A distribution point routing optimization method and system based on GIS and ant colony algorithm

Abstract

The present invention provides a method and system for optimizing the routing of distribution points based on GIS and ant colony algorithm, which belongs to the technical field of distribution management, and specifically comprises: a waybill information management module is responsible for receiving, classifying and initially processing distribution orders, a map information processing module is responsible for using GIS technology to capture and update store location information in real time, an intelligent routing algorithm module is responsible for setting a specific rule engine to perform initial regional segmentation and matching on orders, and provides a preliminary distribution route layout, and generates multiple distribution plans, and an ant colony algorithm optimization module is responsible for applying the ant colony algorithm to optimize the initially generated distribution plan, generate a distribution plan, and reduce the time of distribution processing.

Description

Technical Field

[0001] The present invention belongs to the technical field of distribution management, and in particular relates to a distribution point arrangement optimization method and system based on GIS and ant colony algorithm. Background Art

[0002] With the rapid development of e-commerce, offline physical stores are combined with online order systems to form an O2O business model. However, there are many problems with order processing under this model, especially in logistics and distribution. The existing line system lacks intelligence and automation, resulting in low distribution efficiency and high distribution costs. In addition, the quality of the delivery route directly affects customer satisfaction and store operating costs.

[0003] In response to the above technical problems, the present application specifically provides a distribution point routing optimization method and system based on GIS and ant colony algorithm. Summary of the invention

[0004] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0005] According to one aspect of the present invention, a method and system for optimizing the routing of distribution points based on GIS and ant colony algorithm are provided.

[0006] A distribution point routing optimization method based on GIS and ant colony algorithm, specifically including:

[0007] S1 uses the delivery data of delivery orders in different regions to determine the delivery mileages of delivery orders in different regions based on GIS technology, and uses the delivery mileages of different delivery orders in the region to determine the delivery route optimization region in the region;

[0008] S2: taking the orders in the delivery route optimization area that have been processed with delivery plans but not yet processed as original delivery orders, using the delivery routes of the delivery orders in the delivery route optimization area to determine the deviation from the delivery routes of the original delivery orders in the delivery route optimization area, and using the deviation to determine the target optimization area in the delivery route optimization area;

[0009] S3 takes the delivery orders in the target optimization area and the original delivery orders as optimization target orders, determines the number of optimization target orders in the target optimization area, and when it is determined that the optimization target orders in the target optimization area need to be optimized based on the similarity of the delivery routes between different optimization target orders, proceeds to the next step;

[0010] S4 generates candidate orders based on the similarity of the delivery routes between the optimization target orders, and determines the delivery plan using the candidate orders and the ant colony algorithm.

[0011] The beneficial effects of the present invention are:

[0012] According to the number of optimized target orders in the target optimization area and the similarity of delivery routes between different optimized target orders, it is determined whether the optimized target orders in the target optimization area need to be optimized, thereby avoiding the technical problem that the optimization processing of the delivery plan is too difficult due to the large number of optimized target orders in the target optimization area. At the same time, by further combining the similarity of delivery routes between different optimized target orders, the screening of target optimization areas with a large number of orders and a high degree of similarity in delivery routes is realized, thereby improving the efficiency of generating and processing delivery plans.

[0013] The distribution plan is determined by using alternative orders and ant colony algorithm, thus avoiding the technical problem of excessive difficulty in optimization processing caused by using all the optimization target orders in the target optimization area, improving the efficiency of generating and processing distribution plans, and also ensuring the efficiency of distribution processing in the target optimization area.

[0014] A further technical solution is that the delivery mileage of the delivery order is determined according to the destination of the delivery order.

[0015] A further technical solution is that the method for determining the delivery route optimization area in the area is:

[0016] Determining a delivery difficulty coefficient for the delivery orders in the area based on the delivery mileage of the delivery orders in the area;

[0017] Determining a delivery difficulty coefficient for the delivery orders in the area based on the sum of the delivery difficulty coefficients of different delivery orders;

[0018] Determine whether the area is a delivery route optimization area according to the delivery difficulty coefficient of the delivery orders in the area.

[0019] A further technical solution is that the delivery difficulty coefficient is determined according to a preset processing difficulty corresponding to the delivery mileage of the delivery order in the area.

[0020] On the other hand, the present application provides a distribution point arrangement optimization system based on GIS and ant colony algorithm, which adopts the above-mentioned distribution point arrangement optimization method based on GIS and ant colony algorithm, specifically including:

[0021] Waybill information management module, map information processing module, ant colony algorithm optimization module;

[0022] The shipping order information management module is responsible for receiving, classifying and initially processing the delivery orders;

[0023] The map information processing module is responsible for capturing and updating store location information in real time using GIS technology;

[0024] The intelligent routing algorithm module is responsible for setting a specific rule engine to perform initial regional segmentation and matching of orders, provide a preliminary delivery route layout, and generate multiple delivery plans;

[0025] The ant colony algorithm optimization module is responsible for optimizing the initially generated distribution plan by applying the ant colony algorithm to generate a distribution plan.

[0026] A further technical solution is to further include a visual route arrangement module, which is responsible for clearly displaying the location of each store and the delivery route on the map, and using different colors and lines to indicate the delivery status;

[0027] A further technical solution is to also include a user operation interface, which is responsible for facilitating intuitive operations by the line operator and providing functions of order management and delivery route adjustment.

[0028] A further technical solution is to perform initial regional segmentation and matching of orders, including:

[0029] The order is initially divided and allocated to different regions using the location of the order and the region corresponding to the location.

[0030] A further technical solution is to generate multiple delivery plans, including:

[0031] According to the location of different orders, free combinations can be made to generate multiple delivery plans.

[0032] A further technical solution is to generate a distribution plan, which specifically includes:

[0033] The number of delivery vehicles, delivery sequence and distance between stores in different delivery plans are used as dependent variables, and the delivery time in different delivery plans is used as the target to construct an ant colony algorithm.

[0034] Based on the ant colony algorithm, different delivery plans are optimized to obtain a delivery plan with the shortest delivery time among the delivery plans, and the delivery plan with the shortest delivery time is used as the delivery plan.

[0035] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0036] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings;

[0038] Figure 1 It is a flow chart of the distribution point routing optimization method based on GIS and ant colony algorithm;

[0039] Figure 2 is a flow chart of a method for determining a delivery route optimization region in a region;

[0040] Figure 3 is a flow chart of a method for determining a target optimization area in a distribution route optimization area;

[0041] Figure 4 is a flow chart of a method for determining alternative orders;

[0042] Figure 5 It is a framework diagram of a distribution point routing optimization system based on GIS and ant colony algorithm. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0044] The present invention discloses a store order intelligent routing optimization system based on geographic information system (GIS) and ant colony algorithm. In view of the situation that offline physical stores are facing the demand for efficient logistics distribution under the current O2O business model, the system provides a complete solution to improve the efficiency of logistics distribution and reduce costs. The system works in coordination through multiple modules, including map information processing module, carrier bill management module, intelligent routing module, ant colony algorithm optimization module, visual route arrangement module, etc. These modules jointly realize the real-time processing of order information, intelligent generation and optimization of routes.

[0045] The core of the system is to use GIS technology to accurately render store locations, use intelligent algorithms to match distribution areas and allocate orders, and automatically calculate the optimal distribution route through ant colony algorithms to ensure the minimization of distribution costs and the optimization of distribution time. The system also provides a user-friendly graphical user interface for easy operation by line operators.

[0046] The present invention proposes an intelligent ordering system based on store orders, which is composed of multiple collaborative modules and solves the efficiency and cost problems in store order delivery through innovative technical means. The following are the specific details of the invention:

[0047] Shipping order module: It is required to receive, store and preliminarily classify the fulfillment delivery orders in real time, generate order delivery orders and delivery details, and provide basic data for subsequent intelligent routing.

[0048] Point GIS module: The map module uses GIS technology to record the geographical location information of the store and ensure the accuracy and timeliness of the data. Through precise geographic data, it ensures the accuracy and timeliness of delivery route planning, providing support for efficient delivery.

[0049] Routing module: It is divided into pre-routing mode and real-time routing mode. Pre-routing can automatically assign routes according to routing habits, while real-time routing means that the route arranger can form a preliminary distribution route by simply dragging and dropping in the graphical user interface in the area he is responsible for.

[0050] Algorithm module: After the algorithm module completes the routing, the ant colony algorithm optimizes the preliminary route generated by the route arranger to find a more economical delivery path. At the same time, the algorithm automatically adjusts the route to reduce the delivery distance and time and improve efficiency.

[0051] Picking tasks: After completing the route arrangement, the route arrangement module will summarize the order information of the points on each route and generate the picking tasks for the drivers corresponding to the route.

[0052] Delivery task: After completing the route arrangement, all the goods that need to be delivered and fulfilled under the store will be summarized according to the store locations on each route, and the delivery details of each store location will be generated to record the delivery result information of each store.

[0053] Real-time monitoring: During the picking and delivery process, the driver's operating actions will be recorded, and the system can monitor the driver's picking progress and delivery status in real time.

[0054] Embodiment 1 To solve the above-mentioned problem, according to one aspect of the present invention, Figure 1 As shown, a first aspect is provided. The present invention proposes a distribution point line optimization method based on GIS and ant colony algorithm, which specifically includes:

[0055] S1 uses the delivery data of delivery orders in different regions to determine the delivery mileages of delivery orders in different regions based on GIS technology, and uses the delivery mileages of different delivery orders in the region to determine the delivery route optimization region in the region;

[0056] Furthermore, the delivery mileage of the delivery order is determined according to the destination of the delivery order.

[0057] Specifically, Figure 2 As shown, the method for determining the delivery route optimization area in the area is:

[0058] Determining a delivery difficulty coefficient for the delivery orders in the area based on the delivery mileage of the delivery orders in the area;

[0059] Determining a delivery difficulty coefficient for the delivery orders in the area based on the sum of the delivery difficulty coefficients of different delivery orders;

[0060] Determine whether the area is a delivery route optimization area according to the delivery difficulty coefficient of the delivery orders in the area.

[0061] Furthermore, the delivery difficulty coefficient is determined according to a preset processing difficulty corresponding to the delivery mileage of the delivery orders in the area.

[0062] It should also be noted that when the delivery difficulty coefficient of the delivery orders in the area is greater than a preset difficulty coefficient threshold, the area is determined to be a delivery route optimization area.

[0063] In another embodiment, the method for determining the delivery route optimization area in the area is:

[0064] Based on the delivery mileage of the delivery orders in the area, determining the delivery orders with a delivery mileage greater than a preset delivery mileage;

[0065] Delivery orders with a delivery mileage greater than a preset delivery mileage are regarded as delivery difficulty coefficient orders, and the number of delivery difficulty coefficient orders is used to determine whether the area is a delivery route optimization area.

[0066] Specifically, when the number of orders with the delivery difficulty coefficient is greater than a preset number of orders, the area is determined to be a delivery route optimization area.

[0067] Optionally, when the area does not belong to the delivery route optimization area, there is no need to optimize the delivery plan for the area, and the existing delivery plan is used for delivery, and the delivery order is not delivered temporarily.

[0068] In another embodiment, the method for determining the delivery route optimization area in the area is:

[0069] Acquiring the number of delivery orders in the area, and when the number of delivery orders in the area is greater than a preset number of delivery orders, determining that the area is a delivery route optimization area;

[0070] When the number of delivery orders in the area is not greater than the preset delivery order number:

[0071] Based on the delivery mileage of the delivery orders in the area, determining the total delivery mileage of the delivery orders in the area, when the total delivery mileage of the delivery orders in the area is greater than a preset mileage threshold, determining that the area is a delivery route optimization area;

[0072] When the total delivery mileage of the delivery orders in the area is not greater than the preset mileage threshold:

[0073] When the number of delivery orders in the area is less than the preset order quantity:

[0074] It is determined that the area does not belong to the delivery route optimization area;

[0075] When the number of delivery orders in the area is not less than the preset order quantity:

[0076] Based on the delivery mileage of the delivery orders in the area, when it is determined that there is no delivery order in the area whose delivery mileage is greater than the preset delivery mileage: it is determined that the area does not belong to the delivery route optimization area;

[0077] When there is a delivery order with a delivery mileage greater than the preset delivery mileage:

[0078] The delivery orders with a delivery mileage greater than a preset delivery mileage are taken as screened delivery orders, and when the number of the screened delivery orders is greater than the preset number of screened orders, it is determined that the area belongs to the delivery route optimization area;

[0079] When the quantity of the filtered delivery orders is not greater than the preset filtered order quantity:

[0080] Determining the delivery difficulty coefficient of the delivery orders in the area based on the delivery mileage of the delivery orders in the area, and determining the delivery difficulty coefficient of the delivery orders in the area based on the sum of the delivery difficulty coefficients of different delivery orders;

[0081] Determine whether the area is a delivery route optimization area according to the delivery difficulty coefficient of the delivery orders in the area.

[0082] S2: taking the orders in the delivery route optimization area that have been processed with delivery plans but not yet processed as original delivery orders, and using the delivery routes of the delivery orders in the delivery route optimization area to determine the deviation from the delivery routes of the original delivery orders in the delivery route optimization area, and using the deviation to determine the target optimization area in the delivery route optimization area;

[0083] Furthermore, the original delivery orders in the delivery route optimization area are the delivery orders originally acquired in the delivery route optimization area, specifically, the orders that have been processed for delivery plans but not yet delivered.

[0084] Specifically, the deviation of the delivery routes is based on the route deviation amount between the delivery routes.

[0085] Specifically, Figure 3 As shown, the method for determining the target optimization area in the delivery route optimization area is:

[0086] Determine the route deviation between different delivery orders and the delivery routes of the original delivery orders in the delivery route optimization area according to the deviation of the delivery routes, and determine the original delivery order with the smallest route deviation between different delivery orders and the delivery routes of the original delivery orders according to the route deviation between the different delivery orders and the delivery routes of the original delivery orders;

[0087] The original delivery order with the smallest route deviation is used as a matching order of the delivery order, and the deviation delivery order in the delivery order is determined according to the route deviation between the matching order and the delivery order;

[0088] It is determined whether the delivery route optimization area is a target optimization area based on the number of the deviation delivery orders.

[0089] Furthermore, the deviation delivery order is a delivery order whose route deviation from the matching order of the delivery order is greater than a preset deviation threshold.

[0090] Optionally, when the number of the deviation delivery orders is greater than a preset number of deviation orders, the delivery route optimization area is determined as a target optimization area.

[0091] It should be noted that when the delivery route optimization area does not belong to the target optimization area, there is no need to optimize the delivery plan for the delivery route optimization area. The existing delivery plan is used for delivery processing, and the delivery order is not delivered temporarily.

[0092] In another embodiment, the method for determining the target optimization area in the delivery route optimization area is:

[0093] Determine the route deviation between different delivery orders and the delivery route of the original delivery order based on the deviation from the delivery route of the original delivery order in the delivery route optimization area;

[0094] Determine the original delivery order with the smallest route deviation from the delivery route of the original delivery order, and use the original delivery order with the smallest route deviation as the matching order for the delivery order;

[0095] Determining the sum of route deviations of different delivery orders and matching orders according to the route deviations of the matching order and the delivery order, and when the sum of route deviations is greater than a preset route deviation threshold, determining that the delivery route optimization area belongs to the target optimization area;

[0096] When the sum of route deviations is not greater than the preset route deviation threshold:

[0097] When it is determined that there is no deviation delivery order according to the route deviation amount between the matching order and the delivery order, it is determined that the delivery route optimization area does not belong to the target optimization area;

[0098] When it is determined that there is a deviation delivery order in the delivery order according to the route deviation amount between the matching order and the delivery order:

[0099] Acquire the number of the deviation delivery orders, and when the number of the deviation delivery orders is greater than the preset deviation order number, determine the delivery route optimization area as the target optimization area;

[0100] When the quantity of the deviation delivery orders is not greater than the preset deviation order quantity:

[0101] Determine route deviation coefficients of different deviation delivery orders based on route deviation amounts of different deviation delivery orders and corresponding matching orders, and when the sum of route deviation coefficients of different deviation delivery orders does not meet the requirements, determine the delivery route optimization area as the target optimization area;

[0102] When the sum of the route deviation coefficients of different deviation delivery orders meets the requirements:

[0103] The route deviation coefficients of different delivery orders are determined based on the route deviation amounts of different delivery orders and corresponding matching orders, and whether the delivery route optimization area is the target optimization area is determined based on the sum of the route deviation coefficients of the deviation delivery orders.

[0104] S3 takes the delivery orders in the target optimization area and the original delivery orders as optimization target orders, determines the number of optimization target orders in the target optimization area, and when it is determined that the optimization target orders in the target optimization area need to be optimized based on the similarity of the delivery routes between different optimization target orders, proceeds to the next step;

[0105] Specifically, determining that the optimization target orders in the target optimization area need to be optimized includes:

[0106] Determine route similarity coefficients between delivery routes of different optimized target orders based on similarities between delivery routes of different optimized target orders, and divide the optimized target orders into multiple target order groups based on the route similarity coefficients;

[0107] Determine the screening order group based on the number of optimized target orders in different target order groups;

[0108] Whether the optimization target orders in the target optimization area need to be optimized is determined according to the number of the filtered order groups.

[0109] Furthermore, the screened order group is a target order group in which the number of optimized target orders is greater than a preset number of optimized orders.

[0110] It should be noted that when the number of the screened order groups is greater than the preset number of groups, it is determined that the optimization target orders in the target optimization area need to be optimized.

[0111] S4 generates candidate orders based on the similarity of the delivery routes between the optimization target orders, and determines the delivery plan using the candidate orders and the ant colony algorithm.

[0112] Specifically, Figure 4 As shown, the method for determining the alternative order is:

[0113] Based on the similarity of the delivery routes between the optimization target orders, determining the route similarity coefficients of the delivery routes between different optimization target orders;

[0114] Divide the optimized target orders whose route similarity coefficients are within a preset similarity coefficient range into multiple target order groups;

[0115] The optimized target order with the largest average value of line similarity coefficients between the optimized target order in the target order group and other optimized target orders in the target order group is used as the alternative order of the target order group, and the alternative orders of different target order groups are used to determine the alternative orders.

[0116] Furthermore, the delivery plan is determined by using the candidate orders and the ant colony algorithm, specifically including:

[0117] The delivery plan is determined by using the alternative orders and ant colony algorithm

[0118] Based on the alternative orders and with the goal of minimizing the delivery time of the alternative orders, an ant colony algorithm is used to perform optimization processing to obtain a delivery solution.

[0119] Embodiment 2 On the other hand, as Figure 5 As shown, the present application provides a distribution point arrangement optimization system based on GIS and ant colony algorithm, which adopts the above-mentioned distribution point arrangement optimization method based on GIS and ant colony algorithm, specifically including:

[0120] Waybill information management module, map information processing module, ant colony algorithm optimization module;

[0121] The shipping order information management module is responsible for receiving, classifying and initially processing the delivery orders;

[0122] The map information processing module is responsible for capturing and updating store location information in real time using GIS technology;

[0123] The intelligent routing algorithm module is responsible for setting a specific rule engine to perform initial regional segmentation and matching of orders, provide a preliminary delivery route layout, and generate multiple delivery plans;

[0124] The ant colony algorithm optimization module is responsible for optimizing the initially generated delivery plan by applying the ant colony algorithm to generate a delivery plan.

[0125] It includes system structure design, function implementation of each module, algorithm selection and adjustment, data interaction process and user operation interface implementation, etc.

[0126] Waybill information management module:

[0127] Realize the receipt, classification and preliminary processing of delivery orders.

[0128] Use database technology to store order information and classify it according to business rules.

[0129] Map information processing module:

[0130] Use GIS technology to capture and update store location information in real time to ensure data accuracy and real-time updates on the map.

[0131] Intelligent wiring algorithm module:

[0132] Set up a specific rule engine to perform initial region segmentation and matching on orders.

[0133] Provide preliminary delivery route layout and generate multiple delivery plans.

[0134] Ant colony algorithm optimization module:

[0135] The ant colony algorithm is applied to optimize the initially generated delivery routes and automatically adjust the routes to reduce delivery costs and time.

[0136] The algorithm takes into account the number of delivery vehicles, the order of delivery and the distance between stores.

[0137] The pheromone update formula is:

[0138] From the city To the city The pheromone concentration, is the attenuation coefficient of the pheromone, is the amount of pheromone added by the ants passing through the path within time t.

[0139] The probability of an ant choosing the next city is usually determined by the pheromone concentration and the distance (or other cost), and the formula is as follows: in, is the probability that the ant chooses the next city j from city i, and is a parameter, yes arrive Heuristic information of , usually the inverse of the distance.

[0140] Heuristic Information: Heuristic information is usually inversely proportional to the distance or cost of the problem, as follows: ,in, is from arrive Distance or cost

[0141] Visual route arrangement module:

[0142] Clearly display the location of each store and delivery route on the map.

[0143] Use different colors and lines to indicate delivery status, making it easier for line operators to make adjustments.

[0144] User interface:

[0145] The easy-to-use graphical user interface is designed to allow intuitive operation by the line operator.

[0146] Provides basic functions for order management and delivery route adjustment.

[0147] Through this implementation method, the efficient, accurate and intelligent operation of the system can be ensured, allowing stores to quickly respond to customers' order needs while optimizing costs and improving customer satisfaction.

[0148] Furthermore, it also includes a visual route arrangement module, which is responsible for clearly displaying the location of each store and the delivery route on the map, and using different colors and lines to indicate the delivery status;

[0149] Specifically, it also includes a user operation interface, which is responsible for facilitating intuitive operations by the line operator and providing functions of order management and delivery route adjustment.

[0150] Optionally, the orders are segmented and matched at an early stage, including:

[0151] The order is initially divided and allocated to different regions using the location of the order and the region corresponding to the location.

[0152] Furthermore, multiple delivery plans are generated, including:

[0153] According to the location of different orders, free combinations can be made to generate multiple delivery plans.

[0154] In addition, it should be noted that generating a delivery plan specifically includes:

[0155] The number of delivery vehicles, delivery sequence and distance between stores in different delivery plans are used as dependent variables, and the delivery time in different delivery plans is used as the target to construct an ant colony algorithm.

[0156] Based on the ant colony algorithm, different delivery plans are optimized to obtain a delivery plan with the shortest delivery time among the delivery plans, and the delivery plan with the shortest delivery time is used as the delivery plan.

[0157] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0158] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0159] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A distribution point routing optimization method based on GIS and ant colony algorithm, characterized in that: Specifically include: Using the delivery data of delivery orders in different regions, determining the delivery mileages of delivery orders in different regions based on GIS technology, and determining the delivery route optimization area in the region using the delivery mileages of different delivery orders in the region; The orders in the delivery route optimization area that have been processed with delivery plans but not yet processed are taken as original delivery orders, and the delivery routes of the delivery orders in the delivery route optimization area are used to determine the deviation from the delivery routes of the original delivery orders in the delivery route optimization area, and the target optimization area in the delivery route optimization area is determined by using the deviation; The delivery orders in the target optimization area and the original delivery orders are used as optimization target orders, the number of optimization target orders in the target optimization area is determined, and when it is determined that the optimization target orders in the target optimization area need to be optimized based on the similarity of the delivery routes between the optimization target orders, alternative orders are generated based on the similarity of the delivery routes between the optimization target orders, and the delivery plan is determined based on the alternative orders and the ant colony algorithm; The method for determining the delivery route optimization area in the area is: Determining a delivery difficulty coefficient for the delivery orders in the area based on the delivery mileage of the delivery orders in the area; Determining a delivery difficulty coefficient for the delivery orders in the area based on the sum of the delivery difficulty coefficients of different delivery orders; Determining whether the area is a delivery route optimization area according to a delivery difficulty coefficient of delivery orders in the area; The method for determining the target optimization area in the delivery route optimization area is: Determine the route deviation between different delivery orders and the delivery routes of the original delivery orders in the delivery route optimization area according to the deviation of the delivery routes, and determine the original delivery order with the smallest route deviation between different delivery orders and the delivery routes of the original delivery orders according to the route deviation between the different delivery orders and the delivery routes of the original delivery orders; The original delivery order with the smallest route deviation is used as a matching order of the delivery order, and the deviation delivery order in the delivery order is determined according to the route deviation between the matching order and the delivery order; Determining whether the delivery route optimization area is a target optimization area based on the number of the deviation delivery orders; The method for determining the alternative order is: Based on the similarity of the delivery routes between the optimization target orders, determining the route similarity coefficients of the delivery routes between different optimization target orders; Divide the optimized target orders whose route similarity coefficients are within a preset similarity coefficient range into multiple target order groups; The optimized target order with the largest average value of line similarity coefficients between the optimized target order in the target order group and other optimized target orders in the target order group is used as the alternative order of the target order group, and the alternative orders of different target order groups are used to determine the alternative orders.

2. The method for optimizing the distribution point arrangement based on GIS and ant colony algorithm according to claim 1, characterized in that: The delivery mileage of the delivery order is determined according to the destination of the delivery order.

3. The method for optimizing the distribution point arrangement based on GIS and ant colony algorithm according to claim 1, characterized in that: The delivery difficulty coefficient is determined according to a preset processing difficulty corresponding to the delivery mileage of the delivery order in the area.

4. A distribution point line optimization system based on GIS and ant colony algorithm, adopting a distribution point line optimization method based on GIS and ant colony algorithm as claimed in any one of claims 1 to 3, characterized in that: Specifically include: Waybill information management module, map information processing module, ant colony algorithm optimization module, intelligent routing algorithm module; The shipping order information management module is responsible for receiving, classifying and initially processing the delivery orders; The map information processing module is responsible for capturing and updating store location information in real time using GIS technology; The intelligent routing algorithm module is responsible for setting a specific rule engine to perform initial regional segmentation and matching of orders, provide a preliminary delivery route layout, and generate multiple delivery plans; The ant colony algorithm optimization module is responsible for optimizing the initially generated delivery plan by applying the ant colony algorithm to generate a delivery plan.

5. The distribution point arrangement optimization system based on GIS and ant colony algorithm as claimed in claim 4, characterized in that: It also includes a visual route arrangement module, which is responsible for clearly displaying the location of each store and the delivery route on the map, and using different colors and lines to indicate the delivery status.

6. The distribution point arrangement optimization system based on GIS and ant colony algorithm as claimed in claim 4, characterized in that: It also includes a user operation interface, which is responsible for facilitating intuitive operations by the line operator and providing functions of order management and delivery route adjustment.

7. The distribution point arrangement optimization system based on GIS and ant colony algorithm as claimed in claim 4, characterized in that: Generate a delivery plan, including: The number of delivery vehicles, delivery sequence and distance between stores in different delivery plans are used as dependent variables, and the delivery time in different delivery plans is used as the target to construct an ant colony algorithm. Based on the ant colony algorithm, different delivery plans are optimized to obtain a delivery plan with the shortest delivery time among the delivery plans, and the delivery plan with the shortest delivery time is used as the delivery plan.

Images