Transportation strategy optimization method and device under branch logistics network, and electronic equipment

Abstract

The invention discloses a transportation strategy optimization method and device under a branch logistics network, and electronic equipment. The method comprises the steps of obtaining logistics information corresponding to a target area in the branch logistics network; the target area is an area in which the distribution density of the delivery logistics nodes and / or the receiving logistics nodes is higher than a target density threshold; the logistics information is input into a digital twin model, wiring is carried out through the digital twin model by taking a transportation rule of a target area as a constraint condition and taking transportation cost minimization as a target, a to-be-optimized transportation strategy is generated, and a transportation process of goods among the logistics nodes is simulated according to the to-be-optimized transportation strategy to obtain a simulation result; and optimizing the transportation strategy to be optimized based on the simulation result to obtain an optimized transportation strategy. According to the method and the device, the transportation strategy required in the logistics transportation process can be quickly generated for the target area with relatively high distribution density of the delivery logistics nodes and / or the receiving logistics nodes by means of the computing power of the electronic equipment.

Description

Technical Field

[0001] This application relates to the technical field of logistics transportation. Specifically, it relates to artificial intelligence technology in the field of logistics transportation. More specifically, it relates to an optimization method, device, and electronic device for transportation strategies in a feeder logistics network. Background Art

[0002] Logistics networks can generally be divided into two main parts: the trunk logistics network and the feeder logistics network. These two network modes play a very important role in the logistics distribution system. Among them, the feeder logistics network is the logistics transportation link between the express delivery distribution center and the final retailer or consumer. Given the complexity of the feeder logistics network, it usually requires highly experienced professionals to formulate transportation strategies to ensure the timeliness of the logistics transportation process as much as possible.

[0003] However, the above-mentioned method of manually formulating transportation strategies has high requirements for relevant personnel, not only takes a long time, but also has poor reliability of the formulated transportation strategies. Summary of the Invention

[0004] To solve the above technical problems, this application provides an optimization method, device, and electronic device for transportation strategies in a feeder logistics network to achieve the purpose of quickly generating transportation strategies in a feeder logistics network.

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

[0006] In a first aspect, an embodiment of this application provides an optimization method for transportation strategies in a feeder logistics network. The method includes: obtaining logistics information corresponding to a target area in the feeder logistics network; where the target area is an area where the distribution density of shipping logistics nodes and / or receiving logistics nodes is higher than a target density threshold; the logistics information corresponding to the target area includes: information of each logistics node in the target area; inputting the logistics information into a digital twin model, and using the transportation rules of the target area as constraint conditions and minimizing transportation costs as the goal in the digital twin model to arrange lines, 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 a simulation result; optimizing the transportation strategy to be optimized based on the simulation result to obtain an optimized transportation strategy.

[0007] Optionally, the logistics information corresponding to the target area further includes at least one of the predicted volume of parcels of the target customer, the predicted time of the target customer, and the predicted time of the goods; wherein, the target customer is a customer in the target area whose received and / or sent parcel volume exceeds the target parcel volume threshold, the predicted volume of parcels includes the predicted received parcel volume and / or the predicted sent parcel volume, and the predicted time includes the predicted received time and / or the predicted sent time.

[0008] Optionally, the transportation rules of the target area include that both the received time and the sent time of the goods are within the working hours of the customer to which the goods belong.

[0009] Optionally, after optimizing the transportation strategy to be optimized based on the simulation result to obtain the 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 according to the optimized transportation strategy through the digital twin model 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.

[0010] Optionally, 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 target area as the constraint condition by the digital twin model, 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, including: 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 lines based on the final parameter values by the strategy planning model with the transportation rules of the target area as the constraint condition and minimizing the transportation cost as the goal to generate a transportation strategy to be optimized; simulating the transportation process of the goods between each logistics node according to the transportation strategy to be optimized based on the final parameter values through the simulation model to obtain a simulation result; wherein, the target parameter items include parameter values from different data sources.

[0011] Optionally, using the digital twin model with the transportation rules of the target area as the constraint condition and minimizing the transportation cost as the goal to arrange the lines to generate a transportation strategy to be optimized, includes: using the digital twin model to utilize the operation research optimization algorithm or the reinforcement learning algorithm with the transportation rules of the target area as the constraint condition and minimizing the transportation cost as the goal to arrange the lines to generate a transportation strategy to be optimized.

[0012] Optionally, after optimizing the to-be-optimized transportation strategy based on the simulation result to obtain the optimized transportation strategy, the method further includes: outputting at least one of the optimized transportation strategy, the simulation result, and the current information of each logistics node.

[0013] In a second aspect, an embodiment of the present application provides an optimization device for a transportation strategy under a feeder logistics network. The device includes:

[0014] An information acquisition module, configured to acquire logistics information corresponding to a target area in the feeder logistics network; wherein the target area is an area where the distribution density of the shipping logistics nodes and / or receiving logistics nodes is higher than a target density threshold; the logistics information corresponding to the target area includes: information of each logistics node in the target area;

[0015] A simulation module, configured to input the logistics information into a digital twin model, and through the digital twin model, perform line arrangement with the transportation rules of the target area as constraint conditions and the minimization of transportation costs as the goal to generate a to-be-optimized transportation strategy, and simulate the transportation process of goods between each logistics node according to the to-be-optimized transportation strategy to obtain a simulation result;

[0016] An optimization module, configured to optimize the to-be-optimized transportation strategy based on the simulation result to obtain an optimized transportation strategy.

[0017] In a third aspect, an embodiment of the present application provides an electronic device, 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 for a transportation strategy under a feeder logistics network as described in the first aspect by running the computer program stored in the memory.

[0018] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it implements the optimization method for a transportation strategy under a feeder logistics network as described in the first aspect above.

[0019] In a fifth aspect, an embodiment of the present application provides a computer program product or a computer program. The computer program product includes a computer program, and the computer program is stored in a computer-readable storage medium; a 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 optimization method for a transportation strategy under a feeder logistics network as described in the first aspect.

[0020] The optimization method of the transportation strategy under the branch logistics network provided by this application, after obtaining the logistics information corresponding to the target area in the branch logistics network, inputs the logistics information into the digital twin model, generates the transportation strategy to be optimized with the help of the digital twin model, and conducts simulation according to the transportation strategy to be optimized. The simulation results reflect the cargo transportation status under the transportation strategy to be optimized. Furthermore, the simulation results are used to optimize the transportation strategy to be optimized, and the optimized transportation strategy is obtained. This application utilizes the computing power of electronic devices. For the target area with a relatively high distribution density of shipping logistics nodes and / or receiving logistics nodes, it can quickly generate the transportation strategy required during the logistics transportation process. At the same time, by simulating the logistics transportation process, the reliability of the transportation strategy can also be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to the provided drawings.

[0022] Figure 1 It is a schematic flowchart of an optimization method of a transportation strategy under a branch logistics network provided by an embodiment of this application;

[0023] Figure 2 It is an actual application flowchart of an optimization method of a transportation strategy under a branch logistics network provided by an embodiment of this application;

[0024] Figure 3 It is a structural block diagram of an optimization device of a transportation strategy under a branch logistics network provided by an embodiment of this application;

[0025] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] Unless otherwise defined, the technical terms or scientific terms used in the embodiments of this application should have the ordinary meaning understood by those of ordinary skill in the art to which this application belongs. The "first", "second" and similar terms used in the embodiments of this application do not represent any order, quantity or importance, but are only used to avoid confusion of components.

[0027] Unless otherwise required by the context, throughout the specification, "a plurality of" means "at least two", and "comprising" is construed in an open, inclusive sense, i.e., "including, but not limited to". In the description of the specification, terms such as "one embodiment", "some embodiments", "exemplary embodiments", "examples", "specific examples", or "some examples" are intended to indicate that specific features, structures, materials, or characteristics related to the embodiment or example are included in at least one embodiment or example of the present application. The schematic representations of the above terms do not necessarily refer to the same embodiment or example.

[0028] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0029] Exemplary method

[0030] The embodiment of the present application provides an optimization method for transportation strategies under a feeder logistics network, as Figure 1 shown. The optimization method for transportation strategies under the feeder logistics network includes:

[0031] Step S101: Obtain the logistics information corresponding to the target area in the feeder logistics network.

[0032] In this step, the target area is an area where the distribution density of the shipping logistics nodes and / or receiving logistics nodes is higher than the target density threshold. Among them, 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 relatively high density threshold determined in advance. The target area with a distribution density higher than the target density threshold can be regarded as an area with a dense customer group. Here, the customer group can be understood as a customer group with the need to receive or send parcels. For example, the target area can be the CBD (Central Business District) office area or industrial area, where there are many customer groups with the need to receive or send parcels.

[0033] The logistics information corresponding to the target area includes: information on each logistics node within the target area; where 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, transfer yard, distribution station, logistics network point, etc., but is not limited thereto. It can be understood that the logistics information provides a data basis for formulating transportation strategies between each logistics network point and simulating the transportation of goods between each logistics node. In some embodiments, when the target area is a CBD or industrial area, the logistics information includes all the data required for formulating transportation strategies between each logistics network point within the CBD or industrial area and simulating the transportation of goods between each logistics node within the CBD or industrial area. For example, the location and status of goods, the status, location, running speed, order quantity, goods information, and customer demand of transportation vehicles, etc.

[0034] Step S102: Input the logistics information into the digital twin model, and use the transportation rules of the target area as the constraint conditions in the digital twin model, and minimize the transportation cost as the goal to arrange the lines, generate the 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 the simulation result.

[0035] In this step, the digital twin model is a data model constructed for the corresponding branch logistics network using digital twin technology. Among them, digital twin is a simulation process that makes full use of data such as physical models, sensor updates, and operation history, integrates multiple disciplines, multiple physical quantities, multiple scales, and multiple probabilities, and completes the mapping in the virtual space, so as to reflect the entire life cycle process of the corresponding physical equipment. It can be understood that the digital twin model includes components with different functions, and the generation of the transportation strategy to be optimized and the simulation process are respectively realized through the components with different functions.

[0036] In the process of generating the transportation strategy to be optimized, based on the principle of solving the utilization rate mathematical model, with the logistics information as the input, an initial transportation strategy, that is, the transportation strategy to be optimized, can be obtained by setting constraint conditions and goals. Among them, the transportation rules of the target area are the conditions that need to be met for transporting goods in the target area, and the specific content thereof is not limited here. The transportation cost is the cost generated during the goods transportation process. In the simulation process, the characteristics of the digital twin model are used to simulate the transportation process of goods between each logistics node. Among them, both the logistics information and the transportation strategy to be optimized are input data, so that the process of transporting goods by the branch logistics network according to the logistics information under the transportation strategy to be optimized can be accurately simulated. The simulation result includes various problems that occur during the process of transporting goods in the simulation environment and / or relevant information of each logistics node.

[0037] Step S103: Optimize the transportation strategy to be optimized based on the simulation result to obtain the optimized transportation strategy.

[0038] It should be noted that when optimizing the transportation strategy, the transportation strategy can be optimized specifically 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, and corresponding optimization strategies can be set based on this correlation to optimize the transportation strategy to be optimized through the optimization strategy. Of course, the simulation results can also be directly displayed so that relevant personnel can see the simulation results and optimize the transportation strategy to be optimized based on the simulation results.

[0039] In the embodiments of the present application, after obtaining the logistics information corresponding to the target area in the feeder logistics network, the logistics information is input into the digital twin model, and the digital twin model is used to generate the transportation strategy to be optimized and perform simulation according to the transportation strategy to be optimized. The cargo transportation status under the transportation strategy to be optimized is reflected through the simulation results. Furthermore, the simulation results are used to optimize the transportation strategy to be optimized to obtain the optimized transportation strategy. With the computing power of the electronic device, the present application can quickly generate the transportation strategy required during the logistics transportation process for the target area with a relatively high distribution density of the 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.

[0040] In some embodiments, the logistics information corresponding to the target area further includes at least one of the predicted volume of the target customer, the predicted time of the target customer, and the predicted time of the goods; wherein, the target customer is a customer in the target area whose receiving volume and / or sending volume exceed the target volume threshold, the predicted volume 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.

[0041] It should be noted that in some logistics transportation scenarios, the sending volume or receiving volume of customers may be very large. For example, in the scenario of logistics transportation in the CBD or industrial area, some customers need to send or receive express deliveries 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 volume of express deliveries and the receiving and sending times. Therefore, the obtained logistics information may include the predicted volume of the target customer and the predicted time of the predicted volume of the target customer. The prediction process for the predicted volume and the predicted time is not limited here. In some embodiments, the volume, receiving time, and sending time of large customers can be predicted, and the prediction results can be used as the logistics information. The large customers here are the above-mentioned target customers. Specifically, the target customers can be screened through the historical sending data and historical receiving data of each customer in the target area, but it is not limited thereto.

[0042] Similarly, in the above logistics transportation scenario, to improve the accuracy of the digital twin model, it is necessary to predict the receiving time and / or sending time of the goods and input them as logistics information into the digital twin model as the basis for the digital twin model to generate transportation strategies and simulations. In some embodiments, to improve the accuracy of the digital twin model, relevant information about temporary transfer yards within the target area, vehicle restricted driving information, and vehicle congestion conditions can also be used as logistics information.

[0043] In the embodiments of the present application, relevant data in the scenario of logistics transportation within the CBD or industrial area are used as logistics information and jointly input into the digital twin model, which can handle this logistics scenario and improve the accuracy of the transportation strategy to be optimized and the simulation results.

[0044] In some embodiments, the transportation rules of the target area include: both the receiving time and the sending time of the goods are within the working hours of the customer to whom the goods belong.

[0045] It should be noted that in the CBD or industrial area, usually customers have regular working hours. To improve the success rate of pick-up and delivery, it is usually necessary to pick up and deliver goods during the customers' working hours. For example, the working hours of a certain customer in the CBD are from 10:00 am to 12:00 pm and from 2:00 pm to 6:00 pm. Correspondingly, the receiving time and the sending time of the goods of this customer should be between 10:00 am and 12:00 pm, or between 2:00 pm and 6:00 pm.

[0046] It can be understood that each piece of goods has a promised delivery time, that is, the goods promised delivery time. According to the requirements of logistics transportation services, the transportation needs to be completed within the goods promised delivery time. 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, sometimes an additional temporary transfer yard is added to relieve the logistics pressure. Different from the original transfer yard in the target area, this temporary transfer yard is only put into use during the specified time. However, during the use period, the temporary transfer yard and the original transfer yard have the same functions. Therefore, the transportation rules of the target area can also include that the transportation duration determined based on the associated information of the temporary transfer yard is less than or equal to the goods promised delivery time.

[0047] The functions of the temporary transfer yard in the logistics transportation process will not be elaborated here. In this embodiment, the transportation duration will be determined based on the data required for its implementation functions. These data include but are not limited to the processing efficiency of the temporary transfer yard, shift information, and the distances between the temporary transfer yard and associated logistics nodes. Among them, the processing efficiency of the temporary transfer yard is the efficiency of the temporary transfer yard in processing express deliveries. The shift information is the shift information of the transportation vehicles in the temporary transfer yard. Of course, the transportation rules for the target area may also include: transportation rules associated with the original transfer yard. For example, the transportation duration determined based on the association information of the original transfer yard is less than or equal to the promised delivery time of the goods. It should be noted that other constraint conditions can also be set in the digital twin model. For example, a constraint condition regarding the load capacity, that is, the load capacity of all transportation vehicles is greater than the weight of all goods. A constraint condition regarding vehicle scheduling, that is, all vehicles need to drive in their respective corresponding logistics transportation areas.

[0048] In the embodiments of this application, by setting corresponding constraint conditions based on the logistics transportation rules within the CBD or industrial area, corresponding logistics scenarios can be addressed, and the accuracy of the digital twin model can be improved.

[0049] To further enhance the logistics transportation effect of the operation strategy, after optimizing the transportation strategy to be optimized based on the simulation results and obtaining the optimized transportation strategy, the method further includes:

[0050] Repeatedly execute the following steps until the simulation result of the digital twin model meets the target conditions: Use the digital twin model to simulate the transportation process of the goods between each logistics node again according to the optimized transportation strategy to obtain a new simulation result; Optimize the target transportation strategy based on the new simulation result and update the optimized transportation strategy, where the target transportation strategy is the transportation strategy currently relied on during the simulation process of the digital twin model.

[0051] It should be noted that the target conditions are the expected results / expected transportation effects of the transportation strategy. In some embodiments, the target conditions can be set in advance based on the expectations for the operation strategy. Thus, after determining that the simulation result of a certain simulation meets the target conditions, stop optimizing the transportation strategy and use the current transportation strategy as the finally optimized transportation strategy. Specifically, the simulation result can reflect the goods transportation status under the transportation strategy to be optimized. Therefore, the target conditions can be set based on the expected goods transportation status. For example, the target conditions can be set as: More than a certain threshold percentage of the goods are transported within the promised delivery time, but it is not limited to this.

[0052] It can be understood that the process of repeatedly simulating and optimizing the transportation strategy can be regarded as an iteration of the transportation strategy. Each iteration includes a simulation process and a process of optimizing the transportation strategy. And the transportation strategy used in the simulation process of each iteration is the transportation strategy generated in the step of optimizing the transportation strategy in the previous iteration.

[0053] In the embodiments of the present application, by continuously iterating and updating the transportation strategy, a transportation strategy with better logistics transportation effect can be obtained.

[0054] In some embodiments, the digital twin model includes: a data mining model, a strategy planning model, and a simulation model; inputting logistics information into the digital twin model, and taking the transportation rules of the target area as constraints by the digital twin model, and taking minimizing the transportation cost as the goal to arrange lines, 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, including:

[0055] Data mining is performed on the target parameter items in the logistics information through the data mining model to determine the final parameter values of the target parameter items; based on the final parameter values, the strategy planning model arranges lines with the transportation rules of the target area as constraints and minimizing the transportation cost as the goal to generate a transportation strategy to be optimized; based on the final parameter values, the simulation model simulates the transportation process of goods between each logistics node according to the transportation strategy to be optimized to obtain simulation results; wherein, the target parameter items include multiple parameter values from different data sources.

[0056] It should be noted that the data mining model is used to mine data. Specifically, the data mining model is used to process the parameter values under the same parameter item and from multiple data sources to obtain the accurate parameter value under this parameter item. For example, for the parameter item of the position of the transportation vehicle, its parameter values include the first position information reported by the positioning system of the transportation vehicle, the second position information reported by the logistics information scanning device carried by the operator of the transportation vehicle, and the third position information reported by the sealing strip at the door of the transportation vehicle. The data mining model judges the three position information to determine the accurate position of the transportation vehicle, and uses this accurate position as the final parameter value for other parts of the digital twin model (including but not limited to the strategy planning model and the simulation model).

[0057] The strategy planning model is used to generate a transportation strategy. This strategy planning model can be regarded as a mathematical model, and a transportation strategy is obtained by setting various constraint conditions and optimization goals for solution. The simulation model is used to simulate the transportation process of goods under the branch line logistics network. The simulation environment constructed by this simulation model can be regarded as the real environment composed of each logistics node under the branch line logistics network in the real world.

[0058] In the embodiments of the present application, when the same parameter item of the logistics information includes parameter values from multiple data sources, accurate parameter values can be obtained through data mining for subsequent use, improving the accuracy of the digital twin model.

[0059] In some embodiments, the digital twin model is used to generate an optimized transportation strategy by arranging the lines with the transportation rules of the target area as the constraint conditions and minimizing the transportation cost, including: using the digital twin model to arrange the lines with the transportation rules of the target area as the constraint conditions and minimizing the transportation cost as the goal by using the operation research optimization algorithm or the reinforcement learning algorithm, and generating the optimized transportation strategy to be optimized.

[0060] It should be noted that operation research optimization mainly optimizes the allocation of resources through mathematical models and algorithms to reduce transportation costs and improve transportation efficiency, which has important application value for the logistics industry. The operation research optimization algorithm is usually applied to situations where resources are limited or choices need to be made among many feasible options. For example, problems such as scheduling, path planning, and inventory management. The operation research optimization algorithms in this embodiment include: heuristic algorithms, meta-heuristic algorithms, exact algorithms, approximation algorithms, genetic algorithms, ant colony algorithms, and simulated annealing algorithms, etc., but are not limited to this. Optionally, by optimizing the relationships among the logistics source (special users in the CBD and industrial areas), waypoints (logistics centers), and destinations (customers), the operation of the entire logistics network can be optimized to obtain the best transportation strategy. For example, solving the VRP (Vehicle Routing Problem), which is a problem of how to complete the distribution task by the distribution vehicle in the shortest distance or the shortest time. This embodiment can use the vehicle path as the transportation strategy.

[0061] The reinforcement learning (RL) algorithm is an algorithm based on reinforcement learning. Among them, reinforcement learning enables the agent to learn the long-term rewards of performing various possible actions in a given environment through continuous interaction and learning with the environment, and based on this, formulate the optimal strategy. It can be understood that traditional operation research optimization algorithms such as greedy algorithms and heuristic algorithms are often difficult to find ideal solutions in some complex scenarios. And reinforcement learning, as a decision-making optimization technology, has become an important tool for solving the logistics network optimization problem. Specifically, in the branch logistics network, RL can optimize the logistics path with the help of the feedback information of the digital twin model. By using the reinforcement learning algorithm, the dynamics and uncertainties of the branch logistics network can be better handled, thereby obtaining better optimization effects. For example, reinforcement learning can find the best logistics path by learning historical data and using value-based methods (such as Q-learning and SARSA) or policy-based methods (such as policy gradient and actor-critic methods). At the same time, reinforcement learning can also respond to the dynamic changes of the logistics network through online learning, update the information in real time, and improve the decision-making.

[0062] In the embodiments of the present application, the operation research optimization algorithm or the reinforcement learning algorithm is used in the digital twin model to solve the transportation strategy.

[0063] To facilitate the user to view the situation during the logistics transportation process and optimize the transportation strategy to be optimized based on the simulation results, after obtaining the optimized transportation strategy, the method further includes: outputting at least one of the optimized transportation strategy, the simulation results, and the current information of each logistics node.

[0064] It should be noted that the current information of the logistics node includes the information of the logistics node at different times during the simulation process. Among them, the information of the logistics node is related to its role in the branch logistics network. For example, if the role of the logistics node is a warehouse, the information of the logistics node includes the information related to the situation of the warehouse, which will not be listed one by one here.

[0065] It can be understood that when outputting the optimized transportation strategy, the simulation results, and the current information of each logistics node, the three can be displayed on the display device of the electronic device by means of display, but it is not limited to this. For example, a report recording the information of the three can also be generated and printed out.

[0066] In the embodiment of the present application, by outputting the optimized transportation strategy, the simulation results, and the current information of each logistics node, it is convenient for the user to view the relevant logistics information.

[0067] As Figure 2 shown, the embodiment of the present application provides an actual application flowchart of an optimization method for a transportation strategy under a branch logistics network, including:

[0068] Step S201: Construct a digital twin model. Based on the structure of the branch logistics network, logistics nodes, transportation vehicles, warehouses, and goods, etc., use digital twin technology to build a digital twin model to realize the simulation of the goods transportation process under the branch logistics network. In this embodiment, the physical logistics network of the CBD and the industrial area is built into the digital space. The physical logistics network includes all relevant physical facilities and equipment such as enterprises, warehouses, users, vehicles, and outlets in the CBD and the industrial area. Collect the logistics operation data of the physical logistics network through Internet of Things devices and perform real-time update and monitoring. Among them, the logistics operation data includes but is not limited to the location and status of goods, the status, location, and running speed of transportation vehicles, etc. Collect various data including delivery time, volume situation, and historical delivery records. Create a complete process model from picking up packages at the sender to delivering packages to the recipient according to the collected data.

[0069] It should be noted that in order to build a high-quality digital twin model, the following multiple dimensions are designed in this embodiment: First, use high-quality data. Poor data quality will lead to an increase in the error of the digital twin model, while too small a data scale will lead to model overfitting. Therefore, a large amount of accurate training data needs to be collected. For example, learning user portraits in CBDs and industrial parks, learning personnel habits, setting hyperparameters for commuting times, calibrating the volume of parcels, analyzing the situation of parcel collection and delivery, etc. Second, select appropriate features. Selecting features highly correlated with decision variables is very important for improving the accuracy of the model. If there are unnecessary or low-correlation features, they can be removed through feature selection or feature engineering. Third, model selection and optimization. Multiple machine learning models can be tried, such as linear regression, support vector machine (SVM), decision tree, random forest, neural network, etc., and cross-validation can be used for model selection, and at the same time, the model performance can be optimized by adjusting model parameters. Fourth, update the model. Regularly retrain or adjust the model to make it always reflect the latest state of the actual system. Fifth, incorporate physical knowledge. In many engineering problems, there is already a lot of knowledge of physical, chemical or biological principles. Introducing this knowledge into the model can help the model capture more information and improve prediction accuracy. For example, introducing some mechanism models to assist the data model. There are some data such as road speed limits and mileage within the scope of CBDs and industrial parks, and the fastest vehicle driving time can be calibrated according to the distance to correct the wrong data. Sixth, adopt a hybrid model: In some scenarios, a single model may be difficult to capture all patterns and potential information. At this time, the method of ensemble learning or hybrid model can be tried to improve prediction accuracy.

[0070] Step S202: Train the model with historical data and real-time data under the feeder logistics network to improve the fidelity of the digital twin model.

[0071] Fidelity, as a core indicator of a digital twin model, can measure the accuracy of the digital twin model. For example, conduct digital twin modeling of the feeder logistics network in CBDs and industrial parks. Take historical data: many historical input information such as node coordinates, node shifts, node parcel volumes, vehicle information, route planning information, route execution information, parcel collection and delivery information, and road traffic conditions in CBDs and industrial parks, and input them into the digital twin model for model training until the output results of relevant core indicators such as vehicle lateness, parcel collection and delivery delays, the number of vehicle routes, and the number of vehicles are consistent with the historical real information, indicating that the digital twin model of the feeder logistics network in CBDs and industrial parks is realistic enough. Input future prediction data into a realistic enough digital twin model, and the performance of the relevant core indicators of the prediction data can be obtained to complete a prediction.

[0072] Step S203: Continuously monitor and receive data from sensors and Internet of Things devices, and continuously update the digital twin model and real-time status based on the received data.

[0073] Among them, the data from sensors and Internet of Things devices include: the locations, statuses, and related data of transportation vehicles, warehouses, and goods, the order quantity, goods information, customer demands, and other data. Other data can also be obtained simultaneously, such as the predicted delivery time of pick-up and delivery; the predicted volume and time of large customers; the relevant predicted information of temporary transfer yards; the predicted road condition information and traffic condition information.

[0074] Step S204: Display data such as the real-time logistics network status, goods transportation trajectory, warehouse situation, and supply chain data in the user interface.

[0075] Among them, the user interface can be a customized visualization interface for different users. The data displayed in the user interface can also be customized data for different users. For the data displayed in the user interface, it can include the data directly obtained from the digital twin model, or it can also include: statistical indicators and reports based on the former.

[0076] In the embodiments of the present application, through real-time data collection and digital twin model processing, it is possible to quickly respond to the demand changes during the logistics peak period, optimize the transportation strategy of the logistics network, improve the logistics transportation efficiency, reduce the transportation cost, and ensure the timely delivery of goods. It is possible to monitor the status of the feeder logistics network and the relevant information of transportation vehicles in real time; at the same time, it is possible to automatically adjust the transportation strategy to reduce delays and misallocations and ensure the timely delivery of goods. Provide a visual interface to display the relevant information during the logistics transportation process for the convenience of users to view. At the same time, users can evaluate the advantages and disadvantages of different transportation strategies based on the displayed data and make intelligent decisions. Through model training with historical data and real-time data, it is possible to predict the bottlenecks and problems of the feeder logistics network in advance, avoid the occurrence of potential problems, and ensure the stable operation of the feeder logistics network.

[0077] Exemplary device

[0078] Some embodiments of the present application also provide an optimization device for the transportation strategy under the feeder logistics network, as Figure 3 shown. The optimization device for the transportation strategy under the feeder logistics network includes:

[0079] An information acquisition module 31, configured to acquire the logistics information corresponding to the target area in the feeder logistics network; among them, the target area is an area where the distribution density of the shipping logistics nodes and / or receiving logistics nodes is higher than the target density threshold; the logistics information corresponding to the target area includes: the information of each logistics node in the target area.

[0080] The simulation module 32 is configured to input logistics information into the digital twin model, and through the digital twin model, with the transportation rules of the target area as the constraint conditions and the minimization of transportation costs as the goal, arrange the lines, generate the transportation strategy to be optimized, and simulate the transportation process of the goods between each logistics node according to the transportation strategy to be optimized to obtain the simulation result;

[0081] The optimization module 33 is configured to optimize the transportation strategy to be optimized based on the simulation result to obtain the optimized transportation strategy.

[0082] In some embodiments, the logistics information corresponding to the target area further includes at least one of the predicted volume of the target customer, the predicted time of the target customer, and the predicted time of the goods; wherein, the target customer is a customer in the target area whose received volume and / or sent volume exceeds the target volume threshold, the predicted volume includes the predicted received volume and / or sent volume, and the predicted time includes the predicted received time and / or sent time.

[0083] In some embodiments, the transportation rules of the target area include that both the received time and the sent time of the goods are within the working hours of the customer to which the goods belong.

[0084] In some embodiments, the device further includes an iteration module, which is configured to repeatedly execute the following steps until the simulation result of the digital twin model meets the target conditions: simulate 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; optimize the target transportation strategy based on the new simulation result and update the optimized transportation strategy, where the target transportation strategy is the transportation strategy currently relied on during the simulation process of the digital twin model.

[0085] In some embodiments, 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, through the digital twin model, with the transportation rules of the target area as the constraint conditions and the minimization of transportation costs as the goal, arranging the lines, generating the 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 the simulation result, including: performing data mining on 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 lines through the strategy planning model based on the final parameter values with the transportation rules of the target area as the constraint conditions and the minimization of transportation costs as the goal to generate the transportation strategy to be optimized; simulating the transportation process of the goods between each logistics node through the simulation model based on the final parameter values according to the transportation strategy to be optimized to obtain the simulation result; wherein, the target parameter items include multiple parameter values from different data sources.

[0086] In some embodiments, the simulation module 32 is specifically configured to use an operations research optimization algorithm or a reinforcement learning algorithm through a digital twin model, take the transportation rules of the target area as a constraint condition, and perform line arrangement with the goal of minimizing transportation costs to generate a transportation strategy to be optimized.

[0087] In some embodiments, the device further includes: an output module, configured to output at least one of the optimized transportation strategy, the simulation result, and the current information of each logistics node.

[0088] The optimization device for transportation strategies in a feeder logistics network provided by the embodiments of the present application belongs to the same inventive concept as the optimization method for transportation strategies in a feeder logistics network provided by the above embodiments of the present application. For technical details not described in detail in this embodiment, reference may be made to the specific processing content of the optimization method for transportation strategies in a feeder logistics network provided by the above embodiments of the present application, which will not be elaborated here.

[0089] Exemplary electronic device

[0090] Another embodiment of the present application further proposes an electronic device. Refer to Figure 4 As shown, an exemplary embodiment of the present application further 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 in the optimization method for transportation strategies in a feeder logistics network according to various embodiments of the present application described in the above embodiments of the present application.

[0091] The internal structure of the electronic device can be as Figure 4 As shown, the electronic device includes a processor, a memory, a network interface, and an input device connected through a system bus. Among them, 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, it performs the steps in the optimization method for transportation strategies in a feeder logistics network according to various embodiments of the present application described in the above embodiments of the present application.

[0092] The processor may include a main processor, and may also include a baseband chip, a modem, etc.

[0093] The memory stores a program for implementing the technical solution of the present invention, and may also store an operating system and other key services. Specifically, the program may include program code, and the program code includes computer operation instructions. More specifically, the memory may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk memory, a flash memory, and so on.

[0094] The processor may 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 for controlling the execution of the program of the present invention. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0095] The input device may include a device for receiving user input data and information, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer or a gravity sensor, etc.

[0096] The output device may include a device for allowing information to be output to the user, such as a display screen, a printer, a speaker, etc.

[0097] The communication interface may include a device using any transceiver type to communicate with other devices or communication networks, such as Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0098] The processor executes the program stored in the memory and calls other devices, which can be used to implement each step of the optimization method for the transportation strategy under any one of the branch logistics networks provided in the above embodiments of the present application.

[0099] The electronic device may further include a display component and a voice component. The display component may be a liquid crystal display screen or an electronic ink display screen. The input device of the electronic device may be a touch layer covered on the display component, or a button, a trackball or a touchpad provided on the housing of the electronic device, or an external keyboard, a touchpad or a mouse, etc.

[0100] Those skilled in the art can understand, Figure 4The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the electronic device to which the solution of this application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0101] Exemplary computer program product and storage medium

[0102] In addition to the above methods and devices, the optimization method for the transportation strategy under the feeder logistics network provided by the embodiments of this application may also be a computer program product, which includes computer program instructions. When the computer program instructions are run by a processor, the processor is caused to execute the steps in the optimization method for the transportation strategy under the feeder logistics network according to various embodiments of this application described in the "Exemplary Method" section above of this application.

[0103] The computer program product can be written in any combination of one or more programming languages for the program code to perform the operations of the embodiments of this application. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed completely on the user computing device, partially on the user device, executed as an independent software package, partially on the user computing device and partially on a remote computing device, or completely on a remote computing device or server.

[0104] In addition, the embodiments of this application also provide a computer-readable storage medium, on which a computer program is stored. The computer program is executed by a processor to perform the steps in the optimization method for the transportation strategy under the feeder logistics network according to various embodiments of this application described in the "Exemplary Method" section above of this application.

[0105] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing 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 methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories 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 (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0106] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered as the scope recorded in the present application.

[0107] The above-described embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on 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, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. An optimization method for transportation strategies under a feeder logistics network, characterized in that, The method includes: Obtaining the logistics information corresponding to the target area in the branch logistics network; wherein, the target area is an area where the distribution density of the shipping logistics nodes and / or the receiving logistics nodes is higher than the target density threshold; the logistics information corresponding to the target area includes: the information of each logistics node in the target area; Inputting the logistics information into the digital twin model, and through the digital twin model, taking the transportation rules of the target area as the constraint conditions and the minimization of transportation cost as the goal for line arrangement, 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 logistics information corresponding to the target area further includes at least one of the predicted volume of pieces of the target customer, the predicted time of the target customer, and 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 pieces includes: the predicted receiving volume of pieces and / or the predicted sending volume of pieces, and the predicted time includes: the predicted receiving time and / or the predicted sending time.

3. The method according to claim 1, wherein The transportation rules of the target area include: Both the receiving time and the sending time of the goods are within the working hours of the customer to which the goods belong.

4. The method according to claim 1, 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: Repeatedly executing 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.

5. The method according to claim 1, wherein 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 through the digital twin model, taking the transportation rules of the target area as the constraint conditions and the minimization of transportation cost as the goal for line arrangement, 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, including: Performing data mining on the target parameter items in the logistics information through the data mining model to determine the final parameter values of the target parameter items; Generating a transportation strategy to be optimized through the strategy planning model based on the final parameter values, taking the transportation rules of the target area as the constraint conditions and the minimization of transportation cost as the goal for line arrangement; Simulating the transportation process of the goods between each logistics node according to the transportation strategy to be optimized based on the final parameter values through the simulation model to obtain a simulation result; Wherein, the target parameter items include parameter values from multiple different data sources.

6. The method according to claim 1, wherein Generating a transportation strategy to be optimized through the digital twin model, taking the transportation rules of the target area as the constraint conditions and the minimization of transportation cost as the goal for line arrangement, including: Using an operations research optimization algorithm or a reinforcement learning algorithm through a digital twin model, with the transportation rules of the target area as the constraint conditions, the transportation route is arranged with the goal of minimizing transportation costs to generate a transportation strategy to be optimized.

7. The method according to claim 1, characterized in that After optimizing the transportation strategy to be optimized based on the simulation results to obtain an optimized transportation strategy, the method further includes: Outputting at least one of the optimized transportation strategy, the simulation results, and the current information of each logistics node.

8. An optimization device for transportation strategies under a feeder logistics network, characterized in that, The device includes: An information acquisition module for acquiring the logistics information corresponding to the target area in the branch logistics network; wherein, the target area is an area where the distribution density of the shipping logistics nodes and / or receiving logistics nodes is higher than the target density threshold; the logistics information corresponding to the target area includes: the information of each logistics node in the target area; A simulation module for inputting the logistics information into the digital twin model, using the digital twin model with the transportation rules of the target area as the constraint conditions, arranging the transportation route with the goal of minimizing transportation costs to generate 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 simulation results; An optimization module for optimizing the transportation strategy to be optimized based on the simulation results to obtain an optimized transportation strategy.

9. 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 used to implement the optimization method of the transportation strategy under the branch logistics network according to any one of claims 1 to 7 by running the computer program stored in the memory.

10. 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 branch logistics network according to any one of claims 1 to 7 is implemented.

Images