of procurement efficiency management.

[0140] Example 5, see Figure 1 , Figure 2 and Figure 5 In step S4, the procurement strategy optimization is used to calculate the optimal procurement strategy, specifically, based on the supply chain relationship analysis reference data and the procurement efficiency optimization data, a multi-layer strategy reinforcement learning method improved by multi-objective rewards is used to optimize the procurement strategy to obtain the procurement optimal strategy reference data, including the following steps:

[0141] Step S41: improving the state parameter space, specifically constructing a state parameter space for reinforcement learning and improving the system state vector to obtain improved state parameter space data, including coal inventory status, unit operation status, and carbon emission quota balance status;

[0142] Step S42: multi-layer strategy network modeling, specifically constructing a meta-strategy layer, a procurement dynamic optimization layer, and an intelligent allocation execution layer in sequence, and performing multi-layer strategy reinforcement learning through the multi-layer strategy network modeling to obtain an initial procurement strategy;

[0143] The meta-strategy layer is used to process the formulation of the annual framework agreement and optimize the long-term resource allocation. Specifically, a meta-strategy generator based on a transformer structure is used to generate a meta-procurement strategy. The calculation formula is:

[0144] ;

[0145] In the formula, is the meta-purchasing strategy parameter group, softmax(·) is the classifier function, W Q is the meta-strategy generation weight, K is the key vector, V is the value vector, and d is the dimension value of the key vector;

[0146] The procurement dynamic optimization layer is used to control the dynamic optimization of the monthly procurement rhythm and supply structure. Specifically, a double-delayed deep deterministic policy gradient algorithm is used for optimization calculation. The calculation formula is:

[0147] ;

[0148] In the formula, at is the specific purchasing action taken at the current time t, s t is the improved state parameter space data, u(·) is the policy network function using the double-delayed deep deterministic policy gradient algorithm, the policy network constructs five hidden layers to optimize the nonlinear fitting ability, are the parameters of the policy network, The whole is the random Gaussian noise added, is the Gaussian noise distribution parameter;

[0149] The intelligent allocation execution layer is used to intelligently allocate daily or real-time orders and balance procurement costs and inventory pressure. The calculation formula is:

[0150] ;

[0151] Where P pi is the short-term purchase order decision result of intelligent allocation execution, max is the maximum value function, E[·] is the expected calculation function, p n is the expected return probability of the nth short-term purchase order decision strategy, n is the short-term purchase order decision strategy index, It is in the parameter The probability likelihood function value of obtaining the reward r under is the parameter under historical data D The posterior distribution of , which is calculated using Bayesian updating;

[0152] Step S43: Improvement of the multi-objective reward function, specifically, by introducing procurement cost, delivery deviation, emission index and emergency procurement indicator function, the multi-objective reward function is improved to obtain an improved multi-objective reward function, and the calculation formula is:

[0153] ;

[0154] In the formula, R t is an improved multi-objective reward function, is the purchase cost weight, C t is the purchase cost value, C max is the maximum purchase budget value, is the delivery bias weight, is the delivery deviation time, is the mean delivery deviation, is the emission index weight, m ​​is the emission element index, including sulfur dioxide emission, nitrogen oxide emission and dust emission, E m is the emission index parameter, is the maximum emission limit, is the emergency purchase instruction weight, is the emergency purchase indicator function value, which is used to indicate whether it is an emergency purchase;

[0155] Preferably, the purchase cost weight The specific value of is 0.45, the delivery deviation weight The specific value of is 0.25, and the emission index weight The specific value is 0.2, and the emergency purchase indication weight The value of is 0.1;

[0156] Step S44: disturbance injection improvement, specifically, by introducing a disturbance factor control function, disturbance injection improvement is performed to obtain a disturbance injection function, the calculation formula of which is:

[0157] ;

[0158] Where roll(·) is the disturbance injection function, t is the time index, and g is the disturbance control parameter, which is used to control the degree of disturbance injection. By controlling the value of the disturbance injection function, disturbance simulation is performed, including market price fluctuation disturbance, transportation congestion disturbance, and supply chain disruption disturbance.

[0159] The specific calculation formula of the market price fluctuation disturbance is: ,in, is the historical statistical parameter of market volatility; the specific calculation formula of the transportation congestion disturbance is: ; The specific calculation formula for the supply chain disruption disturbance is: ,in, is the Bernoulli distribution function;

[0160] Preferably, the specific value of the disturbance control parameter is 0.05;

[0161] Step S45: Procurement strategy optimization, specifically, performing phased optimization of procurement strategy optimization through the state parameter space improvement, the multi-layer strategy network modeling, the multi-objective reward function improvement and the disturbance injection improvement, to obtain the optimal procurement strategy reference data;

[0162] The optimal procurement strategy reference data includes a multi-objective procurement strategy vector, a strategy enhancement reference function, and an emergency procurement plan reference data;

[0163] The phased optimization includes an initial stabilization phase, a disturbance introduction phase, and a multi-objective optimization phase;

[0164] The initial stabilization stage is specifically to optimize the standard reinforcement learning procurement strategy based on the state parameter space improvement and multi-layer strategy network modeling to obtain an initial procurement plan;

[0165] The disturbance introduction stage is specifically to introduce price fluctuations, transportation congestion and supply interruption simulations based on the disturbance injection improvement on the basis of the initial procurement plan, and optimize the procurement strategy for disturbance introduction improvement to obtain an anti-disturbance procurement plan;

[0166] The multi-objective optimization stage is specifically to optimize the procurement strategy of multi-objective optimization based on the anti-disturbance procurement plan and the multi-objective reward function, so as to obtain the reference data of the optimal procurement strategy.

[0167] By performing the above operations, in the existing procurement strategy optimization methods, there is a traditional reinforcement learning procurement strategy optimization, which fails to make comprehensive decision analysis for complex procurement processes and various procurement risks, carbon emission indicators and market fluctuations, which leads to the technical problem that the existing methods are difficult to combine the results of supply chain relationship modeling to make multi-directional comprehensive procurement decisions. This solution creatively adopts a multi-layer strategy reinforcement learning method with multi-objective reward improvement to optimize the procurement strategy. By combining state parameter improvement, reward improvement and disturbance control improvement, a multi-layer reinforcement learning basic model is built, which improves the analysis efficiency of the procurement strategy and also improves the overall usability and intelligence of procurement efficiency management.

[0168] Example 6, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In step S5, the procurement efficiency optimization is used to construct an intelligent evaluation method to verify the optimization of procurement strategy and improve procurement efficiency. Specifically, based on the optimal procurement strategy reference data, a multi-dimensional procurement strategy evaluation index is constructed and a procurement strategy effect evaluation is performed. By selecting the procurement strategy with the best evaluation effect, procurement efficiency is optimized to obtain a reference plan for comprehensive optimization of procurement efficiency.

[0169] The multi-dimensional procurement strategy evaluation indicators include economic indicators, reliability indicators, environmental indicators and agility indicators;

[0170] The economic index specifically refers to the deviation rate between actual cost and budgeted cost; the reliability index specifically refers to the frequency of emergency procurement; the environmental index specifically refers to the utilization rate of emission quotas; the agility index specifically refers to the time consumption of procurement strategy response.

[0171] Embodiment 7, see Figure 1 and Figure 2 , this embodiment is based on the above embodiment, and the artificial intelligence-based procurement efficiency optimization management system provided by the present invention includes a data source processing module, a supply relationship modeling module, a procurement strategy optimization module and a comprehensive efficiency optimization module;

[0172] The data source processing module is used for data item collection and data preprocessing, and obtains procurement efficiency optimization data through data item collection and data preprocessing, and sends the procurement efficiency optimization data to the supply relationship modeling module and the procurement strategy optimization module;

[0173] The supply relationship modeling module is used for supply chain relationship modeling, obtains supply chain relationship analysis reference data through supply chain relationship modeling, and sends the supply chain relationship analysis reference data to the procurement strategy optimization module;

[0174] The procurement strategy optimization module is used for procurement strategy optimization, obtains procurement optimal strategy reference data through procurement strategy optimization, and sends the procurement optimal strategy reference data to the comprehensive efficiency optimization module;

[0175] The comprehensive efficiency optimization module is used for optimizing procurement efficiency, and through optimizing procurement efficiency, a comprehensive optimization reference plan for procurement efficiency is obtained.

[0176] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0177] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0178] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A procurement efficiency optimization management method based on artificial intelligence, characterized by: The method comprises the following steps: Step S1: collect data by item to obtain the original data of procurement efficiency optimization management; Step S2: Data preprocessing: data preprocessing is performed through data enhancement and conversion to obtain procurement efficiency optimization data; Step S3: Supply chain relationship modeling, using a dynamic heterogeneous improved graph neural network method to model the supply chain relationship and obtain reference data for supply chain relationship analysis, including the following steps: Step S31: Supply chain heterogeneous graph construction; Step S32: Dynamic evolution reconstruction of graph structure; Step S33: Hierarchical attention improvement, constructing a three-layer hierarchical attention mechanism, including a cross-modal feature fusion attention layer, a spatiotemporal attention layer, and a risk conduction attention layer, to extract graph information; Step S34: Risk propagation modeling; Step S35: Coal quality decomposition modeling; Step S36: Supply chain relationship modeling; Step S4: Procurement strategy optimization, adopting the multi-layer strategy reinforcement learning method with multi-objective reward improvement to optimize the procurement strategy and obtain the reference data of the optimal procurement strategy, including the following steps: Step S41: state parameter space improvement; Step S42: multi-layer strategy network modeling; Step S43: multi-objective reward function improvement; Step S44: disturbance injection improvement; Step S45: procurement strategy optimization; Step S5: Optimize procurement efficiency and obtain a reference plan for comprehensive optimization of procurement efficiency.

2. The artificial intelligence-based procurement efficiency optimization management method according to claim 1 is characterized by: In step S1, the data is collected by item, and is used to collect the original data set required for optimizing procurement efficiency, specifically, by collecting classified data to obtain the original data for optimizing procurement efficiency management; The classified data collection includes production data collection, supply chain data collection and market data collection; The procurement efficiency optimization manages raw data, including production data, supply chain data and market data.

3. The artificial intelligence-based procurement efficiency optimization management method according to claim 2 is characterized by: In step S2, the data preprocessing is used to preprocess the original data, specifically, the original data is managed according to the procurement efficiency optimization, and the data preprocessing is performed through data enhancement and conversion to obtain procurement efficiency optimization data, including the following steps: Step S21: original data mapping, specifically, performing data mapping on the data in the procurement efficiency optimization management original data to obtain classified mapping data; the classified mapping data includes production mapping data, supply chain mapping data and market mapping data; Step S22: preprocessing the production data, specifically, performing feature enhancement processing on the production mapping data, performing feature enhancement on the load rate and coal consumption rate data in the production mapping data through a sliding window feature enhancement operation, obtaining load efficiency features and coal consumption trend features, and obtaining fault risk score features by performing fault frequency statistics on the fault event feature data; Step S23: preprocessing the supply chain data, specifically, performing feature enhancement processing on the supply chain mapping data, constructing supplier quality fluctuation characteristics by reconstructing the time series structure of the coal calorific value detection information in the basic characteristics of the supplier, and obtaining the default probability distribution characteristics by calculating the default probability of the supplier's historical default record information in the basic characteristics of the supplier, and obtaining the supply transportation efficiency characteristics by calculating the transportation efficiency of the supply coal transportation sensor information in the basic characteristics of the supplier; Step S24: market data preprocessing, specifically, performing feature enhancement processing on the market mapping data, obtaining coal price trend features by performing trend decomposition and volatility calculation on the futures price data, and performing linear regression calculation on the carbon price data to obtain a carbon price weight factor, and using the carbon price weight factor as a carbon price feature; Step S25: feature fusion, specifically, obtaining enhanced feature data through the production data preprocessing, the supply chain data preprocessing and the market data preprocessing, and obtaining procurement efficiency optimization data by sequentially performing missing value filling, outlier processing, timestamp synchronization, high-dimensional feature compression and feature labeling; The procurement efficiency optimization data includes optimizing load efficiency characteristics, optimizing coal consumption trend characteristics, optimizing fault risk score characteristics, optimizing supplier quality fluctuation characteristics, optimizing default probability distribution characteristics, optimizing supply and transportation efficiency characteristics, optimizing coal price trend characteristics and optimizing carbon price characteristics.

4. The artificial intelligence-based procurement efficiency optimization management method according to claim 3 is characterized by: In step S3, the supply chain relationship modeling is used to perform digital modeling analysis and risk assessment on the supply chain relationship of the materials to be purchased. Specifically, based on the procurement efficiency optimization data, a dynamic heterogeneous improved graph neural network method is used to perform supply chain relationship modeling to obtain supply chain relationship analysis reference data, including the following steps: Step S31: constructing a heterogeneous graph of a supply chain, specifically constructing a heterogeneous graph of a procurement supply chain according to the procurement efficiency optimization data, and obtaining heterogeneous graph data of the supply chain by defining node types, node attributes and edge types; The node types include supplier nodes, material nodes and logistics nodes; The node attributes include production capacity attributes, supplier credit rating attributes, coal inventory attributes, logistics node throughput capacity attributes, and transportation delay rate attributes; The edge types include supply relationship edges, logistics path edges and risk transmission edges; Step S32: Dynamic evolution reconstruction of the graph structure, specifically building a dynamic evolution mechanism to reconstruct the graph structure, specifically updating the node status once an hour and reconstructing the graph structure topology once a day to reflect the real-time changes in entity status and the impact and changes of supply relationships; Step S33: hierarchical attention improvement, specifically, constructing a three-layer hierarchical attention mechanism, including a cross-modal feature fusion attention layer, a spatiotemporal attention layer, and a risk transmission attention layer, to extract graph information, and through the risk transmission attention layer, to model the risk cascade transmission of the procurement process, and calculate the risk transmission probability reference data; Step S34: risk propagation modeling, specifically, performing supply chain node risk simulation modeling based on the risk propagation probability reference data and the supply chain heterogeneous graph data to obtain procurement risk modeling reference data; Step S35: coal quality decomposition modeling, specifically, performing coal quality decomposition modeling according to the coal consumption trend characteristics and load efficiency characteristics in the procurement efficiency optimization data, and constructing coal quality three-dimensional tensor modeling data and coal quality optimization reference data; Step S36: supply chain relationship modeling, specifically, supply chain relationship modeling is performed through the supply chain heterogeneous graph construction, the graph structure dynamic evolution reconstruction, the hierarchical attention improvement, the risk propagation modeling and the coal quality decomposition modeling to obtain supply chain relationship analysis reference data; The supply chain relationship analysis reference data includes a supplier procurement risk assessment tensor, a supplier risk transmission probability matrix, and a supplier comprehensive assessment value; The supplier procurement risk assessment tensor includes credit risk assessment, delivery risk assessment, combustion quality risk assessment, price assessment and emergency procurement quality assessment.

5. The artificial intelligence-based procurement efficiency optimization management method according to claim 4 is characterized by: In step S33, the cross-modal feature fusion attention layer is used to integrate node data and edge data, and to construct a standard long short-term memory neural network to perform temporal node feature processing to obtain the associative attention weight; The spatiotemporal attention layer is used to introduce a time window attention weight function to analyze the timing characteristics of the supply chain, and obtain the spatiotemporal attention weight through weighted calculation; The risk transmission attention layer is used to calculate the risk transmission probability by integrating the relevance attention weight and the spatiotemporal attention weight to obtain the risk transmission probability reference data. The calculation formula is: ； Where P risk is the reference data of risk propagation probability, is the risk source node, is the transmission target node, sig(·) is the S-type activation function, K is the total number of intermediate nodes, k is the intermediate node index, which is used to represent the intermediate nodes between the risk source node and the transmission target node. is the associative attention weight between the risk source node and the kth intermediate node, is the spatiotemporal attention weight between the kth intermediate node and the transmission target node, t is the time index, is the disturbance influence function, and the standard Gaussian function is used to simulate the disturbance influence. It is the reference value of material quality deviation.

6. The artificial intelligence-based procurement efficiency optimization management method according to claim 5 is characterized by: In step S4, the procurement strategy optimization is used to calculate the optimal procurement strategy, specifically, based on the supply chain relationship analysis reference data and the procurement efficiency optimization data, a multi-level strategy reinforcement learning method improved by multi-objective rewards is used to optimize the procurement strategy to obtain the procurement optimal strategy reference data, including the following steps: Step S41: improving the state parameter space, specifically constructing a state parameter space for reinforcement learning and improving the system state vector to obtain improved state parameter space data, including coal inventory status, unit operation status, and carbon emission quota balance status; Step S42: multi-layer strategy network modeling, specifically constructing a meta-strategy layer, a procurement dynamic optimization layer, and an intelligent allocation execution layer in sequence, and performing multi-layer strategy reinforcement learning through the multi-layer strategy network modeling to obtain an initial procurement strategy; The meta-strategy layer is used to process the formulation of annual framework agreements and optimize long-term resource allocation, and specifically adopts a meta-strategy generator based on a transformer structure to generate meta-procurement strategies; The procurement dynamic optimization layer is used to control the dynamic optimization of the monthly procurement rhythm and supply structure, and specifically adopts a double-delayed deep deterministic policy gradient algorithm for optimization calculation; The intelligent allocation execution layer is used to intelligently allocate daily or real-time orders and balance procurement costs and inventory pressure; Step S43: Improvement of the multi-objective reward function, specifically, by introducing procurement cost, delivery deviation, emission index and emergency procurement indicator function, the multi-objective reward function is improved to obtain an improved multi-objective reward function, and the calculation formula is: ； In the formula, R t is an improved multi-objective reward function, is the purchase cost weight, C t is the purchase cost value, C max is the maximum purchase budget value, is the delivery bias weight, is the delivery deviation time, is the mean delivery deviation, is the emission index weight, m ​​is the emission element index, including sulfur dioxide emission, nitrogen oxide emission and dust emission, E m is the emission index parameter, is the maximum emission limit, is the emergency purchase instruction weight, is the emergency purchase indicator function value, which is used to indicate whether it is an emergency purchase; Step S44: disturbance injection improvement, specifically, by introducing a disturbance factor control function, disturbance injection improvement is performed to obtain a disturbance injection function, the calculation formula of which is: ； Where roll(·) is the disturbance injection function, t is the time index, and g is the disturbance control parameter, which is used to control the degree of disturbance injection. By controlling the value of the disturbance injection function, disturbance simulation is performed, including market price fluctuation disturbance, transportation congestion disturbance, and supply chain disruption disturbance. The specific calculation formula of the market price fluctuation disturbance is: ,in, is the historical statistical parameter of market volatility; the specific calculation formula of the transportation congestion disturbance is: ; The specific calculation formula for the supply chain disruption disturbance is: ,in, is the Bernoulli distribution function; Step S45: Procurement strategy optimization, specifically, performing phased optimization of procurement strategy optimization through the state parameter space improvement, the multi-layer strategy network modeling, the multi-objective reward function improvement and the disturbance injection improvement, to obtain the optimal procurement strategy reference data; The optimal procurement strategy reference data includes a multi-objective procurement strategy vector, a strategy enhancement reference function, and an emergency procurement plan reference data; The phased optimization includes an initial stabilization phase, a disturbance introduction phase, and a multi-objective optimization phase; The initial stabilization stage is specifically to optimize the standard reinforcement learning procurement strategy based on the state parameter space improvement and multi-layer strategy network modeling to obtain an initial procurement plan; The disturbance introduction stage is specifically to introduce price fluctuations, transportation congestion and supply interruption simulations based on the disturbance injection improvement on the basis of the initial procurement plan, and optimize the procurement strategy for disturbance introduction improvement to obtain an anti-disturbance procurement plan; The multi-objective optimization stage is specifically to optimize the fruit strategy of multi-objective optimization based on the anti-disturbance procurement plan and the multi-objective reward function, so as to obtain the reference data of the optimal procurement strategy.

7. The artificial intelligence-based procurement efficiency optimization management method according to claim 6 is characterized by: In step S5, the procurement efficiency optimization is used to construct an intelligent evaluation method to verify the optimization of procurement strategies and improve procurement efficiency. Specifically, based on the optimal procurement strategy reference data, a multi-dimensional procurement strategy evaluation index is constructed and the procurement strategy effect evaluation is performed. By selecting the procurement strategy with the best evaluation effect, procurement efficiency is optimized to obtain a comprehensive optimization reference plan for procurement efficiency. The multi-dimensional procurement strategy evaluation indicators include economic indicators, reliability indicators, environmental indicators and agility indicators; The economic index specifically refers to the deviation rate between actual cost and budgeted cost; the reliability index specifically refers to the frequency of emergency procurement; the environmental index specifically refers to the utilization rate of emission quotas; the agility index specifically refers to the time consumption of procurement strategy response.

8. A procurement efficiency optimization management system based on artificial intelligence, used to implement the procurement efficiency optimization management method based on artificial intelligence as described in any one of claims 1 to 7, characterized in that: It includes data source processing module, supply relationship modeling module, procurement strategy optimization module and comprehensive efficiency optimization module.

9. The artificial intelligence-based procurement efficiency optimization management system according to claim 8, characterized in that: The data source processing module is used for data item collection and data preprocessing, and obtains procurement efficiency optimization data through data item collection and data preprocessing, and sends the procurement efficiency optimization data to the supply relationship modeling module and the procurement strategy optimization module; The supply relationship modeling module is used for supply chain relationship modeling, obtains supply chain relationship analysis reference data through supply chain relationship modeling, and sends the supply chain relationship analysis reference data to the procurement strategy optimization module; The procurement strategy optimization module is used for procurement strategy optimization, obtains procurement optimal strategy reference data through procurement strategy optimization, and sends the procurement optimal strategy reference data to the comprehensive efficiency optimization module; The comprehensive efficiency optimization module is used for optimizing procurement efficiency, and through optimizing procurement efficiency, a comprehensive optimization reference plan for procurement efficiency is obtained.

Images