Optimization method and apparatus for transportation strategy under feeder logistics network, electronic device and storage medium

Abstract

The present application discloses an optimization method and apparatus for a transportation strategy under a feeder logistics network, an electronic device and a storage medium. The method comprises: acquiring logistics information under a feeder logistics network, wherein the logistics information comprises information of each logistics node; inputting the logistics information into a digital twin model, by means of the digital twin model and by taking transportation rules of the feeder logistics network as a constraint condition and transportation cost minimization as an objective, performing route planning to generate a transportation strategy to be optimized, and simulating a transportation process of goods between the logistics nodes on the basis of the transportation strategy to be optimized, so as to obtain a simulation result; and on the basis of the simulation result, optimizing the transportation strategy to be optimized, so as to obtain an optimized transportation strategy. In the present application, on the basis of the computing power of the electronic device, the transportation strategy during logistics transportation can be quickly obtained; and by simulating the logistics transportation process, the reliability of the transportation strategy can be improved.

Description

Optimization method, device, electronic device and storage medium for transportation strategy in feeder logistics network Technical Field

[0001] The present application relates to the field of logistics and transportation technology, specifically, to artificial intelligence technology in the field of logistics and transportation technology, and more specifically, to an optimization method, device, electronic device and storage medium for transportation strategy in a branch logistics network. Background Art

[0002] Logistics networks can generally be divided into two main components: trunk logistics networks and feeder logistics networks. These two network models play a crucial role in the logistics distribution system. Feeder logistics networks serve as the logistics and transportation links between express distribution centers and final retailers or consumers. Given the complexity of feeder logistics networks, highly experienced professionals are often required to develop transportation strategies to ensure timely delivery.

[0003] However, the above-mentioned manual method of formulating transportation strategies places high demands on relevant personnel. It is not only time-consuming, but also the reliability of the formulated transportation strategies is poor. Summary of the Invention

[0004] In order to solve the above technical problems, the present application provides a method, device, electronic device and storage medium for optimizing the transportation strategy under the branch logistics network, so as to achieve the purpose of quickly generating the transportation strategy under the branch logistics network.

[0005] To achieve the above technical objectives, the embodiments of the present application provide the following technical solutions:

[0006] In the first aspect, an embodiment of the present application provides a method for optimizing transportation strategies under a branch logistics network, the method comprising: obtaining logistics information under the branch logistics network; wherein the logistics information comprises: information of each logistics node; inputting the logistics information into a digital twin model, and using the digital twin model to arrange the transportation rules of the branch logistics network as constraints and minimize transportation costs as the goal, generating a transportation strategy to be optimized, and simulating the transportation process of goods between each logistics node according to the transportation strategy to be optimized to obtain simulation results; optimizing the transportation strategy to be optimized based on the simulation results to obtain an optimized transportation strategy.

[0007] On the second aspect, an embodiment of the present application provides an optimization device for transportation strategies under a branch logistics network, and the device includes: an information acquisition module for acquiring logistics information under the branch logistics network; wherein the logistics information includes: information of each logistics node; a simulation module for inputting the logistics information into a digital twin model, and through the digital twin model, the transportation rules of the branch logistics network are used as constraints, and the transportation cost is minimized as the goal to arrange the lines, generate a transportation strategy to be optimized, and simulate the transportation process of goods between each logistics node according to the transportation strategy to be optimized to obtain a simulation result; an optimization module for optimizing the transportation strategy to be optimized based on the simulation result to obtain an optimized transportation strategy.

[0008] In a third aspect, an embodiment of the present application provides an electronic device comprising: a processor and a memory; wherein the memory is connected to the processor, and the memory is used to store a computer program; the processor is used to implement the method for optimizing the transportation strategy under the branch logistics network as described in the first aspect by running the computer program stored in the memory.

[0009] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for optimizing the transportation strategy in the branch logistics network as described in the first aspect is implemented as described above.

[0010] In the fifth aspect, an embodiment of the present application provides a computer program product or a computer program, wherein the computer program product includes a computer program, and the computer program is stored in a computer-readable storage medium; the processor of the computer device reads the computer program from the computer-readable storage medium, and when the processor executes the computer program, it implements the steps of the method for optimizing the transportation strategy under the branch logistics network as described in the first aspect.

[0011] The present application provides a method for optimizing transportation strategies in a branch logistics network. After obtaining logistics information in the branch logistics network, the logistics information is input into a digital twin model. The digital twin model is used to generate a transportation strategy to be optimized, and simulation is performed according to the transportation strategy to be optimized. The simulation results reflect the cargo transportation status under the transportation strategy to be optimized. The simulation results are then used to optimize the transportation strategy to be optimized to obtain the optimized transportation strategy. With the help of the computing power of electronic equipment, the present application can quickly obtain the transportation strategy in the logistics transportation process; at the same time, by simulating the logistics transportation process, the reliability of the transportation strategy can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] FIG1 is a flow chart of a method for optimizing a transportation strategy in a feeder logistics network according to an embodiment of the present application;

[0013] FIG2 is a flowchart of a practical application of a method for optimizing a transportation strategy in a feeder logistics network provided by an embodiment of the present application;

[0014] FIG3 is a structural block diagram of a device for optimizing transportation strategies in a branch logistics network according to an embodiment of the present application;

[0015] FIG4 is a schematic structural diagram of an electronic device provided by an embodiment of the present application;

[0016] FIG5 is a block diagram of a computer program product provided by one embodiment of the present application;

[0017] FIG6 is a block diagram of a computer-readable storage medium according to an embodiment of the present application. DETAILED DESCRIPTION

[0018] Exemplary Methods

[0019] The embodiment of the present application provides a method for optimizing the transportation strategy in a branch logistics network. As shown in FIG1 , the method for optimizing the transportation strategy in the branch logistics network includes:

[0020] Step S101: Obtain logistics information under the branch logistics network.

[0021] In this step, the logistics information includes: information of each logistics node; a logistics node is a place used to store, transfer or process goods during the logistics transportation process. For example, a logistics node can be a warehouse, a transfer yard, a distribution station, a logistics network, etc., but is not limited thereto. It can be understood that the logistics information provides a data basis for formulating a branch logistics network / transportation strategy between each logistics network and simulating the transportation of goods between each logistics node. In some embodiments, the logistics information under the branch logistics network includes: formulating a branch logistics network / transportation strategy between each logistics network and all data required for simulating the transportation of goods between each logistics node. For example, logistics information includes but is not limited to the location, status and related data of transport vehicles, warehouses and goods, order quantity, goods information and customer demand, etc.

[0022] Step S102: Input the logistics information into the digital twin model, and use the digital twin model to arrange the routes with the transportation rules of the branch logistics network as constraints and the goal of minimizing transportation costs, generate a transportation strategy to be optimized, and simulate the transportation process of goods between various logistics nodes according to the transportation strategy to be optimized to obtain simulation results.

[0023] In this step, the digital twin model is a data model constructed using digital twin technology for the feeder logistics network. Digital twins leverage data from physical models, sensor updates, and operational history, integrating multidisciplinary, multi-physics, multi-scale, and multi-probabilistic simulation processes to map the entire lifecycle of the corresponding physical equipment in a virtual space. It should be understood that the digital twin model includes components with different functions, each of which is used to generate the optimized transportation strategy and simulation process.

[0024] When generating the transportation strategy to be optimized, the principles of mathematical model solving are utilized, with logistics information as input. By setting constraints and objectives, an initial transportation strategy, i.e., the transportation strategy to be optimized, is obtained. The transportation rules of the branch logistics network are the conditions that must be met for cargo transportation within the branch logistics network. Alternatively, if the transportation rules of the branch logistics network include transportation rules for the target area, the transportation rules for the target area are the conditions that must be met for cargo transportation within the target area. The specific content of the transportation rules of the branch logistics network is not specified here. Transportation costs are the expenses incurred during the transportation of goods. During the simulation process, the characteristics of the digital twin model are utilized to simulate the transportation process of goods between various logistics nodes. Both logistics information and the transportation strategy to be optimized are input data, allowing for accurate simulation of the process of transporting goods within the branch logistics network according to the logistics information under the transportation strategy to be optimized. The simulation results include various issues that occur during the transportation of goods in the simulation environment and / or relevant information about each logistics node.

[0025] Step S103: Optimize the transportation strategy to be optimized based on the simulation results to obtain an optimized transportation strategy.

[0026] It should be noted that when optimizing a transportation strategy, the strategy can be optimized based on the cargo transportation status under the corresponding transportation strategy. The simulation results can reflect the cargo transportation status under the transportation strategy to be optimized. Therefore, there is a certain correlation between the simulation results and the transportation strategy. Based on this correlation, a corresponding optimization strategy can be set to optimize the transportation strategy to be optimized. Of course, the simulation results can also be displayed directly, allowing relevant personnel to see the simulation results and optimize the transportation strategy to be optimized based on the simulation results.

[0027] The following describes the optimization method of transportation strategy in the feeder logistics network for two scenarios. The first scenario is the logistics peak scenario, and the second scenario is the logistics scenario in a designated area.

[0028] The following describes the optimization method of the transportation strategy in the feeder logistics network for the first scenario.

[0029] In some embodiments, the logistics information under the branch logistics network also includes: at least one of the predicted quantity of goods, vehicle resource reserve information, and personnel reserve information of the consolidation logistics node and / or the bulk logistics node.

[0030] It should be noted that in some logistics and transportation scenarios, the volume of express parcels requiring transport can vary significantly over a short period of time. For example, during peak logistics scenarios, express parcel volume can experience a significant increase or decrease within a very short period of time. In this case, to ensure the accuracy of the transportation strategy to be optimized and the simulation results, it is necessary to predict the parcel volume. Therefore, the acquired logistics information may include: predicted parcel volumes for consolidation logistics nodes and / or bulk logistics nodes. Consolidation logistics nodes are logistics nodes that centrally process parcels received from customers. Therefore, the predicted parcel volume for consolidation logistics nodes can also be referred to as the predicted parcel volume received. The process for predicting the predicted parcel volume is not defined herein. In some embodiments, predictions can be made for the type and volume of parcels received for each network point, distribution center, or transfer station, and the prediction results can be used as logistics information. Bulk logistics nodes are logistics nodes that centrally process parcels to be delivered to customers. Therefore, the predicted parcel volume for bulk logistics nodes can also be referred to as the predicted parcel volume delivered. The process for predicting the predicted parcel volume is not defined herein. In some embodiments, the delivery type and delivery quantity can be predicted for each network point, distribution station, and transfer yard, and the prediction results can be used as logistics information.

[0031] It's understandable that during peak logistics periods, timeliness of shipments is typically prioritized to minimize a poor customer experience and prevent production accidents caused by overflowing transit points. Furthermore, during peak logistics periods, vehicle resources are difficult to obtain and require longer wait times. Therefore, during peak logistics periods, vehicle resources are tightly allocated to ensure sufficient transport capacity and avoid last-minute requests. Specifically, during peak logistics periods, additional vehicle resources may be reserved to better complete transportation tasks. Therefore, the acquired logistics information may include vehicle resource reserve information. This vehicle resource reserve information may include the predicted additional vehicle resources required to prepare for peak logistics periods. In some embodiments, data such as vehicle type, number of vehicles, vehicle operating areas, vehicle availability time periods, and vehicle restrictions may be predicted, and the prediction results may be used as logistics information. Similarly, during peak logistics periods, additional staff may be reserved to better complete transportation tasks. Therefore, the acquired logistics information may include personnel reserve information. This personnel reserve information may include the predicted additional human resources required to prepare for peak logistics periods. In some embodiments, data such as personnel type, working time period, and number of personnel may be predicted, and the prediction results may be used as logistics information.

[0032] Furthermore, during peak logistics scenarios, additional forecasts can be made for delivery and collection capacity during peak periods. For example, the express handling capacity of transit stations and logistics outlets can be predicted, and the results can be used as logistics information. Furthermore, during peak periods, shifts are frequently adjusted, which is not factored into transportation strategy formulation. However, shift information for transit stations and logistics outlets can also be entered and used as logistics information. Similarly, data on route execution, traffic congestion, wait times, and changes in operation times can be collected for each route and logistics node, and used as logistics information.

[0033] In an embodiment of the present application, relevant data in logistics peak scenarios are used as logistics information and input into the digital twin model, which can cope with logistics peak scenarios and improve the accuracy of the transportation strategy to be optimized and the simulation results.

[0034] In some embodiments, the transportation cost includes at least one of: transportation route change cost, transportation vehicle change cost, and personnel change cost.

[0035] It should be noted that during off-peak logistics periods, the frequency of changes in transport routes, transport vehicles, and personnel is relatively low and can generally be ignored. However, during peak logistics periods, the frequency of these three changes increases significantly, leading to inefficient communication at the execution level and failure to achieve the desired results. Therefore, when considering transportation costs, all three factors need to be taken into account. The cost of a transport route change is the change in costs associated with a transport route change, the cost of a transport vehicle change is the change in costs associated with a transport vehicle change, and the cost of a personnel change is the change in costs associated with a personnel change. Personnel changes here include, but are not limited to, increases or decreases in the number of personnel and changes in staff schedules.

[0036] In the embodiment of the present application, the transportation cost is set based on the logistics transportation characteristics under the logistics peak scenario, which can cope with the logistics peak scenario and improve the accuracy of the transportation strategy to be optimized and the simulation results.

[0037] In some embodiments, the transportation rules of the branch logistics network include: the transportation time determined based on the associated information of the temporary transfer station is less than or equal to the promised delivery time of the goods; the associated information includes: the processing efficiency of the temporary transfer station, the shift information and at least one of the distances between the temporary transfer station and the associated logistics nodes.

[0038] It should be noted that each cargo has a promised time limit, that is, the cargo promised time limit. According to the requirements of the logistics and transportation business, the transportation needs to be completed within the cargo promised time limit. Therefore, when generating the transportation strategy to be optimized, it is necessary to ensure that the generated operation strategy meets the time limit requirements. At the same time, during the peak logistics period, additional temporary transfer yards are usually added to alleviate the peak pressure. Different from the original transfer yards in the branch logistics network, this temporary transfer yard is only put into use at the specified time. However, during the period of use, the temporary transfer yard and the original transfer yard have the same functions. Therefore, the aforementioned time limit requirements can be regarded as the transportation time determined based on the associated information of the temporary transfer yard being less than or equal to the cargo promised time limit.

[0039] The functions of temporary transfer stations in the logistics transportation process will not be discussed in detail here. This embodiment determines the transportation duration based on the data required to implement these functions. This data includes, but is not limited to, the temporary transfer station's processing efficiency, shift information, and the distance between the temporary transfer station and the associated logistics node. The temporary transfer station's processing efficiency refers to the efficiency of the temporary transfer station in processing express shipments. Shift information refers to the shift information of the transport vehicles within the temporary transfer station.

[0040] It's understandable that the transportation rules of the feeder logistics network also include those associated with existing transfer points. For example, the transportation time determined based on the associated information of the existing transfer points must be less than or equal to the promised delivery time. Of course, other constraints can also be set in the digital twin model, such as a load constraint requiring that the load of all transport vehicles exceed the weight of all cargo, or a vehicle scheduling constraint requiring that all vehicles travel within their respective logistics transport areas.

[0041] In the embodiment of the present application, corresponding constraints are set based on the temporary transfer site under the logistics peak scenario, which can cope with the logistics peak scenario and improve the accuracy of the digital twin model.

[0042] In an embodiment of the present application, after obtaining the above-mentioned logistics information under the branch logistics network, the logistics information is input into the digital twin model, and the transportation strategy to be optimized is generated with the help of the digital twin model, and simulation is performed according to the transportation strategy to be optimized. The simulation results reflect the cargo transportation status under the transportation strategy to be optimized. The simulation results are then used to optimize the transportation strategy to be optimized to obtain the optimized transportation strategy. With the help of the computing power of electronic equipment, the present application can quickly obtain the transportation strategy in the logistics transportation process; at the same time, by simulating the logistics transportation process, the reliability of the transportation strategy can be improved.

[0043] The above is a description of the optimization method of the transportation strategy under the branch logistics network for the first scenario. The following is a description of the optimization method of the transportation strategy under the branch logistics network for the second scenario, as follows.

[0044] The designated area can be understood as the target area, and the target area is an area where the distribution density of shipping logistics nodes and / or receiving logistics nodes is higher than the target density threshold. The distribution density is the number of shipping logistics nodes and / or receiving logistics nodes per unit area. The target density threshold can be a predetermined higher density threshold. The target area with a distribution density higher than the target density threshold can be regarded as an area with a dense customer base. The customer base here can be understood as a customer base with a need to receive or send parcels. For example, the target area can be a CBD (Central Business District) office area or industrial area, where there are many customer groups with a need to receive or send parcels.

[0045] In some embodiments, the logistics information under the branch logistics network also includes: logistics information corresponding to the target area, and the logistics information corresponding to the target area includes: information on each logistics node in the target area; a logistics node is a place used to store, transfer or process goods during the logistics transportation process. For example, a logistics node can be a warehouse, a transfer yard, a distribution station, a logistics network, etc., but is not limited to this. It can be understood that the logistics information provides a data basis for formulating transportation strategies between various logistics networks and simulating the transportation of goods between various logistics nodes. In some embodiments, when the target area is a CBD or an industrial area, the logistics information includes all the data required to formulate transportation strategies between various logistics networks in the CBD or industrial area and to simulate the transportation of goods between various logistics nodes in the CBD or industrial area, such as the location and status of the goods, the status, location, running speed, order quantity, cargo information and customer demand of the transport vehicles.

[0046] In some embodiments, the logistics information corresponding to the target area also includes: at least one of: the predicted quantity of target customers, the predicted time of target customers, and the predicted time of goods; the target customer is a customer in the target area whose receiving and / or sending volume exceeds the target quantity threshold, the predicted quantity includes: the predicted receiving quantity and / or sending quantity, and the predicted time includes: the predicted receiving time and / or sending time.

[0047] It should be noted that in some logistics and transportation scenarios in designated areas, the customer's sending or receiving volume may be very large. For example, in the scenario of logistics and transportation within a CBD or industrial area, some customers need to send or receive express parcels in batches. At this time, in order to ensure the accuracy of the transportation strategy to be optimized and the simulation results, it is necessary to predict the express parcel volume and the sending and receiving time. Therefore, the obtained logistics information may include: the predicted parcel volume of the target customer and the predicted time of the predicted parcel volume of the target customer. The prediction process of the predicted parcel volume and predicted time is not limited here. In some embodiments, the parcel volume, receiving time and sending time can be predicted for major customers, and the prediction results can be used as logistics information. The major customers here are the above-mentioned target customers. Specifically, the historical sending data and historical receiving data of each customer in the target area can be used to screen out target customers with a large number of sending or receiving needs, but is not limited to this.

[0048] Similarly, in the aforementioned logistics and transportation scenarios within a designated area, to improve the accuracy of the digital twin model, it is necessary to predict the delivery and / or delivery times of goods. This prediction is then fed into the digital twin model as logistics information, serving as the basis for the digital twin model to generate transportation strategies and simulations. In some embodiments, to further enhance the accuracy of the digital twin model, information regarding temporary transfer stations within the target area, vehicle restrictions, and vehicle congestion conditions can also be incorporated as logistics information.

[0049] In an embodiment of the present application, relevant data in the logistics transportation scenario within the CBD or industrial area are input into the digital twin model as logistics information, which can cope with the logistics scenario and improve the accuracy of the transportation strategy to be optimized and the simulation results.

[0050] In some embodiments, the transportation rules of the feeder logistics network include: transportation rules for a target area, and the transportation rules for the target area include: the collection time and the shipment time of the goods are both within the office hours of the customer to whom the goods belong.

[0051] It should be noted that customers in CBDs or industrial areas typically have regular office hours. To improve delivery success rates, it's often necessary to visit customers during their office hours. For example, a customer in a CBD might have office hours from 10:00 AM to 12:00 PM and from 2:00 PM to 6:00 PM. Accordingly, the pickup and delivery times for this customer's shipment should fall between 10:00 AM and 12:00 PM, or between 2:00 PM and 6:00 PM.

[0052] It is understandable that each cargo has a promised time limit, that is, the cargo promised time limit. According to the requirements of the logistics and transportation business, the transportation needs to be completed within the cargo promised time limit. Therefore, when generating the transportation strategy to be optimized, it is necessary to ensure that the generated operation strategy meets the time limit requirements. At the same time, in the scenario of logistics transportation within the CBD or industrial area, additional temporary transfer yards are sometimes added to alleviate logistics pressure. Different from the original transfer yard in the target area, this temporary transfer yard is only put into use at the specified time. However, during use, the temporary transfer yard and the original transfer yard have the same functions. Therefore, the transportation rules of the target area can also include a transportation time determined based on the associated information of the temporary transfer yard that is less than or equal to the cargo promised time limit.

[0053] The functions of the temporary transfer station in the logistics transportation process will not be described in detail here. This embodiment will determine the transportation time based on the data required to realize its functions. These data include but are not limited to the processing efficiency of the temporary transfer station, the shift information and the distance between the temporary transfer station and the associated logistics nodes. The processing efficiency of the temporary transfer station is the efficiency of the temporary transfer station in processing express parcels. The shift information is the shift information of the transport vehicles in the temporary transfer station. Of course, the transportation rules of the target area can also include: transportation rules associated with the original transfer station. For example, the transportation time determined based on the associated information of the original transfer station is less than or equal to the promised time limit for the goods. It is worth noting that other constraints can also be set in the digital twin model, for example, constraints on load capacity, that is, the load capacity of all transport vehicles is greater than the weight of all goods. Constraints on vehicle scheduling, that is, all vehicles must travel in their respective corresponding logistics transportation areas.

[0054] In the embodiment of the present application, setting corresponding constraints based on the logistics and transportation rules within the CBD or industrial area can cope with corresponding logistics scenarios and improve the accuracy of the digital twin model.

[0055] In an embodiment of the present application, after obtaining the logistics information corresponding to the target area in the branch logistics network, the logistics information is input into the digital twin model, and the transportation strategy to be optimized is generated with the help of the digital twin model, and the transportation strategy to be optimized is simulated. The simulation results reflect the cargo transportation status under the transportation strategy to be optimized. The simulation results are then used to optimize the transportation strategy to be optimized to obtain the optimized transportation strategy. With the help of the computing power of electronic equipment, the present application can quickly generate the transportation strategy required in the logistics transportation process for the target area with a high distribution density of shipping logistics nodes and / or receiving logistics nodes; at the same time, by simulating the logistics transportation process, the reliability of the transportation strategy can also be improved.

[0056] The above is a description of the optimization method of the transportation strategy under the feeder logistics network for the second scenario. The following will describe the optimization method of the transportation strategy under the feeder logistics network without distinguishing between scenarios. The details are as follows.

[0057] In order to further improve the logistics and transportation effect of the operation strategy, the transportation strategy to be optimized is optimized based on the simulation results. After obtaining the optimized transportation strategy, the method further includes:

[0058] Repeat the following steps until the simulation results of the digital twin model meet the target conditions: use the digital twin model to simulate the transportation process of goods between logistics nodes again according to the optimized transportation strategy to obtain new simulation results; optimize the target transportation strategy based on the new simulation results, and update the optimized transportation strategy, where the target transportation strategy is the transportation strategy currently used in the digital twin model simulation process.

[0059] It should be noted that the target condition is the expected result / expected transportation effect of the transportation strategy. In some embodiments, the target condition can be set in advance based on the expectation of the operation strategy. Therefore, after determining that the simulation result of a certain simulation meets the target condition, the optimization of the transportation strategy is stopped, and the current transportation strategy is used as the final optimized transportation strategy. Specifically, the simulation result can reflect the cargo transportation status under the transportation strategy to be optimized. Therefore, the target condition can be set based on the expected cargo transportation status. For example, the target condition is set to: all cargo exceeding a certain threshold ratio are transported within the promised time limit, but it is not limited to this.

[0060] It's understandable that the repeated simulation and optimization of transportation strategies can be considered an iteration of the transportation strategy. Each iteration includes a simulation and a transportation strategy optimization process. The transportation strategy used in the simulation process in each iteration is the same as the one generated in the optimization step of the previous iteration.

[0061] In the embodiment of the present application, a transportation strategy with better logistics and transportation effects can be obtained by continuously iterating and updating the transportation strategy.

[0062] In some embodiments, the digital twin model includes: a data mining model, a strategy planning model, and a simulation model; logistics information is input into the digital twin model, and the digital twin model arranges the routes based on the transportation rules of the branch logistics network as constraints and the goal of minimizing transportation costs, generates a transportation strategy to be optimized, and simulates the transportation process of goods between various logistics nodes according to the transportation strategy to be optimized, obtaining simulation results, including:

[0063] The target parameter items in the logistics information are mined through the data mining model to determine the final parameter values ​​of the target parameter items; the strategy planning model is used to arrange the routes based on the final parameter values ​​with the transportation rules of the branch logistics network as constraints and the transportation cost minimization as the goal to generate the transportation strategy to be optimized; the simulation model is used to simulate the transportation process of goods between various logistics nodes according to the transportation strategy to be optimized based on the final parameter values ​​to obtain simulation results; wherein, the target parameter items include multiple parameter values ​​from different data sources.

[0064] It should be noted that the data mining model is used to mine data. Specifically, the data mining model is used to process parameter values ​​under the same parameter item and from multiple data sources to obtain accurate parameter values ​​under the parameter item. For example, the parameter item of the location of the transport vehicle, its parameter value includes the first position information reported by the positioning system of the transport vehicle, the second position information reported by the logistics information scanning device carried by the operator of the transport vehicle, and the third position information reported by the sealing strip at the door of the transport vehicle. The data mining model judges the three position information, determines the exact position of the transport vehicle, and uses the exact position as the final parameter value for use by other parts of the digital twin model (including but not limited to the strategic planning model and the simulation model).

[0065] The strategic planning model is used to generate transportation strategies. This model can be viewed as a mathematical model, solving it by setting various constraints and optimization objectives to obtain the transportation strategy. The simulation model is used to simulate the cargo transportation process within a feeder logistics network. The simulation environment created by this model can be considered the actual environment formed by the various logistics nodes within a feeder logistics network.

[0066] In an embodiment of the present application, when the same parameter item of logistics information includes parameter values ​​from multiple data sources, accurate parameter values ​​can be obtained through data mining for subsequent use, thereby improving the accuracy of the digital twin model.

[0067] In some embodiments, a digital twin model is used to arrange the transportation rules of the branch logistics network as constraints and minimize the transportation cost as the goal to generate a transportation strategy to be optimized, including: using a digital twin model to use an operations optimization algorithm or a reinforcement learning algorithm to arrange the transportation rules of the branch logistics network as constraints and minimize the transportation cost as the goal to generate a transportation strategy to be optimized.

[0068] It should be noted that operations research optimization primarily uses mathematical models and algorithms to optimize resource allocation to reduce transportation costs and improve transportation efficiency, and has significant application value in the logistics industry. Operational optimization algorithms are typically applied to situations where resources are limited or when a choice must be made among many feasible options, such as scheduling, route planning, and inventory management. The operations research optimization algorithms used in this embodiment include, but are not limited to, heuristic algorithms, metaheuristic algorithms, exact algorithms, approximate algorithms, genetic algorithms, ant colony algorithms, and simulated annealing algorithms.

[0069] Alternatively, if the transport rules of the feeder logistics network include those for the target area, the relationship between the logistics source (CBD, special users in industrial areas), waypoints (logistics centers), and destinations (customers) can be optimized to optimize the operation of the entire logistics network and achieve the optimal transportation strategy. For example, solving the Vehicle Routing Problem (VRP) is a problem that seeks to determine how delivery vehicles can complete their delivery tasks within the shortest distance or time. In this embodiment, vehicle routing can be used as a transportation strategy.

[0070] Reinforcement learning (RL) algorithms are based on reinforcement learning. Reinforcement learning enables intelligent agents to learn the long-term rewards of performing various possible actions in a given environment through continuous interaction and learning from the environment, and based on this, develop optimal strategies. Understandably, traditional operations optimization algorithms, such as greedy and heuristic algorithms, often struggle to find ideal solutions in certain complex scenarios. However, reinforcement learning, as a decision-making optimization technique, has become an important tool for solving logistics network optimization problems. Specifically, in branch logistics networks, RL can leverage feedback from digital twin models to optimize logistics routes. By using reinforcement learning algorithms, the dynamics and uncertainties of branch logistics networks can be better addressed, resulting in better optimization results. For example, reinforcement learning can identify optimal logistics routes by learning from historical data using value-based methods (such as Q-learning and State-Action-Reward-State-Action (SARSA)) or policy-based methods (such as policy gradient and actor-critic methods). Furthermore, reinforcement learning can also adapt to the dynamic changes of logistics networks through online learning, providing real-time updates and improved decision-making.

[0071] In an embodiment of the present application, an operations optimization algorithm or a reinforcement learning algorithm is used in a digital twin model to solve the transportation strategy.

[0072] In order to facilitate users to view the situation during the logistics transportation process, the transportation strategy to be optimized is optimized based on the simulation results. After obtaining the optimized transportation strategy, the method also includes: outputting at least one of the optimized transportation strategy, simulation results and current information of each logistics node.

[0073] It should be noted that the current information of a logistics node includes information about the logistics node at different times during the simulation. This information is related to its role in the branch logistics network. For example, if the logistics node plays the role of a warehouse, the logistics node information includes information related to the warehouse's status, which is not listed here.

[0074] It is understood that when outputting the optimized transportation strategy, simulation results, and current information of each logistics node, the three can be displayed on a display device of an electronic device, but is not limited thereto. For example, a report recording the three information can be generated and printed.

[0075] In the embodiment of the present application, by outputting the optimized transportation strategy, simulation results and current information of each logistics node, it is convenient for users to view relevant logistics information.

[0076] The following describes the optimization method of the transportation strategy in the feeder logistics network under the first and second scenarios based on actual applications.

[0077] As shown in FIG2 , the embodiment of the present application provides a practical application flow chart of a method for optimizing a transportation strategy in a feeder logistics network, including:

[0078] Step S201: Construct a digital twin model. Using digital twin technology, the model is constructed based on the branch logistics network's structure, logistics nodes, transport vehicles, warehouses, and cargo. This model is used to simulate / emulate the cargo transportation process within the branch logistics network. This digital twin model not only includes the simulation / emulation functionality but also a mathematical model for determining transportation strategies. When constructing the mathematical model, constraints and optimization objectives are set based on the various logistics and transportation rules within the branch logistics network. For example, transportation cost, transportation time, and cargo loading rate are used as constraints and / or optimization objectives to optimize the branch logistics network and determine transportation strategies.

[0079] For example, in the logistics and transportation scenario of the target area, the physical logistics network of the central business district (CBD) and industrial zone is built into the digital space. This physical logistics network includes all relevant physical facilities and equipment, including businesses, warehouses, users, vehicles, and outlets in the CBD and industrial zone. IoT devices are used to collect logistics operation data from the physical logistics network, which is updated and monitored in real time. This logistics operation data includes, but is not limited to, the location and status of goods, and the status, location, and speed of transport vehicles. Various data is collected, including delivery time, cargo volume, and historical delivery records. Based on this collected data, a complete process model is created, from pickup at the sender to delivery at the recipient.

[0080] It's worth noting that building a high-quality digital twin model requires design considerations from multiple perspectives. First, use high-quality data. Poor data quality will increase the error of the digital twin model, while insufficient data can lead to model overfitting. Therefore, it's essential to collect a large amount of accurate training data. For example, this can involve learning user profiles for CBDs and industrial areas, studying employee habits, setting hyperparameters for commuting times, calibrating package volumes, and analyzing delivery and collection patterns. Second, select appropriate features. Selecting features that are highly correlated with the decision variables is crucial for improving model accuracy. If unnecessary or poorly correlated features are present, they can be removed through feature selection or feature engineering. Third, for model selection and optimization, various machine learning models can be explored, such as linear regression, support vector machines (SVMs), decision trees, random forests, and neural networks. Cross-validation can be used for model selection, while model parameters can be adjusted to optimize performance. Fourth, update the model: regularly retrain or adjust the model to ensure it always reflects the latest state of the actual system. Fifth, incorporate physics knowledge. Many engineering problems already rely on a wealth of knowledge about physical, chemical, or biological principles. Incorporating this knowledge into the model can help capture more information and improve predictive accuracy. For example, by introducing mechanistic models to supplement the data model, data such as road speed limits and mileage within a central business district or industrial zone can be used to calibrate the fastest vehicle travel time based on the distance traveled and correct erroneous data. Sixth, employ hybrid models. In some scenarios, a single model may struggle to capture all patterns and potential information. In these cases, ensemble learning or hybrid models can be used to improve predictive accuracy.

[0081] Step S202: Improve the accuracy of the digital twin model by training the model with historical data and real-time data under the feeder logistics network.

[0082] Accuracy can also be understood as realism. Realism, as a core metric of a digital twin model, measures its accuracy. For example, consider the digital twin modeling of a feeder logistics network within a central business district (CBD) and industrial zone. Historical data, including node coordinates, node shifts, node shipment volume, vehicle information, route planning, route execution, delivery and collection information, and road traffic conditions, is fed into the digital twin model for training. Training is performed until the output of core metrics such as vehicle delays, delivery and collection delays, number of routes, and number of vehicles matches historical data. This indicates that the digital twin model of the feeder logistics network within the CBD and industrial zone is sufficiently realistic. By inputting future forecast data into this sufficiently realistic digital twin model, the performance of the core metrics associated with the forecast data can be determined, completing a prediction.

[0083] Step S203: Monitor and receive data from sensors and IoT devices in real time, and continuously update the digital twin model and real-time status through the received data.

[0084] Data from sensors and IoT devices includes the location, status, and related data of transport vehicles, warehouses, and cargo, as well as order quantities, cargo information, and customer demand. Other data can also be collected simultaneously, such as predicted delivery times for pickup and delivery; predicted volume and delivery times for major customers; forecast information on temporary transfer sites; and forecast information on road and traffic conditions.

[0085] Optionally, the interface of the supply chain system and the logistics management system is used in the electronic device that executes the method provided in this embodiment, so that the synchronization and transmission of real-time data can be achieved to ensure the timeliness and accuracy of the planning. Optionally, after receiving the data, the data can be cleaned, integrated and converted, and the processed data can be input into the digital twin model. It is understandable that when a new order is generated or a problem occurs in one or some links in the branch logistics network, these data will be reflected in the received data, and then the digital twin model will automatically analyze and adjust the transportation route, warehouse allocation and transportation vehicle schemes, and output the corresponding simulation results.

[0086] It should be noted that during off-peak periods, the volume and frequency of cargo at various logistics outlets and transfer stations do not change frequently. However, during peak periods, changes in cargo volume, transit stations, shifts, and personnel can occur daily, every shift, and even every hour. Because the data received is not completely accurate, this data must be updated in real time and corrected based on existing data. In other words, the entire feeder logistics network must be frequently adjusted based on real-time peak dynamic data.

[0087] Step S204: Displaying real-time logistics network status, cargo transportation trajectory, warehouse status, supply chain data and other data in the user interface.

[0088] The user interface can be a customized visualization interface for different users. The data displayed in the user interface can also be customized for different users. The data displayed in the user interface can include data directly obtained from the digital twin model, and can also include statistical indicators and reports derived from the former.

[0089] In the embodiments of the present application, through real-time data collection and digital twin model processing, it is possible to quickly respond to changes in demand during logistics peak periods, optimize the transportation strategy of the logistics network, improve logistics transportation efficiency, reduce transportation costs, and ensure that goods are delivered on time. The status of the branch logistics network and relevant information of the transport vehicles can be monitored in real time, and emergencies can be discovered and handled in a timely manner; at the same time, the transportation strategy can be automatically adjusted to reduce delays and mismatches and ensure that goods are delivered on time. A visual interface is provided to display relevant information in the logistics transportation process for user viewing. At the same time, users can evaluate the pros and cons of different transportation strategies through the displayed data and make intelligent decisions. Through model training with historical data and real-time data, bottlenecks and problems in the branch logistics network can be predicted in advance, potential problems can be avoided, and the stable operation of the branch logistics network can be ensured.

[0090] Exemplary devices

[0091] Some embodiments of the present application further provide a device for optimizing a transportation strategy in a branch logistics network. As shown in FIG3 , the device for optimizing a transportation strategy in a branch logistics network includes:

[0092] The information acquisition module 31 is used to obtain logistics information under the branch logistics network; the logistics information includes: information of each logistics node;

[0093] The simulation module 32 is used to input logistics information into the digital twin model, arrange the routes using the transportation rules of the branch logistics network as constraints and the goal of minimizing transportation costs through the digital twin model, generate a transportation strategy to be optimized, and simulate the transportation process of goods between various logistics nodes according to the transportation strategy to be optimized to obtain simulation results;

[0094] The optimization module 33 is used to optimize the transportation strategy to be optimized based on the simulation results to obtain the optimized transportation strategy.

[0095] In some embodiments, the transportation rules of the branch logistics network include: the transportation time determined based on the associated information of the temporary transfer station is less than or equal to the promised delivery time of the goods; the associated information includes: the processing efficiency of the temporary transfer station, the shift information or at least one of the distances between the temporary transfer station and the associated logistics nodes.

[0096] In some embodiments, the logistics information under the branch logistics network also includes: at least one of the predicted quantity of goods, vehicle resource reserve information or personnel reserve information of the consolidation logistics node and / or the bulk logistics node.

[0097] In some embodiments, the transportation cost includes at least one of: transportation route change cost, transportation vehicle change cost, or personnel change cost.

[0098] In some embodiments, the transportation rules of the branch logistics network include: transportation rules for the target area, the transportation rules for the target area include: the receipt time and the shipment time of the goods are both within the office hours of the customer to whom the goods belong, and the target area is an area where the distribution density of shipping logistics nodes and / or receiving logistics nodes is higher than the target density threshold.

[0099] In some embodiments, the logistics information under the branch logistics network also includes: logistics information corresponding to the target area, and the logistics information corresponding to the target area includes: at least one of the predicted quantity of target customers, the predicted time of target customers, or the predicted time of goods; the target customer is a customer in the target area whose receiving and / or sending volume exceeds the target quantity threshold, the predicted quantity includes: the predicted receiving quantity and / or sending quantity, and the predicted time includes: the predicted receiving time and / or sending time.

[0100] In some embodiments, the transportation strategy to be optimized is optimized based on the simulation results. After obtaining the optimized transportation strategy, the device further includes: an iteration module for repeatedly executing the following steps until the simulation results of the digital twin model meet the target conditions: re-simulating the transportation process of goods between logistics nodes according to the optimized transportation strategy through the digital twin model to obtain new simulation results; optimizing the target transportation strategy based on the new simulation results, and updating the optimized transportation strategy. The target transportation strategy is the transportation strategy currently used in the simulation process of the digital twin model.

[0101] In some embodiments, the digital twin model includes: a data mining model, a strategy planning model and a simulation model; the simulation module 32 is specifically used to: perform data mining on the target parameter items in the logistics information through the data mining model to determine the final parameter value of the target parameter item; arrange the transportation rules of the branch logistics network as constraints based on the final parameter value through the strategy planning model, and minimize the transportation cost as the goal to generate a transportation strategy to be optimized; simulate the transportation process of goods between each logistics node according to the transportation strategy to be optimized based on the final parameter value through the simulation model to obtain a simulation result; the target parameter item includes multiple parameter values ​​from different data sources.

[0102] In some embodiments, the simulation module 32 is specifically used to use an operations optimization algorithm or a reinforcement learning algorithm through a digital twin model to arrange the transportation rules of the branch logistics network as constraints and minimize the transportation cost as the goal to generate a transportation strategy to be optimized.

[0103] In some embodiments, after optimizing the transportation strategy to be optimized based on the simulation results and obtaining the optimized transportation strategy, the device further includes: an output module for outputting at least one of the optimized transportation strategy, simulation results, or current information of each logistics node.

[0104] In addition, what is shown in FIG3 is only one embodiment of the device for optimizing the transportation strategy under the branch logistics network, rather than all embodiments. Based on the embodiment of the device for optimizing the transportation strategy under the branch logistics network in this application, all other embodiments obtained by those skilled in the art without making any creative work shall fall within the scope of protection of this application.

[0105] The apparatus for optimizing transportation strategies in a branch logistics network provided in the embodiments of this application is based on the same inventive concept as the method for optimizing transportation strategies in a branch logistics network provided in the aforementioned embodiments of this application. Technical details not fully described in this embodiment can be found in the specific processing details of the method for optimizing transportation strategies in a branch logistics network provided in the aforementioned embodiments of this application and will not be further elaborated here.

[0106] Exemplary electronic devices

[0107] Another embodiment of the present application also proposes an electronic device, as shown in Figure 4. An exemplary embodiment of the present application also provides an electronic device, including: a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, it executes the steps of the method for optimizing the transportation strategy under the branch logistics network according to various embodiments of the present application described in the above embodiments of the present application.

[0108] The internal structure of the electronic device can be shown in Figure 4. The electronic device includes a processor, a memory, a network interface and an input device connected through a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps of the method for optimizing the transportation strategy under the branch logistics network according to various embodiments of the present application described in the above embodiments of the present application are performed.

[0109] The processor may include a main processor, and may also include a baseband chip, a modem, etc.

[0110] The memory stores a program for executing the technical solution of the present application, and may also store an operating system and other key services. Specifically, the program may include program code, and the program code includes computer operating instructions. More specifically, the memory may include read-only memory (ROM), other types of static storage devices that can store static information and instructions, random access memory (RAM), other types of dynamic storage devices that can store information and instructions, disk storage, flash, etc.

[0111] The processor can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application solution, or a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component.

[0112] Input devices may include devices that receive data and information input by a user, such as a keyboard, mouse, camera, scanner, light pen, voice input device, touch screen, pedometer, or gravity sensor.

[0113] Output devices may include means that allow information to be output to a user, such as display screens, printers, speakers, and the like.

[0114] The communication interface may include any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0115] The processor executes the program stored in the memory and calls other devices, which can be used to implement the various steps of the optimization method of the transportation strategy in any branch logistics network provided by the above embodiments of the present application.

[0116] The electronic device may further include a display component and a voice component. The display component may be a liquid crystal display or an electronic ink display. The input device of the electronic device may be a touch layer covering the display component, or a button, trackball or touchpad provided on the housing of the electronic device, or an external keyboard, touchpad or mouse.

[0117] Those skilled in the art will understand that the structure shown in FIG4 is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components. In other words, FIG4 shows only one embodiment of the electronic device, not all embodiments. Based on the electronic device embodiment in the present application, all other embodiments obtained by those skilled in the art without further creative work shall fall within the scope of protection of the present application.

[0118] Exemplary computer program products and storage media

[0119] In addition to the above-mentioned methods and devices, as shown in Figure 5, the method for optimizing the transportation strategy under the branch logistics network provided by the embodiment of the present application can also be a computer program product 500, which includes a computer program / instruction 510. When the computer program / instruction 510 is executed by the processor, the processor executes the steps of the method for optimizing the transportation strategy under the branch logistics network according to various embodiments of the present application described in the above-mentioned "Exemplary Method" section of the present application.

[0120] The computer program product may be written in any combination of one or more programming languages ​​to implement the program code for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0121] FIG5 shows only one embodiment of a computer program product, not all embodiments. All other embodiments obtained by those skilled in the art based on the computer program product embodiment in this application without any creative work shall fall within the scope of protection of this application.

[0122] In addition, as shown in Figure 6, an embodiment of the present application also provides a computer-readable storage medium 600, on which a computer program 610 is stored. The computer program 610 is executed by the processor to perform the steps of the method for optimizing the transportation strategy under the branch logistics network according to various embodiments of the present application described in the above "Exemplary Method" section of the present application.

[0123] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0124] In addition, FIG6 shows only one embodiment of a computer-readable storage medium, not all embodiments. All other embodiments obtained by those skilled in the art based on the computer-readable storage medium embodiment in this application without any creative work shall fall within the scope of protection of this application.

[0125] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0126] The above-described embodiments merely represent several embodiments of the present application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the solutions provided by the embodiments of the present application. It should be noted that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all fall within the scope of protection of the present application. Therefore, the scope of protection of the patent application shall be based on the appended claims.

Claims

1. An optimization method for transportation strategies under a feeder logistics network, characterized in that, The method includes: Obtaining logistics information under the branch logistics network; wherein, the logistics information includes information of each logistics node; Inputting the logistics information into a digital twin model, and through the digital twin model, taking the transportation rules of the branch logistics network as constraint conditions and minimizing the transportation cost as the goal to arrange the lines, generating a transportation strategy to be optimized, and simulating the transportation process of the goods between each logistics node according to the transportation strategy to be optimized to obtain a simulation result; Optimizing the transportation strategy to be optimized based on the simulation result to obtain an optimized transportation strategy.

2. The method according to claim 1, characterized in that, The transportation rules of the branch logistics network include: The transportation duration determined based on the association information of the temporary transfer yard is less than or equal to the committed delivery time of the goods; wherein, the association information includes at least one of the processing efficiency of the temporary transfer yard, the shift information, or the distance between the temporary transfer yard and the associated logistics node.

3. The method according to claim 2, wherein The logistics information under the branch logistics network further includes at least one of the predicted volume of goods at the consolidation logistics node and / or the break-bulk logistics node, the vehicle resource reserve information, or the personnel reserve information.

4. The method according to claim 2 or 3, characterized in that, The transportation cost includes at least one of the transportation route change cost, the transportation vehicle change cost, or the personnel change cost.

5. The method according to claim 1, characterized in that, The transportation rules of the branch logistics network include the transportation rules of the target area, and the transportation rules of the target area include: both the receiving time and the sending time of the goods are within the office hours of the customer to which the goods belong, and the target area is an area where the distribution density of the shipping logistics node and / or the receiving logistics node is higher than the target density threshold.

6. The method according to claim 5, wherein The logistics information under the branch logistics network further includes the logistics information corresponding to the target area, and the logistics information corresponding to the target area includes at least one of the predicted volume of goods of the target customer, the predicted time of the target customer, or the predicted time of the goods; wherein, the target customer is a customer in the target area whose receiving volume and / or sending volume exceeds the target volume threshold, the predicted volume of goods includes the predicted receiving volume and / or the predicted sending volume, and the predicted time includes the predicted receiving time and / or the predicted sending time.

7. The method according to any one of claims 1 to 6, characterized in that After optimizing the transportation strategy to be optimized based on the simulation result to obtain an optimized transportation strategy, the method further includes: Repeating the following steps until the simulation result of the digital twin model meets the target conditions: Simulating the transportation process of the goods between each logistics node again through the digital twin model according to the optimized transportation strategy to obtain a new simulation result; Optimizing the target transportation strategy based on the new simulation result and updating the optimized transportation strategy, wherein the target transportation strategy is the transportation strategy currently relied on during the simulation process of the digital twin model.

8. The method according to any one of claims 1 to 7, characterized in that, The digital twin model includes: a data mining model, a strategy planning model, and a simulation model; Inputting the logistics information into the digital twin model, and using the transportation rules of the feeder logistics network as constraints, and minimizing the transportation cost as the objective to arrange the routes, generating an optimized transportation strategy to be optimized, and simulating the transportation process of the goods between each logistics node according to the optimized transportation strategy to be optimized to obtain a simulation result, including: Data mining the target parameter items in the logistics information through the data mining model to determine the final parameter values of the target parameter items; arranging the routes with the transportation rules of the feeder logistics network as constraints and minimizing the transportation cost as the objective through the strategy planning model based on the final parameter values to generate the optimized transportation strategy to be optimized; simulating the transportation process of the goods between each logistics node according to the optimized transportation strategy to be optimized through the simulation model based on the final parameter values to obtain the simulation result; Wherein, the target parameter items include multiple parameter values from different data sources.

9. The method according to any one of claims 1 to 8, characterized in that, The arranging the routes with the transportation rules of the feeder logistics network as constraints and minimizing the transportation cost as the objective through the digital twin model to generate an optimized transportation strategy to be optimized includes: Using the operation research optimization algorithm or the reinforcement learning algorithm through the digital twin model with the transportation rules of the feeder logistics network as constraints and minimizing the transportation cost as the objective to arrange the routes to generate the optimized transportation strategy to be optimized.

10. The method according to any one of claims 1 to 9, characterized in that After optimizing the optimized transportation strategy to be optimized based on the simulation result to obtain an optimized transportation strategy, the method further includes: Outputting at least one of the optimized transportation strategy, the simulation result or the current information of each logistics node.

11. An optimization device for transportation strategies under a feeder logistics network, characterized in that, The device includes: An information acquisition module, configured to acquire logistics information under the feeder logistics network; wherein, the logistics information includes: information of each logistics node; A simulation module, configured to input the logistics information into the digital twin model, and use the transportation rules of the feeder logistics network as constraints, and minimize the transportation cost as the objective to arrange the routes, generate an optimized transportation strategy to be optimized, and simulate the transportation process of the goods between each logistics node according to the optimized transportation strategy to be optimized to obtain a simulation result; An optimization module, configured to optimize the optimized transportation strategy to be optimized based on the simulation result to obtain an optimized transportation strategy.

12. An electronic device, characterized in that, Including: A processor and a memory; Wherein, the memory is connected to the processor, and the memory is used to store a computer program; The processor is configured to implement the optimization method of the transportation strategy under the feeder logistics network as described in any one of claims 1 to 10 by running the computer program stored in the memory.

13. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is run by the processor, the optimization method of the transportation strategy under the feeder logistics network as described in any one of claims 1 to 10 is implemented.

Images