Intelligent supply chain production, transportation and sales cooperative scheduling method and system

Abstract

The invention relates to the technical field of supply chain data management, in particular to an intelligent supply chain production, transportation and sales collaborative scheduling method and system. The method comprises the following steps: calculating a target smoothing parameter of a sales node according to a standard deviation of historical supply data of the sales node, and determining a sales demand predicted quantity of the sales node according to the target smoothing parameter of each sales node; calculating edge weights of various selectable vehicles to sales nodes in the commodity supply chain graph; planning an effective transportation path of each type of selectable vehicles according to the edge weights of the selectable vehicles to the sales nodes in the commodity supply chain graph, and determining the selectable degree of the effective path of each type of selectable vehicles according to the sales nodes on the effective path of each type of selectable vehicles and the sales demand prediction quantity of the sales nodes; according to the selectable degree of the effective path of each type of selectable vehicles, commodity scheduling in the commodity supply chain graph is realized, and the efficiency of supply chain production, transportation and sales collaborative scheduling is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of supply chain data management, and particularly to an intelligent supply chain production, transportation and sales collaborative scheduling method and system. Background Art

[0002] In supply chain management, the high-efficiency of production, transportation and sales collaborative scheduling is the core link to enhance the overall competitiveness and respond to market dynamic changes. Through collaborative scheduling, the production plan can be dynamically matched with the sales forecast and inventory level, and timely warnings can be given for abnormal states.

[0003] In the supply chain of products, there are a large number of sales nodes, various types of transport vehicles and highly dynamic demand changes, etc. Therefore, an efficient method for realizing the collaborative management of production, transportation and sales in the supply chain is needed. By analyzing the demand changes of each node for prediction, and using the predicted demand quantities of each node to dynamically plan the optimal transportation path, so as to achieve the efficient collaboration of production, transportation and sales links, and improve the overall supply chain response speed and operation efficiency. At present, the exponential smoothing algorithm is mostly used to obtain the predicted quantity of goods, and the Dijkstra algorithm is used to find the shortest path in the supply chain. The Dijkstra algorithm takes each vehicle as the starting point, and realizes the set of the shortest paths according to the distance weights between other nodes and the starting point until all nodes are traversed.

[0004] However, when the Dijkstra algorithm seeks the optimal path, it does not consider the load and cost consumed by the transport vehicle, and the exponential smoothing algorithm uses a fixed smoothing coefficient without considering the influence of factors such as seasons or promotional holidays on the market product demand, resulting in a lag in the prediction result and deviation from the actual demand. Therefore, how to accurately obtain the product demand quantity and efficiently transport the relevant goods to each sales node is the problem to be solved at present. Summary of the Invention

[0005] In order to solve the technical problem of how to accurately obtain the product demand quantity and efficiently transport the relevant goods to each sales node, the present invention provides an intelligent supply chain production, transportation and sales collaborative scheduling method and system.

[0006] In the first aspect, the present invention provides an intelligent supply chain production, transportation and sales collaborative scheduling method, adopting the following technical solutions: An intelligent supply chain production, transportation and sales collaborative scheduling method includes the steps of: Obtain the optional vehicles of the factory, the sales nodes in the commodity supply chain diagram and their historical supply data within a preset time period; calculate the target smoothing parameter of the sales node according to the standard deviation of the historical supply data of the sales node, and determine the predicted sales demand quantity of the sales node according to the target smoothing parameters of each sales node; calculate the edge weights of various optional vehicles to the sales nodes in the commodity supply chain diagram: ; , are respectively the edge weight and distance from the th type of optional vehicle to the i-th sales node in the commodity supply chain diagram, is the loading capacity of the th type of optional vehicle, is the predicted sales demand volume of the i-th sales node in the commodity supply chain diagram, is the exponential function with base e, is the standard normalization function, is the maximum value function; plan the effective paths for each type of optional vehicle to transport according to the edge weights of the optional vehicles to the sales nodes in the commodity supply chain diagram, and determine the selectability of each type of optional vehicle's effective path according to the sales nodes on the effective paths of each type of optional vehicle and the predicted sales demand volume of the sales nodes; realize the commodity scheduling in the commodity supply chain diagram according to the selectability of each type of optional vehicle's effective path.

[0007] According to the intelligent supply chain production, transportation and sales collaborative scheduling method provided by the present invention, after predicting the predicted sales demand volume of the commodity and then performing commodity scheduling according to the predicted sales demand volume of the sales nodes, the efficiency of commodity scheduling can be effectively improved. When obtaining the predicted sales demand volume of each sales node for the commodity, by introducing the standard deviation to dynamically adjust the smoothing parameter of each sales node, the present invention can effectively cope with market fluctuations and improve the accuracy of demand prediction, thereby providing a reliable basis for production stock preparation. When performing scheduling after accurately obtaining the predicted sales demand volume of each sales node for the commodity, the present invention plans the transportation paths by calculating the edge weights of each type of optional vehicle to each sales node in the commodity supply chain diagram, comprehensively considers the unloading volume, transportation distance and vehicle loading capacity of each type of optional vehicle, dynamically calculates the path weights and evaluates the path preference degree, ensuring the maximization of resource utilization rate and the minimization of transportation cost, thereby effectively improving the efficiency of commodity scheduling in the commodity supply chain diagram.

[0008] According to an intelligent supply chain production, transportation and sales collaborative scheduling method provided by the present invention, before obtaining the optional vehicles of the factory, the sales nodes in the commodity supply chain diagram and their historical supply data within a preset period, it further includes: obtaining all the sales manufacturers of a factory as sales nodes according to the enterprise ERP system, constructing the commodity supply chain diagram of the factory according to the coordinate positions between the sales nodes, obtaining all the deployable vehicles of the factory as optional vehicles, and determining the loading capacity of each type of optional vehicle.

[0009] By constructing the commodity supply chain diagram of the factory, the present invention can comprehensively and intuitively analyze the sales nodes and operation conditions of this type of commodity, so that subsequent vehicle transportation commodity scheduling can be accurately realized based on this.

[0010] An intelligent supply chain production, transportation and sales collaborative scheduling method provided by the present invention, calculating the target smoothing parameter of the sales node according to the standard deviation of the historical supply data of the sales node, includes: ; , are the target smoothing parameter of the th sales node and the standard deviation of the historical supply data respectively, is the preset smoothing parameter, is the total number of sales nodes, is the th sales node and the th sales node DTW distance of the historical supply data, is the th sales node and the maximum value of the DTW distance of the historical supply data of other sales nodes, is the standard normalization function.

[0011] The present invention takes into account that when there are large fluctuations in the historical supply data of the sales node, the fixed preset smoothing parameter cannot accurately capture this fluctuation, resulting in prediction errors. Therefore, the present invention provides an accurate calculation method for the target smoothing parameter of the sales node. By dynamically adjusting the target smoothing parameter of the sales node, various changes in the historical supply data can be accurately and timely obtained, so as to accurately obtain the sales demand prediction value of the sales node.

[0012] An intelligent supply chain production, transportation and sales collaborative scheduling method provided by the present invention, determining the sales demand prediction quantity of the sales node according to the target smoothing parameter of each sales node, includes: using the target smoothing parameter of each sales node in the exponential smoothing method to obtain the sales demand prediction quantity of each sales node.

[0013] An intelligent supply chain production, transportation and sales collaborative scheduling method provided by the present invention, planning the effective path of each type of optional vehicle transportation according to the edge weight from the optional vehicle to the sales node in the commodity supply chain diagram, includes: taking the optional vehicle after loading as the initial node, taking the sales node corresponding to the maximum value of the edge weight between the initial node and all sales nodes as the new initial node of this type of optional vehicle, continuing to obtain the maximum value of the edge weight between the new initial node and the remaining sales nodes, and so on in a cycle until the maximum value of the edge weight between the new initial node and the remaining sales nodes is 0, stopping the cycle, and connecting all the initial nodes to obtain the effective path of this type of optional vehicle.

[0014] An intelligent supply chain production, transportation and sales collaborative scheduling method provided by the present invention, determining the selectability of the effective path of each type of optional vehicle, includes: ; is the option degree of the effective path of the th type of optional vehicle, is the number of sales nodes on the effective path of the th type of optional vehicle, is the total number of sales nodes, is the predicted sales demand of the th sales node on the effective path of the th type of optional vehicle, is the loading capacity of the th type of optional vehicle.

[0015] In the present invention, considering that only the consumption cost in the transportation process is considered in the process of constructing the effective path, when determining the best choice of each path, the resource utilization degree on the effective path of each type of optional vehicle also needs to be considered. Therefore, the present invention provides an accurate calculation method for the option degree of the effective path of the optional vehicle. By analyzing the resource utilization degree on each effective path, low consumption and maximized resource utilization can be achieved during scheduling.

[0016] According to an intelligent supply chain production, transportation and sales collaborative scheduling method provided by the present invention, the commodity scheduling in the commodity supply chain diagram is realized according to the option degree of the effective path of each type of optional vehicle, including: taking the effective path corresponding to the maximum value of the option degrees of all types of optional vehicle effective paths as the first running path in the commodity supply chain diagram, and marking all the sales nodes on the first running path; obtaining all the unmarked sales nodes to construct a secondary distribution diagram of the commodity supply chain, and continuing to mark until all the sales nodes are marked to obtain the marking result, so as to realize the commodity scheduling.

[0017] According to an intelligent supply chain production, transportation and sales collaborative scheduling method provided by the present invention, the realization of the commodity scheduling includes: allocating corresponding optional vehicles for each sales node according to the marking result for distribution.

[0018] According to an intelligent supply chain production, transportation and sales collaborative scheduling method provided by the present invention, after the realization of the commodity scheduling in the commodity supply chain diagram, it further includes: real-time monitoring of the transportation paths of the optional vehicles.

[0019] By real-time monitoring of the transportation paths of the optional vehicles, the present invention can obtain the actual position of the vehicle and the expected arrival time, so as to flexibly adjust the surrounding vehicles to undertake emergency orders and avoid situations such as empty running or idle transportation capacity.

[0020] In the second aspect, the present invention provides an intelligent supply chain production, transportation and sales collaborative scheduling system, adopting the following technical solutions: An intelligent supply chain production, transportation and sales collaborative scheduling system, comprising: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned intelligent supply chain production, transportation and sales collaborative scheduling method is implemented.

[0021] By adopting the above technical solution, a computer program is generated from the above-mentioned intelligent supply chain production, transportation and sales collaborative scheduling method and stored in the memory to be loaded and executed by the processor, so as to manufacture a terminal device according to the memory and the processor, which is convenient to use.

[0022] The present invention has the following technical effects: Based on the above technical solution, an intelligent supply chain production, transportation and sales collaborative scheduling method and system provided by the present invention can effectively improve the efficiency of commodity scheduling by predicting the pre-sale demand volume of commodities and then scheduling commodities according to the pre-sale demand volume of sales nodes. When obtaining the pre-sale demand volume of each sales node for commodities, the present invention can effectively cope with market fluctuations and improve the accuracy of demand prediction by introducing the standard deviation to dynamically adjust the smoothing parameter of each sales node, so as to provide a reliable basis for production stock preparation. When scheduling after accurately obtaining the pre-sale demand volume of each sales node for commodities, the present invention calculates the edge weights of each type of optional vehicle to each sales node in the commodity supply chain diagram for transportation path planning, comprehensively considers the unloading volume, transportation distance and vehicle load of each type of optional vehicle, dynamically calculates the path weights and evaluates the path preference degree, ensuring the maximization of resource utilization rate and the minimization of transportation cost, thereby effectively improving the efficiency of commodity scheduling in the commodity supply chain diagram. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic flowchart of an intelligent supply chain production, transportation and sales collaborative scheduling method provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention.

[0025] The embodiment of the present invention discloses an intelligent supply chain production, transportation and sales collaborative scheduling method, which provides a basis for reasonable planning of production, transportation and sales of the supply chain by analyzing the edge weights of each type of optional vehicle in the factory delivering goods to sales nodes on each path, so as to accurately achieve collaborative scheduling and improve the accuracy and efficiency of supply chain scheduling.

[0026] Specifically, please refer to Figure 1 as shown in Figure 1It is a schematic flowchart of an intelligent supply chain production, transportation and sales collaborative scheduling method provided by an embodiment of the present invention. The method specifically includes the following steps: S1: Obtain the optional vehicles of the factory, the sales nodes in the commodity supply chain diagram, and their historical supply data within a preset time period.

[0027] Among them, the length of the preset time period can be set to one month, and the historical supply data within the preset time period is the supply data of the sales node in the past month. The length of the preset time period can be specifically set according to actual needs.

[0028] For the convenience of understanding, an embodiment of the present invention is described by taking the scheduling of any kind of commodity as an example, but it does not mean that the embodiments of the present invention are only limited to this.

[0029] Exemplarily, when obtaining the historical supply data of the sales node within the preset time period, the order placement time of the most recent supply data of the sales node can be used as the end time of the preset time period.

[0030] An example is given to illustrate the method for obtaining the historical supply data within the preset time period: If the order placement time of the most recent supply data of a sales node is 18:00 on May 27th, then the historical supply data of this node within the preset time period is all the supply data from 18:00 on April 27th to 18:00 on May 27th.

[0031] In order to avoid data loss or errors caused by unified processing of data with different dimensions, in an embodiment of the present invention, all the collected data can be preprocessed first.

[0032] Among them, the preprocessing method can be missing data interpolation, data normalization to eliminate dimensions, etc., which can be specifically set according to actual needs, and the embodiments of the present invention do not limit this too much here.

[0033] It should be noted that when planning the best path for supply chain scheduling, in addition to the path length, it is also necessary to comprehensively consider the load capacity of the transportation vehicle for the commodity and the transportation cost, so as to improve the accuracy of supply chain scheduling and maximize resource utilization. In the actual operation process of the supply chain, if the factory starts production and stock preparation only after receiving the commodity order, there will be a lag in order preparation and transportation, reducing the operating efficiency of the supply chain. The market demand for commodities is usually relatively stable, and it also shows regularity in the short term in some seasonal or festival promotion situations. Therefore, an embodiment of the present invention can predict the demand for commodities based on the commodity sales situation in the past period of time, so as to effectively reduce the situation of insufficient commodity storage.

[0034] Exemplarily, in the embodiments of the present invention, before obtaining the optional vehicles of the factory, the sales nodes in the commodity supply chain diagram, and their historical supply data within a preset period, the following steps are further included: obtaining all the sales manufacturers of a factory as sales nodes according to the enterprise ERP system, constructing the commodity supply chain diagram of the factory according to the coordinate positions between the sales nodes, obtaining all the deployable vehicles of the factory as optional vehicles, and determining the loading capacity of each type of optional vehicle.

[0035] Specifically, all the sales situations of the commodity and the order placement situations of each sales manufacturer are recorded in the enterprise ERP system, which integrates the full-process information from the supplier to the customer. By accessing the enterprise ERP system, the factory can obtain all the historical sales situations of the commodity, where the historical sales situations at least include the location of each sales node, the quantity of the commodity ordered for each order and the order time, and all the deployable vehicles of the factory that produce the commodity.

[0036] It can be understood that after collecting the historical supply data of each sales node according to the above steps, the sales demand prediction quantity of each sales node can be obtained by processing the historical supply data through the exponential smoothing method. However, the exponential smoothing method uses a fixed smoothing parameter and cannot accurately respond to the fluctuating historical supply data, resulting in the subsequent inability to accurately achieve the collaborative scheduling of the supply chain based on the relatively inaccurate sales demand prediction quantity. Therefore, the embodiments of the present invention provide a method for dynamically adjusting the smoothing parameter of the sales node. By analyzing the fluctuation situation of the historical supply data of the sales node, the sales demand prediction quantity of each sales node can be accurately obtained, that is, the following steps are executed.

[0037] S2: Calculate the target smoothing parameter of the sales node according to the standard deviation of the historical supply data of the sales node, and determine the sales demand prediction quantity of the sales node according to the target smoothing parameters of each sales node.

[0038] It should be noted that the exponential smoothing method smooths the time series data through weighted averaging, and the weights decay exponentially with time. The weights of recent data will increase, and the higher the smoothing parameter, the higher the weight of recent data. For the sales node with large fluctuations in historical supply data, it is necessary to increase its smoothing parameter, so as to weaken the influence of historical trends and strengthen the weight of recent observations to adapt to rapid changes, so as to accurately obtain the sales demand prediction quantity of each sales node. For the sales node with small fluctuations in historical supply data, similar weights can be set for historical data and recent data.

[0039] Exemplarily, in the embodiments of the present invention, to calculate the target smoothing parameter of the sales node, the following relational expression can be referred to: ; is the The target smoothing parameter of each sales node, is the standard deviation of the historical supply data of the th sales node, is the preset smoothing parameter, is the total number of sales nodes, is the th sales node and the th sales node's DTW distance of historical supply data, is the maximum value of the DTW distance between the th sales node and the historical supply data of other sales nodes, is the standard normalization function, .

[0040] Among them, the preset smoothing parameter can be set to 0.5, and can be specifically set according to actual needs. The specific steps to obtain the DTW distance of the historical supply data between sales nodes can be realized by the prior art, and are not elaborated in the embodiments of the present invention.

[0041] In the above formula, is used to characterize the fluctuation degree of the commodity demand quantity of the historical supply data of the current th sales node. The larger this value is, the greater the possibility that there are fluctuations caused by seasonal, festival or its own accidental factors in the historical supply data of the current sales node. is used to characterize the consistency between the recent demand change of the current th sales node for the commodity and the recent demand change of other sales nodes for the commodity. The larger this value is, the less similar the recent demand of this sales node for the commodity is to the demand of other nodes.

[0042] Specifically, when the fluctuation degree of the recent commodity demand quantity of the current sales node is larger, if the similarity of the demand change between the current sales node and other sales nodes is higher, it indicates that the current sales node is more likely to be affected by the same factors such as seasonal or festival promotions, resulting in demand fluctuations. The demand pattern of the current sales node may continue this fluctuation trend. Therefore, it is necessary to increase the smoothing parameter to enhance the attention to recent data, so as to accurately capture this change. On the contrary, if the similarity of the demand change between the current sales node and other sales nodes is lower, it indicates that the change of the current sales node is more likely to be accidental fluctuations. At this time, it is also necessary to appropriately increase the weight of recent data, so as to reduce the impact of sudden fluctuations.

[0043] When the fluctuation degree of the recent commodity demand quantity of the current sales node is smaller, it indicates that the demand degree of the current sales node for the commodity is in a stable change state. At this time, the preset smoothing parameter can be maintained for continued prediction.

[0044] After obtaining the target smoothing parameter for the demand prediction of each sales node according to the above steps, the predicted sales demand volume of the sales node can be determined based on the target smoothing parameter of the sales node.

[0045] Exemplarily, in the embodiment of the present invention, determining the predicted sales demand volume of the sales node according to the target smoothing parameter of each sales node includes: using the target smoothing parameter of each sales node in the exponential smoothing method to obtain the predicted sales demand volume of each sales node.

[0046] Specifically, when obtaining the predicted sales demand volume of the sales node, the actual demand volume and the predicted sales demand volume in the most recent supply data of the sales node can be obtained first. Substituting the target smoothing parameter of the sales node, the actual demand volume, and the predicted sales demand volume in the most recent supply data into the single exponential smoothing formula, the predicted sales demand volume of the sales node for the commodity can be obtained. The single exponential smoothing formula is an existing formula and will not be elaborated in the embodiment of the present invention.

[0047] After obtaining the predicted sales demand volume of each sales node for the commodity according to the above steps, the factory can allocate corresponding vehicles for each sales node according to the existing optional vehicles for delivery, so as to achieve efficient distribution, improve the transportation efficiency of the supply chain, that is, execute the following steps.

[0048] S3: Calculate the edge weights of various optional vehicles to the sales nodes in the commodity supply chain diagram, and plan the effective paths of each type of optional vehicle transportation according to the edge weights of the optional vehicles to the sales nodes in the commodity supply chain diagram.

[0049] It can be understood that the distribution of the sales nodes of the commodity is usually relatively discrete. When the factory allocates freight vehicles, in order to reduce the transportation cost, the products of the same sales node will be planned in the same vehicle as much as possible. And the loading capacities of different vehicles for the commodity are not the same. When planning according to the predicted sales demand volume of each sales node, it is necessary to consider the adaptability of vehicles with different loading capacities to each sales node. Therefore, in the embodiment of the present invention, when planning the operation routes of the vehicles, the location of the factory can be used as the initial node of each loaded optional vehicle. By comprehensively considering the loading capacity of the vehicle, the predicted sales demand volume of the sales node, and the distance between the paths, the weights of each type of optional vehicle from the initial node to each sales node can be accurately obtained.

[0050] Exemplarily, in the embodiment of the present invention, calculating the edge weights of each type of optional vehicle to each sales node in the commodity supply chain diagram can be specifically referred to the following relational expressions: ; is the edge weight of the th type of optional vehicle to the i-th sales node in the commodity supply chain diagram. is the distance from the optional vehicle of the category to the i-th sales node in the commodity supply chain diagram, is the loading capacity of the optional vehicle of the category, is the predicted sales demand of the i-th sales node in the commodity supply chain diagram, is the exponential function with base e, is the standard normalization function, is the maximum value function.

[0051] In the above formula, represents the ratio of the remaining loading capacity to the total capacity after the optional vehicle of the category directly unloads at the i-th sales node. The smaller this value, the more the optional vehicle of the category directly unloads at the i-th sales node, and the lower the cost for the optional vehicle of the category to transport the remaining goods to other sales nodes. When obtaining the possibility of each category of optional vehicle going to each sales node, optional vehicles with the same loading capacity as the predicted sales demand or with a loading capacity greater than the predicted sales demand can be preferentially combined and allocated, so as to effectively avoid the cost waste caused by insufficient freight volume of the optional vehicle and the need for multiple transports. By the situation where the loading capacity is less than the predicted sales demand can be zeroed out to avoid the influence of negative values on the weight calculation.

[0052] To sum up, if the unloading volume of the optional vehicle of the current category at this sales node is more and the distance is closer, it means that the efficiency of planning this category of optional vehicle to transport the goods required by this sales node is higher, and the corresponding edge weight is also higher. On the contrary, it means that the efficiency of planning this category of optional vehicle to transport the goods required by this sales node is lower, the cost is higher, and the corresponding edge weight is also smaller.

[0053] After obtaining the edge weights of each category of optional vehicle to each sales node in the commodity supply chain diagram according to the above steps, the sales node that each category of optional vehicle needs to reach for the first time can be planned according to the edge weights, and the reached sales node can be used as the new initial node, and continue to calculate the edge weights between the new initial node and the remaining sales nodes, and so on, until the effective paths of each category of optional vehicle are finally obtained.

[0054] Exemplarily, in the embodiments of the present invention, planning the effective path for each type of optional vehicle according to the edge weight from the optional vehicle to the sales node in the commodity supply chain diagram includes: taking the optional vehicle after loading as the initial node, and taking the sales node corresponding to the maximum edge weight between the initial node and all sales nodes as the new initial node of this type of optional vehicle, and continuing to obtain the maximum edge weight between the new initial node and the remaining sales nodes, and so on in a cycle until the maximum edge weight between the new initial node and the remaining sales nodes is 0, then stopping the cycle, and connecting all the initial nodes to obtain the effective path of this type of optional vehicle.

[0055] It can be understood that if the maximum edge weight between the initial node and all the remaining sales nodes is 0, it means that the cargo capacity of this type of optional vehicle is less than the predicted sales demand value of each remaining sales node, and the transportation consumption cost of this type of optional vehicle from the initial node to all other sales nodes is relatively high. Therefore, the effective path of this type of optional vehicle ends here.

[0056] After obtaining the effective path of each type of optional vehicle according to the above steps, the optionality of the effective path of each type of optional vehicle planned according to the above method can be determined according to the sales nodes on the effective path of each type of optional vehicle and the predicted sales demand volume of the sales nodes, that is, the following steps are executed.

[0057] S4: Determine the optionality of the effective path of each type of optional vehicle according to the sales nodes on the effective path of each type of optional vehicle and the predicted sales demand volume of the sales nodes; realize the commodity scheduling in the commodity supply chain diagram according to the optionality of the effective path of each type of optional vehicle.

[0058] It should be noted that the above steps can obtain the effective path of each type of optional vehicle by comprehensively considering the transportation consumption cost, but do not consider whether the resource utilization is maximized. Therefore, in the embodiments of the present invention, it is also necessary to analyze whether the transportation nodes passed by the effective path of each type of optional vehicle achieve the maximum resource utilization, so as to obtain the optimal path and ensure that the high-efficiency and low-consumption transport vehicles preferentially cover each sales node.

[0059] Exemplarily, in the embodiments of the present invention, determining the optionality of the effective path of each type of optional vehicle includes: ; is the optionality of the effective path of the th type of optional vehicle, is the number of sales nodes on the effective path of the th type of optional vehicle, is the total number of sales nodes, is the predicted sales demand volume of the th sales node on the effective path of the th type of optional vehicle, is the loading capacity of the class of alternative vehicles.

[0060] In the above formula, represents the ratio of the number of sales nodes passed by the effective path of this class of alternative vehicles to the total number of sales nodes in the commodity supply chain graph. The larger this value, the greater the proportion of sales nodes covered by the effective path of this class of alternative vehicles, and the more sales nodes can be served in a larger range.

[0061] represents the ratio of the total predicted sales demand of the sales nodes passed by the effective path of this class of alternative vehicles to the loading capacity of this class of alternative vehicles. The larger this value, the higher the degree of demand satisfaction of the effective path for the sales nodes on its effective path, and the higher the load efficiency. Therefore, if the number of sales nodes passed by the effective path is more and the degree of demand satisfaction for each sales node is higher, the resource utilization rate is higher and the coverage is wider, and the selectability of this effective path is higher.

[0062] Based on this, the selectability of the effective path of each class of alternative vehicles can be obtained.

[0063] Exemplarily, in the embodiment of the present invention, commodity scheduling in the commodity supply chain graph is implemented according to the selectability of the effective path of each class of alternative vehicles, including: taking the effective path corresponding to the maximum value of the selectability of the effective paths of all classes of alternative vehicles as the first running path in the commodity supply chain graph, and marking all the sales nodes on the first running path; obtaining all the unmarked sales nodes to construct a secondary distribution graph of the commodity supply chain, and continuing to mark until all the sales nodes are marked, obtaining a marking result, and implementing commodity scheduling.

[0064] Among them, the marking method can be the type of alternative vehicle corresponding to the sales node and the order of the sales node in the effective path. The planning direction of the effective path is one-way, that is, the alternative vehicle will not return to the previously reached node.

[0065] It can be understood that when planning the effective path based on the above steps, some sales nodes may not be in the effective path (for example, when the predicted sales demand of the sales node is greater than the cargo capacity of the alternative vehicle, the edge weight corresponding to it is 0, etc.), or the selectability of the effective path of this class of alternative vehicles is not the maximum value of the selectability between nodes. Therefore, for the remaining unmarked sales nodes, a secondary distribution graph of the commodity supply chain needs to be constructed, and the maximum value of the selectability in the secondary distribution graph of the commodity supply chain is continuously obtained according to the content recorded in the above steps to mark the remaining sales nodes, and so on, until the edge weights of all the remaining sales nodes are 0 and no effective path can be constructed, then the calculation of the maximum value of the selectability is stopped, and manual assignment marking is performed according to actual needs, and finally all the sales nodes in the commodity supply chain graph are marked.

[0066] After marking all sales nodes according to the above steps, the optional vehicles can be allocated according to the marking results.

[0067] Exemplarily, in the embodiment of the present invention, to achieve commodity scheduling, it includes: allocating corresponding optional vehicles to each sales node according to the marking results for distribution.

[0068] Exemplarily, in the embodiment of the present invention, after achieving commodity scheduling in the commodity supply chain diagram, it further includes: real-time monitoring of the transportation paths of the optional vehicles.

[0069] It can be seen that in the embodiment of the present invention, when achieving collaborative scheduling of production, transportation, and sales in the supply chain, the optional vehicles of the factory, the sales nodes in the commodity supply chain diagram, and their historical supply data within a preset time period can be obtained; calculate the target smoothing parameter of the sales node according to the standard deviation of the historical supply data of the sales node, determine the predicted sales demand volume of the sales node according to the target smoothing parameters of each sales node; calculate the edge weights of various optional vehicles in the commodity supply chain diagram to the sales nodes: ; , are respectively the edge weight and distance from the th type of optional vehicle in the commodity supply chain diagram to the i-th sales node, is the loading capacity of the th type of optional vehicle, is the predicted sales demand volume of the i-th sales node in the commodity supply chain diagram, is the exponential function with base e, is the standard normalization function, is the maximum value function; plan the effective paths of each type of optional vehicle transportation according to the edge weights of the optional vehicles in the commodity supply chain diagram to the sales nodes, determine the selectability of the effective paths of each type of optional vehicle according to the sales nodes on the effective paths of each type of optional vehicle and the predicted sales demand volume of the sales nodes; achieve commodity scheduling in the commodity supply chain diagram according to the selectability of the effective paths of each type of optional vehicle, effectively improving the efficiency of collaborative scheduling of production, transportation, and sales in the supply chain.

[0070] The embodiment of the present invention also discloses an intelligent supply chain production, transportation, and sales collaborative scheduling system, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, it implements an intelligent supply chain production, transportation, and sales collaborative scheduling method provided by the present invention.

[0071] The above system further includes other components well-known to those skilled in the art such as a communication bus and a communication interface, and their settings and functions are known in the art, so they will not be elaborated here.

[0072] In the present invention, the foregoing memory may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0073] The above are all preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention shall be covered within the protection scope of the present invention.

Claims

1. An intelligent supply chain production, transportation and sales collaborative scheduling method, characterized in that Including: Obtain the optional vehicles of the factory, the sales nodes in the commodity supply chain diagram, and their historical supply data within a preset time period; Calculate the target smoothing parameter of the sales node according to the standard deviation of the historical supply data of the sales node, and determine the predicted sales demand volume of the sales node according to the target smoothing parameters of each sales node; Calculate the edge weights from various optional vehicles to the sales nodes in the commodity supply chain diagram: ； , are respectively the edge weight and distance from the th type of optional vehicle to the i-th sales node in the commodity supply chain diagram, is the loading capacity of the th type of optional vehicle, is the predicted sales demand volume of the i-th sales node in the commodity supply chain diagram, is the exponential function with base e, is the standard normalization function, is the maximum value function; Plan the effective transportation paths of each type of optional vehicle according to the edge weights from the optional vehicles to the sales nodes in the commodity supply chain diagram, and determine the selectability of the effective paths of each type of optional vehicle according to the sales nodes on the effective paths of each type of optional vehicle and the predicted sales demand volume of the sales nodes; Realize the commodity scheduling in the commodity supply chain diagram according to the selectability of the effective paths of each type of optional vehicle.

2. The intelligent supply chain production, transportation and sales collaborative scheduling method according to claim 1, wherein Before the step of obtaining the optional vehicles of the factory, the sales nodes in the commodity supply chain diagram, and their historical supply data within a preset time period, it further includes: Obtain all the sales manufacturers of a factory as sales nodes according to the enterprise ERP system, construct the commodity supply chain diagram of the factory according to the coordinate positions between the sales nodes, obtain all the deployable vehicles of the factory as optional vehicles, and determine the loading capacity of each type of optional vehicle.

3. An intelligent supply chain production, transportation and sales collaborative scheduling method according to claim 1, characterized in that, The step of calculating the target smoothing parameter of the sales node according to the standard deviation of the historical supply data of the sales node includes: ； , are the target smoothing parameter of the th sales node and the standard deviation of historical supply data, is the preset smoothing parameter, is the total number of sales nodes, is the th sales node and the th sales node's DTW distance of historical supply data, is the maximum value of the DTW distance between the th sales node and the historical supply data of other sales nodes, is the standard normalization function.

4. An intelligent supply chain production, transportation and sales collaborative scheduling method according to claim 1, characterized in that The step of determining the predicted sales demand volume of the sales node according to the target smoothing parameters of each sales node includes: Use the target smoothing parameters of each sales node in the exponential smoothing method to obtain the predicted sales demand volume of each sales node.

5. An intelligent supply chain production, transportation and sales collaborative scheduling method according to claim 1, characterized in that The step of planning the effective transportation paths of each type of optional vehicle according to the edge weights from the optional vehicles to the sales nodes in the commodity supply chain diagram includes: Take the optional vehicle after loading as the initial node, take the sales node corresponding to the maximum edge weight between the initial node and all sales nodes as the new initial node of this type of optional vehicle, continue to obtain the maximum edge weight between the new initial node and the remaining sales nodes, and so on in a loop until the maximum edge weight between the new initial node and the remaining sales nodes is 0, then stop the loop, and connect all the initial nodes to obtain the effective path of this type of optional vehicle.

6. The intelligent supply chain production, transportation and sales collaborative scheduling method according to claim 1, characterized in that, The step of determining the selectability of the effective paths of each type of optional vehicle includes: ； is the option degree of the effective path of the th type of optional vehicle, is the number of sales nodes on the effective path of the th type of optional vehicle, is the total number of sales nodes, is the predicted sales demand of the th sales node on the effective path of the th type of optional vehicle, is the loading capacity of the th type of optional vehicle.

7. An intelligent supply chain production, transportation and sales collaborative scheduling method according to claim 1, characterized in that, The step of realizing the commodity scheduling in the commodity supply chain diagram according to the selectability of the effective paths of each type of optional vehicle includes: Take the effective path corresponding to the maximum selectability of the effective paths of all types of optional vehicles as the first running path in the commodity supply chain diagram, and mark all the sales nodes on the first running path; obtain all the unmarked sales nodes to construct a secondary allocation diagram of the commodity supply chain, and continue to mark until all the sales nodes are marked to obtain the marking result and realize the commodity scheduling.

8. An intelligent supply chain production, transportation and sales collaborative scheduling method according to claim 7, characterized in that The step of realizing the commodity scheduling includes: Allocate corresponding optional vehicles for distribution to each sales node according to the marking result.

9. An intelligent supply chain production, transportation and sales collaborative scheduling method according to claim 1, characterized in that, After the step of realizing the commodity scheduling in the commodity supply chain diagram, it further includes: Monitor the transportation paths of the optional vehicles in real time.

10. An intelligent supply chain production, transportation and sales collaborative scheduling system, characterized in that, Including: A processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement an intelligent supply chain production, transportation and sales collaborative scheduling method according to any one of claims 1-9.

Images