An intelligent supply chain production, transportation and marketing collaborative scheduling method and system

Abstract

The present application relates to the technical field of supply chain data management, and more particularly to a kind of intelligent supply chain production and marketing coordination scheduling method and system.The method comprises the following steps: calculating the target smoothing parameter of the sales node according to the standard deviation of the historical supply data of the sales node, determining the sales demand forecast of the sales node according to the target smoothing parameter of each sales node;Calculate the edge weight of each type of optional vehicle in the commodity supply chain graph to the sales node;According to the edge weight of the optional vehicle in the commodity supply chain graph to the sales node, the effective path of each type of optional vehicle transportation is planned, and the optional degree of each type of optional vehicle effective path is determined according to the sales node on each type of optional vehicle effective path and the sales demand forecast of the sales node;According to the optional degree of each type of optional vehicle effective path, the commodity scheduling in the commodity supply chain graph is realized, and the efficiency of supply chain production and marketing coordination scheduling is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of supply chain data management, and particularly relates to an intelligent supply chain production, transportation and marketing collaborative scheduling method and system. BACKGROUND

[0002] In supply chain management, efficient production, transportation and marketing collaborative scheduling is the core link to improve overall competitiveness and respond to market dynamic changes. Through collaborative scheduling, production planning can be dynamically matched with sales forecasting and inventory levels, and abnormal conditions can be timely warned.

[0003] In the product supply chain, a large number of sales nodes, various types of transport vehicles and highly dynamic demand changes are involved, so an efficient supply chain production, transportation and marketing collaborative management method is needed. The method predicts demand changes by analyzing each node, dynamically plans the optimal transportation path using the predicted demand of each node, and realizes efficient collaboration between production, transportation and marketing to improve the overall supply chain response speed and operational efficiency. Currently, the predicted quantity of goods is obtained by an exponential smoothing algorithm, and the shortest path in the supply chain is found by Dijkstra algorithm. Dijkstra algorithm takes each vehicle as a starting point, and realizes the collection of the shortest path according to the distance weight between other nodes and the starting point until all nodes are traversed.

[0004] However, Dijkstra algorithm does not consider the carrying capacity and consumption cost of transport vehicles when seeking the best path, and exponential smoothing algorithm uses a fixed smoothing coefficient and does not consider the influence of seasonal or promotional holidays on market product demand, resulting in lagging prediction results and deviation from actual demand. Therefore, how to accurately obtain product demand and efficiently transport related goods to each sales node is a problem to be solved. SUMMARY

[0005] To solve the technical problem of how to accurately obtain product demand and efficiently transport related goods to each sales node, the present application provides an intelligent supply chain production, transportation and marketing collaborative scheduling method and system.

[0006] In the first aspect, the present application provides an intelligent supply chain production, transportation and marketing collaborative scheduling method, which adopts the following technical scheme:

[0007] An intelligent supply chain production, transportation and marketing collaborative scheduling method, comprising the steps of:

[0008] Obtain the sales nodes and their historical supply data for a preset time period in the factory's optional vehicle and commodity supply chain diagram; calculate the target smoothing parameter for each sales node based on the standard deviation of its historical supply data, and determine the sales demand forecast for each sales node based on its target smoothing parameter; calculate the edge weights from each optional vehicle type to the sales node in the commodity supply chain diagram.

[0009] ;

[0010] , The first The edge weights and distances of optional vehicles in the commodity supply chain graph to the i-th sales node. For the first The load capacity of optional vehicles. Let represent the predicted sales demand for the i-th sales node in the commodity supply chain diagram. It is an exponential function with base e. For the standard normalized function, To find the maximum value function; based on the edge weights of the optional vehicles in the commodity supply chain graph to the sales nodes, plan the effective transportation path for each type of optional vehicle; based on the sales nodes on the effective path of each type of optional vehicle and the sales demand forecast of the sales nodes, determine the selectivity of the effective path of each type of optional vehicle; and realize commodity scheduling in the commodity supply chain graph based on the selectivity of the effective path of each type of optional vehicle.

[0011] This invention improves the efficiency of commodity scheduling by predicting the sales demand forecast for each commodity and then scheduling the commodities based on the predicted sales demand at each sales node. When obtaining the predicted sales demand for each commodity at each sales node, this invention dynamically adjusts the smoothing parameter of each sales node by introducing standard deviation, effectively addressing market fluctuations and improving the accuracy of demand forecasting, thus providing a reliable basis for production and inventory preparation. After accurately obtaining the predicted sales demand for each commodity at each sales node, this invention calculates the edge weights of each type of optional vehicle in the commodity supply chain graph to plan transportation routes. It comprehensively considers the unloading volume, transportation distance, and vehicle load capacity of each type of optional vehicle, dynamically calculates path weights, and evaluates path optimization to ensure maximum resource utilization and minimum transportation costs, thereby effectively improving the efficiency of commodity scheduling in the commodity supply chain graph.

[0012] According to the intelligent supply chain production, transportation and sales collaborative scheduling method provided by the application, the selectable vehicles of a factory, the sales nodes in a commodity supply chain graph and the historical supply data of the sales nodes in a preset time period are obtained, and the method further comprises the following steps: obtaining all sales manufacturers of a factory as the sales nodes according to an enterprise ERP system, constructing a commodity supply chain graph of the factory according to the coordinate positions of the sales nodes, obtaining all the deployable vehicles of the factory as the selectable vehicles, and determining the loading capacity of each type of the selectable vehicles.

[0013] The commodity supply chain graph of the factory is constructed, so that the sales nodes and the running conditions of the commodities can be comprehensively and intuitively analyzed, and the subsequent vehicle transportation commodity scheduling can be accurately realized based on the analysis.

[0014] According to the intelligent supply chain production, transportation and sales collaborative scheduling method provided by the application, the target smoothing parameter of the sales node is calculated according to the standard deviation of the historical supply data of the sales node, and the method comprises the following steps:

[0015] ;

[0016] 、 The target smoothing parameter of the i th sales node is denoted as a i, the standard deviation of the historical supply data of the i th sales node is denoted as b i, the preset smoothing parameter is denoted as c, the total number of the sales nodes is denoted as n, the DTW distance between the historical supply data of the i th sales node and the historical supply data of the j th sales node is denoted as d i j, the maximum value of the DTW distance between the historical supply data of the i th sales node and the historical supply data of other sales nodes is denoted as e i, and the standard normalization function is denoted as f.

[0017] The application considers that when the historical supply data of the sales node has a large fluctuation, the fixed preset smoothing parameter cannot accurately capture the fluctuation, resulting in a prediction error, so the application provides an accurate calculation method of the target smoothing parameter of the sales node, and the target smoothing parameter of the sales node is dynamically adjusted, so that various changes in the historical supply data can be accurately and timely obtained, and the sales demand prediction value of the sales node can be accurately obtained.

[0018] According to the intelligent supply chain production, transportation and sales collaborative scheduling method provided by the application, the target smoothing parameter of the sales node is calculated according to the standard deviation of the historical supply data of the sales node, and the method comprises the following steps:

[0019] ​​​​​​​​​According to the intelligent supply chain production, transportation and sales collaborative scheduling method provided by the present invention, the step of planning the effective transportation path of each type of optional vehicle based on the edge weights of optional vehicles to sales nodes in the commodity supply chain graph includes: taking the optional vehicle after loading as the initial node, 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, continuing to obtain the maximum edge weight between the new initial node and the remaining sales nodes, and repeating this process until the maximum edge weight between the new initial node and the remaining sales nodes is 0, stopping the loop, and connecting all initial nodes to obtain the effective path of this type of optional vehicle.

[0020] According to the intelligent supply chain production, transportation, and sales collaborative scheduling method provided by the present invention, determining the selectivity of the effective path for each type of optional vehicle includes:

[0021] ;

[0022] For the first The selectivity of the effective route for each vehicle. For the first The number of sales nodes on the valid routes of the optional vehicles. This represents the total number of sales nodes. For the first The first of the optional vehicle valid paths Forecasted sales demand for each sales node. For the first The load capacity of the optional vehicle class.

[0023] This invention takes into account that only the consumption cost of the transportation process is considered in the process of constructing an effective route. When determining the optimal choice of each route, it is also necessary to consider the resource utilization degree on the effective routes of each type of optional vehicle. Therefore, this invention provides a precise method for calculating the selectivity of the effective routes of optional vehicles. By analyzing the resource utilization degree on each effective route, low consumption and maximum resource utilization can be achieved during scheduling.

[0024] According to the intelligent supply chain production, transportation and sales collaborative scheduling method provided by the present invention, the step of realizing commodity scheduling in the commodity supply chain diagram based on the selectivity of the effective paths of each type of optional vehicles includes: taking the effective path corresponding to the maximum selectivity of the effective paths of all types of optional vehicles as the first running path in the commodity supply chain diagram, and marking all sales nodes on the first running path; obtaining all unmarked sales nodes to construct a secondary allocation diagram of the commodity supply chain, continuing to mark until all sales nodes are marked, obtaining the marking result, and realizing commodity scheduling.

[0025] According to the intelligent supply chain production and sales collaborative scheduling method provided by the application, the goods scheduling is realized, and each sales node is allocated a corresponding optional vehicle for distribution according to the marking result.

[0026] According to the intelligent supply chain production and sales collaborative scheduling method provided by the application, the goods scheduling in the goods supply chain diagram is realized, and then the transport paths of the optional vehicles are monitored in real time.

[0027] According to the intelligent supply chain production and sales collaborative scheduling method provided by the application, the goods scheduling in the goods supply chain diagram is realized, and then the transport paths of the optional vehicles are monitored in real time.

[0028] In the second aspect, the application provides an intelligent supply chain production and sales collaborative scheduling system, which adopts the following technical scheme:

[0029] The intelligent supply chain production and sales collaborative scheduling system comprises a processor and a memory, and the memory stores computer program instructions.

[0030] According to the above technical scheme, the above-mentioned intelligent supply chain production and sales collaborative scheduling method is generated into a computer program and stored in the memory to be loaded and executed by the processor, so that a terminal device is manufactured according to the memory and the processor, and the use is facilitated.

[0031] The application has the following technical effects:

[0032] Based on the above technical scheme, the intelligent supply chain production and sales collaborative scheduling method and system provided by the application can effectively improve the efficiency of goods scheduling by scheduling goods according to the sales demand prediction of sales nodes after predicting the sales demand prediction of goods. When obtaining the sales demand prediction of goods of each sales node, the application dynamically adjusts the smoothing parameter of each sales node by introducing the standard deviation, which can effectively cope with market fluctuations and improve demand prediction accuracy, thereby providing a reliable basis for production and inventory. When scheduling after accurately obtaining the sales demand prediction of goods of each sales node, the application plans the transport path by calculating the edge weight of each type of optional vehicle to each sales node in the goods supply chain diagram, comprehensively considers the unloading capacity, transport distance and vehicle load of each type of optional vehicle, dynamically calculates the path weight and evaluates the path optimization degree, ensures the maximum utilization of resources and the minimization of transport cost, and thereby effectively improves the efficiency of goods scheduling in the goods supply chain diagram. BRIEF DESCRIPTION OF DRAWINGS

[0033] Figure 1A flowchart of a smart supply chain production, transportation and sales collaborative scheduling method is provided in the embodiments of the present application. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application.

[0035] The embodiments of the present application disclose a smart supply chain production, transportation and sales collaborative scheduling method. The method analyzes the edge weight of each type of optional vehicle of a factory on each path to deliver goods to a sales node, and provides a basis for reasonable planning of production, transportation and sales of a supply chain, so that collaborative scheduling can be accurately realized, and the accuracy and efficiency of supply chain scheduling are improved.

[0036] For details, please refer to Figure 1 as shown, Figure 1 A flowchart of a smart supply chain production, transportation and sales collaborative scheduling method is provided in the embodiments of the present application. The method specifically includes the following steps:

[0037] S1: Obtain optional vehicles of a factory, sales nodes in a commodity supply chain graph and historical supply data in a preset time period.

[0038] The length of the preset time period can be set to one month, and the historical supply data in the preset time period is the supply data of the sales node in the past one month. The length of the preset time period can be set according to actual needs.

[0039] For ease of understanding, the embodiments of the present application take scheduling of any type of commodity as an example for description, but it does not mean that the embodiments of the present application are limited to this.

[0040] For example, when obtaining the historical supply data of the sales node in the preset time period, the order time of the latest supply data of the sales node can be taken as the end time of the preset time period.

[0041] An example of the method for obtaining the historical supply data in the preset time period is as follows: the order time of the latest supply data of a sales node is May 27, 18:00, and the historical supply data of the sales node in the preset time period is all the supply data from April 27, 18:00 to May 27, 18:00.

[0042] In order to avoid data loss or errors in uniform processing of different dimensional data, in the embodiments of the present application, all collected data can be preprocessed.

[0043] The preprocessing mode can be missing data interpolation, data normalization dimension elimination, etc. and can be set according to actual needs, and the embodiment of the application does not make too many limitations here.

[0044] It should be noted that when planning the best path of the supply chain scheduling, in addition to the path length, the load capacity of the transport vehicle to the goods and the transportation cost also need to be considered comprehensively, so as to improve the accuracy of the supply chain scheduling and maximize the utilization of resources. In the actual operation of the supply chain, if the factory starts production and preparation of goods after waiting for the order of goods, the order preparation and transportation will have a lag, which reduces the operation efficiency of the supply chain. The demand for goods in the market is usually stable, and in some seasonal or holiday promotion cases, it will also show regularity in a short period of time. Therefore, the embodiment of the application can predict the demand for goods according to the sales of goods in the past period of time, so as to effectively reduce the situation of insufficient storage of goods.

[0045] For example, in the embodiment of the application, the factory selectable vehicle, the sales node in the commodity supply chain diagram and the historical supply data in the preset period are obtained, and before that, the following steps are further included: obtaining all sales vendors of a factory as sales nodes according to an enterprise ERP system, constructing a commodity supply chain diagram of the factory according to the coordinate positions between the sales nodes, obtaining all deployable vehicles of the factory as selectable vehicles, and determining the loading capacity of each type of selectable vehicle.

[0046] Specifically, the enterprise ERP system records all sales of the goods and the ordering situation of each sales vendor, and integrates the whole process information from the supplier to the customer. The factory can obtain all historical sales of the goods by accessing the enterprise ERP system, wherein the historical sales at least include the position of each sales node, the quantity of goods ordered by each order and the ordering time, and all deployable vehicles of the factory producing the goods.

[0047] It can be understood that after collecting the historical supply data of each sales node according to the above steps, the sales demand prediction of each sales node can be obtained by processing the historical supply data by the exponential smoothing method. However, the exponential smoothing method uses a fixed smoothing parameter and cannot accurately respond to the fluctuation of the historical supply data, which leads to the fact that the subsequent supply chain cannot be accurately coordinated and scheduled based on the sales demand prediction with low accuracy. Therefore, the embodiment of the application provides a method for dynamically adjusting the smoothing parameter of the sales node, which can accurately obtain the sales demand prediction of each sales node by analyzing the fluctuation of the historical supply data of the sales node, that is, the following steps are executed.

[0048] S2: calculating the target smoothing parameter of the sales node according to the standard deviation of the historical supply data of the sales node, and determining the sales demand prediction of the sales node according to the target smoothing parameter of each sales node.

[0049] It's important to note that exponential smoothing smooths time-series data using a weighted average method. The weights decrease exponentially over time, with recent data receiving more weight. Higher smoothing parameters result in higher weights for recent data. For sales periods with significant historical supply data volatility, the smoothing parameter needs to be increased to weaken the influence of historical trends and strengthen the weight of recent observations, adapting to rapid changes and accurately predicting sales demand for each period. Conversely, for sales periods with less historical supply data volatility, similar weights can be assigned to historical and recent data.

[0050] For example, in an embodiment of the present invention, the target smoothing parameter for the sales node is calculated using the following formula:

[0051] ;

[0052] For the first The target smoothing parameters for each sales node For the first Standard deviation of historical supply data for each sales node To preset smoothing parameters, This represents the total number of sales nodes. For the first The sales node and the first DTW distance of historical supply data for each sales node For the first The maximum DTW distance between a sales node and other sales nodes in historical supply data. For the standard normalized function, .

[0053] The preset smoothing parameter can be set to 0.5, and the specific setting can be adjusted according to actual needs. The specific steps for obtaining the DTW distance of historical supply data between sales nodes can be implemented using existing technologies, and will not be elaborated upon here in this embodiment of the invention.

[0054] In the above formula, Used to characterize the current number The higher the value, the greater the likelihood that the historical supply data for the current sales node contains fluctuations in commodity demand caused by seasonal, holiday, or other occasional factors. Used to characterize the current number The consistency of recent changes in demand for goods at a particular sales node with recent changes in demand for goods at other sales nodes. The larger this value, the less similar the recent demand for goods at that sales node is to the demand at other nodes.

[0055] Specifically, in the case that the fluctuation degree of the demand quantity of the recent goods of the current sales node is greater, if the demand change similarity 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 holiday promotion, resulting in fluctuation of demand, and the demand pattern of the current sales node can continue this fluctuation trend, so the smoothing parameter needs to be increased to increase the attention to the recent data, so as to accurately capture the change. On the contrary, if the demand change similarity 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 an accidental fluctuation, at this time, the weight of the recent data also needs to be appropriately increased, so as to reduce the influence of the sudden fluctuation.

[0056] In the case that the fluctuation degree of the demand quantity of the recent goods of the current sales node is smaller, it indicates that the demand degree of the current sales node for the goods is in a stable change state, at this time, the preset smoothing parameter can be maintained to continue the prediction.

[0057] After obtaining the target smoothing parameter of the demand prediction of each sales node for the goods according to the above steps, the sales demand prediction quantity of the sales node can be determined according to the target smoothing parameter of the sales node.

[0058] For example, in the embodiment of the application, the sales demand prediction quantity of the sales node is determined according to the target smoothing parameter of the sales node, which 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.

[0059] Specifically, when obtaining the sales demand prediction quantity of the sales node, the actual demand quantity in the latest supply data and the sales demand prediction quantity of the sales node can be obtained first, and the target smoothing parameter of the sales node, the actual demand quantity in the latest supply data and the sales demand prediction quantity are brought into the one-time exponential smoothing formula, so that the sales demand prediction quantity of the sales node for the goods can be obtained, wherein the one-time exponential smoothing formula is an existing formula, and the embodiment of the application will not be repeated here.

[0060] After obtaining the sales demand prediction quantity of each sales node for the goods according to the above steps, the factory can allocate corresponding vehicles to each sales node according to the existing optional vehicles for delivery, so as to realize efficient distribution and improve the transportation efficiency of the supply chain, that is, the following steps are executed.

[0061] S3: Calculate the edge weight of each type of optional vehicle to the sales node in the commodity supply chain graph, and plan the effective path of the transportation of each type of optional vehicle according to the edge weight of the optional vehicle to the sales node in the commodity supply chain graph.

[0062] It is understandable that the distribution of sales nodes for goods is usually quite dispersed. When allocating delivery vehicles, factories, in order to reduce transportation costs, will try to group products for the same sales node onto the same vehicle. However, different vehicles have different load capacities for goods. When planning based on the sales demand forecast for each sales node, it is necessary to consider the suitability of vehicles with different load capacities for each sales node. Therefore, in planning the vehicle's route, this embodiment of the invention can use the factory's location as the initial node for each optional vehicle after loading. By comprehensively considering the vehicle's load capacity, the sales demand forecast for each sales node, and the distance between paths, the weight of each type of optional vehicle from the initial node to each sales node can be accurately obtained.

[0063] For example, in this embodiment of the invention, the edge weights from each type of optional vehicle to each sales node in the commodity supply chain graph are calculated, as detailed in the following formula:

[0064] ;

[0065] For the first The edge weights of optional vehicles in the commodity supply chain graph up to the i-th sales node. For the first The distance of the optional vehicle to the i-th sales node in the commodity supply chain graph. For the first The load capacity of optional vehicles. Let represent the predicted sales demand for the i-th sales node in the commodity supply chain diagram. It is an exponential function with base e. For the standard normalized function, This is the function for finding the maximum value.

[0066] In the above formula, Indicates the first The ratio of the remaining load capacity of optional vehicles after unloading at the i-th sales node to the total load; the smaller this value, the better the i-th sales node. The more goods a vehicle of the class can directly unload at the i-th sales node, the better. The lower the cost of using a particular type of optional vehicle to transport remaining goods to other sales nodes, the better. When assessing the likelihood of each type of optional vehicle reaching different sales nodes, priority should be given to combining and allocating optional vehicles with load capacities that match or exceed the sales demand forecast. This effectively avoids costly waste caused by insufficient load capacity requiring multiple transports. Cases where the cargo volume is less than the sales demand forecast can be zeroed out to avoid the impact of negative values ​​on the weighting calculation.

[0067] In summary, if the optional vehicle of the current category has more unloading quantity and is closer to the sales node, it means that the optional vehicle of the category has higher efficiency in planning to transport the goods required by the sales node, and the corresponding edge weight is higher. On the contrary, it means that the optional vehicle of the category has lower efficiency in planning to transport the goods required by the sales node, and the cost is higher, and the corresponding edge weight is smaller.

[0068] After obtaining the edge weight of each category of optional vehicle to each sales node in the goods supply chain graph according to the above steps, the sales node that each category of optional vehicle needs to arrive at first can be planned according to the edge weight, and the arrived sales node is taken as a new initial node, and the edge weight between the new initial node and the remaining sales nodes is calculated, and the cycle is continued, and finally the effective path of each category of optional vehicle is obtained.

[0069] For example, in the embodiment of the application, the effective path of the transportation of each category of optional vehicle is planned according to the edge weight of the optional vehicle to the sales node in the goods supply chain graph, which comprises: taking the loaded optional vehicle as an initial node, taking the sales node corresponding to the maximum edge weight of the initial node and all sales nodes as a new initial node of the category of optional vehicle, continuing to obtain the maximum edge weight between the new initial node and the remaining sales nodes, and the cycle is continued until the maximum edge weight between the new initial node and the remaining sales nodes is 0, and the cycle is stopped, and all initial nodes are connected to obtain the effective path of the category of optional vehicle.

[0070] 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 carrying capacity of the category of optional vehicle is less than the sales demand prediction value of each remaining sales node, and the transportation cost of the category of optional vehicle from the initial node to all the remaining sales nodes is high, so the effective path of the category of optional vehicle ends here.

[0071] After obtaining the effective path of each category of optional vehicle according to the above steps, the optional degree of the effective path of each category of optional vehicle planned in the above manner can be determined according to the sales nodes on the effective path of each category of optional vehicle and the sales demand prediction value of the sales nodes, that is, the following steps are executed.

[0072] S4: determining the optional degree of the effective path of each category of optional vehicle according to the sales nodes on the effective path of each category of optional vehicle and the sales demand prediction value of the sales nodes; and realizing the goods scheduling in the goods supply chain graph according to the optional degree of the effective path of each category of optional vehicle.

[0073] 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, the embodiment of the present application still needs to analyze whether the transportation nodes passed by the effective path of each type of optional vehicle reach the resource utilization maximization, so as to obtain the optimal path, and ensure that the high-efficiency and low-consumption transportation vehicle preferentially covers each sales node.

[0074] For example, in the embodiment of the present application, the selectability of the effective path of each type of optional vehicle is determined, including:

[0075] ;

[0076] the selectability of the effective path of the first type of optional vehicle, the number of sales nodes on the effective path of the first type of optional vehicle, the total number of sales nodes, the number of sales nodes on the effective path of the first type of optional vehicle, the sales demand prediction of the first sales node on the effective path of the first type of optional vehicle, the loading capacity of the first type of optional vehicle. In the above formula, the ratio of the number of sales nodes passed by the effective path of the optional vehicle to the total number of sales nodes in the commodity supply chain diagram, the larger the value, the more the proportion of sales nodes covered by the effective path of the optional vehicle, and the more the effective path of the optional vehicle can serve multiple sales nodes in a larger range.

[0077] the ratio of the total amount of sales demand prediction of the sales nodes passed by the effective path of the optional vehicle to the loading capacity of the optional vehicle, the larger the value, the higher the demand satisfaction degree of the effective path to the sales nodes on the effective path, and the higher the load efficiency. Therefore, the more the number of sales nodes passed by the effective path and the higher the demand satisfaction degree of each sales node, the higher the resource utilization rate and the wider the coverage, and the higher the selectability of the effective path. Based on this, the selectability of the effective path of each type of optional vehicle can be obtained.

[0078]

[0079] Based on this, the selectability of the effective path of each type of optional vehicle can be obtained.

[0080] ​​​For example, in the embodiment of the present application, the commodity scheduling in the commodity supply chain graph is realized according to the selectivity of each type of optional vehicle effective path, including: taking the effective path corresponding to the maximum value of the selectivity of all types of optional vehicle effective paths as the first running path in the commodity supply chain graph, and marking all the sales nodes on the first running path; obtaining all unmarked sales nodes to construct a commodity supply chain secondary distribution graph, and continuing to mark until the marking of all sales nodes is completed, obtaining a marking result, and realizing commodity scheduling.

[0081] The marking manner can be the type of the optional 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 unidirectional, that is, the optional vehicle will not return to the previously arrived node.

[0082] It can be understood that, when the effective path is planned based on the above steps, part of the sales nodes can not be in the effective path (for example, the sales demand prediction of the sales node is greater than the load of the optional vehicle, and the edge weight corresponding thereto is 0, etc.), or the selectivity of the effective path of this type of optional vehicle is not the maximum value of the selectivity between nodes, therefore, for the remaining unmarked sales nodes, a commodity supply chain secondary distribution graph needs to be constructed, and the maximum value of the selectivity in the commodity supply chain secondary distribution graph is obtained according to the content recorded in the above steps to mark the remaining sales nodes, and the cycle is continued until the edge weight of all the remaining sales nodes is 0 and the calculation of the maximum value of the selectivity is stopped, and manual distribution marking is performed according to actual needs, and finally the marking of all the sales nodes in the commodity supply chain graph is completed.

[0083] After all the sales nodes are marked according to the above steps, the optional vehicles can be distributed according to the marking result.

[0084] For example, in the embodiment of the present application, the commodity scheduling is realized, including: according to the marking result, the corresponding optional vehicle is distributed for each sales node for distribution.

[0085] For example, in the embodiment of the present application, the commodity scheduling in the commodity supply chain graph is realized, and then further includes: real-time monitoring the transportation path of the optional vehicle.

[0086] It can be seen that, in the embodiment of the present application, when the supply chain production, transportation and marketing collaborative scheduling is realized, the factory optional vehicle, the sales node in the commodity supply chain graph and the historical supply data in the preset period thereof can be obtained; the target smoothing parameter of the sales node is calculated according to the standard deviation of the historical supply data of the sales node, and the sales demand prediction of the sales node is determined according to the target smoothing parameter of each sales node; the edge weight of each type of optional vehicle to the sales node in the commodity supply chain graph is calculated:

[0087] ;

[0088] , The first The edge weights and distances of optional vehicles in the commodity supply chain graph to the i-th sales node. For the first The load capacity of optional vehicles. Let represent the predicted sales demand for the i-th sales node in the commodity supply chain diagram. It is an exponential function with base e. For the standard normalized function, To maximize the function; based on the edge weights of the optional vehicles in the commodity supply chain graph to the sales nodes, the effective transportation path for each type of optional vehicle is planned; based on the sales nodes on the effective path of each type of optional vehicle and the sales demand forecast of the sales nodes, the selectivity of the effective path of each type of optional vehicle is determined; based on the selectivity of the effective path of each type of optional vehicle, commodity scheduling in the commodity supply chain graph is realized, which effectively improves the efficiency of supply chain production, transportation and sales coordination scheduling.

[0089] This 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, an intelligent supply chain production, transportation, and sales collaborative scheduling method provided by this invention is implemented.

[0090] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.

[0091] In this invention, the aforementioned memory can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0092] The above are all preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Therefore, all equivalent changes made in accordance with the structure, shape and principle of the present invention should be covered within the scope of protection of the present invention.

Claims

1. An intelligent supply chain production-distribution-marketing collaborative scheduling method, characterized in that, The method comprises the following steps: Obtaining the factory optional vehicles, the sales nodes in the commodity supply chain graph and the historical supply data of the sales nodes within a preset time period; The target smoothing parameter of the sales node is calculated according to the standard deviation of the historical supply data of the sales node, including: ; , The first The target smoothing parameter for each sales node, and the standard deviation of historical supply data. To preset smoothing parameters, This represents the total number of sales nodes. For the first The sales node and the first DTW distance of historical supply data for each sales node For the first The maximum DTW distance between a sales node and other sales nodes in historical supply data. The standard normalization function is used to determine the sales demand forecast for each sales node based on the target smoothing parameters of each sales node. Calculating the edge weight of each type of optional vehicle to the sales node in the commodity supply chain graph; ； , are the edge weights of the edges from the i-th supply node to the j-th sales node in the supply chain graph, are the distances of the edges from the i-th supply node to the j-th sales node in the supply chain graph, are the loading capacities of the i-th alternative vehicle, are the loading capacities of the i-th alternative vehicle, are the sales demand forecasts of the i-th sales node in the supply chain graph, is an exponential function with base e, is a standard normalizing function, is a max function. According to the edge weight of the optional vehicle to the sales node in the commodity supply chain diagram, the effective path of each type of optional vehicle transportation is planned, including: taking the loaded optional vehicle as the initial node, taking the sales node corresponding to the maximum edge weight of the initial node and all sales nodes as the new initial node of the type of optional vehicle, continuing to obtain the maximum edge weight between the new initial node and the remaining sales nodes, and so on until the maximum edge weight between the new initial node and the remaining sales nodes is 0, stopping the loop, connecting all initial nodes to obtain the effective path of the type of optional vehicle, and determining the selectability 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 sales demand prediction of the sales nodes, including: ; is the selectability of the effective path of the first type of optional vehicle, is the number of sales nodes on the effective path of the first type of optional vehicle, is the total number of sales nodes, is the sales demand prediction of the first sales node on the effective path of the first type of optional vehicle, is the loading capacity of the first type of optional vehicle; According to the optional degree of each type of optional vehicle effective path, the commodity scheduling in the commodity supply chain graph is realized. 2.The intelligent supply chain production-distribution-marketing collaborative scheduling method of claim 1, wherein, Before the step of obtaining the factory optional vehicles, the sales nodes in the commodity supply chain graph and the historical supply data of the sales nodes within a preset time period, the method further comprises the following steps: According to the enterprise ERP system, all sales manufacturers of a factory are obtained as sales nodes, a commodity supply chain graph of the factory is constructed according to the coordinate positions between the sales nodes, all the vehicles that can be allocated of the factory are obtained as optional vehicles, and the loading capacity of each type of optional vehicle is determined. 3.The intelligent supply chain production-distribution-marketing collaborative scheduling method of claim 1, wherein, The step of determining the sales demand prediction of each sales node according to the target smoothing parameter of the sales node comprises the following steps: In the exponential smoothing method, the target smoothing parameter of each sales node is used to obtain the sales demand prediction of each sales node. 4.The intelligent supply chain production-distribution-marketing collaborative scheduling method of claim 1, wherein, The step of realizing the commodity scheduling in the commodity supply chain graph according to the optional degree of each type of optional vehicle effective path comprises the following steps: The effective path corresponding to the maximum value of the optional degree of all types of optional vehicle effective paths is taken as the first running path in the commodity supply chain graph, all the sales nodes on the first running path are marked, all the unmarked sales nodes are obtained to construct a second distribution graph of the commodity supply chain, the marking is continued until the marking of all the sales nodes is completed, a marking result is obtained, and the commodity scheduling is realized. 5.The intelligent supply chain production-distribution-marketing collaborative scheduling method of claim 4, wherein, The step of realizing the commodity scheduling comprises the following steps: According to the marking result, the corresponding optional vehicles are allocated to each sales node for distribution. 6.The intelligent supply chain production-distribution-marketing collaborative scheduling method of claim 1, wherein, After the step of realizing the commodity scheduling in the commodity supply chain graph, the method further comprises the following steps: The transportation path of the optional vehicle is monitored in real time.

7. An intelligent supply chain production, transportation and marketing collaborative scheduling system, characterized in that, The method comprises the following steps: A processor and a memory, the memory stores computer program instructions, when the computer program instructions are executed by the processor, a kind of intelligent supply chain production and transportation marketing collaborative scheduling method according to any one of claims 1-6 is realized.

Images