Multi-machine collaborative logistics distribution path optimization system

Abstract

The invention relates to the technical field of logistics information, and discloses a multi-machine cooperative logistics distribution path optimization system, which is characterized in that the output end of a logistics distribution path module is in signal connection with a data acquisition and preprocessing module, and the output end of the data acquisition and preprocessing module is in signal connection with a task distribution module; the output end of the task distribution module is in signal connection with a path planning module, the output end of the path planning module is in signal connection with a vehicle monitoring and scheduling module, the output end of the vehicle monitoring and scheduling module is in signal connection with a performance evaluation module, and the data acquisition and preprocessing module comprises an order data collection unit. The output end of the logistics resource data integration unit is in signal connection with a traffic data acquisition unit, and the output end of the traffic data acquisition unit is in signal connection with a data cleaning and preprocessing unit. According to the multi-machine cooperation type logistics distribution path optimization system, an algorithm is used for analyzing orders, matching vehicles and drivers and planning a distribution path, so that the vehicles avoid congested road sections, and the driving mileage and time are reduced.

Description

Technical Field

[0001] The present invention relates to the field of logistics information technology, and particularly to a multi-machine collaborative logistics distribution path optimization system. Background Art

[0002] At present, with the booming development of e-commerce and the economy, the logistics industry is in a difficult situation. The explosive growth of e-commerce orders has brought huge pressure to logistics distribution. The traditional distribution mode relying on manual experience is difficult to cope with a large number of orders, and the distribution delay rate is as high as 30%, greatly reducing the customer experience.

[0003] The internal resource allocation of logistics enterprises is chaotic, the vehicle empty load rate often exceeds 40%, and the warehouse goods allocation is also unreasonable, resulting in resource waste and cost increase. At the same time, urban traffic congestion, complex traffic restriction policies, frequent road construction and accidents, and the traditional static map-based path planning cannot respond in real time, and distribution vehicles are often trapped in congested sections. And consumers' expectations for distribution services are getting higher and higher, and 80% of consumers will change logistics enterprises due to logistics problems. Therefore, it is urgent to optimize the logistics distribution path with the help of advanced technologies to improve efficiency and service quality. Summary of the Invention

[0004] The purpose of the present invention is to provide a multi-machine collaborative logistics distribution path optimization system to solve the problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: A multi-machine collaborative logistics distribution path optimization system, including a logistics distribution path module, the output end of the logistics distribution path module is signal-connected to a data collection and preprocessing module, the output end of the data collection and preprocessing module is signal-connected to a task allocation module, the output end of the task allocation module is signal-connected to a path planning module, the output end of the path planning module is signal-connected to a vehicle monitoring and scheduling module, and the output end of the vehicle monitoring and scheduling module is signal-connected to a performance evaluation module;

[0006] The data collection and preprocessing module includes an order data collection unit, the output end of the order data collection unit is signal-connected to a logistics resource data integration unit, the output end of the logistics resource data integration unit is signal-connected to a traffic data acquisition unit, and the output end of the traffic data acquisition unit is signal-connected to a data cleaning and preprocessing unit.

[0007] Preferably, the logistics resource data integration unit collects vehicle information of the company's own vehicles and cooperative fleets, such as license plate numbers, vehicle models, load capacities, vehicle driving speeds, maximum cruising ranges, vehicle statuses (idle, en route, under repair, etc.), records information such as driver names, contact information, driver's license types, driving experience, working time limits, current locations, etc., and obtains data such as the geographical locations, inventory capacities, types of goods stored, inbound and outbound efficiencies of each warehouse.

[0008] Preferably, the task assignment module includes an order clustering analysis unit, the output end of the order clustering analysis unit is signal-connected to a vehicle and driver matching unit, and the output end of the vehicle and driver matching unit is signal-connected to a task assignment optimization algorithm unit.

[0009] Preferably, the vehicle and driver matching unit screens out suitable vehicle types and specific vehicles according to the weight and volume of the ordered goods and the characteristics of the delivery route. For example, for large cargo deliveries, trucks with a large load capacity are preferred; for orders that need to travel on narrow city streets, small and flexible vehicles are selected. Considering the driver's working time limit, driving experience and current location, the vehicle is assigned to a suitable driver, and the driver who is closer to the starting point of the order, has sufficient working time and rich experience is given priority to execute the task.

[0010] Preferably, the path planning module includes an initial path generation unit, the output end of the initial path generation unit is signal-connected to a path optimization algorithm application unit, and the output end of the path optimization algorithm application unit is signal-connected to a real-time traffic condition dynamic adjustment unit.

[0011] Preferably, the path optimization algorithm application unit introduces the ant colony algorithm. By simulating the behavior of ants leaving pheromones on the path, the vehicle dynamically selects a better path during driving according to the pheromone concentration and heuristic information on the path, such as distance and traffic conditions. The algorithm iterates continuously and gradually converges to the global optimal path. For complex distribution networks and dynamically changing traffic conditions, the dynamic programming algorithm is used to optimize the path segment by segment. According to the real-time traffic information, the current optimal branch path is selected at each decision point to adapt to the change of traffic conditions and reduce the delivery time and cost.

[0012] Preferably, the vehicle monitoring and scheduling module includes a vehicle real-time positioning unit, the output end of the vehicle real-time positioning unit is signal-connected to a vehicle status monitoring unit, and the output end of the vehicle status monitoring unit is signal-connected to a vehicle scheduling decision support unit.

[0013] Preferably, the vehicle status monitoring unit uses various sensors installed on the vehicle, such as fuel consumption sensors, tire pressure sensors, engine status sensors, etc., to collect information on the vehicle's fuel consumption, tire pressure, engine operating conditions, etc. in real time, and sets the normal threshold range for various vehicle parameters. When the sensor data exceeds the threshold, the system immediately sends out a warning message to prompt the dispatcher that the vehicle may have a fault or abnormal situation, so as to take timely measures to avoid affecting the delivery task.

[0014] Preferably, the performance evaluation module includes a delivery cost accounting unit, the output end of the delivery cost accounting unit is signal-connected to a delivery efficiency evaluation unit, the output end of the delivery efficiency evaluation unit is signal-connected to a service quality evaluation unit, and the output end of the service quality evaluation unit is signal-connected to a data analysis and feedback unit.

[0015] Compared with the prior art, the present invention provides a multi-machine collaborative logistics distribution path optimization system, which has the following beneficial effects:

[0016] 1. For this multi-machine collaborative logistics distribution path optimization system, the system uses advanced algorithms to perform clustering analysis on orders, accurately matches vehicles with drivers, and plans the optimal distribution path. This enables the vehicle to avoid congested roads, reduce driving mileage and time. For example, in the urban distribution scenario, by dynamically adjusting the path according to real-time road conditions, the average delivery vehicle can save 15 - 30 minutes per trip, greatly improving the delivery efficiency. At the same time, reasonable task allocation ensures an increase in the vehicle load factor, reduces the transportation cost per unit of goods, improves the utilization rate of logistics resources. The multi-machine collaborative logistics distribution path optimization system reduces vehicle fuel consumption and wear by optimizing the path, extends the service life of the vehicle, and reduces the maintenance cost. According to statistics, after using this system, the vehicle fuel consumption is reduced by an average of 10% - 15%, and the maintenance cost is reduced by 15% - 20%. In addition, accurate task allocation and efficient delivery processes reduce labor costs and potential losses caused by delivery delays, comprehensively improving the economic benefits of logistics enterprises.

[0017] 2. The multi-vehicle collaborative logistics distribution route optimization system can monitor the vehicle positions and distribution progress in real time, dynamically adjust the routes and dispatch vehicles according to the road conditions, effectively avoiding distribution delays. The on-time delivery rate of orders has increased significantly, usually reaching over 95%, which is 10 - 20 percentage points higher than that of the traditional distribution mode. Customers can receive goods on time, and their satisfaction has been greatly improved, enhancing their trust and loyalty to the logistics enterprise. Customers can, through the query platform provided by the logistics enterprise, understand the real-time location of the goods in transit and the estimated delivery time. The vehicle monitoring and dispatching module makes the entire distribution process transparent, enabling the enterprise to respond promptly to customer inquiries and complaints and quickly solve problems. This high level of service transparency and traceability helps the logistics enterprise establish a good brand image, stand out in the fierce market competition, and win more customers and business opportunities. Description of the Drawings

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings:

[0019] Figure 1 It is the system flowchart of the present invention;

[0020] Figure 2 It is the flowchart of the data acquisition and preprocessing module of the present invention;

[0021] Figure 3 It is the flowchart of the task assignment module of the present invention;

[0022] Figure 4 It is the flowchart of the route planning module of the present invention;

[0023] Figure 5 It is the flowchart of the vehicle monitoring and dispatching module of the present invention;

[0024] Figure 6 It is the flowchart of the performance evaluation module of the present invention.

[0025] In the figure: 1. Logistics distribution path module; 2. Data collection and preprocessing module; 21. Order data collection unit; 22. Logistics resource data integration unit; 23. Traffic data acquisition unit; 24. Data cleaning and preprocessing unit; 3. Task assignment module; 31. Order clustering analysis unit; 32. Vehicle and driver matching unit; 33. Task assignment optimization algorithm unit; 4. Route planning module; 41. Initial route generation unit; 42. Route optimization algorithm application unit; 43. Real-time traffic condition dynamic adjustment unit; 5. Vehicle monitoring and scheduling module; 51. Vehicle real-time positioning unit; 52. Vehicle status monitoring unit; 53. Vehicle scheduling decision support unit; 6. Performance evaluation module; 61. Distribution cost accounting unit; 62. Distribution efficiency evaluation unit; 63. Service quality evaluation unit; 64. Data analysis and feedback unit. Detailed implementation manner

[0026] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0027] In the present invention, unless otherwise clearly defined and limited, the terms "installation", "connection", "connection", "fixation", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, and it can be the communication inside two components or the interaction relationship between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0028] The present invention provides the following technical solutions:

[0029] Embodiment 1

[0030] Combined with Figures 1-3 , a multi-machine collaborative logistics distribution route optimization system, including a logistics distribution route module 1. The output end of the logistics distribution route module 1 is signal-connected to a data collection and preprocessing module 2. The output end of the data collection and preprocessing module 2 is signal-connected to a task assignment module 3. The output end of the task assignment module 3 is signal-connected to a route planning module 4. The output end of the route planning module 4 is signal-connected to a vehicle monitoring and scheduling module 5. The output end of the vehicle monitoring and scheduling module 5 is signal-connected to a performance evaluation module 6;

[0031] The data collection and preprocessing module 2 includes an order data collection unit 21. The output end of the order data collection unit 21 is signal-connected to a logistics resource data integration unit 22. The output end of the logistics resource data integration unit 22 is signal-connected to a traffic data acquisition unit 23. The output end of the traffic data acquisition unit 23 is signal-connected to a data cleaning and preprocessing unit 24. The task allocation module 3 includes an order clustering analysis unit 31. The output end of the order clustering analysis unit 31 is signal-connected to a vehicle and driver matching unit 32. The output end of the vehicle and driver matching unit 32 is signal-connected to a task allocation optimization algorithm unit 33. The path planning module 4 includes an initial path generation unit 41. The output end of the initial path generation unit 41 is signal-connected to a path optimization algorithm application unit 42. The output end of the path optimization algorithm application unit 42 is signal-connected to a real-time traffic condition dynamic adjustment unit 43.

[0032] Furthermore, the logistics resource data integration unit 22 collects vehicle information of the company's own vehicles and cooperative fleets, such as license plate numbers, vehicle models, load capacities, vehicle driving speeds, maximum cruising ranges, vehicle statuses (idle, on the way, under repair, etc.), records driver names, contact information, driver's license types, driving experience, working time limits, current locations, etc., and obtains data such as the geographical locations, inventory capacities, cargo storage types, inbound and outbound efficiencies of each warehouse. The vehicle and driver matching unit 32 selects suitable vehicle types and specific vehicles for task execution according to the weight and volume of the order goods and the characteristics of the delivery route. For example, for large cargo deliveries, trucks with a large load capacity are preferred; for orders that need to travel on narrow city streets, small and flexible vehicles are selected. Considering the driver's working time limit, driving experience, and current location, the vehicle is assigned to a suitable driver, and drivers who are closer to the order starting point, have sufficient working time, and are experienced are given priority to execute the task. The path optimization algorithm application unit 42 introduces the ant colony algorithm. By simulating the behavior of ants leaving pheromones on the path, the vehicle dynamically selects a better path during driving according to the pheromone concentration and heuristic information (such as distance, traffic conditions) on the path. The algorithm iterates continuously and gradually converges to the global optimal path. For complex distribution networks and dynamically changing traffic conditions, the dynamic programming algorithm is used to optimize the path segment by segment. According to real-time traffic information, the current optimal branch path is selected at each decision point to adapt to the changes in traffic conditions and reduce the delivery time and cost.

[0033] Embodiment 2

[0034] Refer to Figures 1-6, and on the basis of Embodiment 1, it is further obtained that the vehicle monitoring and dispatching module 5 includes a vehicle real-time positioning unit 51. The output end of the vehicle real-time positioning unit 51 is signal-connected to a vehicle status monitoring unit 52. The output end of the vehicle status monitoring unit 52 is signal-connected to a vehicle dispatching decision support unit 53. The performance evaluation module 6 includes a distribution cost accounting unit 61. The output end of the distribution cost accounting unit 61 is signal-connected to a distribution efficiency evaluation unit 62. The output end of the distribution efficiency evaluation unit 62 is signal-connected to a service quality evaluation unit 63. The output end of the service quality evaluation unit 63 is signal-connected to a data analysis and feedback unit 64.

[0035] Furthermore, the vehicle status monitoring unit 52 uses various sensors installed on the vehicle, such as fuel consumption sensors, tire pressure sensors, engine status sensors, etc., to collect information such as fuel consumption, tire pressure, and engine working conditions of the vehicle in real time. The normal threshold range of various vehicle parameters is set. When the sensor data exceeds the threshold, the system immediately sends out a warning message to prompt the dispatcher that the vehicle may have a malfunction or abnormal situation, so as to take timely measures to avoid affecting the distribution task.

[0036] In the actual operation process, when this device is used, the order data collection unit 21 obtains online order information in real time by docking with e-commerce platforms, enterprise sales systems, etc., including order numbers, delivery addresses, cargo weights and volumes, delivery time requirements, etc. For offline orders, the staff manually enters them into the system to ensure comprehensive collection of order data. The logistics resource data integration unit 22 summarizes the vehicle information of the company's own and cooperative fleets, such as license plate numbers, vehicle models, load capacities, driving speeds, cruising ranges, vehicle status, etc.; at the same time, it sorts out driver information, including names, contact information, driver's license types, driving experience, working time limits, and current locations; in addition, it collects data such as the geographical locations, inventory capacities, storage types, and inbound and outbound efficiencies of each warehouse to realize the integration of logistics resource information. The traffic data acquisition unit 23 accesses the professional map service API to obtain traffic condition information in real time, such as factors affecting vehicle driving speeds such as road congestion, traffic accidents, and road construction, and at the same time collects traffic rules in each region, such as restricted driving policies, prohibited sections, and vehicle type speed limit requirements, etc. The data cleaning and preprocessing unit 24 cleans the collected order, logistics resource, and traffic data, uses methods such as mean filling and regression prediction to process missing values, eliminates outliers such as incorrect addresses and unreasonable weights and volumes, and standardizes the data to unify the dimension and value range to provide high-quality data support for subsequent modules;

[0037] The order clustering analysis unit 31 divides the orders into regional clusters with concentrated geographical locations based on the longitude and latitude of the order receiving addresses, using clustering algorithms such as K-Means. Then, in combination with the order delivery time requirements, the orders within each regional cluster are further divided, and the orders with similar delivery times are grouped together to reasonably arrange the delivery batches. The vehicle and driver matching unit 32 selects the appropriate vehicle type and specific vehicle according to the characteristics of the order goods (such as weight, volume, etc.) and the characteristics of the delivery route. At the same time, considering the driver's working time limit, driving experience, and current location, the vehicle is assigned to a suitable driver, and priority is given to drivers who are close to the order starting point, have sufficient working time, and are experienced. The task assignment optimization algorithm unit 33 constructs a cost model that includes factors such as vehicle usage costs (such as fuel consumption, depreciation, etc.), driver salaries, and delivery delay costs, and uses optimization algorithms such as the Hungarian algorithm and genetic algorithm to calculate the optimal order-vehicle-driver assignment plan under the constraints of order delivery time, vehicle load, driver working time, etc., to achieve the reasonable assignment of tasks;

[0038] The initial path generation unit 41 uses the path planning function of the map service to plan the initial driving path for each vehicle with the warehouse as the starting point and the order receiving address as the ending point, and obtains information such as the path distance and estimated driving time. And according to the traffic rule data, the initial path is adjusted to prevent the vehicle from entering restricted or prohibited sections to ensure the legality of the path. The path optimization algorithm application unit 42 introduces the ant colony algorithm to simulate the behavior of ants leaving pheromones on the path, enabling the vehicle to dynamically select a better path according to the pheromone concentration on the path and heuristic information (such as distance, road conditions, etc.). At the same time, the dynamic programming algorithm is used to optimize the path segment by segment, and the current optimal branch path is selected at each decision point according to the real-time traffic information, and the path is continuously iteratively optimized. The real-time road condition dynamic adjustment unit 43: Real-time monitors the changes in road conditions during the vehicle driving process. When the road conditions change and the current path is no longer optimal, the path re-planning program is immediately started, and the optimization algorithm is used to re-plan a new path for the vehicle to avoid congested sections and reach the destination as soon as possible, and the new path information is sent to the driver in a timely manner;

[0039] The vehicle real-time positioning unit 51 collects the vehicle position information in real time through the GPS or Beidou positioning device installed on the vehicle, and transmits it to the system server through the wireless communication module. The vehicle position, driving direction and speed are displayed in the form of icons on the electronic map of the monitoring interface, which is convenient for dispatchers to master the vehicle operation status. The vehicle status monitoring unit 52 collects information such as vehicle fuel consumption, tire pressure, and engine working conditions in real time with the help of fuel consumption sensors, tire pressure sensors, engine status sensors, etc. on the vehicle. Set the normal threshold range for each parameter. When the data exceeds the threshold, the system issues a warning, indicating that the vehicle may have a fault or abnormality. The vehicle dispatching decision support unit 53 calculates the estimated arrival time in real time according to the vehicle real-time position and the order delivery time requirement, compares the actual and planned delivery progress, and timely discovers delays. When sudden situations such as vehicle failures, traffic jams, and temporary order changes occur, the system provides decision support for dispatchers, such as adjusting the vehicle driving route, reallocating delivery tasks, and coordinating the warehouse shipping time, based on real-time data and preset dispatching strategies, to ensure the smooth completion of the delivery task;

[0040] The distribution cost accounting unit 61 statistics the fuel consumption, maintenance, and depreciation costs during the vehicle distribution process, and calculates them according to the driving mileage and usage time. Calculate the labor cost in combination with the driver salary standard and working hours, and statistics other costs such as tolls, parking fees, and insurance premiums, and comprehensively obtain the total cost of each delivery task. The distribution efficiency evaluation unit 62 calculates the order on-time delivery rate, which is the ratio of the number of orders delivered on time to the total number of orders, reflecting the on-time completion of the delivery task. Calculate the average driving speed based on the vehicle driving trajectory and time data, and evaluate the vehicle driving efficiency. Compare the distribution time before and after optimization, calculate the reduction ratio of the distribution time, and measure the improvement effect of the route optimization and dispatching strategy on the distribution efficiency. The service quality evaluation unit 63 collects the customer satisfaction evaluation of the distribution service through online questionnaires, telephone callbacks, etc., covering aspects such as the integrity of goods, the service attitude of distribution personnel, and the accuracy of distribution time. Statistics the number of customer complaints, calculates the complaint rate, and analyzes the reasons for complaints. The data analysis and feedback unit 64 regularly generates performance data reports such as distribution costs, distribution efficiency, and service quality, and displays the index change trends and comparative analysis results in the form of charts. Deeply analyze the system operation problems according to the evaluation results, put forward targeted optimization suggestions, and feedback them to the system development and operation teams to continuously improve and optimize the system and enhance the overall performance of logistics distribution.

[0041] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising said element.

Claims

1. A multi-machine collaborative logistics distribution route optimization system, including a logistics distribution route module (1), characterized in that: The output end of the logistics distribution path module (1) is connected to the data acquisition and preprocessing module (2) by signal. The output end of the data acquisition and preprocessing module (2) is connected to the task assignment module (3) by signal. The output end of the task assignment module (3) is connected to the path planning module (4) by signal. The output end of the path planning module (4) is connected to the vehicle monitoring and scheduling module (5) by signal. The output end of the vehicle monitoring and scheduling module (5) is connected to the performance evaluation module (6) by signal; The data acquisition and preprocessing module (2) includes an order data collection unit (21). The output end of the order data collection unit (21) is connected to a logistics resource data integration unit (22) by signal. The output end of the logistics resource data integration unit (22) is connected to a traffic data acquisition unit (23) by signal. The output end of the traffic data acquisition unit (23) is connected to a data cleaning and preprocessing unit (24) by signal.

2. The multi-machine collaborative logistics distribution route optimization system according to claim 1, wherein: The logistics resource data integration unit (22) collects vehicle information of the company's own vehicles and cooperative fleets, such as license plate numbers, vehicle types, load capacities, vehicle driving speeds, maximum cruising ranges, vehicle statuses (idle, in transit, under repair, etc.), records information such as driver names, contact information, driver's license types, driving experience, working time limits, current locations, etc., and acquires data such as the geographical locations, inventory capacities, cargo storage types, inbound and outbound efficiencies of each warehouse.

3. The multi-machine collaborative logistics distribution path optimization system according to claim 1, characterized in that: The task assignment module (3) includes an order clustering analysis unit (31). The output end of the order clustering analysis unit (31) is connected to a vehicle and driver matching unit (32) by signal. The output end of the vehicle and driver matching unit (32) is connected to a task assignment optimization algorithm unit (33) by signal.

4. A multi-machine collaborative logistics distribution path optimization system according to claim 3, characterized in that: The vehicle and driver matching unit (32) selects suitable vehicle types and specific vehicles for task execution according to the weight and volume of the order goods and the characteristics of the distribution route. For example, for large cargo distribution, trucks with large load capacities are preferred; for orders that need to travel on narrow city streets, small and flexible vehicles are selected. Considering the driver's working time limit, driving experience, and current location, the vehicle is assigned to a suitable driver, and drivers who are closer to the order starting point, have sufficient working time, and are experienced are given priority to execute the task.

5. The multi-machine collaborative logistics distribution path optimization system according to claim 1, wherein: The path planning module (4) includes an initial path generation unit (41). The output end of the initial path generation unit (41) is connected to a path optimization algorithm application unit (42) by signal. The output end of the path optimization algorithm application unit (42) is connected to a real-time traffic condition dynamic adjustment unit (43) by signal.

6. The multi-machine collaborative logistics distribution path optimization system according to claim 5, wherein: The path optimization algorithm application unit (42) introduces the ant colony algorithm. By simulating the behavior of ants leaving pheromones on the path, the vehicle dynamically selects a better path during driving according to the pheromone concentration and heuristic information (such as distance, road conditions, etc.) on the path. The algorithm iterates continuously and gradually converges to the global optimal path. For complex distribution networks and dynamically changing traffic conditions, the dynamic programming algorithm is used to optimize the path segment by segment. According to real-time traffic information, the current optimal branch path is selected at each decision point to adapt to the change of traffic conditions and reduce the distribution time and cost.

7. The multi-machine collaborative logistics distribution path optimization system according to claim 1, wherein: The vehicle monitoring and scheduling module (5) includes a vehicle real-time positioning unit (51). The output signal of the vehicle real-time positioning unit (51) is connected to a vehicle status monitoring unit (52), and the output signal of the vehicle status monitoring unit (52) is connected to a vehicle scheduling decision support unit (53).

8. A multi-machine collaborative logistics distribution path optimization system according to claim 7, characterized in that: The vehicle status monitoring unit (52) uses various sensors installed on the vehicle, such as fuel consumption sensors, tire pressure sensors, engine status sensors, etc., to collect information such as the fuel consumption, tire pressure, and engine working conditions of the vehicle in real time. The normal threshold range of various vehicle parameters is set. When the sensor data exceeds the threshold, the system immediately issues a warning message to prompt the dispatcher that the vehicle may have a fault or abnormal situation, so as to take timely measures to avoid affecting the distribution task.

9. The multi-machine collaborative logistics distribution path optimization system according to claim 1, wherein: The performance evaluation module (6) includes a distribution cost accounting unit (61). The output signal of the distribution cost accounting unit (61) is connected to a distribution efficiency evaluation unit (62), the output signal of the distribution efficiency evaluation unit (62) is connected to a service quality evaluation unit (63), and the output signal of the service quality evaluation unit (63) is connected to a data analysis and feedback unit (64).

Images