Cross-border trade supply chain scheduling optimization method based on ant colony algorithm

Abstract

The invention relates to the technical field of supply chain planning, in particular to a cross-border trade supply chain scheduling optimization method based on an ant colony algorithm. The method comprises the following steps: firstly, according to the prominent condition of an initial matching degree corresponding to a company node in all initial matching degrees, adjusting the initial matching degree, and obtaining the adjusted matching degree; according to the adjusted matching degree of the adjacent company node combination, the initial transaction quality parameters are adjusted, and the adjusted transaction quality parameters of the adjacent company node combination are obtained; and screening an optimal supply chain from all supply chains in the supply chain network according to the adjusted transaction quality parameter of the adjacent company node combination in each supply chain. According to the invention, by deeply analyzing the matching degree between the transportation cost and the companies, the optimal supply chain is better screened out, and the long-term stable benefit of the product supply process is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of supply chain planning, and in particular to a cross-border trade supply chain scheduling optimization method based on ant colony algorithm. Background Art

[0002] As an important part of the global economy, cross-border trade can promote the optimal allocation of resources among countries, thereby improving production efficiency and resource utilization. The core of cross-border trade supply chain scheduling optimization is to optimize the supply chain of products to achieve a more efficient and economical global logistics process. Usually, the supply chain network is built based on the companies corresponding to the industrial link categories, and the optimal supply chain in the supply chain network is found to ensure the benefits of the supply chain process.

[0003] Since the transportation cost of the transaction process of the combination of adjacent companies is the core factor affecting profits, the traditional ant colony algorithm usually determines the optimal supply chain based on the transportation cost of the combination of adjacent companies. However, in the process of determining the optimal supply chain, the traditional ant colony algorithm does not fully consider the degree of fit of the transaction process of the combination of adjacent companies, resulting in the inaccuracy of the optimal supply chain and difficulty in ensuring the long-term benefits of the product supply process. Summary of the invention

[0004] In order to solve the technical problem that it is difficult to ensure the long-term profit of the product supply process by determining the optimal supply chain in the prior art, the purpose of the present invention is to provide a cross-border trade supply chain scheduling optimization method based on ant colony algorithm. The technical solution adopted is as follows:

[0005] A cross-border trade supply chain scheduling optimization method based on ant colony algorithm, the method comprising:

[0006] Obtain all supply chains in the supply chain network; the supply chain includes company nodes corresponding to each industry link category; obtain the transportation cost and transaction information of the combination of adjacent company nodes in each supply chain in each transaction process;

[0007] According to the transportation cost of the adjacent company node combination in each transaction process, the initial transaction quality parameters of the adjacent company node combination are obtained; according to the transaction information of the adjacent company node combination in each transaction process, the initial degree of fit of the adjacent company node combination is obtained; according to the prominence of the initial degree of fit of the company node corresponding to all initial degrees of fit in, the initial degree of fit is adjusted to obtain the adjusted degree of fit; according to the adjusted degree of fit of the adjacent company node combination, the initial transaction quality parameters are adjusted to obtain the adjusted transaction quality parameters of the adjacent company node combination;

[0008] According to the adjusted transaction quality parameters of the adjacent company node combination in each supply chain, the optimal supply chain is screened out from all supply chains in the supply chain network.

[0009] Furthermore, the method for obtaining the initial transaction quality parameter includes:

[0010] According to the overall distribution of the transportation costs of the adjacent company node combination corresponding to all the transaction processes, the overall transportation index of the adjacent company node combination is obtained;

[0011] According to the overall transport index of the adjacent company node combination, the initial transaction quality parameter of the adjacent company node combination is obtained; the overall transport index and the transaction quality parameter are negatively correlated.

[0012] Furthermore, the method for obtaining the initial degree of fit includes:

[0013] The transaction information includes: profit, quality score value and speed score value; the profit, quality score value and speed score value are respectively used as transaction indicators to be analyzed;

[0014] According to the overall distribution of the transaction indicators to be analyzed corresponding to all transaction processes of the adjacent company node combination, the transaction indicators to be analyzed corresponding to the overall transaction indicators of the adjacent company node combination are obtained;

[0015] According to the profit, quality score and speed score corresponding to the overall transaction index, the initial degree of fit of the adjacent company node combination is obtained.

[0016] Furthermore, the method for obtaining the overall transaction index includes:

[0017] The mean of the transaction indicators to be analyzed of all transaction processes of the adjacent company node combination is calculated to obtain the overall transaction indicator corresponding to the transaction indicators to be analyzed of the adjacent company node combination.

[0018] Furthermore, the method for obtaining the initial degree of fit of the adjacent company node combination according to the profit, quality score and speed score corresponding to the overall transaction index includes:

[0019] Calculate the mean of the overall transaction indicators corresponding to the profit, quality score and speed score, normalize the mean, and obtain the initial degree of fit of the adjacent company node combination.

[0020] Furthermore, the method for obtaining the adjusted degree of fit includes:

[0021] The corresponding adjacent industry link category combinations to all initial fit degrees are used as a first set of adjacent industry link category combinations; in the first set, the corresponding company nodes to all initial fit degrees are used as a second set of company nodes;

[0022] According to the prominence of the second set in the first set, obtaining the prominence index of the company node in the first set;

[0023] The company nodes whose prominence index is greater than the preset prominence threshold are regarded as the prominence nodes of the adjacent industrial link category combination;

[0024] If there is no prominent node in the combination of adjacent industrial link categories, the initial degree of fit in the first set is directly used as the adjusted degree of fit;

[0025] If there are prominent nodes in the combination of adjacent industrial link categories, the initial degree of fit in the first set is adjusted according to the prominent index to obtain the adjusted degree of fit.

[0026] Furthermore, the method for obtaining the outstanding indicator includes:

[0027] The mean of all initial fit degrees in the first set is calculated to obtain a first mean; the mean of all initial fit degrees in the second set is calculated to obtain a second mean, the first mean is subtracted from the second mean to obtain a difference, the difference is normalized to obtain a prominent index.

[0028] Furthermore, if there is a prominent node in the combination of adjacent industrial links, the initial degree of fit in the first set is adjusted according to the prominent index, and the method for obtaining the adjusted degree of fit includes:

[0029] In the first set, the initial fit degree corresponding to the combination of adjacent company nodes containing the prominent node is used as the degree to be adjusted; the initial fit degree corresponding to the combination of adjacent company nodes not containing the prominent node is directly used as the adjusted fit degree;

[0030] For the combination of adjacent company nodes including the prominent node, the product of the prominent index corresponding to the degree to be adjusted and the preset ratio is calculated to obtain the reduction ratio; 1 minus the reduction ratio is calculated to obtain the ratio parameter; the ratio parameter is calculated and multiplied by the initial degree of fit to obtain the adjusted degree of fit.

[0031] Furthermore, the method for obtaining the adjusted transaction quality parameter includes:

[0032] The product of the adjusted degree of fit of the adjacent company node combination and the initial transaction quality parameter is calculated to obtain the adjusted transaction quality parameter of the adjacent company node combination.

[0033] Furthermore, the method for obtaining the optimal supply chain includes:

[0034] Based on the ant colony algorithm, the adjusted transaction quality parameters of the combination of adjacent company nodes are used as heuristic information to screen out the optimal supply chain from each supply chain in the supply chain network.

[0035] The present invention has the following beneficial effects:

[0036] Considering that transportation cost is the core factor affecting the quality of the transaction process, the lower the transportation cost, the higher the transaction quality. First, the initial transaction quality parameters of the adjacent company node combination are obtained according to the transportation cost of the adjacent company node combination in each transaction process, and the transaction quality is preliminarily reflected by the initial transaction quality parameters. It is too one-sided to measure the transaction quality of the adjacent company node combination in the supply chain only by transportation cost. Transactions between companies also need to be based on the premise that the companies are mutually compatible. The initial degree of fit is used to preliminarily reflect the degree of fit between the adjacent company node combination. In order to make appropriate adjustments to the initial transaction quality parameters in the future, the initial degree of fit is adjusted to obtain the corresponding adjusted degree of fit of the company node. Thus, the initial transaction quality parameters are adjusted to obtain the adjusted transaction quality parameters of the adjacent company node combination. The adjusted transaction quality parameters combine the transportation cost and the degree of fit between companies, which can more comprehensively reflect the transaction quality. Thus, the adjusted transaction quality parameters are used to screen the best supply chain from all supply chains in the supply chain network. The best supply chain not only ensures low cost and high profit, but also ensures mutual fit between companies, so as to achieve long-term and stable benefits in the product supply process. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 A flowchart of a cross-border trade supply chain scheduling optimization method based on ant colony algorithm provided by an embodiment of the present invention;

[0039] Figure 2 A schematic diagram of a supply chain network provided by an embodiment of the present invention;

[0040] Figure 3 A flow chart of a method for obtaining an initial degree of fit provided by an embodiment of the present invention;

[0041] Figure 4A flow chart of a method for obtaining an adjusted degree of fit provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a cross-border trade supply chain scheduling optimization method based on an ant colony algorithm proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0043] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0044] The following is a detailed description of a cross-border trade supply chain scheduling optimization method based on ant colony algorithm provided by the present invention in conjunction with the accompanying drawings.

[0045] The embodiment of the present invention provides a cross-border trade supply chain scheduling optimization method based on ant colony algorithm, please refer to Figure 1 , which shows a flowchart of a cross-border trade supply chain scheduling optimization method based on ant colony algorithm provided by an embodiment of the present invention, the method comprising the following steps:

[0046] Step S1: Obtain all supply chains in the supply chain network; the supply chain includes company nodes corresponding to each industry link category; obtain the transportation cost and transaction information of the combination of adjacent company nodes in each supply chain in each transaction process.

[0047] In order to determine the optimal supply chain, it is first necessary to obtain the transportation costs and transaction information of all supply chains in the supply chain network and the combination of adjacent company nodes in each supply chain in each transaction process.

[0048] In order to optimize the supply process, considering that the complete supply process of the product is a complete process from raw material supply to product processing and then to sale, the supply process covers four core industrial links: raw material supply, product manufacturing, product distribution and product retail, and each industrial link corresponds to multiple companies. Each industrial link corresponds to multiple companies, that is, the raw material supply industrial link corresponds to multiple raw material supply companies, the product manufacturing industrial link corresponds to multiple product manufacturing companies, the product distribution industrial link corresponds to multiple product distribution companies, and the product retail industrial link corresponds to multiple product retail companies.

[0049] Each industrial link is regarded as each industrial link category, and the company corresponding to the industrial link is regarded as each company node. The four company nodes, a company node of the raw material supply category, a company node of the product manufacturing category, a company node of the product distribution category, and a company node of the product retail category, are connected in series to form a complete supply chain. This means that the supply process is that the raw material supply company sells the raw materials to the product manufacturing company, and then the product manufacturing company sells the products to the product distribution company, and finally the product distribution company sells the products to the product retail company.

[0050] As an example, Figure 2 The figure shows a supply chain network diagram, which accurately reflects the relationship between different company nodes; the raw material supply category includes two company nodes, A1 and A2, which are responsible for providing raw materials; the product manufacturing category includes three company nodes, B1, B2 and B3, which are responsible for processing raw materials into products; the product distribution category has two company nodes, C1 and C2, which are responsible for selling products to various retail outlets; the product retail category includes four company nodes, D1, D2, D3 and D4, which sell products directly to consumers. Each supply chain contains a company node in the raw material supply category, a company node in the product manufacturing category, a company node in the product distribution category, and a company node in the product retail category. Taking A1-B1-C1-D1 as an example, this is a typical supply chain; taking all supply chains composed of all company nodes as a supply chain network, the constructed supply chain network can be as follows Figure 2 shown.

[0051] Among them, according to the order in the supply chain, each industry link category and its previous industry link category are combined as adjacent industry link categories. The adjacent company node combination refers to the company node pair directly connected to the adjacent industry link category combination. For example, the adjacent industry link category combination is the raw material supply category - product manufacturing category, and its corresponding adjacent company node combinations are A1-B1, A1-B2, A1-B3, A2-B1, A2-B2 and A2-B3, indicating that different raw material supply companies provide raw materials to different product manufacturing companies.

[0052] The transportation cost and transaction information of each company in each transaction process corresponding to the combination of adjacent company nodes in each supply chain are obtained from the supply chain database. For example, for the transportation cost and transaction information of any transaction process of the adjacent company node combination A1-B1, the specific acquisition process includes: in any transaction process, calculating the total amount of the transportation process of the raw materials provided by the raw material supply company corresponding to A1 to the product manufacturing company corresponding to B1, as the transportation cost of the adjacent company node combination A1-B1 in the transaction process, the higher the transportation cost, the higher the transaction cost, and the more dissatisfied with the transaction; the profit obtained by the raw material supply company corresponding to A1 from providing raw materials to the product manufacturing company corresponding to B1 is taken as the profit of the adjacent company node combination A1-B1, the higher the profit, the more satisfied with the transaction; the product manufacturing company corresponding to B1 will score the quality of the raw materials provided by the raw material supply company corresponding to A1 to obtain a quality score value; the higher the quality score value, the better the quality, and the more satisfied with the transaction; the product manufacturing company corresponding to B1 will score the speed of the raw materials provided by the raw material supply company corresponding to A1 to obtain a speed score value; the higher the speed score value, the more timely the delivery, and the more satisfied with the transaction, and the profit, quality score value and speed score value are taken as the transaction information of the adjacent company node combination A1-B1 in the transaction process.

[0053] It should be noted that, in order to facilitate calculation, all indicator data involved in the calculation in the embodiment of the present invention are preprocessed to eliminate the dimension effect. The specific means of eliminating the dimension effect are technical means well known to those skilled in the art and are not limited here.

[0054] Step S2: According to the transportation cost of the adjacent company node combination in each transaction process, the initial transaction quality parameters of the adjacent company node combination are obtained; according to the transaction information of the adjacent company node combination in each transaction process, the initial degree of fit of the adjacent company node combination is obtained; according to the prominence of the initial degree of fit of the company node in all the initial degrees of fit, the initial degree of fit is adjusted to obtain the adjusted degree of fit; according to the adjusted degree of fit of the adjacent company node combination, the initial transaction quality parameters are adjusted to obtain the adjusted transaction quality parameters of the adjacent company node combination.

[0055] Considering that transportation cost is the core factor affecting the quality of the transaction process, the lower the transportation cost, the higher the transaction quality. First, the initial transaction quality parameters of the adjacent company node combination are obtained according to the transportation cost of the adjacent company node combination in each transaction process, and the transaction quality is preliminarily reflected by the initial transaction quality parameters. It is too one-sided to measure the transaction quality of the adjacent company node combination in the supply chain only by transportation cost. Transactions between companies also need to be based on the premise that the companies fit each other. The initial degree of fit is used to preliminarily reflect the degree of fit between the adjacent company node combination. In order to make appropriate adjustments to the initial transaction quality parameters in the future, the initial degree of fit is adjusted to obtain the corresponding adjusted degree of fit of the company node. In this way, the initial transaction quality parameters are adjusted to obtain the adjusted transaction quality parameters of the adjacent company node combination. The adjusted transaction quality parameters combine the transportation cost and the degree of fit between companies, which can more comprehensively reflect the transaction quality.

[0056] Considering that cross-border trade involves cross-border logistics, including multiple modes of transportation such as sea, air, and land transportation, as well as possible transshipment, customs clearance and other links, these links are accompanied by expensive transportation costs. The transportation cost of the transaction process is the core factor affecting profits, and the inverse of the transportation cost can initially reflect the quality of the transaction. The traditional ant colony algorithm uses the inverse of the distance between two points as heuristic information. In the embodiment of the present invention, the transportation cost is used to reflect the distance between two company nodes in the adjacent company node combination in the traditional ant colony algorithm. Therefore, it can also be understood that when using the traditional ant colony algorithm to determine the supply chain with the best transaction quality, the inverse of the transportation cost of the adjacent company node combination is usually used as the heuristic information in the ant colony algorithm. The traditional ant colony algorithm often uses the inverse of the transportation cost of the adjacent company node combination as heuristic information. It is too one-sided to measure the transaction quality of the adjacent company node combination in the supply chain only by transportation cost. In order to better screen out the optimal supply chain, the present invention constructs adjusted transaction quality parameters to more comprehensively reflect the transaction quality, and then uses the adjusted transaction quality parameters as heuristic information, so that the ant colony algorithm can more accurately identify high-quality supply chains during the search process, thereby screening out the optimal supply chain.

[0057] Since transportation cost is the core factor affecting the quality of the transaction process, firstly, the initial transaction quality parameters of the adjacent company node combination are obtained through the transportation cost of the adjacent company node combination in each transaction process, and the transaction quality is preliminarily reflected through the initial transaction quality parameters. Preferably, in one embodiment of the present invention, the method for obtaining the initial transaction quality parameters includes:

[0058] According to the overall distribution of transportation costs of all transaction processes corresponding to the adjacent company node combination, the overall transportation index of the adjacent company node combination is obtained; according to the overall transportation index of the adjacent company node combination, the initial transaction quality parameters of the adjacent company node combination are obtained; the overall transportation index and the transaction quality parameter are negatively correlated.

[0059] Specifically for the above steps, the overall distribution is reflected by the mean, the mean of the transportation cost of the adjacent company node combination in all transaction processes is calculated, and the overall transportation index of the adjacent company node combination is obtained; the inverse of the overall transportation index is used as the initial transaction quality parameter of the adjacent company node combination.

[0060] The overall transportation index can reflect the overall transportation cost of the adjacent company node combination in all transaction processes. The smaller the overall transportation index is, the higher the transaction quality of the adjacent company node combination is. The initial transaction quality parameter is then used to preliminarily reflect the transaction quality. The larger the initial transaction quality parameter is, the higher the transaction quality of the adjacent company node combination is.

[0061] Measuring the transaction quality of adjacent company node combinations in the supply chain by only using transportation costs is too one-sided. In order to analyze the degree of fit between adjacent company node combinations, please refer to Figure 3 , which shows a flow chart of a method for obtaining an initial degree of fit in one embodiment of the present invention. Preferably, in one embodiment of the present invention, the method for obtaining an initial degree of fit includes:

[0062] Step S201: Transaction information includes: profit, quality score value and speed score value; the profit, quality score value and speed score value are respectively used as transaction indicators to be analyzed.

[0063] In order to measure the fit of the adjacent company node combination, considering that the higher the profit, quality score and speed score in each transaction, the more satisfied the company is with the transaction, and the more fit the adjacent company node combination is in the transaction, the profit, quality score and speed score are used as the transaction indicators to be analyzed.

[0064] Step S202: according to the overall distribution of the transaction indicators to be analyzed corresponding to all transaction processes of the adjacent company node combination, the transaction indicators to be analyzed of the adjacent company node combination corresponding to the overall transaction indicators are obtained.

[0065] The overall transaction index reflects the overall performance of the transaction indicators to be analyzed in all transaction processes of the adjacent company node combination.

[0066] Preferably, in one embodiment of the present invention, the mean of the transaction indicators to be analyzed of all transaction processes of the adjacent company node combination is calculated to obtain the overall transaction indicator corresponding to the transaction indicator to be analyzed of the adjacent company node combination.

[0067] Step S203: Obtain the initial degree of fit of the adjacent company node combination according to the profit, quality score and speed score corresponding to the overall transaction index.

[0068] The greater the initial degree of fit, the better the profit, product quality and delivery speed of the adjacent company node combination during the transaction, the more satisfied the transaction parties are, and the higher the degree of transaction fit between the adjacent company node combinations.

[0069] Preferably, in one embodiment of the present invention, the mean of the overall transaction index corresponding to the profit, quality score and speed score is calculated, and the mean is normalized to obtain the initial degree of fit of the adjacent company node combination. In one embodiment of the present invention, the normalization method is: normalization is performed using a sigmoid normalization function.

[0070] Considering that the degree of fit of the adjacent company node combination is used to adjust the initial transaction quality parameters, the adjusted transaction quality parameters of the adjacent company node combination are obtained, and the adjusted transaction quality parameters are used as heuristic information. The size of the parameters directly affects the preference of the ant colony algorithm when selecting a path. If the adjusted transaction quality parameters are too large, the algorithm may fall into a local optimal solution and fail to find the global optimal solution. In order to reduce the possibility of generating a local optimum, the original data used to calculate the adjusted transaction quality parameters, that is, the initial degree of fit is too large, and it will be appropriately weakened, thereby reducing the risk of local optimality caused by the excessively large adjusted transaction quality parameters. This allows the ant colony algorithm to consider various factors more evenly during the search process and improve its ability to identify high-quality supply chains.

[0071] For example, for the combination of adjacent industrial links, raw material supply category - product manufacturing category, if the initial fit between company node A1 in the raw material supply category and its adjacent company nodes B1, B2, and B3 is too large, and the fit between other company nodes in the raw material supply category and their adjacent company nodes is relatively small, and the importance of company node A1 is significantly higher than that of other company nodes in the industrial link category, the ant colony algorithm may rely too much on this high-importance node during the search process and tend to choose paths connected to company node A1, even if these paths are not optimal in the global scope. In order to reduce the risk of generating local optimality, it is necessary to appropriately adjust the initial fit to obtain the adjusted fit of the company nodes. Please refer to Figure 4 , which shows a flow chart of a method for obtaining an adjusted degree of fit in one embodiment of the present invention. Preferably, in one embodiment of the present invention, the method for obtaining an adjusted degree of fit includes:

[0072] Step S211: corresponding all initial fit degrees of adjacent industrial link category combinations to each other as a first set of adjacent industrial link category combinations; in the first set, corresponding all initial fit degrees of company nodes to each other as a second set of company nodes.

[0073] By constructing the first and second sets, we can highlight the indicators for subsequent analysis and provide data support.

[0074] For example, for the combination of adjacent industry links, the raw material supply category - product manufacturing category, the raw material supply category - product manufacturing category corresponds to all initial fit degrees as the initial fit degrees of all adjacent company node combinations, that is, the first set of adjacent industry link category combinations includes: A1-B1, A1-B2, A1-B3, A2-B1, A2-B2 and A2-B3 initial fit degrees. In the first set, all initial fit degrees corresponding to company node A1 are used as the second set of company nodes, that is, the second set includes: A1-B1, A1-B2 and A1-B3 initial fit degrees.

[0075] Step S212: obtaining a prominence index of the company node in the first set according to the prominence of the second set in the first set;

[0076] The prominence index reflects the prominence of the initial fit degree of the company node in all the initial fit degrees of the adjacent industrial link categories to which it belongs. The larger the prominence index, the greater the prominence, reflecting the greater the possibility that the company node is a high-importance company node, and the easier it is to produce local optimality.

[0077] Preferably, in one embodiment of the present invention, the method for obtaining the highlight index includes:

[0078] The mean of all initial fit degrees in the first set is calculated to obtain a first mean; the mean of all initial fit degrees in the second set is calculated to obtain a second mean, the first mean minus the second mean is calculated to obtain a difference, and the difference is normalized to obtain a prominence index. In one embodiment of the present invention, the normalization method is: normalization is performed using the norm normalization function to limit the value range to between 0 and 1.

[0079] Step S213: The company nodes whose prominence index is greater than the preset prominence threshold are used as the prominence nodes of the adjacent industrial link category combination.

[0080] The prominent nodes of the adjacent industrial link category combination represent the company nodes with high importance in the adjacent industrial link category combination, which can easily cause the ant colony algorithm to fall into local optimality.

[0081] In one embodiment of the present invention, 0.21 is used as a preset prominence threshold, and the preset prominence threshold is used to filter out prominence nodes. If more prominence nodes are to be filtered out, the implementer can appropriately reduce the preset prominence threshold according to the implementation scenario, and no limitation is made here.

[0082] Step S214: If there is no prominent node in the combination of adjacent industrial link categories, the initial degree of fit in the first set is directly used as the adjusted degree of fit.

[0083] Considering that there are no prominent nodes in the combination of adjacent industrial link categories, which means there are no company nodes with high importance, there is no need to adjust the initial fit degree in the first set, and the initial fit degree in the first set is directly used as the adjusted fit degree.

[0084] Step S215: If there are prominent nodes in the combination of adjacent industrial link categories, the initial degree of fit in the first set is adjusted according to the prominent index to obtain the adjusted degree of fit.

[0085] Taking into account the existence of prominent nodes in the combination of adjacent industrial links, it is necessary to appropriately reduce the initial degree of fit corresponding to the prominent nodes to reduce the risk of producing local optimality.

[0086] Preferably, in one embodiment of the present invention, in the first set, the initial degree of fit corresponding to the combination of adjacent company nodes containing the prominent node is used as the degree to be adjusted; the initial degree of fit corresponding to the combination of adjacent company nodes not containing the prominent node is directly used as the adjusted degree of fit;

[0087] For the adjacent company node combination containing a prominent node, calculate the product of the prominent index corresponding to the degree to be adjusted and the preset ratio to obtain the reduction ratio; calculate 1 minus the reduction ratio to obtain the ratio parameter; calculate the ratio parameter multiplied by the initial degree of fit to obtain the adjusted degree of fit. In one embodiment of the present invention, the preset ratio is 10%, which can be set by the implementer according to the implementation scenario. It should be noted that the degree to be adjusted corresponds to the prominent index. If there is one prominent node in the adjacent company node combination to which the degree to be adjusted belongs, it is the prominent index of the prominent node in the adjacent company node combination to which the degree to be adjusted belongs. If there are two prominent nodes in the adjacent company node combination to which the degree to be adjusted belongs, that is, the adjustment degree corresponds to two prominent indicators, the average of the two prominent indicators is used as the prominent index corresponding to the degree to be adjusted.

[0088] For the above steps, in the first set, the initial degree of fit corresponding to the combination of adjacent company nodes containing the prominent node is used as the degree to be adjusted; the degree to be adjusted reflects the initial degree of fit corresponding to the prominent node. Considering that in order to reduce the risk of generating a local optimum, it is necessary to reduce the initial degree of fit corresponding to the prominent node. The initial degree of fit corresponding to the non-prominent node does not need to be adjusted. The initial degree of fit corresponding to the combination of adjacent company nodes that does not contain the prominent node is directly used as the adjusted degree of fit. For the degree to be adjusted, the degree to which the initial degree of fit corresponding to the prominent node needs to be reduced is reflected by reducing the proportion based on the prominence situation. Through the above steps, the adjusted degree of fit can effectively reduce the risk of local optimum caused by the prominent node, and can better adjust the initial transaction quality parameters.

[0089] By constructing adjusted transaction quality parameters to more comprehensively reflect transaction quality, the adjusted transaction quality parameters can be used as heuristic information in the subsequent process, so that the ant colony algorithm can more accurately identify high-quality supply chains during the search process.

[0090] Preferably, in one embodiment of the present invention, the method for obtaining the adjusted trade quality includes:

[0091] The product of the adjusted degree of fit of the adjacent company node combination and the initial transaction quality parameter is calculated to obtain the adjusted transaction quality parameter of the adjacent company node combination. The adjusted transaction quality parameter combines the transportation cost and the degree of fit between companies, which can more comprehensively reflect the transaction quality and effectively avoid local optimality.

[0092] Step S3: According to the adjusted transaction quality parameters of the adjacent company node combination in each supply chain, the optimal supply chain is selected from all supply chains in the supply chain network.

[0093] The adjusted transaction quality parameters are taken into account to more comprehensively reflect the transaction quality, so as to use the adjusted transaction quality parameters to screen out the best supply chain from all supply chains in the supply chain network. The best supply chain not only ensures low cost and high profitability, but also ensures mutual fit between companies, and realizes long-term stable benefits in the product supply process.

[0094] Preferably, in one embodiment of the present invention, the method for obtaining the optimal supply chain includes:

[0095] Based on the ant colony algorithm, the adjusted transaction quality parameters of the combination of adjacent company nodes are used as heuristic information to screen out the optimal supply chain from each supply chain in the supply chain network.

[0096] By using the adjusted transaction quality parameters as heuristic information, the ant colony algorithm can more accurately identify high-quality supply chains during the search process, thereby screening out the optimal supply chain. The optimal supply chain can better ensure the long-term stable benefits of the product supply process.

[0097] It should be noted that the ant colony algorithm is a technical means well known to those skilled in the art. Here, only the steps of using the adjusted transaction quality parameters of the adjacent company node combination as heuristic information to select the optimal supply chain from each supply chain in the supply chain network are briefly described:

[0098] First, the parameters of the ant colony algorithm are set, and the adjusted transaction quality parameters of the combination of adjacent company nodes are used as heuristic information. In the supply chain network, each ant starts from the starting company node, calculates the transfer probability based on the pheromone concentration and heuristic information at the current location, and selects the next company node as the target point until it returns to the company node corresponding to the starting point of the supply chain after visiting a supply chain. The pheromone matrix is ​​updated according to the length of the supply chain that the ant has traveled and the pheromone update rule. Pheromone update usually includes two processes: pheromone volatilization and pheromone enhancement. The ant movement and pheromone update steps are repeated until the termination condition is met, and finally the optimal supply chain found is output.

[0099] Specifically, applying the optimal supply chain to the supply process can achieve long-term and stable benefits in the product supply process.

[0100] In summary, the embodiment of the present invention provides a cross-border trade supply chain scheduling optimization method based on the ant colony algorithm. First, the initial transaction quality parameters of the adjacent company node combination are obtained through the transportation cost of the adjacent company node combination in each transaction process; according to the prominence of the initial degree of fit of the company node corresponding to all the initial degrees of fit, the initial degree of fit is adjusted to obtain the adjusted degree of fit; according to the adjusted degree of fit of the adjacent company node combination, the initial transaction quality parameters are adjusted to obtain the adjusted transaction quality parameters of the adjacent company node combination; according to the adjusted transaction quality parameters of the adjacent company node combination in each supply chain, the optimal supply chain is screened out from all supply chains in the supply chain network. In the embodiment of the present invention, by deeply exploring the transportation cost and the degree of fit between companies, the optimal supply chain is better screened out to ensure the long-term stable benefits of the product supply process.

[0101] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0102] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A cross-border trade supply chain scheduling optimization method based on ant colony algorithm, characterized in that: The method comprises: Obtain all supply chains in the supply chain network; the supply chain includes company nodes corresponding to each industry link category; obtain the transportation cost and transaction information of the combination of adjacent company nodes in each supply chain in each transaction process; According to the transportation cost of the adjacent company node combination in each transaction process, the initial transaction quality parameters of the adjacent company node combination are obtained; according to the transaction information of the adjacent company node combination in each transaction process, the initial degree of fit of the adjacent company node combination is obtained; according to the prominence of the initial degree of fit of the company node corresponding to all initial degrees of fit in, the initial degree of fit is adjusted to obtain the adjusted degree of fit; according to the adjusted degree of fit of the adjacent company node combination, the initial transaction quality parameters are adjusted to obtain the adjusted transaction quality parameters of the adjacent company node combination; According to the adjusted transaction quality parameters of the adjacent company node combination in each supply chain, the optimal supply chain is screened out from all supply chains in the supply chain network.

2. According to the cross-border trade supply chain scheduling optimization method based on ant colony algorithm according to claim 1, it is characterized in that: The method for obtaining the initial transaction quality parameter includes: According to the overall distribution of the transportation costs of the adjacent company node combination corresponding to all the transaction processes, the overall transportation index of the adjacent company node combination is obtained; According to the overall transport index of the adjacent company node combination, the initial transaction quality parameter of the adjacent company node combination is obtained; the overall transport index and the transaction quality parameter are negatively correlated.

3. According to the cross-border trade supply chain scheduling optimization method based on ant colony algorithm in claim 1, it is characterized in that: The method for obtaining the initial degree of fit includes: The transaction information includes: profit, quality score value and speed score value; the profit, quality score value and speed score value are respectively used as transaction indicators to be analyzed; According to the overall distribution of the transaction indicators to be analyzed corresponding to all transaction processes of the adjacent company node combination, the transaction indicators to be analyzed corresponding to the overall transaction indicators of the adjacent company node combination are obtained; According to the profit, quality score and speed score corresponding to the overall transaction index, the initial degree of fit of the adjacent company node combination is obtained.

4. According to claim 3, a cross-border trade supply chain scheduling optimization method based on ant colony algorithm is characterized in that: The method for obtaining the overall transaction index includes: The mean of the transaction indicators to be analyzed of all transaction processes of the adjacent company node combination is calculated to obtain the overall transaction indicator corresponding to the transaction indicators to be analyzed of the adjacent company node combination.

5. According to claim 3, a cross-border trade supply chain scheduling optimization method based on ant colony algorithm is characterized in that: The method for obtaining the initial degree of fit of the adjacent company node combination according to the profit, quality score value and speed score value corresponding to the overall transaction indicator includes: Calculate the mean of the overall transaction indicators corresponding to the profit, quality score and speed score, normalize the mean, and obtain the initial degree of fit of the adjacent company node combination.

6. According to the cross-border trade supply chain scheduling optimization method based on ant colony algorithm in claim 1, it is characterized in that: The method for obtaining the adjusted degree of fit includes: The corresponding adjacent industry link category combinations to all initial fit degrees are used as a first set of adjacent industry link category combinations; in the first set, the corresponding company nodes to all initial fit degrees are used as a second set of company nodes; According to the prominence of the second set in the first set, obtaining the prominence index of the company node in the first set; The company nodes whose prominence index is greater than the preset prominence threshold are regarded as the prominence nodes of the adjacent industrial link category combination; If there is no prominent node in the combination of adjacent industrial link categories, the initial degree of fit in the first set is directly used as the adjusted degree of fit; If there are prominent nodes in the combination of adjacent industrial link categories, the initial degree of fit in the first set is adjusted according to the prominent index to obtain the adjusted degree of fit.

7. The cross-border trade supply chain scheduling optimization method based on ant colony algorithm according to claim 6 is characterized in that: The method for obtaining the outstanding indicator includes: The mean of all initial fit degrees in the first set is calculated to obtain a first mean; the mean of all initial fit degrees in the second set is calculated to obtain a second mean, the first mean is subtracted from the second mean to obtain a difference, the difference is normalized to obtain a prominent index.

8. According to claim 6, a cross-border trade supply chain scheduling optimization method based on ant colony algorithm is characterized in that: If there is a prominent node in the combination of adjacent industrial links, the initial degree of fit in the first set is adjusted according to the prominent index, and the method for obtaining the adjusted degree of fit includes: In the first set, the initial fit degree corresponding to the combination of adjacent company nodes containing the prominent node is used as the degree to be adjusted; the initial fit degree corresponding to the combination of adjacent company nodes not containing the prominent node is directly used as the adjusted fit degree; For the combination of adjacent company nodes including the prominent node, the product of the prominent index corresponding to the degree to be adjusted and the preset ratio is calculated to obtain the reduction ratio; 1 minus the reduction ratio is calculated to obtain the ratio parameter; the ratio parameter is calculated and multiplied by the initial degree of fit to obtain the adjusted degree of fit.

9. The cross-border trade supply chain scheduling optimization method based on ant colony algorithm according to claim 1 is characterized in that: The method for obtaining the adjusted transaction quality parameter includes: The product of the adjusted degree of fit of the adjacent company node combination and the initial transaction quality parameter is calculated to obtain the adjusted transaction quality parameter of the adjacent company node combination.

10. The cross-border trade supply chain scheduling optimization method based on ant colony algorithm according to claim 1 is characterized in that: The method for obtaining the optimal supply chain includes: Based on the ant colony algorithm, the adjusted transaction quality parameters of the combination of adjacent company nodes are used as heuristic information to screen out the optimal supply chain from each supply chain in the supply chain network.

Images