Big data processing-based multimodal transport organization mode dynamic optimization method

Abstract

The invention discloses a multimodal transport organization mode dynamic optimization method based on big data processing, which relates to the technical field of multimodal transport data optimization, and comprises the steps of collecting various data in a transport process in real time, and carrying out data optimization based on transport network nodes of a target area. A multimodal transport grid model is constructed, first site information and second site information in a multimodal transport planning path are collected, first weather prediction data and second weather prediction data are collected in real time, and the multimodal transport grid model based on weather changes is formed. An optimization algorithm is adopted to solve the multimodal transport path optimization model with constraint conditions and based on weather changes; according to the method, the influence of the weather factors on the transportation mode can be fully considered when the multimodal transportation organization mode is dynamically optimized, the situation that the established transportation mode cannot be safely and successfully executed on schedule due to the weather influence is avoided, the transportation mode can be flexibly adjusted by introducing the first weather prediction data and the second weather prediction data, and the transportation efficiency is improved. Therefore, the smooth operation of multimodal transport is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of multimodal transport data optimization, and in particular to a multimodal transport organization model dynamic optimization method based on big data processing. Background Art

[0002] Intermodal transport refers to the transportation process completed by two or more means of transportation connecting and transferring with each other. This mode of transportation is usually called intermodal transport in my country. Intermodal transport usually includes the organic combination of multiple modes of transportation such as road transport, rail transport, air transport, and water transport, forming an overall network that is interconnected and seamlessly connected. The more common intermodal transport modes in the market include road-water transport, road-rail transport, rail-water transport, air-rail transport, and water-water transport. Among them, rail-water transport is the focus and difficulty of intermodal transport, and it is also one of the key directions promoted by current policies.

[0003] The traditional multimodal transport organization mode dynamic optimization method based on big data processing does not introduce the impact of weather factors on the dynamic optimization of multimodal transport organization mode, and weather factors greatly restrict the normal operation of transportation. Therefore, the present invention proposes a multimodal transport organization mode dynamic optimization method based on big data processing to solve the shortcomings of the prior art. Summary of the invention

[0004] In view of the above problems, the purpose of the present invention is to provide a dynamic optimization method for multimodal transport organization mode based on big data processing. When dynamically optimizing the multimodal transport organization mode, the impact of weather factors on the transportation mode can be fully considered to avoid the established transportation mode being affected by the weather and unable to be successfully executed on schedule and safely. By introducing the first weather forecast data and the second weather forecast data, the transportation mode can be flexibly adjusted to ensure the smooth progress of multimodal transport.

[0005] To achieve the above object, the present invention provides the following technical solutions: The method for dynamic optimization of multimodal transport organization mode based on big data processing includes the following steps: Step 1: Collect various data in the transportation process in real time, and then perform data preprocessing operations on the collected data to obtain standardized data; Step 2: Construct a multimodal transport grid model based on the transport network nodes in the target area; Step 3: collecting site information of multiple first transfer sites in the current target transport mode in the multimodal transport planning path to form first site information, and collecting site information of multiple second transfer sites in the next target transport mode in the multimodal transport planning path to form second site information; Step 4: Real-time collection of the first weather forecast data for the entire transportation process of the current target transportation mode in the multimodal transport planning path, and real-time collection of the second weather forecast data for the entire transportation process of the next target transportation mode; Step 5: inputting the first weather forecast data and the second weather forecast data as well as the first site information and the second site information into the multimodal transport grid model to construct a multimodal transport grid model based on weather changes; Step 6: Determine the objective function of the multimodal transport grid model based on weather changes according to the transport demand, market changes, the first weather forecast data and the second weather forecast data; Step 7: Convert the multimodal transport grid model based on weather changes into a multimodal transport path optimization model based on weather changes, and combine the objective function and the constraint condition function to establish a multimodal transport path optimization model based on weather changes with constraints; Step 8: Use optimization algorithms to solve the multimodal transport path optimization model based on weather changes with constraints.

[0006] A further improvement is that when collecting various data during the transportation process in real time in step 1, it includes but is not limited to collecting various data during the transportation process in real time through the Internet of Things, RFID, and GPS.

[0007] A further improvement is that the various data in the transportation process in step 1 include but are not limited to cargo location, transportation status, transportation environment, transportation cost and transportation time.

[0008] A further improvement is that: in step 2, the transportation network nodes based on the target area, wherein the transportation nodes include but are not limited to ports, airports, railway stations, highway hubs, logistics parks, etc., wherein the transportation network nodes based on the target area also include node information contained in these nodes, specifically the geographical location, transportation capacity, service scope, etc. of the nodes.

[0009] A further improvement is that the first site information and the second site information in step three both include the comprehensive capability information of the site to cope with temporary transit scheduling, site scale information, and supporting transportation capacity information around the site.

[0010] A further improvement is that when the first weather forecast data of the entire transportation process of the current target transportation mode in the multimodal transport planning path is collected in real time in step 4, it includes collecting the first weather forecast data in segments, and collecting the first weather forecast data one by one according to multiple first transfer sites.

[0011] A further improvement is that in step 4, when collecting the second weather forecast data in real time during the entire transportation process of the next target transportation mode in the multimodal transport planning path, it includes collecting the second weather forecast data in segments, and collecting the second weather forecast data one by one according to multiple second transfer stations.

[0012] A further improvement is that in step six, when determining the objective function of the multimodal transport grid model based on weather changes according to transportation demand, market changes, the first weather forecast data and the second weather forecast data, the first weather forecast data and the second weather forecast data are introduced to dynamically adjust the changes in the transportation mode, and the influence rate of the first weather forecast data and the second weather forecast data on the success rate of the current transportation mode is determined, and the influence rate is used as a variable parameter for selecting the objective function.

[0013] A further improvement is that when the impact rate is used as a variable parameter for selecting the objective function in step six, a target threshold of the impact rate is set in the multimodal transport grid model based on weather changes. If the impact rate exceeds the target threshold, the weight of the impact rate as a variable parameter when selecting the objective function is increased to 1.1; if the impact rate does not exceed the target threshold, the weight of the impact rate as a variable parameter when selecting the objective function is changed to 0.9.

[0014] Further improvement is that: the optimization algorithm in step eight includes but is not limited to genetic algorithm, simulated annealing algorithm, particle swarm algorithm, and through iterative calculation, the transportation path, resource allocation and transportation mode are continuously adjusted to find the optimal or suboptimal transportation organization mode.

[0015] The beneficial effects of the present invention are as follows: the present invention forms first site information by collecting site information of multiple first transfer sites in the current target transport mode in the multimodal transport planning path, and forms second site information by collecting site information of multiple second transfer sites in the next target transport mode in the multimodal transport planning path, and collects first weather forecast data in real time during the entire transportation process of the current target transport mode in the multimodal transport planning path, and second weather forecast data in real time during the entire transportation process of the next target transport mode, and then inputs the first weather forecast data and the second weather forecast data as well as the first site information and the second site information into the multimodal transport grid model to form a multimodal transport grid model based on weather changes, and then determines the objective function of the multimodal transport grid model based on weather changes according to transport demand, market changes, the first weather forecast data and the second weather forecast data, so that when dynamically optimizing the multimodal transport organization mode, the influence of weather factors on the transport mode can be fully considered to avoid the established transport mode being affected by the weather and unable to be successfully and safely executed on schedule, and the first weather forecast data and the second weather forecast data can be introduced to realize flexible adjustment of the transport mode to ensure the smooth progress of multimodal transport. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0017] In order to deepen the understanding of the present invention, the present invention will be further described in detail below in conjunction with examples. The examples are only used to explain the present invention and do not constitute a limitation on the protection scope of the present invention.

[0018] according to Figure 1 As shown, this embodiment proposes a method for dynamic optimization of multimodal transport organization mode based on big data processing, including the following steps: Step 1: Real-time collection of various data during transportation, including but not limited to real-time collection of various data during transportation through the Internet of Things, RFID, and GPS, and then pre-processing the collected data, including cleaning, denoising, conversion and other pre-processing operations, to ensure the accuracy and availability of the data and obtain standardized data; IoT technology connects the physical world with the digital world through sensors, controllers, actuators and other devices, and realizes real-time data collection, transmission and processing. In the transportation process, IoT technology can be applied to the following aspects: Sensor application: Various sensors such as temperature sensors, humidity sensors, pressure sensors, etc. are installed in transportation vehicles, cargo packaging or transportation environment to monitor the physical state and environmental conditions of the cargo in real time. These sensors transmit data to the IoT platform wirelessly for subsequent analysis and processing. Equipment interconnection: Through IoT technology, various equipment in the transportation process (such as vehicles, loading and unloading equipment, storage equipment, etc.) are connected to realize information sharing and collaborative work between equipment. For example, the location, speed, load and other information of the transportation vehicle, as well as the inventory status and operating efficiency of the storage equipment can be viewed in real time through the IoT platform. Data analysis and decision support: After processing and analysis, the data collected by the IoT platform can provide decision support for transportation management. For example, by analyzing the driving trajectory and speed changes of the transportation vehicle, the transportation route and scheduling plan can be optimized; by analyzing the physical state and environmental conditions of the cargo, the shelf life and safety of the cargo can be predicted.

[0019] RFID technology automatically identifies target objects and obtains relevant data through wireless radio frequency signals. It has the advantages of non-contact, fast reading, and large-capacity storage. During transportation, RFID technology can be applied to the following aspects: Cargo tracking: RFID tags are attached to the goods, and the tag information is read by the RFID reader at various links in the transportation process (such as warehouses, loading and unloading points, transportation vehicles, etc.) to achieve real-time tracking and positioning of the goods. This helps to improve the transparency and safety of cargo transportation. Inventory management: RFID readers are installed in warehouses to realize automatic inventory counting and management of inventory by reading the RFID tag information on the goods. This can greatly improve the accuracy and efficiency of inventory management. Vehicle management: RFID tags are attached to transportation vehicles, and the tag information is read by the RFID reader, so that the location, load, driving status and other information of the vehicle can be grasped in real time. This helps to optimize vehicle scheduling and route planning.

[0020] GPS technology determines the location information of the target object by receiving satellite signals, and has the advantages of high precision, all-weather, and global coverage. In the transportation process, GPS technology can be applied to the following aspects: Vehicle positioning: Install GPS positioning equipment on the transport vehicle to obtain the vehicle's location information in real time and display it to the management personnel through the Internet of Things platform. This helps the management personnel to grasp the location and driving status of the vehicle in real time and improve the efficiency of transportation management. Route planning: Combined with GIS (geographic information system) technology, the optimal driving route is planned for the vehicle based on the vehicle's location information and transportation needs. This helps to reduce transportation time and cost and improve transportation efficiency.

[0021] Abnormal alarm: When a vehicle deviates from the scheduled route or encounters an abnormal situation (such as speeding, sudden braking, etc.), the GPS positioning device can trigger an alarm mechanism to notify the management personnel in time for processing. This helps to ensure transportation safety and improve emergency response capabilities.

[0022] Step 2: Based on the transportation network nodes of the target area, the transportation nodes include but are not limited to ports, airports, railway stations, highway hubs, logistics parks, etc., and the transportation network nodes based on the target area also include node information contained in these nodes, specifically the geographical location, transportation capacity, service scope, etc. of the nodes, to build a multimodal transportation grid model; Based on the transportation network nodes of the target area, the specific steps of constructing the multimodal transport grid model can be summarized into the following key stages: 1. Preliminary preparation and data collection Identify the target area: First, you need to determine the target area covered by the multimodal transport service, which is usually a relatively clear geographical range, such as a city, province or multinational region; Collecting transportation network node information: Collecting all relevant transportation network node information in the target area, including but not limited to ports, airports, railway stations, highway hubs, logistics parks, etc. This information should include the geographical location, transportation capacity, service scope, etc. of the node; Obtain intermodal transport data: Collect data on the transfer between different modes of transport (such as road, rail, water, and air), including transfer efficiency, cost, time, etc. This data is essential for building an intermodal transport grid model.

[0023] 2. Building a Transportation Grid Model Grid division: Divide the target area into several grids, each grid represents a relatively independent transportation area. The division of grids should be based on comprehensive considerations of geographical characteristics, transportation needs, traffic conditions, etc. Determine node locations: Mark the locations of all collected transport network nodes in the grid model, which will become the key nodes of the multimodal transport grid; Establish connection relationships: Based on multimodal transport data, establish connection relationships between different nodes in the grid model. These connection relationships should reflect the transfer paths and transfer efficiency between different transport modes. Set parameters: Set corresponding parameters for each connection relationship, such as transit time, cost, capacity, etc. These parameters will be used for subsequent multimodal transport path optimization and cost calculation.

[0024] Step 3: collecting the site information of multiple first transfer sites in the current target transport mode in the multimodal transport planning path to form the first site information, and collecting the site information of multiple second transfer sites in the next target transport mode in the multimodal transport planning path to form the second site information, wherein both the first site information and the second site information include the comprehensive capability information of the site to cope with temporary transfer scheduling, site scale information, and supporting transport capacity information around the site; Step 4: real-time collection of first weather forecast data during the entire transportation process of the current target transport mode in the multimodal transport planning path, including segmented collection of first weather forecast data, with the capability of collecting first weather forecast data in one-to-one correspondence according to multiple first transfer stations, and real-time second weather forecast data during the entire transportation process of the next target transport mode, including segmented collection of second weather forecast data, with the capability of collecting second weather forecast data in one-to-one correspondence according to multiple second transfer stations; Step 5: inputting the first weather forecast data and the second weather forecast data as well as the first site information and the second site information into the multimodal transport grid model to construct a multimodal transport grid model based on weather changes; Step 6: According to the transportation demand, market changes, the first weather forecast data and the second weather forecast data, determine the objective function of the multimodal transport grid model based on weather changes, introduce the first weather forecast data and the second weather forecast data to implement dynamic adjustment of the changes in the transportation mode, judge the impact rate of the first weather forecast data and the second weather forecast data on the success rate of the current transportation mode, and use the impact rate as a variable parameter for selecting the objective function. When using the impact rate as a variable parameter for selecting the objective function, it includes setting a target threshold of the impact rate in the multimodal transport grid model based on weather changes. If the impact rate exceeds the target threshold, the weight of the impact rate as a variable parameter when selecting the objective function is increased to 1.1; if the impact rate does not exceed the target threshold, the weight of the impact rate as a variable parameter when selecting the objective function is changed to 0.9; determine the objective function of the multimodal transport grid model, such as minimizing transportation costs, maximizing transportation efficiency, etc. Step 7: Convert the multimodal transport grid model based on weather changes into a multimodal transport path optimization model based on weather changes, and combine the objective function and the constraint function to establish a multimodal transport path optimization model based on weather changes with constraints, such as transportation time limit, transportation capacity limit, etc.; Step 8: Use optimization algorithms to solve the multimodal transport path optimization model based on weather changes with constraints. The optimization algorithms include but are not limited to genetic algorithms, simulated annealing algorithms, and particle swarm algorithms. Through iterative calculations, the transportation paths, resource allocations, and transportation methods are continuously adjusted to find the optimal or suboptimal transportation organization mode.

[0025] The present invention collects the site information of multiple first transfer sites in the current target transportation mode in the multimodal transportation planning path to form the first site information, collects the site information of multiple second transfer sites in the next target transportation mode in the multimodal transportation planning path to form the second site information, collects the first weather forecast data in the whole transportation process of the current target transportation mode in the multimodal transportation planning path in real time, and the second weather forecast data in the whole transportation process of the next target transportation mode in real time, and then inputs the first weather forecast data and the second weather forecast data as well as the first site information and the second site information into the multimodal transportation grid model to form a multimodal transportation grid model based on weather changes, and then determines the objective function of the multimodal transportation grid model based on weather changes according to transportation demand, market changes, the first weather forecast data and the second weather forecast data, so that when dynamically optimizing the multimodal transportation organization mode, the influence of weather factors on the transportation mode can be fully considered to avoid the established transportation mode being affected by the weather and unable to be successfully and safely executed on schedule, and the first weather forecast data and the second weather forecast data can be introduced to realize flexible adjustment of the transportation mode to ensure the smooth progress of multimodal transportation.

[0026] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A dynamic optimization method for multimodal transport organization mode based on big data processing, characterized in that: The following steps are involved: Step 1: Collect various data in the transportation process in real time, and then perform data preprocessing operations on the collected data to obtain standardized data; Step 2: Construct a multimodal transport grid model based on the transport network nodes in the target area; Step 3: collecting site information of multiple first transfer sites in the current target transport mode in the multimodal transport planning path to form first site information, and collecting site information of multiple second transfer sites in the next target transport mode in the multimodal transport planning path to form second site information; Step 4: Real-time collection of the first weather forecast data for the entire transportation process of the current target transportation mode in the multimodal transport planning path, and real-time collection of the second weather forecast data for the entire transportation process of the next target transportation mode; Step 5: inputting the first weather forecast data and the second weather forecast data as well as the first site information and the second site information into the multimodal transport grid model to construct a multimodal transport grid model based on weather changes; Step 6: Determine the objective function of the multimodal transport grid model based on weather changes according to the transport demand, market changes, the first weather forecast data and the second weather forecast data; Step 7: Convert the multimodal transport grid model based on weather changes into a multimodal transport path optimization model based on weather changes, and combine the objective function and the constraint condition function to establish a multimodal transport path optimization model based on weather changes with constraints; Step 8: Use optimization algorithms to solve the multimodal transport path optimization model based on weather changes with constraints.

2. The method for dynamic optimization of multimodal transport organization mode based on big data processing according to claim 1 is characterized by: The step 1 includes, but is not limited to, collecting various data in the transportation process in real time through the Internet of Things, RFID, and GPS.

3. The method for dynamic optimization of multimodal transport organization mode based on big data processing according to claim 2 is characterized by: The various data in the transportation process in step 1 include but are not limited to cargo location, transportation status, transportation environment, transportation cost and transportation time.

4. The method for dynamic optimization of multimodal transport organization mode based on big data processing according to claim 1 is characterized by: The transportation network nodes in step 2 are based on the target area, wherein the transportation nodes include but are not limited to ports, airports, railway stations, highway hubs, logistics parks, etc., wherein the transportation network nodes based on the target area also include the node information contained in these nodes, specifically the geographical location, transportation capacity, service scope, etc. of the nodes.

5. The method for dynamic optimization of multimodal transport organization mode based on big data processing according to claim 1 is characterized by: The first site information and the second site information in step three both include the comprehensive capability information of the site to cope with temporary transit scheduling, site scale information, and supporting transportation capacity information around the site.

6. The method for dynamic optimization of multimodal transport organization mode based on big data processing according to claim 1 is characterized by: In the step 4, when collecting the first weather forecast data of the entire transportation process of the current target transportation mode in the multimodal transport planning path in real time, it includes collecting the first weather forecast data in segments, and collecting the first weather forecast data one by one according to multiple first transfer sites.

7. The method for dynamic optimization of multimodal transport organization mode based on big data processing according to claim 6 is characterized by: In the step 4, when collecting the second weather forecast data of the whole transportation process of the next target transportation mode in the multimodal transport planning path in real time, it includes collecting the second weather forecast data in segments, and collecting the second weather forecast data one by one according to multiple second transfer stations.

8. The method for dynamic optimization of multimodal transport organization mode based on big data processing according to claim 1 is characterized by: In step six, when determining the objective function of the multimodal transport grid model based on weather changes according to transportation demand, market changes, the first weather forecast data and the second weather forecast data, the first weather forecast data and the second weather forecast data are introduced to dynamically adjust the changes in the transportation mode, and the influence rate of the first weather forecast data and the second weather forecast data on the success rate of the current transportation mode is determined, and the influence rate is used as the variable parameter for selecting the objective function.

9. The method for dynamic optimization of multimodal transport organization mode based on big data processing according to claim 8 is characterized by: When the impact rate is used as a variable parameter for selecting the objective function in the step six, it includes setting a target threshold of the impact rate in the multimodal transport grid model based on weather changes. If the impact rate exceeds the target threshold, the weight of the impact rate as a variable parameter when selecting the objective function is increased to 1.1; if the impact rate does not exceed the target threshold, the weight of the impact rate as a variable parameter when selecting the objective function is changed to 0.

9.

10. The method for dynamic optimization of multimodal transport organization mode based on big data processing according to claim 1 is characterized by: The optimization algorithm in step eight includes but is not limited to genetic algorithm, simulated annealing algorithm, and particle swarm algorithm. Through iterative calculation, the transportation path, resource allocation and transportation mode are continuously adjusted to find the optimal or suboptimal transportation organization mode.

Images