Electronic component supply chain intelligent management method and system

Abstract

The application discloses an electronic component supply chain intelligent management method and system, relates to the technical field of intelligent supply chain management, and comprises the following steps: collecting real-time market transaction data of electronic components, wherein the real-time market transaction data comprises historical purchase data, historical inventory data, supplier delivery cycle data and component life cycle data; constructing a demand prediction model of the electronic components to generate a demand prediction result; inputting the demand prediction result into a risk assessment model and outputting a stock-out risk index through a fuzzy comprehensive evaluation method; dividing the electronic components into risk grades according to the stock-out risk index, generating a supplier purchase quota scheme, and realizing intelligent management of the electronic component supply chain. The application effectively improves the prediction accuracy and risk resistance of the supply chain, realizes scientific decision-making and intelligent management of electronic component purchase, and reduces the operation cost and supply interruption risk caused by stock-out.

Description

Technical Field

[0001] This invention relates to the field of intelligent supply chain management technology, and in particular to an intelligent management method and system for the electronic component supply chain. Background Technology

[0002] Supply chain management for electronic components plays a crucial role in modern manufacturing, involving the coordination and optimization of the entire process from raw material procurement and inventory scheduling to final delivery. Traditional supply chain management methods often rely on manual experience or rule-driven management systems, which are prone to problems such as low information processing efficiency, delayed supply-demand matching, and insufficient forecasting capabilities when dealing with scenarios involving large demand fluctuations, complex component categories, and sensitive delivery cycles. Especially against the backdrop of a surge in multi-source heterogeneous data, how to achieve efficient abstraction and intelligent analysis of electronic component supply and demand data has become a key challenge for improving management efficiency and responsiveness. Therefore, there is an urgent need for a data-driven approach to enhance the intelligence level of the electronic component supply chain and achieve accurate matching of supply and demand information and trend prediction.

[0003] CN119863087A discloses a method for supply and demand management of electronic component supply chains, including: S1, abstracting and tagging the acquired electronic data to transform the original complex data into a unified format; S2, selecting a Large Language Model (LLM), inputting the tagged data into the model for analysis, and outputting results including explanations of supply and demand conditions and predictions of future supply and demand trends; S3, using a fine-tuning module to perform personalized training and optimization of the LLM model to enhance its adaptability and predictive ability in specific supply chain scenarios; S4, after building the system, vectorizing the stored tagged supply and demand data and material information, and using vector search technology to achieve rapid matching and querying of supply and demand data. This method, by introducing abstract tagging rule-based technology, improves the uniformity of data processing and the efficiency of intelligent analysis, thereby enhancing the accuracy and response speed of overall supply and demand management. However, this method still has the following shortcomings: it mainly focuses on data processing and prediction models themselves, without considering the upstream and downstream feedback mechanisms and dynamic adjustment mechanisms involved in actual supply chain operations. It is difficult to manage real-time changing market demand and multi-stage logistics constraints in a closed loop, resulting in insufficient ability to respond to emergencies or atypical demand scenarios. Summary of the Invention

[0004] In view of the problems that existing electronic component supply chain management methods lack the ability to respond to real-time market fluctuations, have imperfect risk assessment mechanisms, lack intelligent optimization of supplier quota allocation, and have low accuracy of demand forecasting models, this invention is proposed.

[0005] Therefore, the problem to be solved by this invention is how to improve the accuracy of risk perception and response efficiency in the electronic component supply chain, and realize intelligent management of the entire process from demand forecasting and risk assessment to supplier quota setting and dynamic adjustment.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, embodiments of the present invention provide an intelligent management method for the electronic component supply chain, comprising,

[0008] Collect real-time market transaction data for electronic components, including historical procurement data, historical inventory data, supplier delivery cycle data, and component lifecycle data.

[0009] Based on the historical procurement data and the historical inventory data, a demand forecasting model for electronic components is constructed, and demand forecasting results are generated.

[0010] Based on the supplier delivery cycle data and the component life cycle data, the demand forecast results are input into the risk assessment model, and the stockout risk index is output through fuzzy comprehensive evaluation method.

[0011] Based on the aforementioned shortage risk index, electronic components are classified into risk levels, and supplier procurement quota schemes are generated to achieve intelligent management of the electronic component supply chain.

[0012] As a preferred embodiment of the intelligent supply chain management method for electronic components described in this invention, the method includes: classifying electronic components into risk levels based on the shortage risk index and generating a supplier procurement quota plan, including:

[0013] Based on the shortage risk index, electronic components are divided into high-risk, medium-risk, and low-risk areas;

[0014] For electronic components in high-risk areas, establish supplier qualification rating standards, which include financial status score, production capacity score, historical credit score, and capacity utilization rate.

[0015] Based on the aforementioned supplier qualification rating criteria, suppliers are ranked and high-quality suppliers are selected.

[0016] A genetic algorithm is used to perform multi-objective optimization on the procurement quota of the high-quality supplier to generate a procurement quota scheme Y;

[0017] For electronic components in medium-risk and low-risk areas, a procurement quota plan X is generated according to a preset strategy;

[0018] Based on the procurement quota scheme Y and the procurement quota scheme X, a supplier procurement benchmark quota is set, and a dynamic adjustment mechanism is established. Through the periodic risk index assessment results, the quota allocation is corrected in real time to realize intelligent management of the electronic component supply chain.

[0019] As a preferred embodiment of the intelligent management method for the electronic component supply chain described in this invention, the electronic components are classified into risk levels, including:

[0020] When the shortage risk index of a certain electronic component is greater than the first threshold and the capacity utilization rate exceeds the second threshold, the electronic component will be included in the temporary observation list, and the key indicators of the electronic components in the temporary observation list will be dynamically monitored for three consecutive monitoring cycles. The key indicators include supplier price fluctuations, supplier inventory and market demand growth rate.

[0021] If the supplier’s price fluctuation exceeds the third threshold, or the supplier’s inventory is below the fourth threshold and the market demand growth rate exceeds the fifth threshold, then this electronic component will be classified as a high-risk component.

[0022] If the number of alternative suppliers for electronic components in a high-risk area exceeds the sixth threshold and the supplier concentration index is lower than the seventh threshold, a risk downgrade assessment will be triggered.

[0023] If the market supply-demand ratio is greater than the eighth threshold during the downgrade assessment period and there are no abnormal fluctuations within the continuous monitoring period, then this electronic component will be adjusted to the medium-risk zone.

[0024] If the supplier fulfillment rate of electronic components in the medium-risk zone exceeds the ninth threshold and the inventory turnover rate is lower than the tenth threshold, then the electronic components will be classified into the low-risk zone.

[0025] If a supplier's products enter a high-risk area, the risk level of the associated products will be automatically increased by one level.

[0026] In a preferred embodiment of the intelligent supply chain management method for electronic components described in this invention, the method for obtaining the stockout risk index is as follows:

[0027] A risk assessment model is established based on a deep neural network architecture;

[0028] Historical stockout event data are input into the risk assessment model for training, and the model parameters are optimized using the backpropagation algorithm.

[0029] Construct an evaluation index matrix, and standardize the on-time delivery rate, average delay time and delivery volatility in the supplier delivery cycle data to form a delivery evaluation vector.

[0030] Extract life cycle stage indicators, alternative product indicators, and production stoppage warning indicators from component life cycle data to generate a life cycle assessment vector;

[0031] Based on the demand forecast results, demand growth indicators, volatility indicators, and forecast accuracy indicators are calculated to form a demand assessment vector;

[0032] The delivery assessment vector, the lifecycle assessment vector, and the demand assessment vector are input into the risk assessment model to obtain an initial risk score.

[0033] Establish a fuzzy membership function to map the initial risk score to the [0,1] interval, and construct a fuzzy relation matrix;

[0034] The weight vector of the evaluation index is calculated using the analytic hierarchy process, and the weight vector is combined with the fuzzy relation matrix to output the stockout risk index.

[0035] When the assessment indicators show abnormal fluctuations, the risk assessment model automatically adjusts the risk score weights and recalculates the stockout risk index.

[0036] In a preferred embodiment of the intelligent management method for the electronic component supply chain described in this invention, the method for constructing the risk assessment model is as follows:

[0037] The deep neural network architecture is constructed, wherein the deep neural network architecture includes an input layer, a feature extraction layer, a risk quantization layer, and an output layer; the feature extraction layer is configured with multiple alternating convolutional layers and pooling layers.

[0038] A first neuron group is set in the input layer, wherein the first neuron group corresponds to the input interface of supplier delivery cycle characteristics, component life cycle characteristics and demand forecast characteristics;

[0039] A sliding convolution kernel is set in the convolutional layer of the feature extraction layer, wherein the sliding convolution kernel performs nonlinear transformation on the input features to extract multi-scale feature information;

[0040] Max pooling is used in the pooling layer of the feature extraction layer to reduce the feature dimension while retaining the features.

[0041] A second neuron group is set in the risk quantification layer, wherein the second neuron group combines and weights the extracted feature information through a fully connected layer;

[0042] A third neuron group is set in the output layer, wherein the third neuron group uses the Softmax activation function to output the probability of the risk level;

[0043] A batch normalization layer is set up to standardize the outputs of the feature extraction layer and the risk quantification layer.

[0044] By employing a residual connection structure, skip connections are established between the convolutional blocks of the feature extraction layer to alleviate the gradient vanishing problem and complete the establishment of the risk assessment model.

[0045] In a preferred embodiment of the intelligent supply chain management method for electronic components described in this invention, the method for generating the demand forecasting results is as follows:

[0046] The sequence segmentation method is used to divide the historical procurement data and historical inventory data in real-time market transaction data into training set, validation set and test set according to a preset ratio;

[0047] Construct a long short-term memory network model and capture the long-term dependence on electronic component procurement through a gating mechanism;

[0048] A gradient boosting tree model is constructed, and the nonlinear demand pattern of electronic components is modeled using the decision tree ensemble method. The prediction accuracy is improved by fitting the residuals through an iterative approach.

[0049] The outputs of the Long Short-Term Memory Network model and the Gradient Boosting Tree model are weighted and fused using a stacking ensemble method to form a demand forecasting model.

[0050] The hyperparameters of the demand forecasting model are automatically tuned based on the Bayesian optimization algorithm, and the model performance is optimized on the validation set through cross-validation.

[0051] The test set is input into the optimized demand forecasting model, and combined with safety stock levels and market fluctuation factors, the demand forecast results for electronic components are generated.

[0052] As a preferred embodiment of the intelligent management method for the electronic component supply chain of the present invention, the method for collecting real-time market transaction data is as follows:

[0053] By connecting multiple electronic component trading platforms through market data acquisition interfaces, a data acquisition channel is established to collect real-time market transaction data of electronic components;

[0054] The real-time market transaction data is stored according to data type, forming historical procurement data, historical inventory data, supplier delivery cycle data, and component life cycle data.

[0055] A distributed data processing framework is used to clean the real-time market transaction data, and a time-series feature extraction module is established to perform time-series decomposition on the historical purchase data and the historical inventory data to extract trend items, periodic items and random items.

[0056] Construct a supplier profile model and quantify the indicators of delivery time, delivery accuracy, and delivery quality in the supplier delivery cycle data;

[0057] Set lifecycle status tags for the component lifecycle data, wherein the lifecycle status tags include mass production period, maturity period, decline period and production stoppage warning period;

[0058] The processed real-time market transaction data is stored in a distributed database, and an index structure is built according to timestamps.

[0059] Secondly, embodiments of the present invention provide an intelligent management system for the electronic component supply chain, comprising:

[0060] The data acquisition module is used to collect real-time market transaction data of electronic components, including historical procurement data, historical inventory data, supplier delivery cycle data, and component lifecycle data.

[0061] The demand forecasting module constructs a demand forecasting model for electronic components based on the historical procurement data and the historical inventory data, and generates demand forecasting results.

[0062] The stockout risk assessment module, based on the supplier delivery cycle data and the component life cycle data, inputs the demand forecast results into the risk assessment model and outputs the stockout risk index through fuzzy comprehensive evaluation method;

[0063] The classification management module is used to classify electronic components into risk levels based on the shortage risk index, generate supplier procurement quota schemes, and realize intelligent management of the electronic component supply chain.

[0064] Thirdly, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the computer program instructions, when executed by the processor, implement the steps of the intelligent management method for the electronic component supply chain as described in the first aspect of the present invention.

[0065] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of the intelligent management method for the electronic component supply chain as described in the first aspect of the present invention.

[0066] Compared with existing technologies, the beneficial effects of this invention are as follows: By collecting and integrating real-time market transaction data from multiple dimensions such as historical procurement, inventory, supplier delivery cycles, and lifecycles, a precise demand forecasting model and risk assessment model are constructed, thereby achieving quantitative analysis and dynamic early warning of electronic component shortage risks; by outputting a shortage risk index through fuzzy comprehensive evaluation, electronic components are classified into high, medium, and low risk levels, which not only strengthens the key control capabilities of critical components but also improves the overall precision of resource allocation; by introducing a supplier qualification rating system in high-risk areas and using a genetic algorithm for multi-objective optimization allocation, the optimal allocation of procurement quotas for high-risk components is achieved, improving supply continuity and stability; this method effectively improves the forecasting accuracy and risk resistance of the supply chain, realizes scientific decision-making and intelligent management of electronic component procurement, and significantly reduces operating costs and supply interruption risks caused by shortages. Attached Figure Description

[0067] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0068] Figure 1 This is a flowchart of the intelligent management method for the electronic component supply chain in Example 1.

[0069] Figure 2 This is a system framework diagram of the intelligent management system for the electronic component supply chain in Example 2. Detailed Implementation

[0070] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0071] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0072] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0073] Example 1

[0074] Reference Figure 1 This is the first embodiment of the present invention, which provides an intelligent management method for the electronic component supply chain, including:

[0075] S1: Collect real-time market transaction data for electronic components, including historical procurement data, historical inventory data, supplier delivery cycle data, and component lifecycle data.

[0076] S1.1: Connect to multiple electronic component trading platforms through the market data acquisition interface to establish a data acquisition channel and collect real-time market transaction data of electronic components.

[0077] S1.2: Store real-time market transaction data according to data type to form historical procurement data, historical inventory data, supplier delivery cycle data, and component lifecycle data.

[0078] S1.3: A distributed data processing framework is used to clean real-time market transaction data, and a time series feature extraction module is established to decompose historical procurement data and historical inventory data into time series and extract trend items, periodic items and random items.

[0079] S1.4: Construct a supplier profile model to quantify the delivery time, delivery accuracy, and delivery quality metrics in the supplier delivery cycle data.

[0080] In an optional implementation, the supplier profile model is constructed as follows: A basic supplier feature layer is established, collecting static information about suppliers, including registered capital, establishment date, employee size, and production qualifications; a supplier behavioral feature layer is constructed, converting monthly delivery volume, product quality pass rate, and price fluctuation range from supplier delivery cycle data into dynamic feature vectors; a time decay function is used to process supplier delivery cycle data, assigning differentiated weights to delivery performance at different times; a supplier credit evaluation matrix is ​​set up, mapping supplier performance, quality complaint rate, and payment compliance to credit scores; a collaborative filtering algorithm is introduced, clustering suppliers based on similarity calculations; principal component analysis is used to reduce the dimensionality of the basic feature layer, behavioral feature layer, and credit evaluation matrix, extracting key features; and a supplier profile label system is generated to form the supplier profile model.

[0081] S1.5: Set lifecycle status labels for component lifecycle data, including mass production period, maturity period, decline period and production stoppage warning period.

[0082] S1.6: Store the processed real-time market transaction data into a distributed database and establish an index structure based on timestamps.

[0083] S2: Based on historical procurement data and historical inventory data, construct a demand forecasting model for electronic components and generate demand forecasting results.

[0084] S2.1: The sequence segmentation method is used to divide the historical procurement data and historical inventory data in the real-time market transaction data into training set, validation set and test set according to a preset ratio.

[0085] S2.2: Construct a long short-term memory network model and capture the long-term dependence of electronic component procurement through a gating mechanism.

[0086] It should be noted that the Long Short-Term Memory (LSTM) network model includes an input layer, two LSTM hidden layers, and an output layer.

[0087] In an optional implementation, 128 neurons are set in the first LSTM hidden layer of the Long Short-Term Memory Network model and 64 neurons are set in the second LSTM hidden layer; the effective features are used as input to the Long Short-Term Memory Network model, and the long-term dependencies of electronic component procurement are captured through a gating mechanism.

[0088] S2.3: Construct a gradient boosting tree model, use the decision tree ensemble method to model the nonlinear demand pattern of electronic components, and improve the prediction accuracy by fitting the residuals through iterative methods.

[0089] In an optional implementation, the tree depth of the gradient boosting tree model is set to 6, and the number of trees is set to 100; the effective features are input into the gradient boosting tree model, and the residuals are fitted iteratively to improve the prediction accuracy.

[0090] S2.4: The outputs of the Long Short-Term Memory Network model and the Gradient Boosting Tree model are weighted and fused using a stacked ensemble method to form a demand forecasting model.

[0091] S2.5: Automatically tune the hyperparameters of the demand forecasting model based on the Bayesian optimization algorithm, and optimize the model performance on the validation set through cross-validation.

[0092] S2.6: Input the test set into the optimized demand forecasting model, and combine it with safety stock levels and market fluctuation factors to generate demand forecasting results for electronic components.

[0093] S3: Based on supplier delivery cycle data and component lifecycle data, the demand forecast results are input into the risk assessment model, and the shortage risk index is output through fuzzy comprehensive evaluation method.

[0094] S3.1: Establish a risk assessment model based on a deep neural network architecture.

[0095] In an optional implementation, the risk assessment model is constructed by building a deep neural network architecture, which includes an input layer, a feature extraction layer, a risk quantization layer, and an output layer. The feature extraction layer uses an alternating structure of multiple convolutional and pooling layers. A first neuron group is set in the input layer, corresponding to the input interfaces of supplier delivery cycle features, component lifecycle features, and demand forecast features. A sliding convolutional kernel is set in the convolutional layer of the feature extraction layer, performing a non-linear transformation on the input features to extract multi-scale feature information. Max pooling is used in the pooling layer of the feature extraction layer to reduce feature dimensionality and retain features. A second neuron group is set in the risk quantization layer, combining and weighting the extracted feature information through a fully connected layer. A third neuron group is set in the output layer, using a Softmax activation function to output the probability of the risk level. A batch normalization layer is set to standardize the outputs of the feature extraction layer and the risk quantization layer. A residual connection structure is used to establish skip connections between the convolutional blocks of the feature extraction layer to alleviate the gradient vanishing problem, thus completing the establishment of the risk assessment model.

[0096] S3.2: Input historical stockout event data into the risk assessment model for training, and optimize the model parameters through the backpropagation algorithm.

[0097] S3.3: Construct an evaluation index matrix, and standardize the on-time delivery rate, average delay time and delivery volatility in the supplier delivery cycle data to form a delivery evaluation vector.

[0098] S3.4: Extract life cycle stage indicators, alternative product indicators, and production stoppage warning indicators from the component life cycle data to generate a life cycle assessment vector.

[0099] S3.5: Calculate demand growth indicators, volatility indicators, and forecast accuracy indicators based on demand forecast results to form a demand assessment vector.

[0100] S3.6: Input the delivery assessment vector, life cycle assessment vector, and demand assessment vector into the risk assessment model to obtain the initial risk score.

[0101] S3.7: Establish a fuzzy membership function to map the initial risk score to the [0,1] interval and construct a fuzzy relation matrix.

[0102] S3.8: The weight vector of the evaluation index is calculated using the analytic hierarchy process (AHP). The weight vector is then combined with the fuzzy relation matrix to perform a fuzzy composite operation, and the stockout risk index is output.

[0103] S3.9: When the assessment indicators show abnormal fluctuations, the risk assessment model will automatically adjust the risk score weights and recalculate the stockout risk index.

[0104] S4: Classify electronic components by risk level based on the shortage risk index, generate supplier procurement quota plans, and realize intelligent management of the electronic component supply chain.

[0105] S4.1: Based on the shortage risk index, electronic components are divided into high-risk, medium-risk, and low-risk zones.

[0106] In an optional implementation, when the shortage risk index of a certain electronic component exceeds the first threshold and the capacity utilization rate exceeds the second threshold, the electronic component is included in a temporary observation list. Key indicators for the electronic components on the temporary observation list are dynamically monitored for three consecutive monitoring periods. These key indicators include supplier price fluctuations, supplier inventory, and market demand growth rates. If the supplier price fluctuation exceeds the third threshold, or the supplier inventory is below the fourth threshold and the market demand growth rate exceeds the fifth threshold, the electronic component is classified as high-risk. If the number of alternative suppliers for the electronic component in the high-risk zone exceeds the sixth threshold and the supplier concentration index is below the seventh threshold, a risk downgrade assessment is triggered. If the market supply-demand ratio is greater than the eighth threshold and there are no abnormal fluctuations during the downgrade assessment period, the electronic component is adjusted to the medium-risk zone. If the supplier fulfillment rate of the electronic component in the medium-risk zone exceeds the ninth threshold and the inventory turnover rate is below the tenth threshold, the electronic component is classified as low-risk. If a supplier's product enters the high-risk zone, the risk level of the associated product is automatically upgraded by one level.

[0107] S4.2: For electronic components in high-risk areas, establish supplier qualification rating standards, which include financial status score, production capacity score, historical credit score, and capacity utilization rate.

[0108] S4.3: Based on the supplier qualification rating criteria, rank the suppliers and select high-quality suppliers.

[0109] In an optional implementation, a comprehensive supplier rating matrix is ​​constructed based on the supplier qualification rating criteria, including financial status score, production capacity score, historical credit score, and capacity utilization rate. If a supplier's financial status score is greater than 85 and its revenue growth rate has been positive for the most recent four quarters, then this supplier is included in the financially sound list.

[0110] As illustrated in the example, supplier capacity is categorized as follows: when the average monthly capacity is greater than 1 million units and the capacity utilization rate is less than 80%, it is classified as Grade A capacity; when the average monthly capacity is between 500,000 and 1 million units and the capacity utilization rate is between 80% and 90%, it is classified as Grade B capacity; when the average monthly capacity is less than 500,000 units or the capacity utilization rate is greater than 90%, it is classified as Grade C capacity.

[0111] As illustrated in the example, a dynamic evaluation mechanism for supplier historical credit is established: when the on-time delivery rate is greater than 95% for 12 consecutive months, the credit rating is upgraded by one level; if a major quality problem occurs in a single month or the delivery is delayed for more than 15 days, the credit rating is downgraded by two levels; when a supplier is in the credit observation period, if there are no adverse records for 3 consecutive months, the observation status is lifted.

[0112] As illustrated in the example, the evaluation indicators for supplier competition and cooperation are set as follows: when a supplier supplies to a competitor at the same time, the proportion of exclusive supply agreements must be greater than 60%; if a supplier establishes a strategic alliance with other high-quality suppliers, the cooperation period is more than 2 years and there are no less than 3 cooperation projects per year, the weighted coefficient of the score will be increased by 0.1.

[0113] The example illustrates the construction of supplier preference criteria rules:

[0114] Basic requirements: The financial status score is on the financially sound list, and the production capacity level is A or B;

[0115] Bonus points: Cooperation with strategic clients for more than 3 years, or possession of no less than 5 core patented technologies;

[0116] No-no: Major quality incidents have occurred within the past two years, or there are intellectual property disputes;

[0117] As illustrated in the example, a supplier is included in the list of high-quality suppliers when it meets the following combination of conditions:

[0118] Condition combination one: Financially sound list + Grade A production capacity + Credit rating of Grade A or above + No veto items;

[0119] Condition combination two: Financially sound list + B-level production capacity + credit rating of A or above + two or more bonus items + no veto items;

[0120] As illustrated in the example, a dynamic exit mechanism is set up for suppliers selected for the list of high-quality suppliers:

[0121] If the quarterly assessment score is below 80 points for two consecutive quarters;

[0122] Or a single major quality problem results in customer losses exceeding 1 million yuan;

[0123] Or, the capacity utilization rate exceeds 95% for three consecutive months and there are no plans to expand production.

[0124] S4.4: Use a genetic algorithm to perform multi-objective optimization of the procurement quota of high-quality suppliers and generate procurement quota scheme Y.

[0125] S4.5: Generate procurement quota scheme X for electronic components in medium-risk and low-risk areas according to preset strategies.

[0126] S4.6: Based on procurement quota scheme Y and procurement quota scheme X, set the supplier procurement benchmark quota and establish a dynamic adjustment mechanism. Through the periodic risk index assessment results, the quota allocation is corrected in real time to realize intelligent management of the electronic component supply chain.

[0127] As illustrated in the example, when implementing procurement quota scheme X, if the supplier has a good credit rating, a centralized procurement quota allocation strategy is adopted. The supplier's qualifications are dynamically monitored and evaluated through the central procurement decision-making system. A three-dimensional monitoring mechanism is set up for the supplier's price commitment, delivery capability, and quality assurance. The three-dimensional monitoring mechanism includes real-time price monitoring, delivery cycle monitoring, and quality traceability monitoring. Real-time price monitoring dynamically tracks the supplier's quotations, delivery cycle monitoring evaluates the supplier's capacity utilization rate in real time, and quality traceability monitoring analyzes the supplier's product quality data. If a supplier credit risk warning is issued, the strategy switches to a distributed procurement quota allocation strategy. The supplier's performance is managed in a decentralized manner through regional procurement centers. A two-dimensional monitoring mechanism is set up for the supplier's price commitment and delivery capability. The supplier's product quality data is evaluated regularly through a combination of offline sampling and online feedback. When the evaluation indicators are below the threshold, the system automatically adjusts the supplier's procurement quota ratio.

[0128] As illustrated in the example, when implementing procurement quota plan Y, if a supplier disruption risk occurs, an emergency procurement quota adjustment mechanism is activated. An intelligent risk warning system monitors the supplier's performance throughout the process, establishing a two-dimensional monitoring mechanism for supplier price commitments and delivery capabilities. The intelligent risk warning system accurately identifies the disruption risk. When the risk is confirmed, the procurement management system sends a real-time warning, notifying procurement specialists to activate the alternative supplier resource pool and distribute procurement orders. The procurement management system automatically receives supplier status information from the intelligent risk warning system, dynamically reallocates procurement quotas, and automatically freezes the procurement quotas of problematic suppliers. Once the supplier risk is resolved, the procurement management system conducts a comprehensive evaluation of the supplier. If the evaluation is successful, the supplier's procurement quota is gradually restored until the risk remediation process is complete.

[0129] In summary, this invention constructs accurate demand forecasting and risk assessment models by collecting and integrating real-time market transaction data from multiple dimensions, including historical procurement, inventory, supplier delivery cycles, and lifecycles. This enables quantitative analysis and dynamic early warning of electronic component shortage risks. By outputting a shortage risk index through fuzzy comprehensive evaluation, electronic components are categorized into high, medium, and low risk levels. This not only strengthens the key control capabilities for critical components but also improves the overall precision of resource allocation. In high-risk areas, a supplier qualification rating system is introduced, and a genetic algorithm is used for multi-objective optimization allocation, achieving optimal allocation of procurement quotas for high-risk components and improving supply continuity and stability. This method effectively enhances the forecasting accuracy and risk resistance of the supply chain, enabling scientific decision-making and intelligent management of electronic component procurement, and significantly reducing operating costs and supply disruption risks caused by shortages.

[0130] Example 2

[0131] Reference Figure 2 This is a second embodiment of the present invention. This embodiment also provides an intelligent management system for the electronic component supply chain, comprising:

[0132] The data acquisition module is used to collect real-time market transaction data of electronic components, including historical procurement data, historical inventory data, supplier delivery cycle data, and component lifecycle data.

[0133] The demand forecasting module constructs a demand forecasting model for electronic components based on the historical procurement data and the historical inventory data, and generates demand forecasting results.

[0134] The stockout risk assessment module, based on the supplier delivery cycle data and the component life cycle data, inputs the demand forecast results into the risk assessment model and outputs the stockout risk index through fuzzy comprehensive evaluation method;

[0135] The classification management module is used to classify electronic components into risk levels based on the shortage risk index, generate supplier procurement quota schemes, and realize intelligent management of the electronic component supply chain.

[0136] This embodiment also provides an electronic device, which includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. The processor of this computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for wired or wireless communication with external terminals. Wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a multi-task edge computing resource scheduling method. The display screen of the computer device can be a liquid crystal display screen or an e-ink display screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, a trackball, or a touchpad located on the casing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0137] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method proposed in the above embodiments.

[0138] The storage medium proposed in this embodiment belongs to the same inventive concept as the method proposed in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0139] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the method of the embodiments of the present invention.

[0140] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

[0141] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented using various computer languages.

[0142] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0143] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0144] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0145] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0146] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. An electronic component supply chain intelligent management method, characterized by: The application relates to an electronic component supply chain intelligent management method and system. Collecting real-time market transaction data of electronic components, wherein the real-time market transaction data comprises historical purchase data, historical inventory data, supplier delivery cycle data and component life cycle data; Based on the historical purchase data and the historical inventory data, a demand prediction model of the electronic components is constructed to generate a demand prediction result; Based on the supplier delivery cycle data and the component life cycle data, the demand prediction result is input into a risk assessment model, and a shortage risk index is output by a fuzzy comprehensive evaluation method; According to the shortage risk index, the electronic components are classified into different risk levels, and a supplier purchase quota scheme is generated to realize intelligent management of the electronic component supply chain; The method for obtaining the shortage risk index comprises the following steps: Based on a deep neural network architecture, a risk assessment model is established; Historical shortage event data is input into the risk assessment model for training, and model parameters are optimized by a back propagation algorithm; An evaluation index matrix is constructed, and a delivery evaluation vector is formed by standardizing the delivery timeliness rate, average delay time and delivery fluctuation rate in the supplier delivery cycle data; Life cycle stage indicators, substitute product indicators and production suspension early warning indicators are extracted from the component life cycle data to generate a life cycle evaluation vector; Demand growth indicators, fluctuation indicators and prediction accuracy indicators are calculated based on the demand prediction result to form a demand evaluation vector; The delivery evaluation vector, the life cycle evaluation vector and the demand evaluation vector are input into the risk assessment model to obtain an initial risk score; A fuzzy membership function is established to map the initial risk score to the interval [0, 1], and a fuzzy relation matrix is constructed; An analytic hierarchy process is used to calculate an evaluation index weight vector, the weight vector is subjected to fuzzy compound operation with the fuzzy relation matrix, and a shortage risk index is output; When an evaluation index appears abnormal fluctuation, the risk assessment model automatically adjusts the risk score weight, and the shortage risk index is recalculated.

2. The electronic component supply chain intelligent management method of claim 1, wherein: According to the shortage risk index, the electronic components are classified into different risk levels, and a supplier purchase quota scheme is generated, which comprises the following steps: Based on the shortage risk index, the electronic components are classified into a high-risk area, a medium-risk area and a low-risk area; For the electronic components in the high-risk area, a supplier qualification rating standard is established, wherein the supplier qualification rating standard comprises a financial condition score, a production capacity scale score, a historical credit score and a production capacity utilization rate; Based on the supplier qualification rating standard, the suppliers are sorted, and high-quality suppliers are screened out; A genetic algorithm is used to multi-objectively optimize the purchase quota of the high-quality suppliers to generate a purchase quota scheme Y; For the electronic components in the medium-risk area and the low-risk area, a purchase quota scheme X is generated according to a preset strategy; Based on the purchase quota scheme Y and the purchase quota scheme X, a supplier purchase benchmark quota is set, a dynamic adjustment mechanism is established, and the quota allocation is corrected in real time through periodic risk index evaluation results to realize intelligent management of the electronic component supply chain.

3. The electronic component supply chain intelligent management method of claim 2, wherein: The electronic component risk level classification comprises the following steps: When the out-of-stock risk index of an electronic component is greater than a first threshold value and the capacity utilization rate exceeds a second threshold value, the electronic component is included in a temporary observation list, and key indicators of the electronic component in the temporary observation list are dynamically monitored for three consecutive monitoring periods, wherein the key indicators include supplier quotation fluctuation, supplier inventory, and market demand growth rate; If the supplier quotation fluctuation amplitude exceeds a third threshold value, or the supplier inventory is lower than a fourth threshold value and the market demand growth rate exceeds a fifth threshold value, the electronic component is classified into a high-risk area; If the number of alternative suppliers of the electronic component in the high-risk area is higher than a sixth threshold value and the supplier concentration index is lower than a seventh threshold value, a risk degradation assessment is triggered; When the market supply-demand ratio is greater than an eighth threshold value during the degradation assessment and there is no abnormal fluctuation in the consecutive monitoring periods, the electronic component is adjusted to a medium-risk area; When the supplier performance rate of the electronic component in the medium-risk area exceeds a ninth threshold value and the inventory turnover rate is lower than a tenth threshold value, the electronic component is classified into a low-risk area; If a product of a supplier enters the high-risk area, the risk level of the associated product is automatically increased by one level.

4. The electronic component supply chain intelligent management method of claim 1, wherein: The method for constructing the risk assessment model is, The deep neural network architecture is built, wherein the deep neural network architecture includes an input layer, a feature extraction layer, a risk quantification layer, and an output layer; the feature extraction layer is provided with an alternating structure of multiple convolution layers and pooling layers; A first neuron group is set in the input layer, wherein the first neuron group corresponds to the input interfaces of the supplier delivery cycle feature, the component life cycle feature, and the demand prediction feature; A sliding convolution kernel is set in the convolution layer of the feature extraction layer, wherein the sliding convolution kernel performs nonlinear transformation on the input features to extract multi-scale feature information; In the pooling layer of the feature extraction layer, a max-pooling operation is adopted to reduce the feature dimension and retain the features; A second neuron group is set in the risk quantification layer, wherein the second neuron group combines and allocates weights to the extracted feature information through a fully connected layer; A third neuron group is set in the output layer, wherein the third neuron group adopts a Softmax activation function to probabilistically output the risk level; A batch normalization layer is set to standardize the outputs of the feature extraction layer and the risk quantification layer; A residual connection structure is adopted to establish a jump connection between the convolution blocks of the feature extraction layer, thereby relieving the gradient vanishing problem and completing the establishment of the risk assessment model.

5. The electronic component supply chain intelligent management method of claim 1, wherein: The method for generating the demand prediction result is, Real-time market transaction data is divided into a training set, a validation set, and a test set according to a preset proportion by using a sequence segmentation method; A long short-term memory network model is constructed to capture the long-term dependency of electronic component procurement through a gating mechanism; A gradient boosting tree model is constructed to model the nonlinear demand pattern of electronic components through a decision tree ensemble method, and the prediction accuracy is improved through iterative fitting of residuals; A stacking ensemble method is used to weight and fuse the outputs of the long short-term memory network model and the gradient boosting tree model to form a demand prediction model; The hyperparameters of the demand prediction model are automatically tuned based on a Bayesian optimization algorithm, and the model performance is optimized on the validation set through cross-validation; The test set is input into the tuned demand prediction model, and the demand prediction result of the electronic component is generated by combining the safety inventory level and market fluctuation factors.

6. The electronic component supply chain intelligent management method of claim 5, wherein: The method for collecting real-time market transaction data is, A plurality of electronic component trading platforms are connected through a market data collection interface to establish a data collection channel and collect real-time market transaction data of electronic components; The real-time market transaction data is classified and stored according to data types to form historical procurement data, historical inventory data, supplier delivery cycle data, and component lifecycle data; A distributed data processing framework is used to clean the real-time market transaction data, and a time series feature extraction module is established to decompose the historical procurement data and the historical inventory data into trend items, periodic items, and random items; A supplier portrait model is constructed to quantitatively calculate the indicators of delivery time, delivery accuracy, and delivery quality in the supplier delivery cycle data; The component lifecycle data is set with a lifecycle status label, which includes production period, mature period, recession period, and pre-warning period of production stop; The processed real-time market transaction data is stored in a distributed database and indexed by timestamp.

7. An electronic component supply chain intelligent management system based on the electronic component supply chain intelligent management method according to any one of claims 1 to 6, characterized in that: It comprises, A collection module for collecting real-time market transaction data of electronic components, wherein the real-time market transaction data includes historical procurement data, historical inventory data, supplier delivery cycle data, and component lifecycle data; A demand prediction module for constructing a demand prediction model of electronic components based on the historical procurement data and the historical inventory data to generate a demand prediction result; A shortage risk assessment module for inputting the demand prediction result into a risk assessment model based on the supplier delivery cycle data and the component lifecycle data, and outputting a shortage risk index through a fuzzy comprehensive evaluation method; A division management module for dividing electronic components into risk levels according to the shortage risk index, generating a supplier procurement quota scheme, and realizing intelligent management of the electronic component supply chain.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that: The processor executes the computer program to realize the steps of the electronic component supply chain intelligent management method of any one of claims 1-6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the electronic component supply chain intelligent management method of any one of claims 1-6.

Images