WO2020107583A1 - 基于改进蚁群算法的路线规划方法、装置、终端及介质 - Google Patents

基于改进蚁群算法的路线规划方法、装置、终端及介质 Download PDF

Info

Publication number
WO2020107583A1
WO2020107583A1 PCT/CN2018/122837 CN2018122837W WO2020107583A1 WO 2020107583 A1 WO2020107583 A1 WO 2020107583A1 CN 2018122837 W CN2018122837 W CN 2018122837W WO 2020107583 A1 WO2020107583 A1 WO 2020107583A1
Authority
WO
WIPO (PCT)
Prior art keywords
road
node
travel
factor
information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2018/122837
Other languages
English (en)
French (fr)
Inventor
李思原
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2020107583A1 publication Critical patent/WO2020107583A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"

Definitions

  • This application relates to the field of machine learning technology, in particular to a route planning method, device, terminal and medium based on an improved ant colony algorithm.
  • map navigation software on the market is based on the shortest distance or the shortest time, without considering the safety of user travel.
  • the main purpose of the present application is to provide a route planning method, device, terminal and medium based on an improved ant colony algorithm, aiming to solve the technical problem that the prior art map navigation lacks the safety of considering user travel.
  • the present application provides a route planning method based on an improved ant colony algorithm, including the following steps:
  • the shortest path from the travel start point to the travel end point is searched in the node matrix as the target path.
  • the present application also provides a route planning device based on an improved ant colony algorithm, including:
  • a receiving module configured to receive a route planning request input by a user, where the route planning request includes a trip start point and a trip end point;
  • An obtaining module configured to obtain the roads between the travel start point and the travel end point, and the safety factors of the roads;
  • a building module used to build a node matrix according to the travel starting point, travel ending point and each road;
  • the searching module is configured to search for the shortest path from the travel starting point to the travel ending point in the node matrix according to the improved ant colony algorithm and the safety factor of each road as the target path.
  • the present application also provides a terminal, the terminal includes: a memory, a processor, and computer-readable instructions stored on the memory and executable on the processor, the computer-readable instructions It is configured to implement the steps of the route planning method based on the improved ant colony algorithm as described above.
  • the present application also provides a storage medium on which computer-readable instructions are stored.
  • a route planning method based on the improved ant colony algorithm as described above is implemented A step of.
  • the route planning method, device, terminal and medium based on the improved ant colony algorithm of this embodiment by receiving a route planning request input by a user, the route planning request includes a trip starting point and a trip ending point, and acquiring the trip starting point and the trip end point Between the roads and the safety coefficients of the roads, construct a node matrix based on the travel start point, the travel end point, and the roads, and search for The shortest path from the travel start point to the travel end point is taken as the target path, while considering travel safety, the shortest journey or the shortest distance, solving the technical problem that the prior art map navigation lacks the consideration of user travel safety.
  • FIG. 1 is a schematic structural diagram of a terminal in a hardware operating environment involved in an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a first embodiment of a route planning method based on an improved ant colony algorithm in this application;
  • FIG. 3 is a schematic flowchart of a second embodiment of a route planning method based on an improved ant colony algorithm in this application;
  • FIG. 4 is a schematic flowchart of a third embodiment of a route planning method based on an improved ant colony algorithm in this application;
  • FIG. 5 is a schematic flowchart of a fourth embodiment of a route planning method based on an improved ant colony algorithm in this application;
  • FIG. 6 is a structural block diagram of a first embodiment of a route planning device based on an improved ant colony algorithm in this application.
  • FIG. 1 is a schematic diagram of a terminal structure of a hardware operating environment involved in a solution according to an embodiment of the present application.
  • the terminal may include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005.
  • the communication bus 1002 is used to implement connection communication between these components.
  • the user interface 1003 may include a display (Display), an input module such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
  • the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface).
  • the memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory.
  • RAM Random Access Memory
  • NVM Non-Volatile Memory
  • the memory 1005 may optionally be a storage device independent of the foregoing processor 1001.
  • FIG. 1 does not constitute a limitation on the terminal, and may include more or less components than those illustrated, or combine certain components, or arrange different components.
  • the memory 1005 as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module, and computer-readable instructions.
  • the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 in the terminal of the present application, and the memory 1005 may be provided in the terminal ,
  • the terminal calls the computer-readable instructions stored in the memory 1005 through the processor 1001, and executes the route planning method based on the improved ant colony algorithm provided by the embodiment of the present application.
  • FIG. 2 is a schematic flowchart of a first embodiment of a route planning method based on an improved ant colony algorithm.
  • the route planning method based on the improved ant colony algorithm includes the following steps:
  • Step S10 Receive a route planning request input by the user, where the route planning request includes a trip start point and a trip end point;
  • the execution subject of the method in this embodiment is a terminal.
  • the route planning request input by the user is usually the user's travel start point and travel end point input on the electronic map.
  • Electronic map is a visual digital map as a background, using text, pictures, icons, sound, animation, video and other multimedia as a means of expression, and hardware equipment as a processing platform to display modern information on the comprehensive appearance of cities, enterprises, tourist attractions and other regions product.
  • Step S20 Obtain the roads between the travel start point and the travel end point, and the safety factors of the roads;
  • each path is composed of many roads. After determining the roads from the starting point of the trip to the ending point of the trip Then, based on the safety factor of each road, find the path with the shortest distance, that is, the target path, which combines the safety factor, not just considering the distance problem.
  • the safety factor of each road can be obtained based on user evaluation, or based on street view image analysis. Street image analysis mainly analyzes the congestion rate, greening rate, and the width of roads, such as roads that are too narrow and sparsely populated, generally considered as safety factors The lower road.
  • the street view image can be acquired by a conventional acquisition method, or it can also be obtained by, for example, receiving a camera file sent by a collection vehicle from the camera file.
  • Step S30 Construct a node matrix according to the travel start point, travel end point and each road;
  • a node matrix is constructed, and the starting point and the ending point of travel are used as the starting node and the ending node, respectively, and then the nodes at the time of ant selection are determined according to the endpoints of each road from the starting node to the ending node. For example, if the starting point is A and the ending point is B, A to B may pass through C to D on the road, then C and D are nodes that the ants may choose.
  • Step S40 According to the improved ant colony algorithm and the safety factor of each road, search for the shortest path from the travel start point to the travel end point in the node matrix as the target path.
  • the step of searching the shortest path from the travel start point to the travel end point in the node matrix according to the improved ant colony algorithm and the safety factor of each road includes:
  • the probability of all ants visiting the next node from the current node in the node matrix is corrected until the ants have visited all nodes;
  • allowed k represents the set of destination nodes that Ant k may choose next;
  • represents the information heuristic factor
  • represents the expected heuristic factor
  • i the current node
  • j represents the next target node
  • s means node combination
  • ⁇ ij (t) represents the heuristic function
  • ⁇ ij (t) represents pheromone
  • ⁇ ij is the safety factor of the road corresponding to the next target node.
  • the improved ant colony algorithm corrects the probability of all ants visiting the next node from the current node in the node matrix by introducing a safety factor in the conventional ant colony algorithm.
  • a conventional ant colony algorithm can also be used, and the distance between nodes is considered in conjunction with the safety factor.
  • search in the node matrix The step of the shortest path from the start point of travel to the end point of travel includes:
  • the distance between the current node and the next node is corrected until the ants have visited all nodes;
  • the correction function is:
  • the improved ant colony algorithm is:
  • allowed k represents the set of destination nodes that Ant k may choose next;
  • represents the information heuristic factor
  • represents the expected heuristic factor
  • i the current node
  • j represents the next target node
  • s means node combination
  • ⁇ ij (t) represents the heuristic function
  • d ij represents the distance between two nodes
  • ⁇ ij (t) represents pheromone
  • ⁇ ij is the safety factor of the road corresponding to the next target node.
  • the improved ant colony algorithm in this scheme is to modify the distance between two nodes, and to modify the edge length (distance) of the current node and the next target node in combination with a safety factor The bigger. The probability of being selected will decrease.
  • the safety factor needs to be processed, for example, the default value of the safety factor is 1.
  • the improved ant colony algorithm is used to solve the optimization problem.
  • the basic principles of the ant colony algorithm are as follows:
  • the pheromone concentration is inversely proportional to the length of the path. When the later ants encounter the intersection again, they choose the path with the higher pheromone concentration;
  • the greater the probability of selection for example, the probability of selecting the next node A according to the basic ant colony algorithm is 0.8, the probability of selecting the next node B is 0.5, the probability of selecting the next node C is 0.2, and from the current node to the next
  • the safety factor of the road between a node A is 0.1, and the safety factor of the road from the current node to the next node B is 0.8, and the safety factor of the road from the current node to the next node C is 0.2.
  • the probability that the ants actually select A, B, and C after adopting this scheme considering the safety factor is 0.08, 0.4, and 0.04, respectively.
  • each ant in the ant colony algorithm has the following characteristics:
  • each ant leaves a pheromone on the branch (i, j) it passes through.
  • the probability of ants choosing cities is related to the distance between cities and the pheromone margin contained in the current connecting branch.
  • ants calculate the state transition probability based on the amount of information on each path and the heuristic information of the path.
  • ⁇ ij (t) is the amount of information on the edge (i, j) at time t;
  • allowed k ⁇ C-tabu k ⁇ represents the node that Ant k allows to select next;
  • is the information heuristic factor, indicating the relative importance of the trajectory
  • is the expected heuristic factor, which reflects the importance of the heuristic information in the ant selection path during the movement of the ant;
  • d ij represents the distance between two nodes, and its value range can be quantified as (1 ⁇ 10).
  • it may be a safety factor, the corrected d ij, for example, after the correction
  • this solution will perform iterations of the improved ant colony algorithm according to the actual situation until the number of iterations reaches the preset number of iterations (adjustable, such as 50, 100, etc.) , And then take the last acquired path as the final target path, that is, the path with the shortest distance combined with the safety factor.
  • FIG. 3 is a schematic flowchart of a second embodiment of a route planning method based on an improved ant colony algorithm in this application.
  • the step S20 includes:
  • Step S201 Acquire the roads between the travel start point and travel end point, and the information of the roads;
  • Each road information may be accident information, vehicle speed information, road factor information, user evaluation information, or a street view image of the road.
  • Step S202 Determine the safety factor of each road based on the information of each road.
  • the safety factor of each road is determined according to the information of each road, which can be determined by comprehensive consideration of accident information, vehicle speed information, and road factor information, or it can be combined with user evaluation information for each road
  • the safety factor can be modified. It can also be combined with the street view image of the road to analyze the road congestion rate, greening rate, etc. to determine the safety factor, or it can also consider the above information to analyze the safety factor of each road.
  • FIG. 4 is a schematic flowchart of a third embodiment of a route planning method based on an improved ant colony algorithm in this application.
  • the road information includes accident information, vehicle speed information, and road factor information.
  • the step S202 specifically includes:
  • Step S2021 According to the accident information, vehicle speed information and road factor information, determine the accident index, vehicle speed index and road factor index respectively;
  • the general accident information includes the number of population deaths and the number of vehicle accidents in the preset time period of the road. Due to the difference in the number of population and motor vehicles in the area where the road belongs, it is usually necessary to combine the road The number of people in the area and the number of motor vehicles determine the accident indicators.
  • Accident index number of deaths of the population within the preset time period of traffic accidents in the area to which the road belongs / (number of population in the area to which the road belongs ⁇ number of motor vehicles in the area mentioned by the road) 1/2 .
  • the vehicle speed information usually includes the average vehicle speed v1 and the design speed v of all kinds of cars under free-flow traffic, or the average vehicle speed v2 and design speed v of more than 75% of all kinds of cars under free-flow traffic.
  • the vehicle speed index
  • the higher the speed index the lower the road safety factor.
  • the road factor information includes the smoothness of the road, and the smoothness of the road will affect the driving comfort and safety of the vehicle. Generally, under the condition that other conditions are consistent, the better the road smoothness, the higher the road factor index and the higher the road safety factor.
  • Step S2022 Determine the safety factor of each road according to the accident index, vehicle speed index, and road factor index.
  • the safety factor of each road is inversely proportional to the accident index, inversely proportional to the speed index, and directly proportional to the road factor index.
  • Safety factor of each road ⁇ is the accident index
  • is the vehicle speed index
  • is the road factor.
  • the safety factor of each road may also include a road safety historical evaluation, which can be corrected by obtaining a user's evaluation of road safety; it may also include obtaining a street view image and determining the congestion rate by analyzing the street view image, Greening rate, etc., to determine the safety factor; it can also be a combination of street view images and road safety assessment, comprehensive consideration of the safety factor.
  • FIG. 5 is a schematic flowchart of a fourth embodiment of a route planning method based on an improved ant colony algorithm in this application.
  • the accident information includes the number of police officers, the number of road traffic accidents in the area, the number of road traffic accident deaths in the area, the number of motor vehicles in the area and the number of population in the area; in this embodiment, the Step S2021 specifically includes:
  • Step S2021a Determine the accident indicator according to the number of policemen issued by the public security, the number of road traffic accidents in the area, the number of road traffic accident deaths in the area, the number of motor vehicles in the area and the number of population in the area;
  • the step of determining the accident indicator based on the number of policemen issued by the police, the number of road traffic accidents in the area, the number of road traffic accident deaths in the area, the number of motor vehicles in the area, and the number of population in the area include:
  • represents the accident index
  • n the weight of the number of road traffic accident deaths in the area
  • N1 represents the number of policemen issued by the police
  • N2 represents the number of road traffic accidents in the area
  • N3 represents the number of road traffic accident deaths in the area
  • M1 represents the number of motor vehicles in the area
  • M2 represents the number of people in the area.
  • the embodiments of the present application also provide a computer-readable storage medium, and the computer-readable storage medium may be a non-volatile readable storage medium.
  • Computer-readable instructions are stored on the computer-readable storage medium.
  • the steps of the route planning method based on the improved ant colony algorithm described above are implemented.
  • FIG. 6 is a structural block diagram of a first embodiment of a route planning device based on an improved ant colony algorithm in this application.
  • the route planning device based on the improved ant colony algorithm proposed in the embodiments of the present application includes:
  • the receiving module 601 is configured to receive a route planning request input by a user, where the route planning request includes a trip start point and a trip end point;
  • the route planning request input by the user is usually the user inputting the travel start point and travel end point on the electronic map.
  • the obtaining module 602 is used to obtain the roads between the travel start point and the travel end point, and the safety factors of the roads;
  • the building module 603 is used to build a node matrix according to the travel start point, travel end point and each road;
  • the searching module 604 is configured to search for the shortest path from the travel start point to the travel end point in the node matrix according to the improved ant colony algorithm and the safety factor of each road as the target path.
  • the methods in the above embodiments can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware, but in many cases the former is better Implementation.
  • the technical solution of the present application can essentially be embodied in the form of a software product that contributes to the existing technology, and the computer software product is stored in a storage medium (such as read-only memory/random access)
  • the memory, magnetic disk, and optical disk include several instructions to enable a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to perform the methods described in the embodiments of the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Operations Research (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Navigation (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种基于改进蚁群算法的路线规划方法、装置、终端及介质,属于机器学习技术领域。该方法包括:接收用户输入的路线规划请求,所述路线规划请求包括出行起点和出行终点(S10),获取所述出行起点和出行终点之间的各道路、以及所述各道路的安全系数(S20),根据所述出行起点、出行终点以及各道路,构建节点矩阵(S30),根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径,作为目标路径(S40)。上述方法、装置、终端及介质通过在考虑出行安全性的同时,行程最短或距离最短,解决了现有技术地图导航缺乏考虑用户出行的安全性的技术问题。

Description

基于改进蚁群算法的路线规划方法、装置、终端及介质
本申请要求于2018年11月30日提交中国专利局、申请号为201811451979.9、发明名称为“基于改进蚁群算法的路线规划方法、装置、终端及介质”的中国专利申请的优先权,其全部内容通过引用结合在申请中。
技术领域
本申请涉及机器学习技术领域,尤其涉及一种基于改进蚁群算法的路线规划方法、装置、终端及介质。
背景技术
随着互联网技术的快速发展,智能终端产品越来越多的应用软件出现在人们的生活中,例如各种电子地图,用户只需在电子地图客户端中输入出行地和目的地,就能获取到电子地图服务器端为用户规划的出行路线,为用户提供导航服务。
然而,市面上的地图导航软件大部分是基于距离最短或时间最短,而没有考虑用户出行的安全性。
发明内容
本申请的主要目的在于提供了一种基于改进蚁群算法的路线规划方法、装置、终端及介质,旨在解决现有技术地图导航缺乏考虑用户出行的安全性的技术问题。
为实现上述目的,本申请提供了一种基于改进蚁群算法的路线规划方法,包括如下步骤:
接收用户输入的路线规划请求,所述路线规划请求包括出行起点和出行终点;
获取所述出行起点和出行终点之间的各道路、以及所述各道路的安全系数;
根据所述出行起点、出行终点以及各道路,构建节点矩阵;
根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径,作为目标路径。
基于上述发明目的,本申请还提供一种基于改进蚁群算法的路线规划装置,包括:
接收模块,用于接收用户输入的路线规划请求,所述路线规划请求包括出行起点和出行终点;
获取模块,用于获取所述出行起点和出行终点之间的各道路、以及所述各道路的安全系数;
构建模块,用于根据所述出行起点、出行终点以及各道路,构建节点矩阵;
查找模块,用于根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径,作为目标路径。
基于上述发明目的,本申请还提供一种终端,所述终端包括:存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机可读指令,所述计算机可读指令配置为实现如上述的基于改进蚁群算法的路线规划方法的步骤。
基于上述发明目的,本申请还提供一种存储介质,所述存储介质上存储有计算机可读指令,所述计算机可读指令被处理器执行时实现如上述的基于改进蚁群算法的路线规划方法的步骤。
本实施例的基于改进蚁群算法的路线规划方法、装置、终端及介质,通过接收用户输入的路线规划请求,所述路线规划请求包括出行起点和出行终点,获取所述出行起点和出行终点之间的各道路、以及所述各道路的安全系数,根据所述出行起点、出行终点以及各道路,构建节点矩阵,根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径,作为目标路径,在考虑出行安全性的同时,行程最短或距离最短,解决现有技术地图导航缺乏考虑用户出行的安全性的技术问题。
附图说明
图1是本申请实施例方案涉及的硬件运行环境的终端的结构示意图;
图2为本申请基于改进蚁群算法的路线规划方法第一实施例的流程示意图;
图3为本申请基于改进蚁群算法的路线规划方法第二实施例的流程示意图;
图4为本申请基于改进蚁群算法的路线规划方法第三实施例的流程示意图;
图5为本申请基于改进蚁群算法的路线规划方法第四实施例的流程示意图;
图6为本申请基于改进蚁群算法的路线规划装置第一实施例的结构框图。
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
应当理解,此处所描述的具体实施例仅用以解释本申请,并不用于限定本申请。
参照图1,图1为本申请实施例方案涉及的硬件运行环境的终端结构示意图。
如图1所示,该终端可以包括:处理器1001,例如中央处理器(Central Processing Unit,CPU),通信总线1002、用户接口1003,网络接口1004,存储器1005。其中,通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏(Display)、输入模块比如键盘(Keyboard),可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口(如无线保真(WIreless-FIdelity,WI-FI)接口)。存储器1005可以是高速的随机存取存储器(Random Access Memory,RAM)存储器,也可以是稳定的非易失性存储器(Non-Volatile Memory,NVM),例如磁盘存储器。存储器1005可选的还可以是独立于前述 处理器1001的存储装置。
本领域技术人员可以理解,图1中示出的结构并不构成对终端的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。
如图1所示,作为一种存储介质的存储器1005中可以包括操作系统、数据存储模块、网络通信模块、用户接口模块以及计算机可读指令。
在图1所示的终端中,网络接口1004主要用于与网络服务器进行数据通信;用户接口1003主要用于与用户进行数据交互;本申请终端中的处理器1001、存储器1005可以设置在终端中,所述终端通过处理器1001调用存储器1005中存储的计算机可读指令,并执行本申请实施例提供的基于改进蚁群算法的路线规划方法。
本申请实施例提供了一种基于改进蚁群算法的路线规划方法,参照图2,图2为本申请基于改进蚁群算法的路线规划方法第一实施例的流程示意图。
本实施例中,所述基于改进蚁群算法的路线规划方法包括如下步骤:
步骤S10:接收用户输入的路线规划请求,所述路线规划请求包括出行起点和出行终点;
需要说明的是,本实施例方法的执行主体为终端。用户输入的路线规划请求通常是用户在电子地图上输入出行的出行起点以及出行终点。
电子地图是一种可视化数字地图为背景,用文本、图片、图标、声音、动画、视频等多媒体为表现手段,以硬件设备为处理平台来展示城市、企业、旅游景点等区域综合面貌的现代信息产品。
步骤S20:获取所述出行起点和出行终点之间的各道路、以及所述各道路的安全系数;
需要说明的是,从所述出行起点到所述出行终点可能存在若干条可以通行的路径,而每条路径都是由很多道路组成,确定从所述出行起点到所述出行终点的各道路后,然后基于各道路的安全系数,查找 距离最短的路径,即目标路径,该目标路径结合了安全系数,而不仅是考虑距离问题。
各道路的安全系数可以是根据用户评价得到,也可以是基于街景图像分析得到,街景图像分析主要是分析拥堵率、绿化率、道路的宽窄,例如过窄且人烟稀少的道路,一般考虑为安全系数较低的道路。街景图像的获取可以采用常规的获取方式,也可以采用例如接收采集车发送的摄像文件,从摄像文件中得到。
步骤S30:根据所述出行起点、出行终点以及各道路,构建节点矩阵;
具体实现时,构建节点矩阵,将出行起点、出行终点分别作为起始节点、终止节点,而再根据自起始节点到终止节点的各道路的端点,确定蚂蚁选择时的节点。例如,起点为A,终点为B,A到B可能会经过道路上C到D,则C、D作为蚂蚁可能会选择的节点。
步骤S40:根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径,作为目标路径。
具体实现时,所述根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径的步骤,包括:
根据改进蚁群算法以及各道路的安全系数,修正所有蚂蚁在所述节点矩阵中自当前节点访问下一节点的概率,直至蚂蚁访问完所有节点;
计算每个蚂蚁经过的路径长度,将自所述出行起点至所述出行终点的最短路径作为目标路径;所述改进蚁群算法模型为:
Figure PCTCN2018122837-appb-000001
其中,
Figure PCTCN2018122837-appb-000002
为蚂蚁k选择j节点的概率;
allowed k表示蚂蚁k接下来可能会挑选的目的节点集合;
α表示信息启发式因子;
β表示期望启发式因子;
i表示当前节点;
j表示下一目标节点;
s表示节点结合;
η ij(t)表示启发函数;
τ ij(t)表示信息素;
λ ij为下一目标节点对应的道路的安全系数。
改进蚁群算法通过在常规蚁群算法中引入了安全系数,以此来修正所有蚂蚁在所述节点矩阵中自当前节点访问下一节点的概率。
在另一方案中,也可以常规的蚁群算法,而节点之间的距离结合安全系数考虑,具体实现时,所述根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径的步骤,包括:
根据改进蚁群算法,所有蚂蚁在所述节点矩阵中自当前节点访问下一节点;
根据各道路的安全系数以及修正函数,修正当前节点至下一节点的距离,直至蚂蚁访问完所有节点;
计算每个蚂蚁经过的路径长度,将自所述出行起点至所述出行终点的最短路径作为目标路径;其中,
修正函数为:
Figure PCTCN2018122837-appb-000003
所述改进蚁群算法为:
Figure PCTCN2018122837-appb-000004
其中,
Figure PCTCN2018122837-appb-000005
为蚂蚁k选择j节点的概率;
allowed k表示蚂蚁k接下来可能会挑选的目的节点集合;
α表示信息启发式因子;
β表示期望启发式因子;
i表示当前节点;
j表示下一目标节点;
s表示节点结合;
η ij(t)表示启发函数,
Figure PCTCN2018122837-appb-000006
d ij表示两个节点间的距离;
τ ij(t)表示信息素;
λ ij为下一目标节点对应的道路的安全系数。
本方案中改进蚁群算法是通过对两个节点间的距离进行修正,通过对当前节点与下一目标节点的边长(距离)结合安全系数来进行修
Figure PCTCN2018122837-appb-000007
越大。被选择的概率将减小。
通常需要对安全系数进行处理,例如安全系数默认值为1。
改进蚁群算法是用来寻解决寻优问题的,蚁群算法的基本原理大致如下:
1、蚂蚁在路径上释放信息素;
2、碰到还没走过的路口,就随机挑选一条路走。同时,释放与路径长度有关的信息素;
3、信息素浓度与路径长度成反比,后来的蚂蚁再次碰到该路口时,就选择信息素浓度较高路径;
4、最优路径上的信息素浓度越来越大;
5、最终蚁群找到最优寻食路径。
本方案通过在基本蚁群算法中加入了安全系数λ ij,在蚂蚁选择下一目标节点时的选择概率会结合安全系数来选择,蚂蚁选择下一目标节点时道路的安全系数λ ij越大,则选择的概率越大,例如,按基本蚁群算法选择下一节点A的概率为0.8,选择下一节点B的概率为0.5,选择下一节点C的概率为0.2,而从当前节点到下一节点A之间的道路的安全系数0.1,而从当前节点到下一节点B之间的道路的安 全系数为0.8,从当前节点到下一节点C之间的道路的安全系数为0.2,则采用本方案考虑安全系数后蚂蚁实际选择A、B、C的概率分别为0.08、0.4、0.04。
一般情况下,TSP问题求解中,假设蚁群算法中的每只蚂蚁具有以下特征:
每次移动,每只蚂蚁在其经过的支路(i,j)上都留下信息素。
蚂蚁选择城市的概率与城市之间的距离和当前连接支路上所包含的信息素余量有关。
为了强制蚂蚁进行合法的移动,直到一次移动完成后,才允许蚂蚁游走已访问过的城市(这可由禁忌表来控制);例如:用禁忌表tabuk(j=1,2,3,……,m)来记录蚂蚁k当前走过的城市,集合随着tabuk进化过程作动态调整。在搜索过程中,蚂蚁根据各条路径上的信息量以及路径的启发信息来计算状态转移概率。
结合到本方案中,
Figure PCTCN2018122837-appb-000008
表示在t时刻蚂蚁k考虑安全系数后由当前节点i转移到目标访问节点j的状态转移概率,
τ ij(t)为t时刻边(i,j)上的信息量;
allowed k={C-tabu k}表示蚂蚁k下一步允许选择的节点;
α为信息启发式因子,表示轨迹的相对重要性;
β为期望启发式因子,反映了蚂蚁在运动过程中启发信息在蚂蚁选择路径中的受重视程度;
Figure PCTCN2018122837-appb-000009
d ij表示两节点间的距离,其取值范围可量化为(1~10)。
优选地,在本方案中,也可以是考虑安全系数后,将d ij经过修正,例如修正后的
Figure PCTCN2018122837-appb-000010
同一道路安全系数越大,修正后的d ij’越小,被选择可能性将增大。
进一步地,为了保证最终获得的路线是最优的,本方案会根据实际情况进行改进蚁群算法的迭代,直至迭代次数达到预设的迭代次数(可调,如,50次、100次等),然后将最后一次获取的路径作为最 终的目标路径,即结合了安全系数,且距离最短的路径。
参考图3,图3为本申请基于改进蚁群算法的路线规划方法第二实施例的流程示意图。
基于上述第一实施例,在本实施例中,所述步骤S20,包括:
步骤S201:获取所述出行起点和出行终点之间的各道路、以及所述各道路的信息;
需要说明的是,用户输入的路线规划请求通常是用户在电子地图上输入出行的出行起点以及出行终点。各道路信息可以是事故信息、车速信息、道路因素信息,也可以是用户的评价信息,也可以是道路的街景图像。
步骤S202:根据所述各道路信息,确定各道路的安全系数。
具体实现时,根据所述各道路信息,确定各道路的安全系数,可以是根据事故信息、车速信息、道路因素信息综合考虑确定各道路的安全系数,也可以是结合用户的评价信息对各道路的安全系数进行修正,也可以是结合道路的街景图像分析道路的拥堵率,绿化率等来确定安全系数,也可以同时考虑以上信息综合分析各道路的安全系数。
参考图4,图4为本申请基于改进蚁群算法的路线规划方法第三实施例的流程示意图。
基于上述第二实施例,所述各道路信息包括事故信息、车速信息、道路因素信息,在本实施例中,所述步骤S202,具体包括:
步骤S2021:根据所述事故信息、车速信息、道路因素信息,分别确定事故指标、车速指标、道路因素指标;
需要说明的是,通常事故信息包括道路预设时间段内人口死亡数和预设时间段内车辆事故数,由于道路所属区域内人口数量、机动车的数量有所差异,故通常需要结合道路所属区域内人口数量、机动车的数量确定事故指标。
事故指标=道路所属区域交通事故预设时间段内人口死亡数/(道路所属区域内人口数量×道路所述区域内机动车的数量) 1/2
通常在其他条件一致的情况下,该道路所属区域事故指标越高,说明该道路安全系数越低。
车速信息通常包括自由流交通状态下各类小汽车平均车速v1与设计车速v,也可以是自由流交通状态下75%以上的各类小汽车的平均车速v2与设计车速v。
对应地,车速指标=|v1-v|或者|v2-v|。通常在其他条件一致的情况下,车速指标越高,则道路安全系数越低。
道路因素信息包括道路的平整度,道路的平整度将影响车辆行驶的舒适感以及安全性。通常在其他条件一致的情况下,道路的平整度越好,则道路因素指标越高,道路安全系数越高。
步骤S2022:根据所述事故指标、车速指标、道路因素指标,确定所述各道路的安全系数。
具体实现时,各道路的安全系数与事故指标呈反比,与车速指标呈反比,与道路因素指标呈正比。各道路的安全系数
Figure PCTCN2018122837-appb-000011
γ为事故指标,τ为车速指标,δ为道路因素。
另外,所述各道路的安全系数也可以包括道路安全历史评价,通过获取用户对道路安全的评价,来修正道路的安全系数;也可以包括通过获取街景图像,通过分析街景图像来确定拥堵率,绿化率等,以此判断安全系数;也可以是街景图像和道路安全评价结合起来,综合考虑安全系数。
参考图5,图5为本申请基于改进蚁群算法的路线规划方法第四实施例的流程示意图。
基于上述第三实施例,所述事故信息包括公安出警数、区域内道路交通事故数、区域内道路交通事故死亡人数、区域内机动车数量以及区域内人口数量;在本实施例中,所述步骤S2021,具体包括:
步骤S2021a:根据所述公安出警数、区域内道路交通事故数、区域内道路交通事故死亡人数、区域内机动车数量以及区域内人口数量,确定所述事故指标;
具体地,所述根据所述公安出警数、区域内道路交通事故数、区域内道路交通事故死亡人数、区域内机动车数量以及区域内人口数量, 确定所述事故指标的步骤,包括:
根据公式
Figure PCTCN2018122837-appb-000012
计算所述事故指标;
其中,γ表示事故指标;
n表示区域内道路交通事故死亡人数的权重;
N1表示公安出警数;
N2表示区域内道路交通事故数;
N3表示区域内道路交通事故死亡人数;
M1表示区域内机动车数量;
M2表示区域内人口数量。
此外,本申请实施例还提出一种计算机可读存储介质,所述计算机可读存储介质可以为非易失性可读存储介质。
所述计算机可读存储介质上存储有计算机可读指令,所述计算机可读指令被处理器执行时实现如上文所述的基于改进蚁群算法的路线规划方法的步骤。
参照图6,图6为本申请基于改进蚁群算法的路线规划装置第一实施例的结构框图。
如图6所示,本申请实施例提出的基于改进蚁群算法的路线规划装置包括:
接收模块601,用于接收用户输入的路线规划请求,所述路线规划请求包括出行起点和出行终点;
需要说明的是,用户输入的路线规划请求通常是用户在电子地图上输入出行的出行起点以及出行终点。
获取模块602,用于获取所述出行起点和出行终点之间的各道路、以及所述各道路的安全系数;
构建模块603,用于根据所述出行起点、出行终点以及各道路,构建节点矩阵;
查找模块604,用于根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径,作为目标路径。
本申请基于改进蚁群算法的路线规划装置的其他实施例或具体实现方式可参照上述各方法实施例,此处不再赘述。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者系统所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质(如只读存储器/随机存取存储器、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,空调器,或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种基于改进蚁群算法的路线规划方法,其特征在于,包括如下步骤:
    接收用户输入的路线规划请求,所述路线规划请求包括出行起点和出行终点;
    获取所述出行起点和出行终点之间的各道路、以及所述各道路的安全系数;
    根据所述出行起点、出行终点以及各道路,构建节点矩阵;
    根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径,作为目标路径。
  2. 如权利要求1所述的基于改进蚁群算法的路线规划方法,其特征在于,所述根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径的步骤,包括:
    根据改进蚁群算法以及各道路的安全系数,修正所有蚂蚁在所述节点矩阵中自当前节点访问下一节点的概率,直至蚂蚁访问完所有节点;
    计算每个蚂蚁经过的路径长度,将自所述出行起点至所述出行终点的最短路径作为目标路径;其中,所述改进蚁群算法为:
    Figure PCTCN2018122837-appb-100001
    其中,
    Figure PCTCN2018122837-appb-100002
    为蚂蚁k选择j节点的概率;allowed k表示蚂蚁k接下来可能会挑选的目的节点集合;α表示信息启发式因子;β表示期望启发式因子;i表示当前节点;j表示下一目标节点;s表示节点结合;η ij(t)表示启发函数;τ ij(t)表示信息素;λ ij为下一目标节点对应的道路的安全系数。
  3. 如权利要求1所述的基于改进蚁群算法的路线规划方法,其特征在于,所述根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径的步骤,包括:
    根据改进蚁群算法,所有蚂蚁在所述节点矩阵中自当前节点访问下一节点;
    根据各道路的安全系数以及修正函数,修正当前节点至下一节点的距离,直至蚂蚁访问完所有节点;
    计算每个蚂蚁经过的路径长度,将自所述出行起点至所述出行终点的最短路径作为目标路径;其中,
    修正函数为:
    Figure PCTCN2018122837-appb-100003
    所述改进蚁群算法为:
    Figure PCTCN2018122837-appb-100004
    其中,
    Figure PCTCN2018122837-appb-100005
    为蚂蚁k选择j节点的概率;allowed k表示蚂蚁k接下来可能会挑选的目的节点集合;α表示信息启发式因子;β表示期望启发式因子;i表示当前节点;j表示下一目标节点;s表示节点结合;η ij(t)表示启发函数,
    Figure PCTCN2018122837-appb-100006
    d ij表示两个节点间的距离;τ ij(t)表示信息素;λ ij为下一目标节点对应的道路的安全系数。
  4. 如权利要求1所述的基于改进蚁群算法的路线规划方法,其特征在于,所述获取所述出行起点和出行终点之间的各道路、以及所述各道路的安全系数的步骤,包括:
    获取所述出行起点和出行终点之间的各道路、以及所述各道路的信息;
    根据所述各道路信息,确定各道路的安全系数。
  5. 如权利要求4所述的基于改进蚁群算法的路线规划方法,其特征在于,所述各道路信息包括事故信息、车速信息、道路因素信息;
    相应地,所述根据所述各道路信息,确定各道路的安全系数的步骤,包括:
    根据所述事故信息、车速信息、道路因素信息,分别确定事故指标、车速指标、道路因素指标;
    根据所述事故指标、车速指标、道路因素指标,确定所述各道路的安全系数。
  6. 如权利要求5所述的基于改进蚁群算法的路线规划方法,其特征在于,所述事故信息包括公安出警数、区域内道路交通事故数、区域内道路交通事故死亡人数、区域内机动车数量以及区域内人口数量;
    相应地,所述根据所述事故信息、车速信息、道路因素信息,分别确定事故指标、车速指标、道路因素指标的步骤,包括:
    根据所述公安出警数、区域内道路交通事故数、区域内道路交通事故死亡人数、区域内机动车数量以及区域内人口数量,确定所述事故指标。
  7. 如权利要求6所述的基于改进蚁群算法的路线规划方法,其特征在于,所述根据所述公安出警数、区域内道路交通事故数、区域内道路交通事故死亡人数、区域内机动车数量以及区域内人口数量,确定所述事故指标的步骤,包括:
    根据公式
    Figure PCTCN2018122837-appb-100007
    计算所述事故指标;
    其中,γ表示事故指标;
    n表示区域内道路交通事故死亡人数的权重;
    N1表示公安出警数;
    N2表示区域内道路交通事故数;
    N3表示区域内道路交通事故死亡人数;
    M1表示区域内机动车数量;
    M2表示区域内人口数量。
  8. 一种基于改进蚁群算法的路线规划装置,其特征在于,包括:
    接收模块,用于接收用户输入的路线规划请求,所述路线规划请求包括出行起点和出行终点;
    获取模块,用于获取所述出行起点和出行终点之间的各道路、以及所述各道路的安全系数;
    构建模块,用于根据所述出行起点、出行终点以及各道路,构建节点矩阵;
    查找模块,用于根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径,作为目标路径。
  9. 一种终端,其特征在于,所述终端包括:存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机可读指令,所述计算机可读指令配置为实现以下步骤:
    接收用户输入的路线规划请求,所述路线规划请求包括出行起点和出行终点;
    获取所述出行起点和出行终点之间的各道路、以及所述各道路的安全系数;
    根据所述出行起点、出行终点以及各道路,构建节点矩阵;
    根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径,作为目标路径。
  10. 如权利要求9所述的终端,其特征在于,所述根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径的步骤,包括:
    根据改进蚁群算法以及各道路的安全系数,修正所有蚂蚁在所述节点矩阵中自当前节点访问下一节点的概率,直至蚂蚁访问完所有节点;
    计算每个蚂蚁经过的路径长度,将自所述出行起点至所述出行终点的最短路径作为目标路径;其中,所述改进蚁群算法为:
    Figure PCTCN2018122837-appb-100008
    其中,
    Figure PCTCN2018122837-appb-100009
    为蚂蚁k选择j节点的概率;allowed k表示蚂蚁k接下来可能会挑选的目的节点集合;α表示信息启发式因子;β表示期望启发式因子;i表示当前节点;j表示下一目标节点;s表示节点结合;η ij(t)表示启发函数;τ ij(t)表示信息素;λ ij为下一目标节点对应的道路的安全系数。
  11. 如权利要求9所述的终端,其特征在于,所述根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径的步骤,包括:
    根据改进蚁群算法,所有蚂蚁在所述节点矩阵中自当前节点访问下一节点;
    根据各道路的安全系数以及修正函数,修正当前节点至下一节点的距离,直至蚂蚁访问完所有节点;
    计算每个蚂蚁经过的路径长度,将自所述出行起点至所述出行终点的最短路径作为目标路径;其中,
    修正函数为:
    Figure PCTCN2018122837-appb-100010
    所述改进蚁群算法为:
    Figure PCTCN2018122837-appb-100011
    其中,
    Figure PCTCN2018122837-appb-100012
    为蚂蚁k选择j节点的概率;allowed k表示蚂蚁k接下来可能会挑选的目的节点集合;α表示信息启发式因子;β表示期望启发式因子;i表示当前节点;j表示下一目标节点;s表示节点结 合;η ij(t)表示启发函数,
    Figure PCTCN2018122837-appb-100013
    d ij表示两个节点间的距离;τ ij(t)表示信息素;λ ij为下一目标节点对应的道路的安全系数。
  12. 如权利要求9所述的终端,其特征在于,所述获取所述出行起点和出行终点之间的各道路、以及所述各道路的安全系数的步骤,包括:
    获取所述出行起点和出行终点之间的各道路、以及所述各道路的信息;
    根据所述各道路信息,确定各道路的安全系数。
  13. 如权利要求12所述的终端,其特征在于,所述各道路信息包括事故信息、车速信息、道路因素信息;
    相应地,所述根据所述各道路信息,确定各道路的安全系数的步骤,包括:
    根据所述事故信息、车速信息、道路因素信息,分别确定事故指标、车速指标、道路因素指标;
    根据所述事故指标、车速指标、道路因素指标,确定所述各道路的安全系数。
  14. 如权利要求13所述的终端,其特征在于,所述事故信息包括公安出警数、区域内道路交通事故数、区域内道路交通事故死亡人数、区域内机动车数量以及区域内人口数量;
    相应地,所述根据所述事故信息、车速信息、道路因素信息,分别确定事故指标、车速指标、道路因素指标的步骤,包括:
    根据所述公安出警数、区域内道路交通事故数、区域内道路交通事故死亡人数、区域内机动车数量以及区域内人口数量,确定所述事故指标。
  15. 如权利要求14所述的终端,其特征在于,所述根据所述公安出警数、区域内道路交通事故数、区域内道路交通事故死亡人数、区域内机动车数量以及区域内人口数量,确定所述事故指标的步骤,包括:
    根据公式
    Figure PCTCN2018122837-appb-100014
    计算所述事故指标;
    其中,γ表示事故指标;
    n表示区域内道路交通事故死亡人数的权重;
    N1表示公安出警数;
    N2表示区域内道路交通事故数;
    N3表示区域内道路交通事故死亡人数;
    M1表示区域内机动车数量;
    M2表示区域内人口数量。
  16. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质上存储有计算机可读指令,所述计算机可读指令被处理器执行时实现以下步骤:
    接收用户输入的路线规划请求,所述路线规划请求包括出行起点和出行终点;
    获取所述出行起点和出行终点之间的各道路、以及所述各道路的安全系数;
    根据所述出行起点、出行终点以及各道路,构建节点矩阵;
    根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径,作为目标路径。
  17. 如权利要求16所述的计算机可读存储介质,其特征在于,所述根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径的步骤,包括:
    根据改进蚁群算法以及各道路的安全系数,修正所有蚂蚁在所述节点矩阵中自当前节点访问下一节点的概率,直至蚂蚁访问完所有节点;
    计算每个蚂蚁经过的路径长度,将自所述出行起点至所述出行终点的最短路径作为目标路径;其中,所述改进蚁群算法为:
    Figure PCTCN2018122837-appb-100015
    其中,
    Figure PCTCN2018122837-appb-100016
    为蚂蚁k选择j节点的概率;allowed k表示蚂蚁k接下来可能会挑选的目的节点集合;α表示信息启发式因子;β表示期望启发式因子;i表示当前节点;j表示下一目标节点;s表示节点结合;η ij(t)表示启发函数;τ ij(t)表示信息素;λ ij为下一目标节点对应的道路的安全系数。
  18. 如权利要求17所述的计算机可读存储介质,其特征在于,所述根据改进蚁群算法以及各道路的安全系数,在所述节点矩阵中搜索自所述出行起点至所述出行终点的最短路径的步骤,包括:
    根据改进蚁群算法,所有蚂蚁在所述节点矩阵中自当前节点访问下一节点;
    根据各道路的安全系数以及修正函数,修正当前节点至下一节点的距离,直至蚂蚁访问完所有节点;
    计算每个蚂蚁经过的路径长度,将自所述出行起点至所述出行终点的最短路径作为目标路径;其中,
    修正函数为:
    Figure PCTCN2018122837-appb-100017
    所述改进蚁群算法为:
    Figure PCTCN2018122837-appb-100018
    其中,
    Figure PCTCN2018122837-appb-100019
    为蚂蚁k选择j节点的概率;allowed k表示蚂蚁k接下来可能会挑选的目的节点集合;α表示信息启发式因子;β表示期望启发式因子;i表示当前节点;j表示下一目标节点;s表示节点结 合;η ij(t)表示启发函数,
    Figure PCTCN2018122837-appb-100020
    d ij表示两个节点间的距离;τ ij(t)表示信息素;λ ij为下一目标节点对应的道路的安全系数。
  19. 如权利要求17所述的计算机可读存储介质,其特征在于,所述获取所述出行起点和出行终点之间的各道路、以及所述各道路的安全系数的步骤,包括:
    获取所述出行起点和出行终点之间的各道路、以及所述各道路的信息;
    根据所述各道路信息,确定各道路的安全系数。
  20. 如权利要求19所述的计算机可读存储介质,其特征在于,所述各道路信息包括事故信息、车速信息、道路因素信息;
    相应地,所述根据所述各道路信息,确定各道路的安全系数的步骤,包括:
    根据所述事故信息、车速信息、道路因素信息,分别确定事故指标、车速指标、道路因素指标;
    根据所述事故指标、车速指标、道路因素指标,确定所述各道路的安全系数。
PCT/CN2018/122837 2018-11-30 2018-12-21 基于改进蚁群算法的路线规划方法、装置、终端及介质 Ceased WO2020107583A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811451979.9 2018-11-30
CN201811451979.9A CN109726852A (zh) 2018-11-30 2018-11-30 基于改进蚁群算法的路线规划方法、装置、终端及介质

Publications (1)

Publication Number Publication Date
WO2020107583A1 true WO2020107583A1 (zh) 2020-06-04

Family

ID=66295178

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/122837 Ceased WO2020107583A1 (zh) 2018-11-30 2018-12-21 基于改进蚁群算法的路线规划方法、装置、终端及介质

Country Status (2)

Country Link
CN (1) CN109726852A (zh)
WO (1) WO2020107583A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113326980A (zh) * 2021-05-25 2021-08-31 汕头大学 一种改进蚁群算法的区域景点单程路线多目标规划方法
CN116245433A (zh) * 2022-09-08 2023-06-09 北京国电通网络技术有限公司 基于电力物资运输信息化踏勘的路线规划方法
CN121119330A (zh) * 2025-09-04 2025-12-12 南兴装备股份有限公司 一种基于蚁群混合路径寻优的线绕切结合切割方法及系统
CN121140833A (zh) * 2025-11-19 2025-12-16 浙江理工大学 基于动态信息素惩罚系数的汽车路径规划方法及应用

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109726851A (zh) * 2018-11-30 2019-05-07 平安科技(深圳)有限公司 基于改进蚁群算法的路线规划方法、装置、终端及介质
CN110909670B (zh) * 2019-11-21 2023-06-06 江苏理工学院 一种非结构化道路识别方法
CN112347313A (zh) * 2020-11-10 2021-02-09 中国科学院、水利部成都山地灾害与环境研究所 一种基于大数据的区位优势度路径分析方法
CN112396228A (zh) * 2020-11-16 2021-02-23 西安宇视信息科技有限公司 目标路径确定方法、装置、电子设备及介质
CN113094859B (zh) * 2021-04-20 2022-08-19 嘉兴泰豪装备技术有限公司 电气控制箱线路布线优化方法、系统及存储介质
CN113280828B (zh) * 2021-05-17 2022-11-22 建信金融科技有限责任公司 一种路径规划方法、装置、设备和存储介质
CN115203795B (zh) * 2022-07-11 2026-03-27 三明学院 一种建筑流线生成方法、装置、设备及存储介质
CN115265572A (zh) * 2022-07-25 2022-11-01 中国银行股份有限公司 一种路径生成方法、装置、设备及介质
CN115294791B (zh) * 2022-07-29 2024-11-22 广州新致信息科技有限公司 一种智慧城市用智能交通引导系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130204525A1 (en) * 2012-02-08 2013-08-08 Martin Pfeifle Method and system for routing using uncertainty data
CN106708063A (zh) * 2017-03-22 2017-05-24 江南大学 一种化工灾害现场搜救机器人路径规划方法
CN106779212A (zh) * 2016-12-13 2017-05-31 南京邮电大学 一种基于改进蚁群算法的城市旅游路线规划方法
CN106971245A (zh) * 2017-03-30 2017-07-21 广东工业大学 一种基于改进蚁群算法的路径确定方法及系统
CN108180914A (zh) * 2018-01-09 2018-06-19 昆明理工大学 一种基于蚁群改进和尖峰平滑的移动机器人路径规划方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105589461A (zh) * 2015-11-18 2016-05-18 南通大学 一种基于改进蚁群算法的泊车系统路径规划方法
CN106873599A (zh) * 2017-03-31 2017-06-20 深圳市靖洲科技有限公司 基于蚁群算法和极坐标变换的无人自行车路径规划方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130204525A1 (en) * 2012-02-08 2013-08-08 Martin Pfeifle Method and system for routing using uncertainty data
CN106779212A (zh) * 2016-12-13 2017-05-31 南京邮电大学 一种基于改进蚁群算法的城市旅游路线规划方法
CN106708063A (zh) * 2017-03-22 2017-05-24 江南大学 一种化工灾害现场搜救机器人路径规划方法
CN106971245A (zh) * 2017-03-30 2017-07-21 广东工业大学 一种基于改进蚁群算法的路径确定方法及系统
CN108180914A (zh) * 2018-01-09 2018-06-19 昆明理工大学 一种基于蚁群改进和尖峰平滑的移动机器人路径规划方法

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113326980A (zh) * 2021-05-25 2021-08-31 汕头大学 一种改进蚁群算法的区域景点单程路线多目标规划方法
CN116245433A (zh) * 2022-09-08 2023-06-09 北京国电通网络技术有限公司 基于电力物资运输信息化踏勘的路线规划方法
CN121119330A (zh) * 2025-09-04 2025-12-12 南兴装备股份有限公司 一种基于蚁群混合路径寻优的线绕切结合切割方法及系统
CN121140833A (zh) * 2025-11-19 2025-12-16 浙江理工大学 基于动态信息素惩罚系数的汽车路径规划方法及应用

Also Published As

Publication number Publication date
CN109726852A (zh) 2019-05-07

Similar Documents

Publication Publication Date Title
WO2020107583A1 (zh) 基于改进蚁群算法的路线规划方法、装置、终端及介质
Lee et al. Robust accessibility: Measuring accessibility based on travelers' heterogeneous strategies for managing travel time uncertainty
CN103718000B (zh) 实时地图数据更新系统和方法
JP6671406B2 (ja) 自動的に決定された出発点と選択された目的地との間のナビゲーション案内
CA2988260C (en) System and method for providing contextual information for a location
US10074276B2 (en) Method and apparatus for providing parking availability detection based on vehicle trajectory information
JP6601947B2 (ja) ナビゲーションシステム、ナビゲーション方法及びプログラム
US9057612B1 (en) Systems and methods for unified directions
KR102236869B1 (ko) 생활인프라 공급계획을 위한 접근성 평가 정보를 제공하는 방법
US20150377639A1 (en) Generating Travel Routes for Increased Visual Interest
US10209088B2 (en) Method and apparatus for route calculation considering potential mistakes
US11346683B2 (en) Method and apparatus for providing argumentative navigation routing
US10720049B2 (en) Method and system for generating traffic information to be used in map application executed on electronic device
CN114065055A (zh) 一种智能旅游路线推荐方法及其查询系统
CN113959442A (zh) 基于区域内交通预案路线规划的精细化导航方法
US20170059338A1 (en) Generating Travel Routes for Increased Visual Interest
JP5615777B2 (ja) 経路案内装置及び経路案内方法
WO2020107584A1 (zh) 基于改进蚁群算法的路线规划方法、装置、终端及介质
CN108710969A (zh) 一种旅游智能路径规划方法
JP2022050963A (ja) 旅程作成装置、旅程作成システム、旅程作成方法、及びコンピュータプログラム
US20260038365A1 (en) System and method for determining critical link segments in a geographical area
WO2012128011A1 (ja) 移動体管理システム、移動体管理サーバ、移動体管理方法および移動体管理プログラム
JP6573807B2 (ja) プログラム、情報処理装置、ナビゲーションシステム
US20220333943A1 (en) Method, apparatus, and computer program product for determining familiarity of a person within a geographic region
WO2023244265A1 (en) Improving route suggestions based on user health-related preferences

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18941722

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18941722

Country of ref document: EP

Kind code of ref document: A1