Supply and demand distribution determination method and device, electronic equipment and storage medium

Abstract

The invention provides a supply and demand distribution determination method and device, electronic equipment and a storage medium. The method comprises the following steps: firstly, according to a collection and sales data set, constructing a network atlas taking suppliers and purchasers as nodes; then, according to the network atlas, determining a collection and sales data set of nodes associated with the target node; determining influence parameters according to the acquisition and sales data set of the nodes associated with the target node; and finally, determining the supply and demand distribution state of the target node according to the influence parameters and the acquisition and sales data corresponding to the target node. It can be understood that the supply and demand distribution state of the target node can be predicted more accurately by integrating the multi-node data and the quantitative influence parameters, the problems of scattered collection and sale data and incomplete features are effectively solved, and the prediction precision of the supply and demand distribution is remarkably improved.

Description

Technical Field

[0001] This application relates to the technical field of supply chain, and particularly to a method, device, electronic device and storage medium for determining supply and demand distribution. Background Art

[0002] The supply and demand distribution specifically includes the purchaser demand distribution and the supplier supply distribution. Among them, the purchaser demand distribution represents the distribution degree of purchases made by purchasers from different suppliers; the supplier supply distribution represents the distribution degree of sales made by suppliers to different purchasers.

[0003] In the supply chain management of the railway industry, accurately determining the supply and demand distribution is a key link to ensure stable material supply, reduce operating costs, and improve resource allocation efficiency. In the related art, based on the quantity of goods purchased by purchasers / the quantity of goods supplied by suppliers, the supply and demand distribution of purchasers / suppliers can be predicted.

[0004] However, since the purchase and sales data are distributed at multiple nodes in the procurement process and no complete set of characteristic factors is formed to accurately predict the actual supply and demand distribution situation, and there is a lack of unified integration, the accuracy of the predicted supply and demand distribution is relatively low.

[0005] It should be noted that the information disclosed in the background art part of this application is only intended to deepen the understanding of the general background art of this application, and should not be regarded as an admission or any form of suggestion that this information constitutes the prior art known to those skilled in the art. Summary of the Invention

[0006] In view of this, this application provides a method, device, electronic device and storage medium for determining supply and demand distribution, which is conducive to solving the problem in the prior art that since the purchase and sales data are distributed at multiple nodes in the procurement process and no complete set of characteristic factors is formed to accurately predict the actual supply and demand distribution situation, and there is a lack of unified integration, the accuracy of the predicted supply and demand distribution is relatively low.

[0007] In a first aspect, an embodiment of this application provides a method for determining supply and demand distribution, including: Construct a network graph with suppliers and purchasers as nodes according to the purchase and sales data set, where the purchase and sales data set includes the purchase data of each purchaser and the sales data of each supplier, and the network graph is used to represent the purchase and sales relationship between the supplier and the purchaser; Determine the purchase and sales data set of the nodes associated with the target node according to the network graph, where the target node is a target supplier or a target purchaser; Determine an influence parameter according to the collection of procurement and sales data of the nodes associated with the target node, where the influence parameter is used to characterize the influence of the nodes associated with the target node on the supply and demand distribution of the target node; Determine the supply and demand distribution state of the target node according to the influence parameter and the procurement and sales data corresponding to the target node, where the supply and demand distribution state includes concentrated distribution, moderate distribution, and dispersed distribution.

[0008] In the embodiments of the present application, first, construct a network graph with suppliers and purchasers as nodes according to the collection of procurement and sales data; then, determine the collection of procurement and sales data of the nodes associated with the target node according to the network graph; then, determine the influence parameter according to the collection of procurement and sales data of the nodes associated with the target node; finally, determine the supply and demand distribution state of the target node according to the influence parameter and the procurement and sales data corresponding to the target node. It can be understood that by integrating multi-node data and quantifying the influence parameter, the supply and demand distribution state of the target node can be predicted more accurately, effectively solving the problems of scattered procurement and sales data and incomplete features, and significantly improving the prediction accuracy of the supply and demand distribution.

[0009] In a possible implementation manner, the determining the supply and demand distribution state of the target node according to the influence parameter and the procurement and sales data corresponding to the target node includes: Determine the corrected procurement and sales data corresponding to the target node according to the influence parameter and the procurement and sales data corresponding to the target node; Determine the supply and demand distribution state of the target node according to the corrected procurement and sales data.

[0010] In the embodiments of the present application, first, determine the corrected procurement and sales data corresponding to the target node according to the influence parameter and the procurement and sales data corresponding to the target node; then, determine the supply and demand distribution state of the target node according to the corrected procurement and sales data. It can be understood that by combining the influence parameter with the original procurement and sales data of the target node, the original procurement and sales data is dynamically adjusted to restore the real supply and demand trend, significantly improving the accuracy of the determination of the supply and demand distribution state; at the same time, first determining the corrected procurement and sales data corresponding to the target node further refines the determination logic of the supply and demand distribution state, which is beneficial to the iterative update of the relevant model.

[0011] In a possible implementation manner, the determining the supply and demand distribution state of the target node according to the corrected procurement and sales data includes: Input the corrected procurement and sales data into a supply and demand distribution state prediction model, and output the supply and demand distribution state corresponding to the target node.

[0012] In the embodiments of the present application, the corrected procurement and sales data is input into the supply and demand distribution state prediction model, and the supply and demand distribution state corresponding to the target node is output. It can be understood that directly determining the supply and demand distribution state corresponding to the target node according to the supply and demand distribution state prediction model can achieve higher-precision and faster supply and demand prediction.

[0013] In a possible implementation manner, determining the supply and demand distribution state of the target node according to the corrected procurement and sales data includes: Determining the supply and demand distribution index of the target node according to the corrected procurement and sales data; Determining the supply and demand distribution state of the target node according to the supply and demand distribution index of the target node.

[0014] In the embodiments of the present application, first, the supply and demand distribution index of the target node is determined according to the corrected procurement and sales data; then, the supply and demand distribution state of the target node is determined according to the supply and demand distribution index of the target node. It can be understood that by introducing the supply and demand distribution index, the quantitative evaluation and dynamic classification of the supply and demand distribution state are realized, significantly improving the objectivity and operability of the prediction results. Its technical effects are not only reflected in accurate classification and risk control, but also support decision-making optimization in complex business scenarios through quantitative indicators, providing more efficient and transparent technical support for supply chain management.

[0015] In a possible implementation manner, determining the supply and demand distribution state of the target node according to the supply and demand distribution index of the target node includes: Normalizing the supply and demand distribution index of the target node to obtain the normalized supply and demand distribution index; When the normalized supply and demand distribution index matches the first preset interval, the supply and demand distribution state of the target node is concentrated distribution; When the normalized supply and demand distribution index matches the second preset interval, the supply and demand distribution state of the target node is moderate distribution; When the normalized supply and demand distribution index matches the third preset interval, the supply and demand distribution state of the target node is dispersed distribution; Wherein, the maximum value in the first preset interval is less than the minimum value in the second preset interval; the maximum value in the second preset interval is less than the minimum value in the third preset interval.

[0016] In the embodiments of the present application, the supply-demand distribution index of the target node is normalized to obtain the normalized supply-demand distribution index; when the normalized supply-demand distribution index matches the first preset interval, the supply-demand distribution state of the target node is concentrated distribution; when the normalized supply-demand distribution index matches the second preset interval, the supply-demand distribution state of the target node is moderate distribution; when the normalized supply-demand distribution index matches the third preset interval, the supply-demand distribution state of the target node is dispersed distribution. It can be understood that through normalization processing and preset interval division, the standardized classification of the supply-demand distribution state is realized, significantly improving the fairness of the classification result. Its technical effects are not only reflected in cross-node comparability and dynamic adaptability, but also provide refined and scenario-based supply chain management support for the procurement and sales platform through clear classification boundaries and threshold configurability.

[0017] In a possible implementation manner, before constructing a network graph with suppliers and purchasers as nodes according to the procurement and sales data set, it includes: Obtain the procurement and sales data set within a preset time.

[0018] In the embodiments of the present application, before constructing a network graph with suppliers and purchasers as nodes according to the procurement and sales data set, first obtain the procurement and sales data set within a preset time. It can be understood that it ensures timeliness, quality, and scenario adaptability from the data source, provides a high-value data basis for subsequent network graph construction and supply-demand distribution prediction, and further ensures that the supply-demand distribution state of the finally determined target node is more accurate.

[0019] In a possible implementation manner, the obtaining the procurement and sales data set within a preset time includes: Obtain the original procurement and sales data set within a preset time; Perform data preprocessing on the original procurement and sales data set to determine the procurement and sales data set.

[0020] In the embodiments of the present application, first obtain the original procurement and sales data set within a preset time; then perform data preprocessing on the original procurement and sales data set to determine the procurement and sales data set. It can be understood that by performing data preprocessing on the original procurement and sales data set, it provides a highly reliable data basis for subsequent network graph construction, influence parameter calculation, and supply-demand distribution prediction, and further ensures that the supply-demand distribution state of the finally determined target node is more accurate.

[0021] In a second aspect, the present application provides a supply-demand distribution determination device, including: A network graph construction module, configured to construct a network graph with suppliers and purchasers as nodes according to a purchase and sales data set, where the purchase and sales data set includes the purchase data of each purchaser and the sales data of each supplier, and the network graph is used to represent the purchase and sales relationship between the suppliers and the purchasers; A purchase and sales data set determination module, configured to determine a purchase and sales data set of nodes associated with a target node according to the network graph, where the target node is a target supplier or a target purchaser; An influence parameter determination module, configured to determine an influence parameter according to the purchase and sales data set of nodes associated with the target node, where the influence parameter is used to represent the influence of the nodes associated with the target node on the supply and demand distribution of the target node; A supply and demand distribution state determination module, configured to determine the supply and demand distribution state of the target node according to the influence parameter and the purchase and sales data corresponding to the target node, where the supply and demand distribution state includes concentrated distribution, moderate distribution, and dispersed distribution.

[0022] In a third aspect, an embodiment of the present application provides an image forming apparatus, including: A processor; A memory; And a computer program, where the computer program is stored in the memory, and the computer program includes instructions that, when executed by the processor, cause the electronic device to execute the method according to any one of the first aspect.

[0023] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium includes a stored program, and when the program runs, it controls a device where the computer-readable storage medium is located to execute the method according to any one of the first aspect.

[0024] It can be understood that the supply and demand distribution determination device provided in the second aspect, the electronic device provided in the third aspect, and the computer-readable storage medium provided in the fourth aspect are all used to execute the method provided by the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1Schematic flowchart of a supply and demand distribution determination method provided by an embodiment of the present application.

[0027] Figure 2 Schematic diagram of a supplier and purchaser network map provided by the present application.

[0028] Figure 3 Schematic diagram of another supplier and purchaser network map provided by the present application.

[0029] Figure 4 Schematic diagram of the mechanism of a supply and demand distribution determination device provided by an embodiment of the present application.

[0030] Figure 5 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0031] For a better understanding of the technical solution of the present application, the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0032] It should be clear that the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the scope of protection of the present application.

[0033] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms of "a", "the" and "said" used in the embodiments of the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0034] It should be understood that the term " / and / " used herein is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after.

[0035] The National Railway General Material Procurement Platform, also known as the National Railway Mall, provides a procurement trading platform with railway characteristics for railway internal purchasers. Since the operation of the mall, the purchasers' procurement demands and the services and goods provided by suppliers have shown a diversified development trend. Finding the fit point between purchasers and suppliers, ensuring that production capacity matches market demand, and maintaining a healthy purchasing and sales relationship have become key topics for the development of the mall.

[0036] In the supply chain management of the railway industry, accurately determining the supply and demand distribution is a key link to ensure stable material supply, reduce operating costs, and improve the efficiency of resource allocation. In other words, accurately determining the supply and demand distribution is not only a key means to optimize resource allocation, but also an important support for promoting the digital transformation of the railway industry and improving the overall operating efficiency.

[0037] For the sake of easy understanding, this application first introduces the supply and demand distribution. First of all, the supply and demand distribution specifically includes the purchaser demand distribution and the supplier supply distribution. Among them, the purchaser demand distribution represents the distribution degree of purchasers' purchases from different suppliers; the supplier supply distribution represents the distribution degree of suppliers' sales to different purchasers.

[0038] In the related art, based on the quantity of goods purchased by the purchaser / the quantity of goods supplied by the supplier, the supply and demand distribution of the purchaser / supplier can be predicted.

[0039] However, since the purchase and sales data are distributed at multiple nodes in the procurement process and no complete set of characteristic factors is formed to accurately predict the actual supply and demand distribution situation, and there is a lack of unified integration, the accuracy of the predicted supply and demand distribution is relatively low.

[0040] To address the above problems, in the embodiments of this application, first, according to the purchase and sales data set, a network graph with suppliers and purchasers as nodes is constructed; then, according to the network graph, the purchase and sales data set of the nodes associated with the target node is determined; then, according to the purchase and sales data set of the nodes associated with the target node, the influence parameters are determined; finally, according to the influence parameters and the purchase and sales data corresponding to the target node, the supply and demand distribution status of the target node is determined. It can be understood that by integrating multi-node data and quantifying the influence parameters, the supply and demand distribution status of the target node can be predicted more accurately, effectively solving the problems of scattered purchase and sales data and incomplete characteristics, and significantly improving the prediction accuracy of the supply and demand distribution.

[0041] Specifically, refer to Figure 1 , which is a schematic flow chart of a method for determining supply and demand distribution provided by the embodiments of this application. As Figure 1 shown, it mainly includes the following steps.

[0042] Step S101: According to the purchase and sales data set, construct a network graph with suppliers and purchasers as nodes.

[0043] In the embodiments of this application, first, according to the purchase and sales data set, a network graph with suppliers and purchasers as nodes is constructed. Among them, the purchase and sales data set includes the purchase data of each purchaser and the sales data of each supplier.

[0044] It is understandable that the procurement and sales data set can be divided into a procurement data set and a sales data set. Among them, the procurement data set is used to represent the procurement data of each purchaser; the sales data set is used to represent the sales data of each supplier.

[0045] For the convenience of understanding, the procurement data set and the sales data set will be introduced separately in the following text.

[0046] Procurement data set: In practical applications, in order to cover all the behaviors of purchasers, in a possible implementation, the procurement data set is specifically a set of the procurement data of each purchaser. And the procurement data of each purchaser can include three parts of data. The first part is the basic data information such as the purchase orders, bulk purchase orders, and after-sales orders generated when the purchaser makes purchases in the mall. The second part is the transaction information derived from the above basic data information. The third part is the violation information that occurs during the purchaser's procurement process.

[0047] Specifically, in a possible implementation, the first part of the data specifically includes: the total amount of purchase orders, the total quantity of purchase orders, the total amount of bulk purchase orders, the quantity of bulk purchase orders, the number of suppliers involved, the total number of purchased goods, the total amount of after-sales orders, and the quantity of after-sales orders. Among them, the purchase order and the bulk purchase order are distinguished according to the quantity of purchased goods. When the quantity of purchased goods is greater than the preset quantity of goods, the purchase order is a bulk purchase order.

[0048] In a possible implementation, the second part of the data specifically includes: the average daily purchase amount, the average daily number of purchase orders, the average daily bulk purchase amount, the average daily number of bulk purchase orders, and the average daily number of purchased goods.

[0049] To ensure that purchasers can buy high-quality and low-price goods, a price comparison function is provided. However, due to some reasons, goods with prices exceeding the lowest price across the network are still purchased. Therefore, in a possible implementation, the third part includes: the total amount of the purchased premium goods and the total number of purchase orders for the purchased premium goods.

[0050] Sales data set: In practical applications, in order to cover all the behaviors of suppliers, in a possible implementation, the sales data set is specifically a set of the sales data of each supplier. And the sales data of each supplier can include three parts of data. The first part is the basic data information such as the purchase orders, bulk purchase orders, and after-sales orders received by the supplier in the mall. The second part is the transaction information derived from the above basic information. The third part is the violation information that occurs during the supplier's sales process.

[0051] Specifically, in a possible implementation, the first part of the data specifically includes: the total amount of purchase orders received by the supplier, the total number of purchase orders, the total amount of bulk purchases, the number of bulk purchase orders, the number of purchasers involved, the total number of sold goods, the total amount of after-sales orders, and the number of after-sales orders.

[0052] In a possible implementation, the second part of the data specifically includes: the average daily sales amount, the average daily number of received purchase orders, the average daily amount of bulk purchases, the average daily number of bulk purchase orders, and the average daily number of sold goods. The third part of the data specifically includes: the total amount of the premium goods sold by the supplier and the total number of purchase orders for the premium goods sold by the supplier.

[0053] In the embodiment of the present application, the network graph described above is used to represent the purchase and sales relationship between the supplier and the purchaser. For ease of understanding, refer to Figure 2 , which is a schematic diagram of a network graph of a supplier and a purchaser provided by the present application. As shown in the figure, the figure shows a network graph including five nodes: Supplier A, Supplier B, Supplier C, Purchaser A, and Purchaser B. Among them, the connection line between the supplier and the purchaser is used to represent the existence of a purchase and sales relationship between the supplier and the purchaser. It can be understood that Figure 2 Purchaser B has no purchase and sales relationship with Supplier A and Supplier B.

[0054] It can be understood that by taking the supplier and the purchaser as nodes and using the purchase and sales relationship as the edge, a complete network graph is formed, realizing the unified integration of the purchase and sales data of multiple nodes scattered in the purchase process. This integration method can comprehensively capture the complex relationship between the supplier and the purchaser and provide a data basis for subsequent analysis.

[0055] In a possible implementation, the purchase and sales data set corresponding to each node is incorporated into each node. It can be understood that in practical applications, by extracting the purchase and sales data of the nodes associated with the target node, a complete set of characteristic factors can be formed, solving the problems of data isolation and incomplete features in traditional methods and providing data support for accurate prediction.

[0056] In a possible implementation, before constructing a network graph with the supplier and the purchaser as nodes according to the purchase and sales data set, it is also necessary to first obtain the purchase and sales data set within a preset time.

[0057] It can be understood that by setting a preset time range, the purchase and sales data highly relevant to the current market environment is screened out, avoiding the interference of outdated information in historical data on prediction.

[0058] Specifically, in a possible implementation, the preset time range can be designed as a rolling window to ensure that the model is dynamically updated with market changes. Exemplarily, the data of the most recent 12 months is always retained. After adding new data each month, the data of the earliest month is automatically removed to maintain the timeliness of the prediction results.

[0059] In the embodiments of the present application, the collection of purchase and sales data within the preset time is obtained, ensuring timeliness, quality, and scenario adaptability from the data source, providing a high-value data basis for subsequent network graph construction and supply and demand distribution prediction, and thus ensuring that the supply and demand distribution status of the finally determined target node is more accurate.

[0060] Of course, in actual applications, those skilled in the relevant art in this field can also pre-store the collection of purchase and sales data in the relevant controller, and the present application does not make specific limitations on this.

[0061] Further, in a possible implementation, first, the original collection of purchase and sales data within the preset time is obtained; then, data preprocessing is performed on the original collection of purchase and sales data to determine the collection of purchase and sales data.

[0062] Specifically, in a possible implementation, the data preprocessing of the original collection of purchase and sales data includes removing outliers, duplicate records, or missing fields in the original data. For example, the supplier sales amount may include test orders or negative values entered incorrectly, and the preprocessing can automatically identify and correct them.

[0063] In a possible implementation, the data preprocessing of the original collection of purchase and sales data includes standardizing the scattered original data (such as the order number rules of different suppliers and the units of purchase amounts) into a unified format to ensure compatibility for subsequent analysis. For example, unifying "ten thousand yuan" and "yuan" into the same unit to avoid calculation deviations.

[0064] Of course, the data preprocessing of the original collection of purchase and sales data can also include filling in missing values and correcting contradictory data (such as a purchase quantity of 100 but an amount of 0), etc., and the present application does not make specific limitations on this.

[0065] In the embodiments of the present application, by performing data preprocessing on the original collection of purchase and sales data, a highly reliable data basis is provided for subsequent network graph construction, impact parameter calculation, and supply and demand distribution prediction, and thus ensuring that the supply and demand distribution status of the finally determined target node is more accurate. Step S102: According to the network graph, determine the collection of purchase and sales data of the nodes associated with the target node.

[0066] In the embodiments of the present application, after the network graph is constructed, according to the network graph, determine the collection of purchase and sales data of the nodes associated with the target node.

[0067] For ease of understanding, refer to Figure 3 , which is a schematic diagram of another network map of suppliers and purchasers provided by this application. As shown in the figure, a network map with 7 nodes including Supplier A, Supplier B, Supplier C, Supplier D, Purchaser A, Purchaser B, and Purchaser C is shown. Among them, the connection lines between suppliers and purchasers are used to represent the purchase and sales relationships between suppliers and purchasers.

[0068] Exemplarily, when the target node is Purchaser A, according to the network map, the nodes associated with the target node are determined to be Supplier A, Supplier B, and Supplier C, that is, the sales data sets corresponding to Supplier A, Supplier B, and Supplier C are determined; similarly, when the target node is Supplier C, the nodes associated with the target node are determined to be Purchaser A, Purchaser B, and Purchaser C, that is, the sales data sets corresponding to Purchaser A, Purchaser B, and Purchaser C are determined.

[0069] Step S103: Determine the influence parameters according to the purchase and sales data sets of the nodes associated with the target node.

[0070] In the embodiment of this application, after determining the purchase and sales data sets of the nodes associated with the target node, the influence parameters are determined according to the purchase and sales data sets of the nodes associated with the target node.

[0071] It can be understood that by analyzing the purchase and sales data of the nodes associated with the target node and determining the influence parameters, the influence of these nodes on the supply and demand distribution of the target node can be quantified.

[0072] Specifically, in a possible implementation manner, the purchase data set or the sales data set corresponding to the nodes associated with the target node is combined into a matrix. Exemplarily, the feature set of the purchaser is , where is the purchase data set described above.

[0073] Refer to Figure 3 , when the target node is Purchaser A, first, it is necessary to determine the feature sets of Purchaser A, Supplier A, Supplier B, and Supplier C; then, according to Formula (1) and Formula (2) , the influence parameters of node to node can be determined, that is . Among them, in Formula (1) is the shared parameter of the purchase and sales relationship network for feature enhancement; is the attention mechanism number, and the function of Formula (1) is to splice two matrices and map the spliced result to a real number. is an activation function. For non - negative input values, it directly outputs the value. For negative input values, the output of the function is zero.

[0074] Step S104: Determine the supply - demand distribution state of the target node according to the influence parameter and the procurement and sales data corresponding to the target node.

[0075] In the embodiment of the present application, the supply - demand distribution state of the target node is determined according to the influence parameter and the procurement and sales data corresponding to the target node. Among them, the supply - demand distribution state includes concentrated distribution, moderate distribution, and dispersed distribution.

[0076] It can be understood that classifying the supply - demand distribution state into three categories of "concentrated distribution", "moderate distribution", and "dispersed distribution" according to the influence parameter and the procurement and sales data of the target node can intuitively reflect the actual distribution of the supply - demand relationship and provide a clear basis for decision - making.

[0077] It can be understood that purchasers can optimize procurement policies according to the supply - demand distribution state. For the supply - demand state of "concentrated distribution", more suppliers can be introduced to reduce risks. For the state of "dispersed distribution", purchasers can give priority to key suppliers to ensure stable supply. Suppliers can adjust sales strategies according to the supply - demand distribution state. For example, increase the supply in the "concentrated distribution" area and explore new markets in the "dispersed distribution" area.

[0078] In a possible implementation manner, first, according to the influence parameter and the procurement and sales data corresponding to the target node, determine the corrected procurement and sales data corresponding to the target node; then, according to the corrected procurement and sales data, determine the supply - demand distribution state of the target node.

[0079] Specifically, by combining the influence parameter with the original procurement and sales data of the target node, the original data is dynamically adjusted. For example, if the sales data of a certain supplier shows a short - term anomaly due to unexpected events (such as logistics delays), the correction link can eliminate noise and restore the true supply - demand trend.

[0080] Specifically, in a possible implementation manner, according to formula (3) the corrected procurement and sales data can be determined. Among them, in formula (3) represents the corrected procurement and sales data after the feature fusion of the target node and its surrounding associated nodes; represents the node to node of the influence parameter; is an activation function; is the shared parameter of the procurement and sales relationship network for feature enhancement; is the total number of influence parameters, and the mean value of multiple influence parameters is taken in the formula.

[0081] In the embodiments of the present application, by combining the influencing parameters with the original procurement and sales data of the target node, the original procurement and sales data is dynamically adjusted to restore the true supply and demand trend, significantly improving the accuracy of the determination of the supply and demand distribution state; at the same time, the corrected procurement and sales data corresponding to the target node is first determined, further refining the determination logic of the supply and demand distribution state, which is beneficial to the iterative update of related models.

[0082] In a possible implementation manner, the corrected procurement and sales data is input into the supply and demand distribution state prediction model, and the supply and demand distribution state corresponding to the target node is output. It can be understood that directly determining the supply and demand distribution state corresponding to the target node according to the supply and demand distribution state prediction model can achieve higher-precision and faster supply and demand prediction.

[0083] Of course, in a possible implementation manner, a model that can directly determine the supply and demand distribution state corresponding to the target node can be trained according to relevant algorithms based on the specific derivation process of steps S101 - S104.

[0084] Specifically, first, the supply and demand distribution state corresponding to each node is calculated according to the historical procurement and sales data set. Then, the historical procurement and sales data set and the corresponding supply and demand distribution state are used as the training set and input into the model to train the model. Specifically, for each node in the constructed network graph, calculations are performed according to the above steps S101 - S104, and the relevant parameters of the model are continuously updated according to the iterative prediction results.

[0085] In a possible implementation manner, first, according to the corrected procurement and sales data, the supply and demand distribution index of the target node is determined; then, according to the supply and demand distribution index of the target node, the supply and demand distribution state of the target node is determined.

[0086] It can be understood that by converting the supply and demand distribution state into a numerical "supply and demand distribution index", the concentration or dispersion degree of the supply and demand relationship can be measured more precisely, avoiding the deviation caused by relying on subjective experience or qualitative description in traditional methods. For example, the index can be calculated based on the corrected procurement and sales data, comprehensively reflecting dimensions such as the supply and demand intensity and stability between suppliers and purchasers.

[0087] Specifically, in a possible implementation manner, the supply and demand distribution can be determined according to the concept of information entropy. It can be understood that information entropy is used to measure the uncertainty of the entire probability distribution, and the formula is: , where P(x) is the probability of event x occurring, and the surprise degree is used to represent the unexpected degree of event x. Therefore, multiplying the probability by the surprise degree can be understood as the contribution of a certain event to the overall uncertainty.

[0088] Exemplarily, high probability × low surprise: The event is common and as expected, with low importance. For example, the sun rises on a sunny day. Low probability × high surprise: The event is rare and unexpected, with high importance. For example, it suddenly hails on a sunny day. Therefore, probability multiplied by surprise can be used to measure the contribution of an event to the overall uncertainty or importance.

[0089] According to the above principle, in one possible way, the demand distribution index of the purchaser is In this index, is the quantity of goods purchased by the purchaser from the th supplier, and is the total quantity of purchased goods. Similarly, for the supplier supply distribution index: . In this index, is the quantity of goods sold by the supplier to the th purchaser, and is the total quantity of sold goods.

[0090] It can be understood that the smaller the above index, the more concentrated the suppliers with which the purchaser has a purchasing relationship or the sales targets of the supplier are; on the contrary, the larger the index, the more dispersed the suppliers with which the purchaser has a purchasing relationship or the sales targets of the supplier are.

[0091] In the embodiments of the present application, by introducing the supply-demand distribution index, the quantitative evaluation and dynamic classification of the supply-demand distribution state are realized, significantly improving the objectivity and operability of the prediction results. Its technical effects are not only reflected in accurate classification and risk control, but also support decision-making optimization in complex business scenarios through quantitative indicators, providing more efficient and transparent technical support for supply chain management.

[0092] In one possible implementation, the supply-demand distribution index of the target node is normalized to obtain the normalized supply-demand distribution index; when the normalized supply-demand distribution index matches the first preset interval, the supply-demand distribution state of the target node is concentrated distribution; when the normalized supply-demand distribution index matches the second preset interval, the supply-demand distribution state of the target node is moderate distribution; when the normalized supply-demand distribution index matches the third preset interval, the supply-demand distribution state of the target node is dispersed distribution. Among them, the maximum value in the first preset interval is less than the minimum value in the second preset interval; the maximum value in the second preset interval is less than the minimum value in the third preset interval.

[0093] It is understandable that the normalization process converts the supply-demand distribution indices of different nodes into a unified dimension (such as the range of 0-1), eliminates the biases caused by different data scales (such as procurement amount, number of suppliers), and makes the supply-demand states between different nodes comparable. For example, after normalization, the supply-demand distribution indices of small suppliers and large suppliers can be evaluated for their concentration or dispersion under the same standard.

[0094] Normalization ensures that the classification results are not affected by the absolute values of the original data. For example, in a remote area where the procurement volume is low but the supply-demand relationship is concentrated, its normalized index may be higher than that of a first-tier city node with a high procurement volume but a dispersed distribution.

[0095] Exemplarily, the first preset interval is , the second preset interval is , the third preset interval is , when the supply-demand distribution index after normalization is 0.23, the supply-demand distribution index after normalization matches the first preset interval, and at this time, the supply-demand distribution state of the target node is concentrated distribution; similarly, when the supply-demand distribution index after normalization is 0.9, the supply-demand distribution index after normalization matches the third preset interval, and at this time, the supply-demand distribution state of the target node is dispersed distribution.

[0096] In a possible implementation manner, the interval threshold can be dynamically adjusted according to market environment or policy changes. For example, during the peak season of the railway industry (such as the Spring Festival travel rush), the "concentrated distribution" threshold is temporarily increased to cope with sudden demand fluctuations.

[0097] In the embodiments of the present application, through normalization processing and preset interval division, the standardized classification of the supply-demand distribution state is realized, significantly improving the fairness of the classification results. Its technical effects are not only reflected in cross-node comparability and dynamic adaptability, but also provide refined and scenario-based supply chain management support for the procurement and sales platform through clear classification boundaries and threshold configurability.

[0098] In the embodiments of the present application, first, according to the procurement and sales data set, a network graph with suppliers and purchasers as nodes is constructed; then, according to the network graph, the procurement and sales data set of the nodes associated with the target node is determined; then, according to the procurement and sales data set of the nodes associated with the target node, the influence parameters are determined; finally, according to the influence parameters and the procurement and sales data corresponding to the target node, the supply-demand distribution state of the target node is determined. It is understandable that by integrating multi-node data and quantifying the influence parameters, the supply-demand distribution state of the target node can be predicted more accurately, effectively solving the problems of scattered procurement and sales data and incomplete features, and significantly improving the prediction accuracy of the supply-demand distribution.

[0099] In a possible implementation, this technical solution is not only applicable to the mall in the railway industry, but can also be extended to the supply chain management of other industries, such as retail, manufacturing, logistics, etc. This application does not make specific restrictions on this.

[0100] In a possible implementation, by combining artificial intelligence and machine learning algorithms, the construction of the network graph and the calculation of influence parameters can be further optimized to achieve a higher-precision supply-demand prediction. This application does not make specific restrictions on this.

[0101] Corresponding to the above embodiments, this application also provides a supply-demand distribution determination device. Specifically, refer to Figure 4 , which is a schematic diagram of the mechanism of a supply-demand distribution determination device provided by an embodiment of this application. As shown in the figure, the supply-demand distribution determination device 400 is shown in the figure. Among them, the supply-demand distribution determination device 400 specifically includes: a network graph construction module 401, a purchase and sales data set determination module 402, an influence parameter determination module 403, and a supply-demand distribution status determination module 404. Specifically, the network graph construction module 401 is used to construct a network graph with suppliers and purchasers as nodes according to the purchase and sales data set; the purchase and sales data set determination module 402 is used to determine the purchase and sales data set of the nodes associated with the target node according to the network graph; the influence parameter determination module 403 is used to determine the influence parameter according to the purchase and sales data set of the nodes associated with the target node; the supply-demand distribution status determination module 404 is used to determine the supply-demand distribution status of the target node according to the influence parameter and the purchase and sales data corresponding to the target node.

[0102] It can be understood that the specific functions of the supply-demand distribution determination device can refer to the method embodiments described above. For the sake of brevity of expression, this application does not elaborate here.

[0103] Corresponding to the above embodiments, this application also provides an electronic device. Refer to Figure 5 , which is a schematic diagram of the structure of an electronic device provided by an embodiment of this application. The electronic device 500 may include: a processor 501, a memory 502, and a communication unit 503. These components communicate through one or more buses. Those skilled in the art can understand that the structure of the electronic device shown in the figure does not constitute a limitation on the embodiments of the present invention. It can be a bus structure, a star structure, and may also include more or fewer components than shown in the figure, or combine some components, or different component arrangements.

[0104] Among them, the communication unit 503 is used to establish a communication channel, so that the electronic device can communicate with other devices. Receive user data sent by other devices or send user data to other devices.

[0105] The processor 501 is the control center of the electronic device. It connects various parts of the entire electronic device through various interfaces and circuits, and executes various functions of the electronic device and / or processes data by running or executing software programs, instructions, and / or modules stored in the memory 502, and by invoking the data stored in the memory. The processor may be composed of an integrated circuit (IC). For example, it may be composed of a single packaged IC, or may be composed of multiple packaged ICs with the same or different functions connected together. For example, the processor 501 may include only a central processing unit (CPU). In the embodiments of the present invention, the CPU may be a single-core processor or may include multiple cores.

[0106] The memory 502 is used to store the execution instructions of the processor 501. The memory 502 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disc.

[0107] When the execution instructions in the memory 502 are executed by the processor 501, the electronic device 500 is enabled to execute Figure 1 Some or all of the steps in the illustrated embodiments.

[0108] In a specific implementation, the present application also provides a computer storage medium. Among them, the computer storage medium can store a program, and when the program is executed, it can include some or all of the steps in the embodiments of the simulation scenario generation method provided by the present invention. The storage medium may be a magnetic disk, an optical disc, a read-only memory (ROM), or a random access memory (RAM), etc.

[0109] In a specific implementation, the present application also provides a computer program product. Among them, the computer program product contains executable instructions, and when the executable instructions are executed on a computer, the computer is enabled to execute some or all of the steps in the embodiments of the simulation scenario generation method provided by the present invention.

[0110] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the relationship between associated objects and indicates that there can be three relationships. For example, A and / or B can represent the cases of A existing alone, A and B existing simultaneously, and B existing alone. Here, A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0111] Those of ordinary skill in the art can realize that the various units and algorithm steps described in the embodiments disclosed herein can be implemented by a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0112] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0113] In several embodiments provided by the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM for short), random access memory (RAM for short), magnetic disks, or optical discs that can store program codes.

[0114] For the same or similar parts among the various embodiments in this specification, reference can be made to each other. In particular, for the device embodiments and terminal embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the descriptions in the method embodiments.

Claims

1. A method for determining supply and demand distribution, characterized in that: include: According to the procurement and sales data set, a network graph with suppliers and purchasers as nodes is constructed, wherein the procurement and sales data set includes the procurement data of each purchaser and the sales data of each supplier, and the network graph is used to characterize the procurement and sales relationship between the supplier and the purchaser; Determine, according to the network graph, a set of purchase and sales data of the node associated with a target node, wherein the target node is a target supplier or a target purchaser; Determine an influence parameter according to a set of purchase and sales data of the node associated with the target node, wherein the influence parameter is used to characterize the influence of the node associated with the target node on the supply and demand distribution of the target node; The supply and demand distribution state of the target node is determined according to the influencing parameters and the purchase and sales data corresponding to the target node, and the supply and demand distribution state includes concentrated distribution, moderate distribution and dispersed distribution.

2. The method according to claim 1, characterized in that Determining the supply and demand distribution state of the target node according to the influencing parameter and the purchase and sales data corresponding to the target node includes: Determine the corrected procurement and sales data corresponding to the target node according to the influencing parameter and the procurement and sales data corresponding to the target node; The supply and demand distribution status of the target node is determined based on the corrected procurement and sales data.

3. The method according to claim 2, characterized in that Determining the supply and demand distribution state of the target node according to the corrected procurement and sales data includes: The corrected procurement and sales data is input into a supply and demand distribution state prediction model, and the supply and demand distribution state corresponding to the target node is output.

4. The method according to claim 2, characterized in that: Determining the supply and demand distribution state of the target node according to the corrected procurement and sales data includes: Determining the supply and demand distribution index of the target node according to the corrected procurement and sales data; The supply and demand distribution state of the target node is determined according to the supply and demand distribution index of the target node.

5. The method according to claim 4, characterized in that The determining, according to the supply and demand distribution index of the target node, the supply and demand distribution state of the target node comprises: Normalizing the supply and demand distribution index of the target node to obtain the normalized supply and demand distribution index; When the normalized supply and demand distribution index matches the first preset interval, the supply and demand distribution state of the target node is concentrated distribution; When the normalized supply and demand distribution index matches the second preset interval, the supply and demand distribution state of the target node is moderately distributed; When the normalized supply and demand distribution index matches the third preset interval, the supply and demand distribution state of the target node is dispersed distribution; The maximum value in the first preset interval is smaller than the minimum value in the second preset interval; and the maximum value in the second preset interval is smaller than the minimum value in the third preset interval.

6. The method according to claim 1, characterized in that Before constructing a network graph with suppliers and purchasers as nodes based on the procurement and sales data set, it includes: Get the collection of purchase and sales data within the preset time.

7. The method according to claim 6, characterized in that The step of obtaining a set of purchase and sales data within a preset time period includes: Get the original purchase and sales data set within the preset time; The original procurement and sales data set is subjected to data preprocessing to determine the procurement and sales data set.

8. A supply and demand distribution determination device, characterized in that: include: A network graph construction module, used to construct a network graph with suppliers and purchasers as nodes based on the procurement and sales data set, wherein the procurement and sales data set includes the procurement data of each purchaser and the sales data of each supplier, and the network graph is used to characterize the procurement and sales relationship between the supplier and the purchaser; A procurement and sales data set determination module, used to determine the procurement and sales data set of the node associated with the target node according to the network graph, wherein the target node is a target supplier or a target purchaser; An influence parameter determination module, used to determine an influence parameter according to a set of purchase and sales data of the node associated with the target node, wherein the influence parameter is used to characterize the influence of the node associated with the target node on the supply and demand distribution of the target node; The supply and demand distribution status determination module is used to determine the supply and demand distribution status of the target node according to the influencing parameters and the purchase and sales data corresponding to the target node, and the supply and demand distribution status includes concentrated distribution, moderate distribution and dispersed distribution.

9. An electronic device, characterized in that: include: processor; Memory; And a computer program, wherein the computer program is stored in the memory, and the computer program includes instructions, and when the instructions are executed by the processor, the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

Images