Region division method and device

Based on the location data and logistics data, the particle swarm algorithm is iteratively updated the initial set and historical optimal solutions. Combined with diversity judgment, the problems of long time for branch splitting in the existing technology and difficult to apply the results are solved, achieving high efficiency , accurate regional division.

CN119090381APending Publication Date: 2024-12-06BEIJING JINGDONG YUANSHENG TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411179666.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-26
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

When the existing outlet splitting method is evaluated based on a facility site selection problem model with capacity limitation, the outlet layout is frequently disrupted, the division time is long and the application is difficult, making it difficult to achieve efficient area division.

Method used

Using particle swarm algorithm based on location data and logistics data, the target set is generated to determine the region division results through iterative updates of the initial set and historical optimal solutions, combined with preset offset conditions and diversity judgment, and simplifying the network splitting process .

Benefits of technology

It significantly reduces the time consumption and complexity of regional division, improves the efficiency and accuracy of division results, and achieves rapid and accurate splitting of outlets.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119090381A_ABST
    Figure CN119090381A_ABST
Patent Text Reader

Abstract

The invention discloses a region division method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of obtaining position data and logistics data of a target area, obtaining an initial set of division results of the target area based on the data, further determining a target offset set based on a historical optimal solution, and finally determining a division result set of the target area through loop iteration, and a corresponding division scheme is determined. According to the embodiment, the region can be re-divided based on the division scheme contained in the position data of the existing target region, so that the modified data is reduced, and the region division efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for dividing a region. Background Art

[0002] The rapid development of e-commerce has driven the rapid expansion of express logistics, and the orders of express logistics are also growing rapidly. In order to better improve the quality of logistics services in the region, express terminal distribution outlets, which are the spatial gathering points operated by express companies, urgently need to take corresponding expansion operations. When carrying out expansion operations, the solution for outlet splitting needs to split the original outlet coverage into several new terminal outlets with new coverage to achieve refined division of outlet coverage.

[0003] The current network splitting method mainly evaluates the network layout optimization model based on the Capacitated Facility Location Problem (CFLP) model, and plans and reviews the network distribution layout of the region. However, when solving the problem through this model, the planned network layout is often completely disrupted and re-divided, which takes a long time and is difficult to apply the division results. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a method and device for dividing a region, which can further determine the region division result based on the existing location data. The division scheme consumes less time and the division result scheme is easy to implement.

[0005] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for dividing a region is provided, comprising:

[0006] Obtain location data and logistics data of the target area;

[0007] generating an initial set of partitioning results including a target quantity based on the location data and logistics data of the target area;

[0008] Repeat the operations of determining a target offset distance set based on an initial set and a historical optimal solution, determining a target set based on the initial set, the target offset distance set and a preset offset condition, and updating the historical optimal solution and the initial set based on the target set until a preset iteration stop condition is met, and determining the updated target set as a target partition result set;

[0009] A target area partitioning scheme is determined based on the target partitioning result set.

[0010] Optionally, before updating the historical optimal solution and the initial set based on the target set, the method also includes: judging whether the target set satisfies a preset diversity condition and obtaining a judgment result; when the judgment result is that the preset diversity condition is not satisfied, generating a random offset distance and updating the target set based on the random offset distance.

[0011] Optionally, the preset diversity condition is a preset diversity threshold condition, and whether the target set satisfies the preset diversity condition is judged to obtain a judgment result, including: calculating the diversity of the target set based on the target set and the historical optimal solution; when the diversity of the target set is less than or equal to the preset diversity threshold, determining that the judgment result does not satisfy the preset diversity condition; when the diversity of the target set is greater than the preset diversity threshold, determining that the judgment result satisfies the preset diversity condition.

[0012] Optionally, generating a random offset distance includes: randomly generating an offset distance; and regenerating the offset distance when the offset distance does not meet a preset offset condition.

[0013] Optionally, updating the historical optimal solution based on the target set includes: determining the optimal solution in the target set based on the target set and a preset objective function; and updating the historical optimal solution based on the optimal solution in the target set.

[0014] Optionally, determining a target offset distance set based on an initial set and a historical optimal solution includes: determining a first offset distance set based on the initial set and the historical optimal solution; determining a second offset distance set based on the first offset distance set and a target random number; and calculating a target offset distance set based on the first offset distance set and the second offset distance set.

[0015] According to another aspect of an embodiment of the present invention, a device for dividing a region is provided, including:

[0016] An acquisition module is used to acquire location data and logistics data of a target area;

[0017] An initialization module, used for generating an initial set of partitioning results including a target quantity based on location data and logistics data of a target area;

[0018] A determination module is used to repeatedly perform operations of determining a target offset distance set based on an initial set and a historical optimal solution, determining a target set based on the initial set, a target offset distance set and a preset offset condition, and updating the historical optimal solution and the initial set based on the target set until a preset iteration stop condition is met, determining the updated target set as a target partition result set; and determining a partitioning scheme for a target area based on the target partition result set.

[0019] Optionally, the device also includes: a judgment module, used to judge whether the target set meets the preset diversity condition and obtain a judgment result; a generation module, used to generate a random offset distance and update the target set based on the random offset distance when the judgment result is that the preset diversity condition is not met.

[0020] Optionally, the preset diversity condition is a preset diversity threshold condition, and the judgment module is used to judge whether the target set meets the preset diversity condition and obtain a judgment result, including: a calculation module, used to calculate the diversity of the target set based on the target set and the historical optimal solution; a determination module, used to determine that the judgment result does not meet the preset diversity condition when the diversity of the target set is less than or equal to the preset diversity threshold; when the diversity of the target set is greater than the preset diversity threshold, determine that the judgment result meets the preset diversity condition.

[0021] Optionally, a generation module, used to generate a random offset distance, includes: a generation module, used to randomly generate an offset distance; when the offset distance does not meet a preset offset condition, regenerate the offset distance.

[0022] Optionally, an update module, used to update the historical optimal solution based on the target set, includes: a determination module, used to determine the optimal solution in the target set based on the target set and a preset objective function; an update module, used to update the historical optimal solution based on the optimal solution in the target set.

[0023] Optionally, a determination module, used to determine a target offset distance set based on an initial set and a historical optimal solution, includes: a determination module, used to determine a first offset distance set based on the initial set and the historical optimal solution; a second offset distance set based on the first offset distance set and a target random number; and a calculation module, used to calculate the target offset distance set based on the first offset distance set and the second offset distance set.

[0024] According to another aspect of an embodiment of the present invention, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the area division method provided by an embodiment of the present invention.

[0025] According to another aspect of an embodiment of the present invention, a computer readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the region division method provided by an embodiment of the present invention is implemented.

[0026] According to another aspect of the embodiments of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method for dividing regions provided by the embodiments of the present invention is implemented.

[0027] An embodiment of the above invention has the following advantages or beneficial effects: it can initialize the initial set of regional division results based on the acquired location and logistics data of the target area, and combine the target offset distance set and the target set determined by the historical optimal solution, update the historical optimal solution and the initial set through loop iteration, and obtain the final target division result. Further, the regional division result is determined, and further splitting of the network points based on the existing regional division data is realized, which reduces the complexity of regional division and improves the efficiency of division.

[0028] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0030] Figure 1 is a schematic diagram of main steps of a method for dividing regions according to an embodiment of the present invention;

[0031] Figure 2 is a schematic flow chart of a method for dividing regions according to an embodiment of the present invention;

[0032] Figure 3 It is a network point coverage map before splitting and a network point coverage map after splitting;

[0033] Figure 4 is a schematic diagram of main modules of a device for dividing a region according to an embodiment of the present invention;

[0034] Figure 5 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0035] Figure 6 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0037] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, storage and other aspects of user personal information involved in the technical solution disclosed in the present invention are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information, network security and national security.

[0038] It should be noted that in the technical solution of the present invention, the collection, use, storage, sharing and transfer of user personal information involved are in compliance with the provisions of relevant laws and regulations, and it is necessary to inform the user and obtain the user's consent or authorization. When applicable, the user's personal information is de-identified and / or anonymized and / or encrypted.

[0039] Figure 1 FIG. 1 is a schematic diagram of main steps of a method for dividing regions according to an embodiment of the present invention. Figure 1 As shown, the region decomposition method of the embodiment of the present invention mainly includes the following steps S101 to S104.

[0040] Step S101, obtaining location data and logistics data of the target area.

[0041] Obtain the location data of the target area, including road fences, network point coordinates, etc. This data is the location data corresponding to the existing division scheme of the target area; obtain the logistics data of the target area, including order data, warehouse / store data, etc. This data is the logistics data corresponding to the location data, specifically, the logistics coordinates within each divided network point.

[0042] Optionally, the acquired data is preprocessed and serialized into a data structure required by the model input.

[0043] Step S102, generating an initial set of division results including a target quantity based on the location data and logistics data of the target area.

[0044] Initialize the CFLP model parameters, including iteration rounds, number of swarm particles, etc. Input the acquired location data of the target area into the initialized model to obtain a set of randomly initialized partitioning results. Among them, the use of the CFLP model is based on the discrete particle swarm algorithm (DSPO). The number of swarm particles set is the number of partitioning results output by the model, that is, the number of solutions in the set of partitioning results; the target number is the number of swarm particles. Among them, the constraints of the model include the maximum order constraint and the coverage area of ​​each network point in the partition result is a connected area.

[0045] Step S103, repeatedly performing the operations of determining a target offset distance set based on the initial set and the historical optimal solution, determining a target set based on the initial set, the target offset distance set and the preset offset condition, and updating the historical optimal solution and the initial set based on the target set, until a preset iteration stop condition is met, and determining the updated target set as the target partition result set.

[0046] The basic idea of ​​the particle swarm optimization (PSO) is to map the problem to be optimized into a multidimensional search space, and to find the optimal solution by continuously iteratively updating the speed and position of the particles. Each particle represents a solution, and searches in the search space based on its own experience and neighborhood information. The particle updates its position according to its current position and speed, and uses the individual historical best position (pbest) and the entire group historical best position (gbest) as references. Through continuous iterative updates, the particles gradually converge on the global optimal solution. The particle position X is an N-dimensional vector, where N is the number of road areas, and the value of each dimension is the network point code to which the current road area belongs, that is, a road area is represented as , i represents the i-th road area, j represents the i-th road area belongs to the j-th network point, then a partitioning scheme, that is, the position of the current particle can be expressed as:

[0047] ,

[0048] The target offset distance set is calculated based on the initial set and the historical optimal solution. Specifically, the offset distance of each particle in the initial set compared with the historical optimal solution (particle) is calculated respectively, and the offset distance of each particle is formed into a set to obtain the target offset distance set. The best historical position The historical optimal position can be an individual historical optimal position or a group historical optimal position. After determining the target offset distance set, the target set after the initial set offset is determined by combining the initial set and the preset offset condition. Recalculate according to the target set, determine the optimal solution in the target set, use the optimal solution in the target set as the updated historical optimal solution, and use the target set as the updated initial set. Repeat the above operation until the preset iteration stop condition is met, that is, when the number of executions of the above operation meets the preset iteration rounds, determine the updated target set as the target partition result set of the final output of the model.

[0049] Optionally, the particle's offset distance v is also an N-dimensional vector, expressed as:

[0050]

[0051] Where N represents the number of road areas. Indicates the destination network point code to be exchanged in the next step of the road area. Indicates that the current road area is not exchanged.

[0052] The determined target set is expressed as , the value of each dimension of the new position is expressed by the following formula:

[0053]

[0054] Step S104: determining a target area division scheme based on the target division result set.

[0055] The optimal solution is determined according to the determined target partition result set, and the network point partitioning scheme corresponding to the optimal solution is determined as the final partitioning scheme of the target area. Among them, the optimal solution is the population optimal solution.

[0056] According to the area division method provided by the embodiment of the present invention, it is possible to obtain an initial set of area division results based on the location and logistics data of the acquired target area, and to combine the target offset distance set and the target set determined by the historical optimal solution, and to update the historical optimal solution and the initial set through cyclic iteration to obtain the final target division result. Furthermore, the area division result is determined, and further splitting of the network points based on the existing area division data is realized, thereby reducing the complexity of area division and improving the efficiency of division.

[0057] Optionally, before updating the historical optimal solution and the initial set based on the target set, the method further includes: judging whether the target set meets the preset diversity condition and obtaining a judgment result; when the judgment result is that the preset diversity condition is not met, generating a random offset distance and updating the target set based on the random offset distance. Before updating the initial set according to the determined target set, it is also necessary to judge the diversity of the target set. Specifically, it is judged whether the particles in the target set meet the preset diversity condition and obtain the corresponding judgment result. When the judgment result is that the preset diversity condition is not met, it means that the particles in the particle group gradually converge and are prone to premature convergence problems. Therefore, a random offset distance is generated as a repulsion operator to enrich the diversity of particles. Specifically, the generated random offset distance is summed with the target set to obtain the summed set as the updated target set.

[0058] Optionally, based on the similarity between particles in the target set, it is determined whether the diversity condition is met. When the similarity is greater than a first threshold, it is determined that the diversity condition is not met; if it is not greater than the first threshold, it is determined that the diversity condition is met.

[0059] Optionally, the preset diversity condition is a preset diversity threshold condition, and judging whether the target set satisfies the preset diversity condition and obtaining a judgment result includes: calculating the diversity of the target set based on the target set and the historical optimal solution; when the diversity of the target set is less than or equal to the preset diversity threshold, determining the judgment result as not satisfying the preset diversity condition; when the diversity of the target set is greater than the preset diversity threshold, determining the judgment result as satisfying the preset diversity condition. The preset diversity condition may be a diversity threshold condition, specifically, a preset similarity threshold condition. Calculating the diversity of the target set based on the target set and the historical optimal solution is specifically to calculate the similarity of particles based on the target set and the historical optimal solution. and The similarity calculation formula is:

[0060]

[0061] in, Describes the location and The proportion of dimensions with the same data in It means and The data of all dimensions are the same. If it is equal to 0, the data of all dimensions are different, so Based on the individual diversity of this particle, the particle position The difference between the historical best position gbest and the individual best position pbest:

[0062]

[0063] Among them, if , then the three are exactly the same if The two are completely different, so .

[0064] Furthermore, the diversity of particle swarm It is defined as the mean of all particle diversity and is expressed as:

[0065]

[0066] Among them, size is the number of particles in the particle group, that is, the particle group size.

[0067] According to the region division method provided by the embodiment of the present invention, it is possible to initialize an initial set of division results based on the acquired position data of the target region, determine a target offset distance set based on the historical optimal solution, determine the target set in combination with the preset offset condition, and further update the historical optimal solution and the initial set for subsequent iterative operations. According to the final updated result, the target division result set and the corresponding division scheme are determined, so as to achieve rapid and accurate division of the target region. In addition, before updating the historical optimal solution and the initial set, it is necessary to determine whether the solution in the target set meets the diversity condition, and update the target set according to the result, so as to ensure the diversity of the target set and further improve the accuracy of the final region division result set.

[0068] Optionally, generating a random offset distance includes: randomly generating an offset distance; when the offset distance does not meet a preset offset condition, regenerating the offset distance. When generating the offset distance, since it is a randomly generated distance, there may be problems that do not meet the model constraints. For example, a partitioning scheme requires that the range of the same network point is connected, and there are no problems with enclaves or interspersed road areas, which can easily cause the failure of updating the target set and reduce the speed of population evolution. Therefore, setting corresponding preset offset conditions can ensure that the population, that is, the particle group, tends to evolve in an effective direction. Specifically, the preset offset condition requires that the randomly generated offset distance has a valid value only in the component speed of the network point boundary road area, and the other components are all empty operations.

[0069] According to the area division method of the embodiment of the present invention, when dividing the target area, it is possible to judge the diversity of the target set obtained including the division results, and when the corresponding preset diversity conditions are not met, the diversity of the target set is enriched by randomly generated offset distances, thereby improving the accuracy of the division results. At the same time, the random offset distances generated based on the preset offset conditions can ensure that the population evolves in an effective direction, reduce the width of the particles, that is, avoid a large number of invalid solutions, and improve the iteration speed of the model.

[0070] Optionally, updating the historical optimal solution based on the target set includes: determining the optimal solution in the target set based on the target set and the preset objective function; updating the historical optimal solution based on the optimal solution in the target set. pbest is the optimal solution of the current particle. After each iteration, it will be judged based on the cost. If the current cost is less than the historical optimal solution pbest, the current solution becomes pbest; gbest is the global optimal solution. After each round of iteration, the pbests of different particles are compared, and the solution with the minimum cost is compared with gbest. If the cost of the current round is smaller, the best pbest in the current round becomes gbest. Among them, the cost is calculated based on the objective function of the model.

[0071] Optionally, determining a target offset distance set based on an initial set and a historical optimal solution includes: determining a first offset distance set based on the initial set and the historical optimal solution; determining a second offset distance set based on the first offset distance set and a target random number; and calculating a target offset distance set based on the first offset distance set and the second offset distance set.

[0072] Based on the difference between each particle in the initial set and the historical optimal solution, the target offset distance set of each particle is obtained, that is, the calculation formula of the target offset distance v is:

[0073]

[0074] Among them, the calculation is compared and The value of the component in each dimension and , if they are the same, that is, the component velocity of the corresponding dimension Equal to -1, if different, make , The component velocity of any dimension in can be expressed as:

[0075]

[0076] To ensure particle diversity, the second offset distance set is determined based on the determined first offset distance set and the target random number, and the repulsion operator is expressed as , where c is a constant, , it has a certain probabilistic meaning. In actual calculation, a random number rand between 0 and 1 will be randomly generated. is the item in the first offset distance set, and Each component in Defined as:

[0077]

[0078] Furthermore, in order to reduce invalid evolution, the neighborhood search operator is: , each of which Defined as

[0079]

[0080] Where rand is a random number between 0 and 1. and When neither is -1, With equal probability, randomly select one from two. When one of them is -1, The one whose value is not -1.

[0081] According to the region division method provided by the embodiment of the present invention, it is possible to initialize the initial set of division results based on the acquired position data of the target region, determine the target offset distance set based on the historical optimal solution, and then determine the target set, so as to update the historical optimal solution and the initial set, so as to facilitate subsequent iterative operations. The division scheme is determined according to the final updated result, so that the target region is quickly and accurately divided on the basis of the original division scheme. In addition, before updating the historical optimal solution and the initial set, it is necessary to determine whether the target set meets the diversity condition. When the diversity condition is not met, the population diversity is increased by introducing the exclusion operator and the neighborhood search operator, so as to ensure the diversity of the target set, further improve the accuracy and division speed of the final region division result set, and achieve the generation of high-quality real-time division results.

[0082] like Figure 2 The flowchart of the method for dividing the area provided by the embodiment of the present invention is shown, including: preprocessing the location data and logistics data of the obtained outlets, initializing the model, specifically including: initializing the model parameters (iteration rounds, number of particles, number of sites before and after splitting); randomly initializing the division result according to the constraints. Determine whether the current model meets the iteration rounds. If it meets the requirements, the output result, that is, the division result of the target area, is calculated according to gbest, and the division result is output; if it does not meet the requirements, the offset distance v is calculated according to pbest and gbest, and the new particle state X is calculated, and the population diversity is calculated according to the new X. Determine whether the diversity condition is met. If it meets the requirements, the current particle state is updated, and new pbest and gbest are calculated according to the new X and the objective function, and return to determine whether the iteration rounds are met. If the diversity constraint is not met, the random offset distance generated by the repulsion operator is used to return the updated X.

[0083] like Figure 3 Shown are the dot coverage map before and after splitting, where one dot is split into two dots.

[0084] Figure 4 is a schematic diagram of a region division device 400 provided in an embodiment of the present invention, such as Figure 4 As shown, the region division device 400 according to the embodiment of the present invention mainly includes: an acquisition module 401 , an initialization module 402 and a determination module 403 .

[0085] An acquisition module 401 is used to acquire location data and logistics data of a target area;

[0086] Initialization module 402, used to generate an initial set of division results including a target quantity based on the location data and logistics data of the target area;

[0087] The determination module 403 is used to repeatedly perform operations of determining a target offset distance set based on an initial set and a historical optimal solution, determining a target set based on the initial set, the target offset distance set and a preset offset condition, and updating the historical optimal solution and the initial set based on the target set until a preset iteration stop condition is met, determining the updated target set as a target partition result set; and determining a partitioning scheme for the target area based on the target partition result set.

[0088] Optionally, the device also includes: a judgment module 404, used to judge whether the target set meets the preset diversity condition and obtain a judgment result; a generation module 405, used to generate a random offset distance and update the target set based on the random offset distance when the judgment result is that the preset diversity condition is not met.

[0089] Optionally, the preset diversity condition is a preset diversity threshold condition, and the judgment module 404 is used to judge whether the target set meets the preset diversity condition and obtain a judgment result, including: a calculation module 407, used to calculate the diversity of the target set based on the target set and the historical optimal solution; a determination module 403, used to determine that the judgment result does not meet the preset diversity condition when the diversity of the target set is less than or equal to the preset diversity threshold; when the diversity of the target set is greater than the preset diversity threshold, determine that the judgment result meets the preset diversity condition.

[0090] Optionally, the generation module 405 is used to generate a random offset distance, including: the generation module 405 is used to randomly generate an offset distance; when the offset distance does not meet a preset offset condition, regenerate the offset distance.

[0091] Optionally, the updating module 406 is used to update the historical optimal solution based on the target set, including: a determining module 403 is used to determine the optimal solution in the target set based on the target set and a preset objective function; and an updating module 406 is used to update the historical optimal solution based on the optimal solution in the target set.

[0092] Optionally, a determination module 403, used to determine a target offset distance set based on an initial set and a historical optimal solution, includes: a determination module 403, used to determine a first offset distance set based on the initial set and the historical optimal solution; a second offset distance set based on the first offset distance set and a target random number; and a calculation module 407, used to calculate a target offset distance set based on the first offset distance set and the second offset distance set.

[0093] According to the region division device provided by the embodiment of the present invention, it is possible to initialize the initial set of division results based on the acquired position data of the target region, determine the target offset distance set based on the historical optimal solution, and then determine the target set, so as to update the historical optimal solution and the initial set, so as to facilitate the subsequent iterative operation. The division scheme is determined according to the final updated result, so that the target region is quickly and accurately divided on the basis of the original division scheme. In addition, before updating the historical optimal solution and the initial set, it is necessary to determine whether the target set meets the diversity condition. When the diversity condition is not met, the population diversity is increased by introducing the exclusion operator and the neighborhood search operator, so as to ensure the diversity of the target set, further improve the accuracy and division speed of the final region division result set, and achieve the generation of high-quality real-time division results.

[0094] Figure 5 An exemplary system architecture 500 is shown to which the method for dividing regions or the device for dividing regions according to the embodiments of the present invention can be applied.

[0095] like Figure 5 As shown, system architecture 500 may include terminal devices 501, 502, 503, a network 504 and a server 505. Network 504 is used to provide a medium for communication links between terminal devices 501, 502, 503 and server 505. Network 504 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0096] Users can use terminal devices 501, 502, 503 to interact with server 505 through network 504 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 501, 502, 503, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0097] The terminal devices 501 , 502 , and 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0098] The server 505 may be a server that provides various services, such as a background management server that provides support for shopping websites browsed by users using the terminal devices 501, 502, and 503. The background management server may analyze and process the received data such as the area division request, and feed back the processing result (such as the division result - only an example) to the terminal device.

[0099] It should be noted that the region division method provided in the embodiment of the present invention is generally executed by the server 505 , and accordingly, the region division device is generally disposed in the server 505 .

[0100] It should be understood that Figure 5 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0101] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 of a terminal device or a server suitable for implementing an embodiment of the present invention. Figure 6 The terminal device or server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0102] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0103] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0104] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are executed.

[0105] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0106] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0107] The units or modules involved in the embodiments of the present invention may be implemented by software or hardware. The units or modules described may also be set in a processor. For example, they may be described as: a processor includes an acquisition module, an initialization module, and a determination module. The names of these units or modules do not, in some cases, constitute limitations on the units or modules themselves. For example, the acquisition module may also be described as a "module for acquiring location data and logistics data of a target area."

[0108] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes: obtaining location data and logistics data of a target area;

[0109] An initial set of partition results containing the target quantity is obtained by randomly initializing the location data and logistics data of the target area;

[0110] Repeat the operations of determining a target offset distance set based on an initial set and a historical optimal solution, determining a target set based on the initial set, the target offset distance set and a preset offset condition, and updating the historical optimal solution and the initial set based on the target set until a preset iteration round condition is met, and determining the updated target set as a target partition result set;

[0111] Determine the division scheme of the target area based on the target division result set

[0112] According to the technical solution of the embodiment of the present invention, it is possible to obtain an initial set of regional division results based on the location and logistics data of the acquired target area, and combine the target offset distance set and the target set determined by the historical optimal solution, and update the historical optimal solution and the initial set through loop iteration to obtain the final target division result. Furthermore, the regional division result is determined, and further splitting of the network points based on the existing regional division data is realized, which reduces the complexity of regional division and improves the efficiency of division.

[0113] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for dividing a region, characterized in that: include: Obtain location data and logistics data of the target area; generating an initial set of partitioning results including a target quantity based on the location data and logistics data of the target area; Repeating the operations of determining a target offset distance set based on the initial set and a historical optimal solution, determining a target set based on the initial set, the target offset distance set and a preset offset condition, and updating the historical optimal solution and the initial set based on the target set until a preset iteration stop condition is met, and determining the updated target set as a target partition result set; A partitioning scheme for the target area is determined based on the target partitioning result set.

2. The method according to claim 1, characterized in that Before updating the historical optimal solution and the initial set based on the target set, the method further includes: Determine whether the target set meets a preset diversity condition and obtain a determination result; When the judgment result is that the preset diversity condition is not met, a random offset distance is generated, and the target set is updated based on the random offset distance.

3. The method according to claim 2, characterized in that The preset diversity condition is a preset diversity threshold condition, and the determining whether the target set meets the preset diversity condition to obtain a determination result includes: Calculating the diversity of the target set based on the target set and the historical optimal solution; When the diversity of the target set is less than or equal to a preset diversity threshold, determining that the judgment result does not meet the preset diversity condition; When the diversity of the target set is greater than a preset diversity threshold, it is determined that the judgment result satisfies the preset diversity condition.

4. The method according to claim 2 or 3, characterized in that: The generating of the random offset distance comprises: Randomly generate offset distance; When the offset distance does not meet the preset offset condition, the offset distance is regenerated.

5. The method according to claim 1, characterized in that The updating of the historical optimal solution based on the target set includes: Determine the optimal solution in the target set based on the target set and a preset target function; The historical optimal solution is updated based on the optimal solution in the target set.

6. The method according to claim 4, characterized in that The determining of the target offset distance set based on the initial set and the historical optimal solution includes: Determine a first offset distance set based on the initial set and the historical optimal solution; Determine a second offset distance set based on the first offset distance set and a target random number; The target offset distance set is calculated based on the first offset distance set and the second offset distance set.

7. A device for dividing a region, characterized in that: include: An acquisition module is used to acquire location data and logistics data of a target area; An initialization module, used to generate an initial set of division results including a target quantity based on the location data and logistics data of the target area; a determination module, configured to repeatedly perform operations of determining a target offset distance set based on the initial set and a historical optimal solution, determining a target set based on the initial set, the target offset distance set and a preset offset condition, and updating the historical optimal solution and the initial set based on the target set, until a preset iteration stop condition is met, and determining the updated target set as a target partition result set; A partitioning scheme for the target area is determined based on the target partitioning result set.

8. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.