Cross-border e-commerce supply chain data analysis method and system based on artificial intelligence

Abstract

The invention relates to the technical field of cross-border e-commerce supply chains, and discloses a cross-border e-commerce supply chain data analysis method and system based on artificial intelligence. The method has the advantages that the cross-border e-commerce supply chain data analysis method and system based on artificial intelligence are provided, the method is executed by a processor, and the method comprises the steps of obtaining cross-border e-commerce supply chain data; analyzing through an artificial intelligence algorithm to obtain a supply chain analysis result of each type of products; obtaining a product number set, and matching the product number set with the supply chain analysis result to obtain a product number supply chain analysis result; establishing a product supply visual network model; determining main product nodes in the product supply network model according to the product supply visual network model; and determining a product supply route between the target product node and the main product node. According to the method, through an artificial intelligence analysis method, an effective cross-border e-commerce supply chain high-efficiency transportation method is provided.

Description

Technical Field

[0001] The present invention relates to the field of cross-border e-commerce supply chain technology, and in particular to a cross-border e-commerce supply chain data analysis method and system based on artificial intelligence. Background Art

[0002] The cross-border e-commerce supply chain refers to the supply chain system formed by cross-border e-commerce companies' business activities such as commodity procurement, logistics transportation, warehousing, storage, and sales on a global scale. It involves different countries and regions and is a complex value chain network.

[0003] At present, once the user identity information is verified, the e-commerce company will establish a communication connection with the user, obtain the user's target product, generate temporary product information based on the user's identity information, and then obtain the user's payment method. Based on the temporary product information and payment method, a temporary order is generated. After the temporary order is paid, the order process information is generated based on the order number, and then the order process information and user identity information are sent to the logistics system to receive the delivery information and the estimated delivery time. Finally, the order process information is tracked regularly.

[0004] In the prior art, due to the increasing diversification and constant changes in consumer demand, the shortest distance selection for domestic and foreign transportation cannot be made according to different export destinations during the export process, resulting in low transportation efficiency. Summary of the invention

[0005] The present invention provides a cross-border e-commerce supply chain data analysis method based on artificial intelligence to achieve the function of high-efficiency transportation of the cross-border e-commerce supply chain.

[0006] In the first aspect, in order to solve the above technical problems, the present invention provides a cross-border e-commerce supply chain data analysis method based on artificial intelligence, comprising:

[0007] Obtain cross-border e-commerce supply chain data;

[0008] According to the cross-border e-commerce supply chain, the supply chain analysis results of each type of product are obtained through artificial intelligence algorithm analysis;

[0009] According to the mapping relationship between product name and product number, a product number set is obtained, and the product number set is matched with the supply chain analysis result to obtain the product number supply chain analysis result;

[0010] According to the product number supply chain analysis results, a product supply visualization network model is established;

[0011] According to the product supply visualization network model, determining the main product nodes in the product supply network model;

[0012] According to the main product nodes and product supply visualization network model, a product supply route between the target product node and the main product node is determined.

[0013] Preferably, the cross-border e-commerce supply chain data includes:

[0014] Historical order data, including order delivery time and order delivery quantity;

[0015] Inventory data, including information on the quantity and status of various products in the warehouse;

[0016] Transportation data, including the time, location, mode and route of transportation of various products;

[0017] Supplier data, including supplier location and product production information.

[0018] Preferably, the cross-border e-commerce supply chain is analyzed by an artificial intelligence algorithm to obtain supply chain analysis results for each type of product, including:

[0019] Arrange the cross-border e-commerce product data corresponding to each product to form a cross-border e-commerce product data matrix;

[0020] Input the cross-border e-commerce product data matrix into the K-means clustering algorithm, perform clustering operations, and complete product classification;

[0021] The cross-border e-commerce product data of similar products are input into the linear regression model to obtain the supply chain analysis results for each type of product.

[0022] Preferably, the objective function of the K-means clustering algorithm is:

[0023]

[0024] Among them, J is the index value to measure the product clustering effect, K represents the number of categories the product is divided into, and x i represents the data feature vector of the i-th product, μk 表 represents the central feature vector of the kth product category group, C k represents the kth product category group.

[0025] Preferably, obtaining a product number set according to a mapping relationship between a product name and a product number, matching the product number set with a supply chain analysis result, and obtaining a product number supply chain analysis result includes:

[0026] Establish a mapping table between product names and product numbers, obtain the product numbers of all products by querying the mapping table, and form a product number set;

[0027] Traverse each data item in the supply chain analysis results and find the product information corresponding to the product number set;

[0028] For successfully matched product numbers and supply chain analysis results, relevant data is extracted and integrated to form specific content in the product number supply chain analysis results;

[0029] Perform data cleansing and normalization on product number supply chain analysis results.

[0030] Preferably, the step of establishing a product supply visualization network model based on the product number supply chain analysis result includes:

[0031] The product number is used as a node, and the product association relationship in the product number supply chain analysis result is used as an edge;

[0032] Assign attributes to each node and edge; the attributes of the node include basic information, supply status and transparency of the product, and the attributes of the edge include the strength and direction of the supply relationship;

[0033] Using visualization tools, nodes and edges are displayed according to preset layout rules to form a product supply visualization network model.

[0034] Preferably, the steps of the algorithm of the product supply visualization network model include:

[0035] Construct a product node set V and an edge set E; where V = {v1, v2, ..., v n} is the product node set, E={(v i , v j )|v i , v j ∈V} is the edge set;

[0036] Construct the road edge weight function:

[0037]

[0038] Where X is the delivery time range, expressed as X = {X1, X2, ..., X m}, T is the delivery time, m is the number of segments in the delivery time range;

[0039] Construct a piecewise assignment function for the country where the consumer is located:

[0040]

[0041] Where Y represents the country where the consumer is located, and n represents the number of country segments;

[0042] According to the road edge weight function and the segmented value function, a product supply visualization network model is obtained:

[0043] w(v i , v j )=f(X)×g(Y)

[0044] Among them, w(v i , v j ) represents the final weight.

[0045] Preferably, determining the main product nodes in the product supply network model according to the product supply visualization network model includes:

[0046] Calculate the degree of each node in the product supply visualization network model, where the degree is defined as the number of edges connected to the node;

[0047] Set a degree threshold and mark nodes with a degree greater than the degree threshold as candidate main product nodes;

[0048] Analyze the importance index of the product corresponding to the candidate main product node in the supply chain; the importance index includes the sales proportion, profit contribution, and the impact of out-of-stock on the supply chain of the product;

[0049] According to the importance index, a main product node is determined from candidate main product nodes.

[0050] Preferably, determining the product supply route between the target product node and the main product node according to the main product node and the product supply visualization network model includes:

[0051] Starting from the main product node, traverse all paths in the product supply visualization network model to find the path connected to the target product node;

[0052] For each path, calculate its path distance;

[0053] Set a distance threshold and select paths with a path distance lower than the distance threshold as candidate supply routes;

[0054] Performing reliability evaluation on the candidate supply routes to obtain reliability evaluation results; wherein the reliability evaluation indicators include transportation stability and supplier credibility;

[0055] According to the reliability evaluation result, a product supply route between a target product node and a main product node is determined from candidate supply routes.

[0056] In a second aspect, the present invention provides a cross-border e-commerce supply chain data analysis method based on artificial intelligence, comprising:

[0057] Data acquisition module, to obtain cross-border e-commerce supply chain data;

[0058] An intelligent algorithm module, based on the cross-border e-commerce supply chain, obtains supply chain analysis results for each type of product through artificial intelligence algorithm analysis;

[0059] The product number module obtains the product number set based on the mapping relationship between the product name and the product number, matches the product number set with the supply chain analysis result, and obtains the product number supply chain analysis result;

[0060] A model building module, which builds a product supply visualization network model according to the product number supply chain analysis results;

[0061] A main node determination module, which determines the main product nodes in the product supply network model according to the product supply visualization network model;

[0062] The supply route planning module determines the product supply route between the target product node and the main product node according to the main product node and the product supply visualization network model.

[0063] In a third aspect, the present invention also provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements any one of the above-mentioned artificial intelligence-based cross-border e-commerce supply chain data analysis methods.

[0064] In a fourth aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned artificial intelligence-based cross-border e-commerce supply chain data analysis methods.

[0065] Compared with the prior art, the present invention has the following beneficial effects: an embodiment of the present invention provides a cross-border e-commerce supply chain data analysis method and system based on artificial intelligence, the method being executed by a processor, including obtaining cross-border e-commerce supply chain data; obtaining supply chain analysis results for each type of product through artificial intelligence algorithm analysis based on the cross-border e-commerce supply chain; obtaining a product number set based on a mapping relationship between product names and product numbers, matching the product number set with the supply chain analysis results to obtain product number supply chain analysis results; establishing a product supply visualization network model based on the product number supply chain analysis results; determining the main product nodes in the product supply network model based on the product supply visualization network model; determining the product supply route between the target product node and the main product node based on the main product nodes and the product supply visualization network model.

[0066] This method provides an effective and efficient transportation method for the cross-border e-commerce supply chain through artificial intelligence analysis methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 It is a schematic diagram of the process of a cross-border e-commerce supply chain data analysis method based on artificial intelligence provided by the first embodiment of the present invention;

[0068] Figure 2 It is a schematic diagram of the structure of a cross-border e-commerce supply chain data analysis system based on artificial intelligence provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0069] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0070] Reference Figure 1 The first embodiment of the present invention provides a cross-border e-commerce supply chain data analysis method based on artificial intelligence, comprising the following steps:

[0071] S11, obtain cross-border e-commerce supply chain data;

[0072] S12, according to the cross-border e-commerce supply chain, obtaining supply chain analysis results for each type of product through artificial intelligence algorithm analysis;

[0073] S13, obtaining a product number set according to the mapping relationship between the product name and the product number, matching the product number set with the supply chain analysis result, and obtaining a product number supply chain analysis result;

[0074] S14, establishing a product supply visualization network model according to the product number supply chain analysis result;

[0075] S15, determining the main product nodes in the product supply network model according to the product supply visualization network model;

[0076] S16, determining a product supply route between the target product node and the main product node according to the main product node and the product supply visualization network model.

[0077] This AI-based cross-border e-commerce supply chain data analysis method has brought innovation and change to supply chain management in the cross-border e-commerce field.

[0078] This method obtains cross-border e-commerce supply chain data from multiple channels, including historical order data, inventory data, transportation data, and supplier data. These rich data sources provide a solid foundation for comprehensive analysis of the cross-border e-commerce supply chain. When analyzing through artificial intelligence algorithms, the cross-border e-commerce product data corresponding to each product is first compiled into a matrix, and then the K-means clustering algorithm is used to classify the products so that similar products can be accurately classified. Then, the data of similar products is input into the linear regression model to obtain detailed supply chain analysis results for each type of product. This process gives full play to the efficiency and accuracy of artificial intelligence algorithms and can deeply explore the various characteristics and trends of products in the supply chain. This method obtains the product number set according to the mapping relationship between product name and product number, and matches it with the supply chain analysis results; this step ensures the accurate correspondence of product information and provides accurate data support for the subsequent establishment of a visual network model. After the product supply visual network model is established, the structure of the supply chain can be intuitively presented; users can clearly see the network relationship of product supply, the main product nodes, and key information such as supply routes; this not only facilitates the decision-making process of supply chain management, but also helps enterprises quickly discover potential problems and optimization points; determining the main product nodes and the product supply routes between the target product nodes and the main product nodes helps enterprises focus on key products and key links, optimize resource allocation, and improve the overall efficiency of the supply chain; in terms of precise analysis, the use of artificial intelligence algorithms makes the analysis results of each type of product more accurate and reliable, providing strong data support for the strategic decision-making of enterprises. The establishment of a visual network model greatly improves the intuitiveness and convenience of supply chain management, making complex supply chain relationships clear at a glance; at the same time, the efficient matching and positioning process can quickly and accurately determine the location and status of products in the supply chain, greatly improving the efficiency and accuracy of supply chain management, and winning advantages for cross-border e-commerce companies in the fierce market competition.

[0079] In step S11, cross-border e-commerce supply chain data is obtained.

[0080] It should be noted that the cross-border e-commerce supply chain data includes:

[0081] Historical order data, including order delivery time and order delivery quantity;

[0082] Inventory data, including information on the quantity and status of various products in the warehouse;

[0083] Transportation data, including the time, location, mode and route of transportation of various products;

[0084] Supplier data, including supplier location and product production information.

[0085] The purchase time in historical order data can help analyze consumer purchasing behavior patterns, predict sales trends, arrange marketing activities and customer service duty hours, and make inventory and logistics plans; the purchase of products can help understand consumer preferences and needs, and adjust product portfolios and purchasing strategies; the purchase quantity reflects the scale of market demand, and can reasonably arrange production and inventory, predict demand changes and adjust business strategies; the purchase price helps to understand market price sensitivity and product price positioning, formulate reasonable pricing strategies, evaluate costs and profits, and optimize the supply chain cost structure. The number of products in the warehouse in the inventory data allows companies to understand inventory levels, avoid out-of-stock or inventory backlogs, and reasonably arrange procurement and production; status information can timely grasp the quality, damage, etc. of products, making it easier to take corresponding measures. The transportation time in the transportation data can be used to evaluate logistics efficiency, reasonably arrange shipping time and estimated delivery time, and improve customer satisfaction; the location can track the location of goods to ensure the safety and timely delivery of goods; the mode of transportation affects the logistics cost and speed, and enterprises can choose the appropriate mode of transportation according to different needs; the transportation path information helps to optimize the logistics route, and the supplier location in the supplier data is related to the logistics cost and delivery time. Enterprises can choose suppliers that are closer or have convenient transportation; product production status information allows enterprises to understand the supplier's production capacity and supply stability, ensure timely delivery, and ensure the smooth operation of the supply chain.

[0086] In step S12, based on the cross-border e-commerce supply chain, an artificial intelligence algorithm is used to analyze the supply chain to obtain supply chain analysis results for each type of product.

[0087] It should be noted that the objective function of the K-means clustering algorithm is:

[0088]

[0089] Among them, J is the index value to measure the product clustering effect, K represents the number of categories the product is divided into, and x i Represents the data feature vector of the i-th product, μ k represents the central feature vector of the kth product category group, C k represents the kth product category group.

[0090] In an optional embodiment, firstly, the cross-border e-commerce product data is compiled to obtain a feature matrix, which includes product attributes, sales data and supplier information; the number of categories K is determined; the products are classified according to the distance between them and the central vector; the central vector is updated until the objective function is stable; and the data of similar products are input into a linear regression model to obtain the supply chain analysis results of each type of product.

[0091] The cross-border e-commerce product data corresponding to each product is arranged into a matrix, which realizes the structured arrangement of data and provides an orderly data basis for subsequent analysis. By inputting the cross-border e-commerce product data matrix into the K-means clustering algorithm for clustering operation, different products can be classified according to the intrinsic characteristics of the products. This classification helps to better understand the similarities and differences between products, so that products with similar attributes are classified into one category, which is convenient for targeted management and analysis of different types of products. After completing the product classification, the cross-border e-commerce product data of similar products are input into the linear regression model to obtain the supply chain analysis results of each type of product. This process can deeply explore the specific performance and trends of each type of product in the supply chain. Through the analysis results, we can understand the demand law of each type of product, the relationship between inventory level and sales, the impact of transportation efficiency on product supply and other information, which provides a strong basis for enterprises to make scientific decisions in all aspects of supply chain management. For product categories with long transportation time, production and delivery can be arranged in advance to ensure that market demand is met in time. At the same time, through a comprehensive evaluation of the supply chain analysis results of each type of product, enterprises can optimize the operating efficiency of the entire cross-border e-commerce supply chain, improve customer satisfaction, and enhance market competitiveness.

[0092] In step S13, a product number set is obtained according to the mapping relationship between the product name and the product number, and the product number set is matched with the supply chain analysis result to obtain the product number supply chain analysis result.

[0093] In an optional embodiment, the product number set is obtained according to the mapping relationship between the product name and the product number, and the product number set is matched with the supply chain analysis result to obtain the product number supply chain analysis result, including: establishing a mapping table between the product name and the product number, obtaining the product numbers of all products by querying the mapping table to form a product number set; traversing each data in the supply chain analysis result to find the product information corresponding to the product number set; for the successfully matched product numbers and supply chain analysis results, extracting and integrating the relevant data to form the specific content in the product number supply chain analysis result; and performing data cleaning and normalization on the product number supply chain analysis result.

[0094] Establishing a mapping table between product names and product numbers and obtaining product number sets provides a standardized way for accurate product identification and management. In the cross-border e-commerce supply chain, there are many types of products and different naming methods. Product numbers can achieve unified and accurate identification to avoid confusion caused by non-standard or ambiguous names; matching product number sets with supply chain analysis results can associate specific products with corresponding supply chain analysis results; traversing the supply chain analysis results to find corresponding product information ensures that each product can have a clear positioning and interpretation in the supply chain analysis; data integration is performed for successfully matched product numbers and supply chain analysis results, making the product supply chain clearer and more specific. In this way, the situation of a single product in each link of the supply chain can be understood, providing a basis for accurate supply chain management; data cleaning and standardization of product number supply chain analysis results can help improve data quality and availability; removing redundant, erroneous or non-standard data makes the analysis results more accurate and reliable, and facilitates subsequent decision-making and operations. At the same time, the standardized results also facilitate information sharing and collaborative work between different departments, improving the management efficiency and synergy of the entire cross-border e-commerce supply chain.

[0095] In step S14, a product supply visualization network model is established according to the product number supply chain analysis result.

[0096] In an optional embodiment, a product supply visualization network model is established based on the product number supply chain analysis results, including: taking the product number as the node, and taking the product association relationship in the product number supply chain analysis results as the edge; assigning attributes to each node and edge; wherein the attributes of the node include the basic information, supply status and transparency of the product, and the attributes of the edge include the strength and direction of the supply relationship; using a visualization tool, the nodes and edges are displayed according to preset layout rules to form a product supply visualization network model.

[0097] This process uses product numbers as nodes and product relationships as edges, which is a very effective way to build a supply chain network structure. In this way, each product is abstracted as a node, and the supply relationship between products is represented as the edges connecting these nodes. Such a graph structure can clearly show the position of different products in the supply chain and their mutual relationship. For example, if there is an edge between two product nodes, it means that the two products have a direct supply relationship in the supply chain, which is an upstream and downstream relationship or a complementary product relationship. Attribute assignment technology also plays a key role in this process. For node attributes, the basic information of the product can be obtained through database query or data preprocessing, including descriptive information such as the product name, specification, category, etc. This information can help users quickly identify different products. The supply situation comes from the inventory management system and production planning system. For example, the inventory level can reflect the current inventory quantity of the product, the production progress can show the production status of the product, and the delivery time can let users know when the product can be delivered to the next link. The transparency attribute can be determined by achieving full traceability of the product through blockchain technology. If a product can be clearly tracked and recorded at each link in the supply chain, then its transparency is higher, and users can trust the source and quality of the product more. For edge attributes, the strength of the supply relationship can be determined based on factors such as the transaction frequency and supply volume between products. If two products are frequently traded and the supply volume is large, the supply relationship strength of the edge between them is high. This means that the two products are closely connected in the supply chain and have a great impact on each other. The direction of the supply relationship clarifies the supply flow between products, such as from suppliers to manufacturers, from manufacturers to distributors. Such directional attributes allow users to clearly understand the flow path of products in the supply chain, which helps to analyze the efficiency and optimization direction of the supply chain. Visualization tools are used to display nodes and edges according to preset layout rules to form a product supply visualization network model. Visualization tools can use visualization functions provided by various graphics drawing software or data analysis platforms. Through reasonable layout rules, such as placing related product nodes in similar positions and representing edges with high supply relationship strength with thicker lines, the visualization network model can be made clearer and easier to read. Users can intuitively understand the structure and relationship of the entire product supply through this visualization network model, so as to better manage and make decisions in the supply chain.

[0098] It should be noted that the steps of the algorithm of the product supply visualization network model include:

[0099] Construct a product node set V and an edge set E; where V = {v1, v2, ..., v n} is the product node set, E={(v i, v j )|v i , v j ∈V} is the edge set;

[0100] Construct the road edge weight function:

[0101]

[0102] Where X is the delivery time range, expressed as X = {X1, X2, ..., X m}, T is the delivery time, m is the number of segments in the delivery time range;

[0103] Construct a piecewise assignment function for the country where the consumer is located:

[0104]

[0105] Where Y represents the country where the consumer is located, and n represents the number of country segments;

[0106] According to the road edge weight function and the segmented value function, a product supply visualization network model is obtained:

[0107] w(v i , v j )=f(X)×g(Y)

[0108] Among them, w(v i , v j ) represents the final weight.

[0109] The product node set V represents different products. Each product is a node in the network. The edge set E represents the relationship between products. If two products have a supply relationship or other connections, an edge is formed between the corresponding nodes. In the highway edge weight function f(X), X is the delivery time range, which is divided into multiple segments X1, X2, ... X m , T is the delivery time, and different values ​​are assigned according to the different segments to which the delivery time T belongs. For example, when T∈X1, the function value is 1; when T∈X2, the function value is 2, and so on. This function reflects the impact of delivery time on the weight of network edges. In the segmented assignment function g(Y) of the consumer’s country, Y represents the consumer’s country, and different countries are divided into n segments Y1, Y2...Y n , different values ​​are assigned according to the different segments to which the consumer’s country belongs. For example, when Y∈y1, the function value is 1; when Y∈Y2, the function value is 2, and so on. This function takes into account the impact of the consumer’s country on the network edge weight. The final weight w(v i , v j)=f(X)×g(Y), which combines the two factors of delivery time and the country where the consumer is located. The weights of the edges between nodes in the product supply visualization network are determined by the product of these two factors, thereby constructing a more comprehensive visualization network model to better analyze and understand the product supply situation.

[0110] By constructing the product node set V and the edge set E, the basic architecture of the product supply visualization network model is clarified. Using product numbers as nodes and product associations as edges, the positions and relationships of different products in the supply chain can be intuitively presented. This makes the structure of the supply chain clearer and helps managers quickly understand the role and function of each product in the entire supply system; assigning attributes to nodes and edges further enriches the information. The attributes of the nodes include the basic information of the product, supply status, and transparency, so that people can quickly understand the specific situation of each product. The attributes of the edges include the strength and direction of the supply relationship, which helps to analyze the closeness and flow of supply between different products, and provides a specific direction for optimizing the supply chain; the highway edge weight function and the segmented assignment function of the consumer's country are used to construct the final weight w(v i , v j )=f(X)×g(Y), taking into account the two key factors of delivery time and the country where the consumer is located. The piecewise function f(X) of the delivery time range reflects the impact of logistics efficiency on the supply chain. Shorter delivery time means higher customer satisfaction and more efficient supply chain operation, while longer delivery time requires measures to be taken for optimization. The piecewise assignment function g(Y) of the country where the consumer is located takes into account the impact of factors such as market demand, regulations and policies in different countries on the supply chain. Different countries have different consumption habits, import policies, etc. By assigning values ​​to countries in segments, supply chain planning and adjustments can be better carried out according to the conditions of different countries, so that the product supply visualization network model can more comprehensively and accurately reflect the actual situation of the cross-border e-commerce supply chain, and provide a powerful tool and decision-making basis for the optimization and management of the supply chain.

[0111] In step S15, main product nodes in the product supply network model are determined according to the product supply visualization network model.

[0112] In an optional embodiment, determining the main product nodes in the product supply network model based on the product supply visualization network model includes: calculating the degree of each node in the product supply visualization network model, where the degree is defined as the number of edges connected to the node; setting a degree threshold, marking nodes with a degree greater than the degree threshold as candidate main product nodes; analyzing the importance indicators of the products corresponding to the candidate main product nodes in the supply chain; wherein the importance indicators include the product's sales share, profit contribution, and the impact of out-of-stock on the supply chain; and determining the main product nodes from the candidate main product nodes based on the importance indicators.

[0113] By calculating the degree of each node in the product supply visualization network model (i.e., the number of edges connected to the node), we can intuitively understand the degree of connection of each product in the supply chain network. A node with a higher degree means that the product has a supply relationship with more other products and is in a more critical position in the supply chain; setting a degree threshold and marking nodes with a degree greater than the degree threshold as candidate main product nodes is a preliminary screening method. It can quickly focus on products with high connectivity in the supply network, providing a range for further determining the main product nodes; analyzing the importance indicators of the products corresponding to the candidate main product nodes in the supply chain, including the product's sales share, profit contribution, and the impact of out-of-stock on the supply chain. Products with a high sales share usually contribute more to the company's revenue, products with a high profit contribution directly affect the company's profitability, and products with a large impact on the supply chain due to out-of-stock indicate that they play a key role in the stability and reliability of the supply chain; based on these importance indicators, the main product nodes are determined from the candidate main product nodes. This ensures that the determined main product nodes not only have a high connectivity in the supply network, but also play an important role in the company's operations and the stable operation of the supply chain; this method helps companies accurately identify key products in the supply chain, so that they can focus on and manage these main product nodes, optimize resource allocation, improve the efficiency and stability of the supply chain, reduce risks, and ensure the company's economic benefits and market competitiveness.

[0114] In step S16, the product supply route between the target product node and the main product node is determined according to the main product node and the product supply visualization network model.

[0115] In an optional embodiment, the method of determining the product supply route between the target product node and the main product node based on the main product node and the product supply visualization network model includes: taking the main product node as the starting point, traversing all paths in the product supply visualization network model, and finding a path connected to the target product node; for each path, calculating its path distance; setting a distance threshold, and screening out paths with path distances lower than the distance threshold as candidate supply routes; performing reliability evaluation on the candidate supply routes to obtain reliability evaluation results; wherein, the reliability evaluation indicators include transportation stability and supplier credibility; and determining the product supply route between the target product node and the main product node from the candidate supply routes based on the reliability evaluation results.

[0116] Starting from the main product node, traversing all the paths in the product supply visualization network model and finding the path connected to the target product node helps to clarify the potential flow direction of the product in the supply chain. In this way, a set of paths connecting the target product and the main product can be screened out from the overall supply chain network, providing a basis for subsequent analysis and selection; calculating the path distance for each path can quantify the length or complexity of different paths. Path distance can be measured in different ways according to actual conditions, such as transportation time, transportation cost, etc. By calculating the path distance, more efficient paths can be preliminarily screened out, reducing the scope of subsequent evaluation; setting a distance threshold and screening out paths with path distances below the distance threshold as candidate supply routes further narrows the selection range and focuses on relatively shorter or more efficient paths. These candidate supply routes meet the requirements for efficiency to a certain extent; the reliability of the candidate supply routes is evaluated, taking into account indicators such as transportation stability and supplier credibility; transportation stability ensures that products can arrive at the destination on time and safely during transportation, avoiding delays or losses caused by transportation problems; supplier credibility is related to product quality and supply reliability, and suppliers with high credibility are more likely to provide stable and high-quality products; through reliability evaluation, it can be ensured that the selected supply route not only has an advantage in distance, but also has high reliability in actual operation; based on the reliability evaluation results, the product supply route between the target product node and the main product node is determined from the candidate supply routes; the route determined in this way takes into account efficiency and reliability, and can provide clear guidance for the company's supply chain management, optimize the product supply process, improve the overall operational efficiency and stability of the supply chain, reduce risks, and ensure the smooth progress of the company's production and sales activities.

[0117] Compared with the prior art, the present invention has the following beneficial effects: the method obtains cross-border e-commerce supply chain data from multiple channels, including historical order data, inventory data, transportation data, and supplier data. These rich data sources provide a solid foundation for comprehensive analysis of the cross-border e-commerce supply chain. When analyzing through artificial intelligence algorithms, the cross-border e-commerce product data corresponding to each product is first organized into a matrix, and then the K-means clustering algorithm is used to classify the products so that similar products can be accurately classified. Then, the data of similar products are input into the linear regression model to obtain detailed supply chain analysis results for each type of product. This process gives full play to the efficiency and accuracy of artificial intelligence algorithms, and can deeply explore the various characteristics and trends of products in the supply chain. This method obtains the product number set according to the mapping relationship between product name and product number, and matches it with the supply chain analysis results; this step ensures the accurate correspondence of product information and provides accurate data support for the subsequent establishment of a visual network model. After the product supply visual network model is established, the structure of the supply chain can be intuitively presented; users can clearly see the network relationship of product supply, the main product nodes, and key information such as supply routes; this not only facilitates the decision-making process of supply chain management, but also helps enterprises quickly discover potential problems and optimization points; determining the main product nodes and the product supply routes between the target product nodes and the main product nodes helps enterprises focus on key products and key links, optimize resource allocation, and improve the overall efficiency of the supply chain; in terms of precise analysis, the use of artificial intelligence algorithms makes the analysis results of each type of product more accurate and reliable, providing strong data support for the strategic decision-making of enterprises. The establishment of a visual network model greatly improves the intuitiveness and convenience of supply chain management, making complex supply chain relationships clear at a glance; at the same time, the efficient matching and positioning process can quickly and accurately determine the location and status of products in the supply chain, greatly improving the efficiency and accuracy of supply chain management, and winning advantages for cross-border e-commerce companies in the fierce market competition.

[0118] Reference Figure 2 The second embodiment of the present invention provides a cross-border e-commerce supply chain data analysis system based on artificial intelligence, including:

[0119] Data acquisition module, to obtain cross-border e-commerce supply chain data;

[0120] An intelligent algorithm module, based on the cross-border e-commerce supply chain, obtains supply chain analysis results for each type of product through artificial intelligence algorithm analysis;

[0121] The product number module obtains the product number set based on the mapping relationship between the product name and the product number, matches the product number set with the supply chain analysis result, and obtains the product number supply chain analysis result;

[0122] A model building module, which builds a product supply visualization network model according to the product number supply chain analysis results;

[0123] A main node determination module, which determines the main product nodes in the product supply network model according to the product supply visualization network model;

[0124] The supply route planning module determines the product supply route between the target product node and the main product node according to the main product node and the product supply visualization network model.

[0125] It should be noted that the cross-border e-commerce supply chain data analysis system based on artificial intelligence provided in an embodiment of the present invention is used to execute all the process steps of the cross-border e-commerce supply chain data analysis method based on artificial intelligence in the above embodiment. The working principles and beneficial effects of the two correspond one to one, so they will not be repeated here.

[0126] The embodiment of the present invention further provides a terminal device. The terminal device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned embodiments of the cross-border e-commerce supply chain data analysis method based on artificial intelligence are implemented, for example Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the main node determination module.

[0127] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the terminal device.

[0128] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of terminal devices and do not constitute a limitation on the terminal device. The terminal device may include more or fewer components than the above components, or may combine certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0129] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0130] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0131] Wherein, if the module / unit integrated in the terminal device 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 such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-0nly Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0132] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0133] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A cross-border e-commerce supply chain data analysis method based on artificial intelligence, characterized in that: Executed by the processor, including: Obtain cross-border e-commerce supply chain data; According to the cross-border e-commerce supply chain, the supply chain analysis results of each type of product are obtained through artificial intelligence algorithm analysis; According to the mapping relationship between product name and product number, a product number set is obtained, and the product number set is matched with the supply chain analysis result to obtain the product number supply chain analysis result; According to the product number supply chain analysis results, a product supply visualization network model is established; According to the product supply visualization network model, determining the main product nodes in the product supply network model; According to the main product nodes and product supply visualization network model, a product supply route between the target product node and the main product node is determined.

2. The cross-border e-commerce supply chain data analysis method based on artificial intelligence according to claim 1 is characterized in that: The cross-border e-commerce supply chain data includes: Historical order data, including order delivery time and order delivery quantity; Inventory data, including information on the quantity and status of various products in the warehouse; Transportation data, including the time, location, mode and route of transportation of various products; Supplier data, including supplier location and product production information.

3. The cross-border e-commerce supply chain data analysis method based on artificial intelligence according to claim 1 is characterized in that: According to the cross-border e-commerce supply chain, the supply chain analysis results of each type of product are obtained through artificial intelligence algorithm analysis, including: Arrange the cross-border e-commerce product data corresponding to each product to form a cross-border e-commerce product data matrix; Input the cross-border e-commerce product data matrix into the K-means clustering algorithm, perform clustering operations, and complete product classification; The cross-border e-commerce product data of similar products are input into the linear regression model to obtain the supply chain analysis results for each type of product.

4. The cross-border e-commerce supply chain data analysis method based on artificial intelligence according to claim 3 is characterized in that: The objective function of the K-means clustering algorithm is: Among them, J is the index value to measure the product clustering effect, K represents the number of categories the product is divided into, and x i Represents the data feature vector of the i-th product, μ k represents the central feature vector of the kth product category group, C k represents the kth product category group.

5. The cross-border e-commerce supply chain data analysis method based on artificial intelligence according to claim 1 is characterized in that: The method of obtaining a product number set based on the mapping relationship between the product name and the product number, matching the product number set with the supply chain analysis result, and obtaining the product number supply chain analysis result includes: Establish a mapping table between product names and product numbers, obtain the product numbers of all products by querying the mapping table, and form a product number set; Traverse each data item in the supply chain analysis results and find the product information corresponding to the product number set; For successfully matched product numbers and supply chain analysis results, relevant data is extracted and integrated to form specific content in the product number supply chain analysis results; Perform data cleansing and normalization on product number supply chain analysis results.

6. The cross-border e-commerce supply chain data analysis method based on artificial intelligence according to claim 1 is characterized in that: The step of establishing a product supply visualization network model based on the product number supply chain analysis result includes: The product number is used as a node, and the product association relationship in the product number supply chain analysis result is used as an edge; Assign attributes to each node and edge; the attributes of the node include basic information, supply status and transparency of the product, and the attributes of the edge include the strength and direction of the supply relationship; Using visualization tools, nodes and edges are displayed according to preset layout rules to form a product supply visualization network model.

7. The cross-border e-commerce supply chain data analysis method based on artificial intelligence according to claim 6 is characterized in that: The steps of the algorithm of the product supply visualization network model include: Construct product node set V and edge set E; where V = {v1, v2, ..., v n } is the set of product nodes, E={(v i , v j )|v i , v j ∈V} is the edge set; Construct the road edge weight function: Where X is the delivery time range, expressed as X = {X1, X2, ..., X m }, T is the delivery time, m is the number of segments in the delivery time range; Construct a piecewise assignment function for the country where the consumer is located: Where Y represents the country where the consumer is located, and n represents the number of country segments; According to the road edge weight function and the segmented value function, a product supply visualization network model is obtained: w(v i ,v j )=f(X)×g(Y) Among them, w(v i , v j ) represents the final weight.

8. The cross-border e-commerce supply chain data analysis method based on artificial intelligence according to claim 1 is characterized in that: Determining the main product nodes in the product supply network model according to the product supply visualization network model includes: Calculate the degree of each node in the product supply visualization network model, where the degree is defined as the number of edges connected to the node; Set a degree threshold and mark nodes with a degree greater than the degree threshold as candidate main product nodes; Analyze the importance index of the product corresponding to the candidate main product node in the supply chain; the importance index includes the sales proportion, profit contribution, and the impact of out-of-stock on the supply chain of the product; According to the importance index, a main product node is determined from candidate main product nodes.

9. The cross-border e-commerce supply chain data analysis method based on artificial intelligence according to claim 1 is characterized in that: Determining the product supply route between the target product node and the main product node according to the main product node and the product supply visualization network model includes: Starting from the main product node, traverse all paths in the product supply visualization network model to find the path connected to the target product node; For each path, calculate its path distance; Set a distance threshold and select paths with a path distance lower than the distance threshold as candidate supply routes; Performing reliability evaluation on the candidate supply routes to obtain reliability evaluation results; wherein the reliability evaluation indicators include transportation stability and supplier credibility; According to the reliability evaluation result, a product supply route between a target product node and a main product node is determined from candidate supply routes.

10. A cross-border e-commerce supply chain data analysis system based on artificial intelligence, characterized in that: include: Data acquisition module, to obtain cross-border e-commerce supply chain data; An intelligent algorithm module, based on the cross-border e-commerce supply chain, obtains supply chain analysis results for each type of product through artificial intelligence algorithm analysis; The product number module obtains the product number set based on the mapping relationship between the product name and the product number, matches the product number set with the supply chain analysis result, and obtains the product number supply chain analysis result; A model building module, which builds a product supply visualization network model according to the product number supply chain analysis results; A main node determination module, which determines the main product nodes in the product supply network model according to the product supply visualization network model; The supply route planning module determines the product supply route between the target product node and the main product node according to the main product node and the product supply visualization network model.

Images