Multi-party collaborative optimization method and system for urban logistics distribution

Abstract

The invention relates to the technical field of logistics optimization management, and provides a multi-party collaborative optimization method and system for urban logistics distribution, and the method comprises the steps: obtaining the vehicle information of various types of vehicles in an urban logistics distribution fleet and the order information of a plurality of logistics orders; the method comprises the following steps: extracting a plurality of distribution centers, network points and distribution destinations of urban logistics distribution, constructing a distribution graph structure, and obtaining a shortest distribution path for each logistics order; obtaining a plurality of order categories and the total cargo weight of each order category; obtaining a preferred transportation factor; quantizing time transportation cost; constructing a transportation objective function in combination with the optimized transportation factors; and obtaining an optimal transport vehicle type for each section of road in the shortest distribution path of each order type, thereby carrying out logistics vehicle distribution on each logistics order, and realizing multi-party collaborative optimization distribution of urban logistics. The objective of the invention is to solve the problem that a logistics distribution fleet is complex in vehicle type and cannot accurately distribute tasks.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics optimization management, and in particular to a multi-party collaborative optimization method and system for urban logistics distribution. Background Art

[0002] Multi-party collaborative optimization for urban logistics distribution requires integrating multiple factors, including vehicles, road networks, orders, transportation capacity, and time costs, to achieve collaborative optimization of urban logistics distribution networks and improve logistics distribution efficiency. Due to the diverse modes of transportation, the transportation methods used to reach specific cities vary. Consequently, cities are distributed with multiple distribution centers related to transportation modes. The order types and transportation timelines further require the collaborative optimization of distribution network nodes in terms of time costs.

[0003] The traditional scheduling algorithms in the existing urban logistics distribution process cannot accurately assign tasks to various types of vehicles in the logistics distribution fleet. They do not consider the vehicle type and function, and are prone to mismatch problems such as "light vehicles with heavy goods" or refrigerated trucks performing ordinary tasks, which reduces resource utilization. At the same time, the road rights restrictions of different vehicles and the impact of the number of orders placed at different times on vehicle capacity and assembly time of distribution network nodes are not taken into account in traditional scheduling algorithms. As a result, the distribution network only assigns tasks based on vehicle idleness, and cannot give full play to the corresponding functions of various types of vehicles. At the same time, the assembly time is extended due to the influence of the number of orders, resulting in cargo backlogs, which seriously affects the efficiency of urban logistics collaborative distribution. Summary of the Invention

[0004] The present invention provides a multi-party collaborative optimization method and system for urban logistics distribution to solve the problem that existing logistics distribution fleets have complex vehicle types and cannot accurately allocate tasks. The technical solutions adopted are as follows: The present invention proposes a multi-party collaborative optimization method for urban logistics distribution, which includes the following steps: Obtain vehicle information for various types of vehicles in the city's logistics delivery fleet, including vehicle function, vehicle load, vehicle speed, and road restriction information; obtain the transportation origin and destination, order type, and cargo weight of several logistics orders; Based on the transportation origin and destination of logistics orders and the delivery process, several distribution centers, outlets, and delivery destinations for urban logistics distribution are extracted and a distribution graph structure is constructed. The shortest delivery path is obtained for each logistics order based on the order type in the distribution graph structure. Logistics orders are divided based on the shortest delivery path to obtain several order categories and the total weight of the goods in each order category. The vehicle load, vehicle function, and road restriction information of each type of vehicle are combined to obtain the optimal transportation factor for each road segment in the shortest delivery path for each order category. Analyze the impact of the number of logistics orders in each order category on the assembly time of each node in the shortest delivery path. Combined with the vehicle speed of each type of vehicle and the distance of each road segment in the shortest delivery path, quantify the time transportation cost of each road segment in the shortest delivery path for each order category for each type of vehicle. Combined with the optimal transportation factor, construct the transportation objective function for each road segment in the shortest delivery path for each order category for each type of vehicle. Based on the transportation objective function, the optimal transportation vehicle type is obtained for each section of the shortest delivery path for each order category, and logistics vehicles are allocated to each logistics order.

[0005] Optionally, the method of extracting several distribution centers, outlets, and distribution destinations of urban logistics distribution and constructing a distribution map structure includes the following specific methods: Extract several distribution centers and outlets in the city, as well as the roads used to transport goods from each distribution center to each outlet. Take each distribution center and outlet as a node, the road as the edge between the nodes corresponding to the distribution center and the outlet, and the distance corresponding to the road as the edge value. Based on the transportation destinations in a large number of logistics orders, several transportation destinations belonging to the same area are jointly used as the distribution destinations of the corresponding area. Each distribution destination is used as a node, and the driving roads and corresponding distances of each outlet to each distribution destination are obtained. The edge values ​​between the corresponding nodes of the outlets and the corresponding nodes of the distribution destinations are obtained. Based on the edges and edge values ​​of each node and the nodes, a graph structure is constructed and used as the distribution graph structure.

[0006] Optionally, the shortest delivery path is obtained in the following way: For any logistics order, obtain the node of the transportation destination corresponding to its transportation end point in the distribution graph structure, determine the outlets that the logistics order passes through during the transportation process based on the transportation destination nodes and the order type of the logistics order, obtain the corresponding nodes of the outlets and distribution destinations in the transportation process of the logistics order, and obtain the shortest delivery path for the logistics order in the distribution graph structure based on the corresponding nodes of the distribution center, outlets and distribution destinations.

[0007] Optionally, the method of obtaining the plurality of order categories and the total weight of goods of each order category includes: Combine several logistics orders with the same shortest delivery path into one order category; The total weight of goods for all logistics orders in any order category is taken as the total weight of goods for that order category.

[0008] Optionally, the preferred transportation factor for each type of vehicle on each road segment in the shortest delivery path for each order category is obtained by: For any road segment in the shortest delivery route for any order category and any type of vehicle, obtain the ratio of the total weight of the goods for that order category to the vehicle load capacity of that type of vehicle. If the ratio is less than or equal to 1, use the ratio as the transport matching factor for that order category and that type of vehicle. If the ratio is greater than 1, convert the ratio into a mixed fraction, use the proper fraction as the numerator, and the sum of the integer part plus 1 as the denominator to obtain the ratio, which serves as the transport matching factor for that order category and that type of vehicle. Obtain the road restriction information corresponding to the road section and the type of vehicle. For vehicle functions, obtain the word vector of the order type corresponding to the order category and the word vector of the vehicle function of the type of vehicle. Use the cosine similarity of the two word vectors as the type matching factor between the order category and the type of vehicle. The product of the transport matching factor, the type matching factor and the road restriction information corresponding to the road segment and the vehicle type is used as the preferred transport factor for the road segment for the vehicle type in the shortest delivery path of the order category.

[0009] Optionally, the time transportation cost of each road segment in the shortest delivery path for each order category for each type of vehicle is obtained in the following specific method: Based on the number of logistics orders in each order category and the number of logistics orders of other order categories on each section of the shortest delivery path, combined with the total weight of the goods in the order category, the loading and unloading time cost of each section of the shortest delivery path for each order category is obtained; For any road segment in the shortest delivery path for any order category, obtain the speeds of all vehicles of any type on that road segment, as well as the departure times corresponding to each speed. Then, obtain the average of the times when all logistics orders in that order category arrive at the departure node on that road segment, and use this as the ideal departure time for that road segment in the shortest delivery path for that order category. The absolute value of the difference between the departure time corresponding to any vehicle speed and the ideal departure time is used as the time deviation of the vehicle speed, and the difference obtained by subtracting the time deviation from 24 hours is used as the time proximity of the vehicle speed. The time proximity of all vehicle speeds on the road section is weighted and normalized, and the result is used as the time weight of each vehicle speed. The weighted sum of all vehicle speeds on the road section based on the time weight is used as the driving speed of this type of vehicle on this road section in the shortest delivery path for this order category. The ratio of the distance of this road section to the driving speed is used as the transportation time cost of this type of vehicle on this road section in the shortest delivery path for this order category. The product of the loading and unloading time cost of this section of road in the shortest delivery path of this order category and the transportation time cost of this type of vehicle in this section of road is used as the time transportation cost of this section of road in the shortest delivery path of this order category for this type of vehicle.

[0010] Optionally, the specific method for obtaining the loading and unloading time cost of each road segment in the shortest delivery path for each order category is as follows: For any road segment in the shortest delivery path of any order category, obtain several other order categories that are the same as the road segment in the shortest delivery path of the order category as similar categories to the order category; The total weight of the goods in this order category and all its similar categories is linearly normalized, and the result obtained is used as the weight reference weight for this order category and its similar categories. Based on the weight reference weight, the number of logistics orders in this order category and its similar categories is weighted and averaged, and the result obtained is used as the loading and unloading time cost of this section of road in the shortest delivery path for this order category.

[0011] Optionally, the specific method for constructing the transportation objective function for each road segment in the shortest delivery path for each order category for each type of vehicle is as follows: The expression formed by dividing the preferred transportation factor of any road section in the shortest delivery path of any order category for any type of vehicle by the time transportation cost of this road section for this type of vehicle is used as the transportation objective function for this road section in the shortest delivery path of this order category for this type of vehicle.

[0012] Optionally, the specific method for obtaining the optimal transport vehicle type for each road segment in the shortest delivery path for each order category based on the transport objective function includes: For any section of road in the shortest delivery path of any order category, the vehicle type corresponding to the maximum output value of the transportation objective function corresponding to the road is used as the optimal transportation vehicle type for this section of road in the shortest delivery path for all logistics orders under this order category.

[0013] The present invention also proposes a multi-party collaborative optimization system for urban logistics distribution, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above method are implemented.

[0014] The beneficial effects of the present invention are as follows: the present invention analyzes the distribution of collection and distribution centers, outlets and distribution destinations in the urban logistics distribution process, classifies logistics orders into order categories and obtains the shortest distribution path, combines the functions, load capacity and road restriction information of various types of vehicles in the distribution fleet, and performs optimal matching analysis on each section of road and vehicle in the shortest distribution path, while taking into account the assembly time and vehicle speed, and further considers the time transportation cost based on the optimal analysis of roads and vehicles, so as to achieve the optimal matching of roads and vehicles; wherein, through the transportation starting point and end point of the logistics order, combined with the distribution center and outlet distribution of the logistics distribution network, a distribution graph structure is constructed and the shortest distribution path is generated for the logistics order, and the logistics orders with the same shortest distribution path are classified to obtain order categories, and the orders are sorted. The total weight of goods is obtained for each category, and an optimization analysis is performed on each road section and each type of vehicle transportation in the shortest distribution path, so as to optimize the analysis of each order category from the perspective of vehicle capacity and function; in each road section of the shortest distribution path, the number of logistics orders in the order category directly affects the length of its assembly time at each node, so it is necessary to combine the relationship between road distance and vehicle speed to reduce the impact of long assembly time on the distribution process under normal time flow; combined with the optimal transportation factor, a comprehensive optimization matching analysis is performed on each road section and transportation vehicle type in the shortest distribution path from the two aspects of transportation capacity and time cost, so as to allocate transportation vehicles for logistics orders, so as to achieve coordinated optimization of distribution centers, outlets, transportation capacity, assembly time and transportation vehicles in the urban logistics distribution process. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0016] Figure 1 A flow chart of a multi-party collaborative optimization method for urban logistics distribution provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] See also Figure 1, which shows a flow chart of a multi-party collaborative optimization method for urban logistics distribution provided by an embodiment of the present invention, the method comprising the following steps: Step S001: Obtain vehicle information of various types of vehicles in the urban logistics distribution fleet; obtain the transportation starting point and end point, order type and cargo weight of several logistics orders.

[0019] The purpose of this embodiment is to conduct a comprehensive capacity analysis based on the distribution centers, outlets and distribution sites in the urban logistics distribution network, combined with multiple types of vehicles in the distribution fleet, such as large trucks, refrigerated trucks, medium-sized vans, new energy vans, unmanned delivery vehicles and three-wheeled trucks used by couriers for daily delivery. Combined with the cost analysis of assembly time and transportation time, a comprehensive optimization analysis of the distribution network, capacity and time cost in urban logistics distribution is conducted to achieve efficient use of various types of vehicles for logistics distribution. First, it is necessary to obtain vehicle information and related information of logistics orders.

[0020] Specifically, for several vehicles in the urban logistics distribution fleet, which correspond to several types of vehicles, vehicle information of each type of vehicle, including vehicle function, vehicle load, vehicle speed and road restriction information, is obtained; for each type of vehicle, the vehicle function is first obtained, and the vehicle function usually corresponds to the order type. For example, air express type orders usually require new energy vans for fast transportation, cold chain fresh type orders require refrigerated trucks for transportation, large and heavy type orders require large trucks for transportation, and medium-sized vans are used to transport a large number of ordinary express type orders. Unmanned delivery vehicles and couriers' three-wheeled trucks are mainly affected by road restrictions during the delivery process, and their corresponding vehicle functions are transportation between outlets and distribution sites. ; Vehicle load directly obtains the rated load of each type of vehicle; road restriction information is the restriction of various types of vehicles between distribution network nodes, such as yellow-label trucks are prohibited from driving on some sections of the road. The collected data is expressed as whether various types of vehicles are prohibited from driving on the driving roads from the distribution center to the outlets, and on the driving roads from the outlets to the distribution stations. Prohibition is represented by 0 and non-prohibition is represented by 1; vehicle speed is the average speed of various types of transport vehicles in the corresponding driving roads in multiple historical transportation processes on the corresponding roads, that is, the average speed of vehicles in any historical transportation. At the same time, the departure time of each historical transportation is recorded (there is no date limit, it is the corresponding time in 24 hours a day).

[0021] Furthermore, several logistics orders arriving at the current city on the same day are obtained, and the distribution center where the logistics orders arrive is used as the transportation starting point of the logistics orders, and the delivery address is used as the transportation end point of the logistics orders, and the cargo weight of each logistics order is recorded; at the same time, the order type of each logistics order is recorded, such as air express, air cold chain fresh food, large heavy goods express, ordinary express and other order types.

[0022] It should be noted that the multi-party collaborative optimization of urban logistics distribution needs to consider the distribution network including distribution centers, outlets, distribution sites (distribution destinations, such as door-to-door delivery, express stations and express lockers, etc.), the transportation capacity of logistics vehicles and the loading and unloading and distribution time loss of each node. Due to the variety of vehicles in the urban logistics distribution fleet, the distribution centers involve multiple transportation modes such as aviation, terminals, land transportation and rail transportation, and there are differences in the order types corresponding to logistics orders. It is necessary to target the distribution network for logistics orders based on order types and delivery processes to achieve effective utilization of logistics vehicles, while considering the time loss of nodes to achieve overall multi-party optimization of urban logistics distribution.

[0023] Step S002: Based on the transportation starting point and end point of the logistics order, as well as the distribution process, extract several distribution centers, outlets and distribution destinations of urban logistics distribution and construct a distribution map structure. For each logistics order combined with the order type, obtain the shortest distribution path in the distribution map structure; divide the logistics orders based on the shortest distribution path to obtain several order categories and the total weight of goods for each order category; combine the vehicle load, vehicle function and road restriction information of each type of vehicle to obtain the preferred transportation factor of each road section in the shortest distribution path of each order category for each type of vehicle.

[0024] It should be noted that after the goods arrive at the corresponding city by air, land, sea and rail, they first arrive at various distribution centers in the city, such as land distribution centers, aviation distribution centers, etc., and then the distribution center determines the delivery of the goods to various outlets in the city based on the delivery address of the logistics order. After arriving at the outlet, the goods are delivered by couriers or unmanned delivery fleets. The delivery destinations include express stations, express cabinets and specific addresses for door-to-door delivery. The distribution graph structure is constructed by taking the distribution centers, outlets and delivery destinations as nodes. At the same time, the road information of logistics vehicles is basically fixed during the delivery process between nodes, and the actual distance of the road traveled is used as the edge value; at the same time, for each logistics order based on its delivery address and logistics type, the outlets and delivery destinations are determined, and the shortest path is extracted in the distribution graph structure.

[0025] Preferably, in one embodiment of the present invention, based on the transportation starting point and end point of the logistics order and the delivery process, a number of distribution centers, outlets and delivery destinations of urban logistics distribution are extracted and a distribution graph structure is constructed. The shortest delivery path is obtained in the distribution graph structure for each logistics order in combination with the order type. The specific method includes: Extract several distribution centers and outlets in the city, as well as the driving roads from each distribution center to each outlet (the distribution centers and outlets can be directly obtained based on the logistics distribution network. The driving roads are fixed in most cases. If they are not fixed, the shortest distance roads are used as the driving roads. This will not be repeated in this embodiment). Take each distribution center and outlet as a node, the driving roads as the edges between the nodes corresponding to the distribution center and the outlet, and the distances corresponding to the driving roads as the edge values. At the same time, based on the transportation destinations, i.e., delivery addresses, in a large number of logistics orders, take several transportation destinations of door-to-door delivery, express lockers, and express stations belonging to the same area (usually a residential area or community) as the delivery destinations of the corresponding area, that is, one area corresponds to one delivery destination, and take each delivery destination as a node. At the same time, obtain the driving roads and corresponding distances from each outlet to each delivery destination, and obtain the edge values ​​between the nodes corresponding to the outlets and the nodes corresponding to the delivery destinations. Then, based on the edges and edge values ​​between the nodes and the nodes, construct a graph structure as the distribution graph structure.

[0026] Furthermore, for any logistics order, the node of the transportation destination corresponding to its transportation end point in the distribution graph structure is obtained, and the outlets passed by the logistics order during the transportation process are determined based on the nodes of the transportation destination and the order type of the logistics order (such as air express and ordinary land transportation, even if the delivery destination is the same, there are differences in the transportation outlets). Then, the outlets and the corresponding nodes of the delivery destination in the transportation process of the logistics order are obtained. At the same time, the corresponding distribution center is known according to the order type. Based on the nodes corresponding to the distribution center, outlets and delivery destination, the shortest delivery path for the logistics order in the distribution graph structure is obtained.

[0027] It should be further explained that the shortest delivery path corresponds to a fixed route of a distribution center-outlet-delivery destination. Logistics orders are classified based on the same shortest delivery path, so that the vehicle selection for each section of the shortest delivery path can be preferentially evaluated based on similar logistics orders in the future.

[0028] Preferably, in one embodiment of the present invention, the logistics orders are divided based on the shortest delivery path to obtain several order categories and the total weight of goods in each order category, including the following specific methods: Several logistics orders with the same shortest delivery route and the same order type are grouped as one order category; the cumulative sum of the cargo weights of all logistics orders in any order category is taken as the total cargo weight of that order category.

[0029] Preferably, in one embodiment of the present invention, the preferred transportation factor for each type of vehicle is obtained for each road segment in the shortest delivery path for each order category by combining the vehicle load, vehicle function, and road restriction information of each type of vehicle. The specific method includes: It should be noted that the order types of logistics orders in the same order category are the same, which determines the matching relationship between various types of vehicles and their vehicle functions. For example, the order type of air-transported cold chain fresh food needs to be transported by vehicles with refrigeration functions, so the matching relationship between the order type and vehicle function corresponding to the order category is analyzed; at the same time, the driving roads in the shortest delivery path and the road restriction information of the vehicle itself are analyzed to determine whether the corresponding vehicle can be transported on the corresponding driving roads. Combined with the difference between the vehicle load and the total weight of the goods in the order category, the transportation cost is taken into consideration, so as to conduct an optimal analysis of the matching between each section of the shortest delivery path corresponding to the order category and each type of vehicle.

[0030] Specifically, for any section of the shortest delivery route for any order category, and for any type of vehicle, obtain the ratio of the total weight of the goods of the order category to the vehicle load of the vehicle of this type. If the ratio is less than or equal to 1, use the ratio as the transportation matching factor for the order category and the vehicle of this type. If the ratio is greater than 1, convert the ratio into a mixed fraction, use the proper fraction part of the mixed fraction as the numerator, and the sum of the integer part plus 1 as the denominator to obtain the ratio, which is used as the transportation matching factor for the order category and the vehicle of this type.

[0031] Furthermore, the road restriction information corresponding to the section of road and the type of vehicle is obtained, that is, whether the corresponding type of vehicle is restricted from driving, 0 for prohibiting driving and 1 for allowing driving, which has been obtained in step S001; for vehicle functions, the word vector of the order type corresponding to the order category and the word vector of the vehicle function of the type of vehicle are obtained, and the cosine similarity of the two word vectors is used as the type matching factor between the order category and the type of vehicle, wherein the word vector is obtained using the Word2vec model, and the number of vector dimensions in the word vector is the same to ensure the calculation of cosine similarity; the product of the transportation matching factor, the type matching factor and the road restriction information corresponding to the section of road and the type of vehicle is used as the preferred transportation factor for the section of road for the type of vehicle in the shortest delivery path of the order category.

[0032] It should be noted that the closer the ratio of the total weight of the goods to the vehicle load is to 1, the closer its transport capacity is to meeting the transportation of all goods of the corresponding order category, and the larger the transport matching factor; if the ratio exceeds 1, it means that one vehicle of the corresponding type cannot transport all the goods, and it is necessary to reconsider whether the transport is matched through the true fraction part of the mixed fraction. At the same time, the integer part plus 1 indicates how many vehicles are needed, and the transport matching factor is adjusted. The more vehicles are needed and the smaller the true fraction part is, the less matched it is, and a larger vehicle is needed for the corresponding transportation; combined with the road restriction information and the matching relationship between the vehicle function and the order type, since there are certain synonyms in the text description of the vehicle function and the order type to express the correlation, the matching judgment is made through the similarity of the word vector, and the optimal transport factor is obtained.

[0033] At this point, through the transportation starting and ending points of the logistics order, combined with the distribution centers and outlets of the logistics distribution network, a distribution graph structure is constructed and the shortest distribution path is generated for the logistics order. At the same time, logistics orders with the same shortest distribution path are classified to obtain order categories, and the total weight of the goods is obtained for the order category. The optimization analysis is then carried out for each section of road and each type of vehicle transportation in the shortest distribution path, so as to optimize the analysis of each order category from the perspective of vehicle capacity and function.

[0034] Step S003: Analyze the impact of the number of logistics orders in each order category on the assembly time of each node in the shortest delivery path. Combined with the vehicle speed of each type of vehicle and the distance of each road segment in the shortest delivery path, quantify the time transportation cost of each road segment in the shortest delivery path for each order category for each type of vehicle. Combined with the optimal transportation factor, construct the transportation objective function for each road segment in the shortest delivery path for each order category for each type of vehicle.

[0035] It should be noted that after the optimal capacity matching analysis, the corresponding time transportation cost needs to be analyzed. The larger the number of logistics orders in the same order category, the longer the loading and unloading time of the transport vehicle when it leaves and arrives at the node, and the greater the impact on the overall logistics distribution process time. On this basis, it is necessary to consider the time spent by the transport vehicle on the road based on the vehicle speed and road network conditions, so as to quantify the time transportation cost of each section of road under the corresponding vehicle.

[0036] Preferably, in one embodiment of the present invention, the impact of the number of logistics orders in each order category on the assembly time of each node in the shortest delivery path is analyzed. The time transportation cost of each road segment in the shortest delivery path for each order category for each type of vehicle is quantified based on the vehicle speed and the distance of each road segment in the shortest delivery path. The specific method includes: For any section of the shortest delivery path for any order category, obtain several other order categories that are the same as the section of the shortest delivery path for the order category as the similar categories of the order category; perform linear normalization on the total weight of the goods of the order category and all its similar categories, and use the result as the weight reference weight for the order category and its similar categories; based on the weight reference weight, perform weighted averaging on the number of logistics orders for the order category and its similar categories, and use the result as the loading and unloading time cost for the section of the shortest delivery path for the order category.

[0037] It should be noted that there are some identical roads from the distribution center to the outlets, but different order categories are caused by different delivery destinations. Similarly, there are some identical roads from the outlets to the delivery destinations, but different order categories are caused by different distribution centers. During the loading and unloading process, since the roads are the same, they will be loaded into the same or the same type of transport vehicles. Therefore, the loading and unloading time cost needs to consider all categories. At the same time, the heavier the weight of the goods during the loading and unloading process, the longer it takes to load, unload and sort. The corresponding total weight of the goods is used as the weight to weight and average the time spent on the loading and unloading process directly determined by the number of logistics orders, so as to quantify the loading and unloading time cost.

[0038] It should be further explained that the actual vehicle speed in the vehicle information matches the driving road. It is the vehicle speed of the corresponding transport vehicle under multiple historical transports on the corresponding driving road (the average speed of traveling on this section of road). The transport speed of each type of vehicle on the current transport driving road is determined with reference to the historical vehicle speed. The transport time cost is quantified in combination with the distance, and then the time transport cost is obtained in combination with the loading and unloading time cost.

[0039] Furthermore, for this section of road, several vehicle speeds corresponding to any type of vehicle on this section of road (historically recorded vehicle speeds) and the departure time corresponding to each vehicle speed are obtained, and the average time of arrival at the departure node of this section of road for all logistics orders in this order category (the average time of arrival at the distribution center or online store) is obtained as the ideal departure time of this section of road in the shortest delivery path of this order category; the absolute value of the difference between the departure time corresponding to any vehicle speed and the ideal departure time is used as the time deviation of the vehicle speed, and the difference obtained by subtracting the time deviation from 24 hours is used as the time proximity of the vehicle speed; the time proximity of all vehicle speeds on this section of road is weighted and normalized, and the result is used as the time weight of each vehicle speed. Based on the time weight, a weighted sum is taken for all vehicle speeds on this section of road, and the result is used as the driving speed of this type of vehicle on this section of road in the shortest delivery path of this order category; the ratio of the distance (actual length) of this section of road to the driving speed is used as the transportation time cost of this type of vehicle on this section of road in the shortest delivery path of this order category.

[0040] Furthermore, the product of the loading and unloading time cost of this section of road in the shortest delivery path of this order category and the transportation time cost of this type of vehicle in this section of road is used as the time transportation cost of this section of road in the shortest delivery path of this order category for this type of vehicle.

[0041] It should be further explained that the time transportation cost comprehensively considers the transportation time of the vehicle during the transportation process and the cargo loading and unloading time of the outlets, and combines the optimal transportation factor to consider the optimal matching relationship between the transportation capacity and vehicle functions and the order category, and comprehensively constructs the transportation objective function to achieve the optimal matching analysis between each section of road and each type of vehicle in the shortest delivery path of the order category.

[0042] Preferably, in one embodiment of the present invention, in combination with the optimal transportation factor, a transportation objective function for each road segment in the shortest delivery path for each order category for each type of vehicle is constructed, including the specific method as follows: The expression formed by dividing the preferred transportation factor of any road section in the shortest delivery path of any order category for any type of vehicle by the time transportation cost of this road section for this type of vehicle is used as the transportation objective function for this road section in the shortest delivery path of this order category for this type of vehicle. The ratio of the preferred transportation factor to the time transportation cost is the output value of the transportation objective function for the corresponding type of vehicle.

[0043] At this point, in each section of the shortest delivery route, the number of logistics orders in the order category directly affects the length of assembly time at each node. Therefore, it is necessary to consider the relationship between road distance and vehicle speed to reduce the impact of longer assembly times on the delivery process under normal time flow. In combination with the optimal transportation factor, a comprehensive analysis of the optimal matching of each section of the shortest delivery route and the type of transport vehicle is conducted from the perspectives of transportation capacity and time cost, providing a basis for subsequent optimization.

[0044] Step S004: Based on the transport objective function, the optimal transport vehicle type is obtained for each road segment in the shortest delivery path of each order category, so as to allocate logistics vehicles to each logistics order and realize multi-party collaborative optimization of urban logistics delivery.

[0045] Specifically, for any section of road in the shortest delivery path of any order category, the vehicle type corresponding to the maximum output value of the transportation objective function corresponding to the road is used as the optimal transportation vehicle type for this section of road in the shortest delivery path for all logistics orders under this order category on that day. Then, corresponding transportation vehicles are obtained for each section of road in the shortest delivery path of each logistics order under this order category, thereby realizing multi-party collaborative optimization of urban logistics distribution, and achieving comprehensive and multi-faceted collaborative optimization from distribution centers, outlets and delivery destinations, as well as transportation capacity, assembly time and transportation vehicles.

[0046] At this point, by analyzing the distribution of distribution centers, outlets and delivery destinations in the urban logistics distribution process, logistics orders are classified and the shortest distribution path is obtained. Combined with the functions, load capacity and road restriction information of various types of vehicles in the distribution fleet, the optimal matching analysis of each section of road and vehicle in the shortest distribution path is carried out. At the same time, the assembly time and vehicle speed are taken into consideration. The time transportation cost is further considered based on the optimal analysis of roads and vehicles to achieve the optimal matching of roads and vehicles, and thus the transportation vehicles are allocated for logistics orders, so as to realize the coordinated optimization of distribution centers, outlets, transportation capacity, assembly time and transportation vehicles in the urban logistics distribution process.

[0047] Another embodiment of the present invention provides a multi-party collaborative optimization system for urban logistics distribution, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, steps S001 to S004 of the above method are implemented.

[0048] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A multi-party collaborative optimization method for urban logistics distribution, characterized by: The method comprises the following steps: Obtain vehicle information for various types of vehicles in the city's logistics delivery fleet, including vehicle function, vehicle load, vehicle speed, and road restriction information; obtain the transportation origin and destination, order type, and cargo weight of several logistics orders; Based on the transportation origin and destination of logistics orders and the delivery process, several distribution centers, outlets, and delivery destinations for urban logistics distribution are extracted and a distribution graph structure is constructed. The shortest delivery path is obtained for each logistics order based on the order type in the distribution graph structure. Logistics orders are divided based on the shortest delivery path to obtain several order categories and the total weight of the goods in each order category. The vehicle load, vehicle function, and road restriction information of each type of vehicle are combined to obtain the optimal transportation factor for each road segment in the shortest delivery path for each order category. Analyze the impact of the number of logistics orders in each order category on the assembly time of each node in the shortest delivery path. Combined with the vehicle speed of each type of vehicle and the distance of each road segment in the shortest delivery path, quantify the time transportation cost of each road segment in the shortest delivery path for each order category for each type of vehicle. Combined with the optimal transportation factor, construct the transportation objective function for each road segment in the shortest delivery path for each order category for each type of vehicle. Based on the transportation objective function, the optimal transportation vehicle type is obtained for each section of the shortest delivery path for each order category, and logistics vehicles are allocated to each logistics order.

2. The multi-party collaborative optimization method for urban logistics distribution according to claim 1 is characterized in that: The specific method of extracting several distribution centers, outlets and distribution destinations of urban logistics distribution and constructing a distribution map structure includes: Extract several distribution centers and outlets in the city, as well as the roads used to transport goods from each distribution center to each outlet. Take each distribution center and outlet as a node, the road as the edge between the nodes corresponding to the distribution center and the outlet, and the distance corresponding to the road as the edge value. Based on the transportation destinations in a large number of logistics orders, several transportation destinations belonging to the same area are jointly used as the distribution destinations of the corresponding area. Each distribution destination is used as a node, and the driving roads and corresponding distances of each outlet to each distribution destination are obtained. The edge values ​​between the corresponding nodes of the outlets and the corresponding nodes of the distribution destinations are obtained. Based on the edges and edge values ​​of each node and the nodes, a graph structure is constructed and used as the distribution graph structure.

3. The multi-party collaborative optimization method for urban logistics distribution according to claim 1 is characterized in that: The specific method for obtaining the shortest delivery path is as follows: For any logistics order, obtain the node of the transportation destination corresponding to its transportation end point in the distribution graph structure, determine the outlets that the logistics order passes through during the transportation process based on the transportation destination nodes and the order type of the logistics order, obtain the corresponding nodes of the outlets and distribution destinations in the transportation process of the logistics order, and obtain the shortest delivery path for the logistics order in the distribution graph structure based on the corresponding nodes of the distribution center, outlets and distribution destinations.

4. The multi-party collaborative optimization method for urban logistics distribution according to claim 1 is characterized in that: The specific method for obtaining the order categories and the total weight of the goods in each order category is as follows: Combine several logistics orders with the same shortest delivery path into one order category; The total weight of goods for all logistics orders in any order category is taken as the total weight of goods for that order category.

5. The multi-party collaborative optimization method for urban logistics distribution according to claim 1 is characterized in that: The preferred transportation factor for each type of vehicle on each road segment in the shortest delivery path for each order category is obtained in the following way: For any road segment in the shortest delivery route for any order category and any type of vehicle, obtain the ratio of the total weight of the goods for that order category to the vehicle load capacity of that type of vehicle. If the ratio is less than or equal to 1, use the ratio as the transport matching factor for that order category and that type of vehicle. If the ratio is greater than 1, convert the ratio into a mixed fraction, use the proper fraction as the numerator, and the sum of the integer part plus 1 as the denominator to obtain the ratio, which serves as the transport matching factor for that order category and that type of vehicle. Obtain the road restriction information corresponding to the road section and the type of vehicle. For vehicle functions, obtain the word vector of the order type corresponding to the order category and the word vector of the vehicle function of the type of vehicle. Use the cosine similarity of the two word vectors as the type matching factor between the order category and the type of vehicle. The product of the transport matching factor, the type matching factor and the road restriction information corresponding to the road segment and the vehicle type is used as the preferred transport factor for the road segment for the vehicle type in the shortest delivery path of the order category.

6. The multi-party collaborative optimization method for urban logistics distribution according to claim 1 is characterized in that: The specific method for obtaining the time transportation cost of each road segment in the shortest delivery path for each order category under each type of vehicle is as follows: Based on the number of logistics orders in each order category and the number of logistics orders of other order categories on each section of the shortest delivery path, combined with the total weight of the goods in the order category, the loading and unloading time cost of each section of the shortest delivery path for each order category is obtained; For any road segment in the shortest delivery path for any order category, obtain the speeds of all vehicles of any type on that road segment, as well as the departure times corresponding to each speed. Then, obtain the average of the times when all logistics orders in that order category arrive at the departure node on that road segment, and use this as the ideal departure time for that road segment in the shortest delivery path for that order category. The absolute value of the difference between the departure time corresponding to any vehicle speed and the ideal departure time is used as the time deviation of the vehicle speed, and the difference obtained by subtracting the time deviation from 24 hours is used as the time proximity of the vehicle speed; The time proximity of all vehicle speeds on this road segment is weighted and normalized, and the result is used as the time weight of each vehicle speed. Based on the time weight, the speeds of all vehicles on this road segment are weighted and summed, and the result is used as the driving speed of this type of vehicle on this road segment in the shortest delivery path for this order category. The ratio of the distance of this road segment to the driving speed is used as the transportation time cost of this type of vehicle on this road segment in the shortest delivery path for this order category. The product of the loading and unloading time cost of this section of road in the shortest delivery path of this order category and the transportation time cost of this type of vehicle in this section of road is used as the time transportation cost of this section of road in the shortest delivery path of this order category for this type of vehicle.

7. The multi-party collaborative optimization method for urban logistics distribution according to claim 6 is characterized in that: The specific method for obtaining the loading and unloading time cost of each road segment in the shortest delivery path for each order category is as follows: For any road segment in the shortest delivery path of any order category, obtain several other order categories that are the same as the road segment in the shortest delivery path of the order category as similar categories to the order category; Perform linear normalization on the total weight of the goods in this order category and all its similar categories, and use the result as the weight reference weight for this order category and its similar categories; Based on the weight reference weight, the number of logistics orders in the order category and its similar categories is weighted and averaged, and the result is used as the loading and unloading time cost of the road section in the shortest delivery path of the order category.

8. The multi-party collaborative optimization method for urban logistics distribution according to claim 1 is characterized in that: The specific method for constructing the transportation objective function for each road segment in the shortest delivery path for each order category for each type of vehicle is as follows: The expression formed by dividing the preferred transportation factor of any road section in the shortest delivery path of any order category for any type of vehicle by the time transportation cost of this road section for this type of vehicle is used as the transportation objective function for this road section in the shortest delivery path of this order category for this type of vehicle.

9. The multi-party collaborative optimization method for urban logistics distribution according to claim 1 is characterized in that: The specific method for obtaining the optimal transport vehicle type for each road segment in the shortest delivery path for each order category based on the transport objective function includes: For any section of road in the shortest delivery path of any order category, the vehicle type corresponding to the maximum output value of the transportation objective function corresponding to the road is used as the optimal transportation vehicle type for this section of road in the shortest delivery path for all logistics orders under this order category.

10. A multi-party collaborative optimization system for urban logistics distribution, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the multi-party collaborative optimization method for urban logistics distribution as described in any one of claims 1 to 9 are implemented.

Images