CN113865605A - AI-based urban disaster prevention risk avoidance path planning method and device - Google Patents
AI-based urban disaster prevention risk avoidance path planning method and device Download PDFInfo
- Publication number
- CN113865605A CN113865605A CN202111060937.4A CN202111060937A CN113865605A CN 113865605 A CN113865605 A CN 113865605A CN 202111060937 A CN202111060937 A CN 202111060937A CN 113865605 A CN113865605 A CN 113865605A
- Authority
- CN
- China
- Prior art keywords
- information
- refuge
- road network
- path
- road
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000002265 prevention Effects 0.000 title claims abstract description 22
- 238000012163 sequencing technique Methods 0.000 claims description 9
- 230000004308 accommodation Effects 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3461—Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types, segments such as motorways, toll roads, ferries
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses an AI-based urban disaster prevention and risk avoidance path planning method and device, wherein the method comprises the following steps: obtaining urban personnel information, refuge place information and map information, and matching a refuge place for each person according to the urban personnel information, the refuge place information and the map information; determining a first road network corresponding to the personnel according to the personnel information, the matched refuge place information and the map information, wherein the first road network is all road information between the personnel and the matched refuge places; and f optimal refuge paths for the people to reach the refuge are determined according to the personnel information, the matched refuge place information and the first road network. So as to realize that urban personnel can effectively and quickly escape to a refuge place after encountering natural disasters.
Description
Technical Field
The invention relates to the technical field of urban disaster prevention, in particular to an AI-based urban disaster prevention risk avoiding path planning method and device.
Background
With the advance of urbanization, the urban scale is continuously enlarged, the urban population is increased year by year, natural disasters such as flood, typhoon, earthquake, fire and the like bring more and more obvious harm to the city, especially to the central urban area with highly concentrated population, and in recent years, due to frequent occurrence of extreme weather, urban disaster prevention and avoidance are an important problem in urban development and construction. In urban development and construction, a large number of places for disaster avoidance, such as urban green lands, are built in China, so that the urban disaster avoidance problem is better solved. However, when a disaster occurs temporarily, the disaster often causes a panic mind to people, and people often cannot correctly judge where people should escape under an emergency situation, so that people cannot fast and effectively avoid natural disasters. Therefore, after a natural disaster occurs, how to scientifically, reasonably and orderly guide urban personnel to escape to a refuge place is a problem to be solved in an urban disaster emergency plan.
Disclosure of Invention
The invention provides an AI-based urban disaster prevention and danger avoidance path planning method and device, which are used for realizing effective and rapid escape of urban personnel to a refuge place after encountering natural disasters. The specific technical scheme is as follows:
in a first aspect, an embodiment of the present invention provides an AI-based urban disaster prevention and risk avoidance path planning method, including:
obtaining urban personnel information, refuge place information and map information, and matching a refuge place for each person according to the urban personnel information, the refuge place information and the map information;
determining a first road network corresponding to the personnel according to the personnel information, the matched refuge place information and the map information, wherein the first road network is all road information between the personnel and the matched refuge places;
and f optimal refuge paths for the people to reach the refuge are determined according to the personnel information, the matched refuge place information and the first road network, wherein f is a positive integer.
Optionally, the personnel information includes: the total number of urban personnel and urban personnel distribution information, and the refuge place information comprises: the position information of the refuge, the accommodation capacity of the refuge and the number of the refuge.
Optionally, the first road network includes information of all road intersections between people and refuge places matched with the people and information of each road, where the number of the roads in the first road network is m, and m is a positive integer.
Optionally, determining f optimal refuge paths for people to reach the refuge according to the people information, the refuge information matched with the people information, and the first road network, where f is a positive integer, and includes:
determining a departure node according to a first road network and the departure position information of personnel, wherein the departure node is a road intersection closest to the departure position of the personnel in the first road network;
determining a target node according to the first road network and the refuge place position information matched with the person, wherein the target node is a road intersection closest to the refuge place position matched with the person;
determining a first danger avoiding path according to the starting node, the destination node and the first road network, wherein the first danger avoiding path is the shortest path between the personnel and the refuge place;
determining m sub-optimal risk avoiding paths according to the starting node, the destination node and the first network, wherein the sub-optimal risk avoiding paths are risk avoiding paths except the first risk avoiding path;
sequencing the first risk avoiding path and the m sub-optimal risk avoiding paths according to the path length to obtain f front optimal risk avoiding paths;
wherein f is less than or equal to m.
Optionally, determining the suboptimal risk-avoiding path as a risk-avoiding path other than the first risk-avoiding path according to the departure node, the destination node, and the first road network, includes:
an obtaining step, namely deleting one piece of road information in a first road network to obtain a second road network;
determining a second risk avoiding path according to the starting node, the destination node and a second road network, wherein the second risk avoiding path is the shortest path from the starting node to the destination node in the second road network;
and circularly executing the obtaining step and the determining step, and deleting other road information in the first road network in sequence until m shortest risk avoidance paths are obtained.
In a second aspect, an embodiment of the present invention provides an AI-based urban disaster prevention and risk avoidance path planning apparatus, including;
the matching module is used for acquiring urban personnel information, refuge place information and map information and matching a refuge place for each person according to the urban personnel information, the refuge place information and the map information;
the first determining module is used for determining a first road network corresponding to the personnel according to the personnel information, the matched refuge place information and the map information, wherein the first road network is all road information between the personnel and the matched refuge places;
and the second determining module is used for determining f optimal refuge paths for the people to reach the refuge according to the personnel information, the matched refuge information and the first road network, wherein f is a positive integer.
Optionally, the personnel information includes: the total number of urban personnel and urban personnel distribution information, and the refuge place information comprises: the position information of the refuge, the accommodation capacity of the refuge and the number of the refuge.
Optionally, the first road network includes information of all road intersections between people and refuge places matched with the people and information of each road, where the number of the roads in the first road network is m, and m is a positive integer.
Optionally, the second determining module is configured to:
determining a departure node according to a first road network and the departure position information of personnel, wherein the departure node is a road intersection closest to the departure position of the personnel in the first road network;
determining a target node according to the first road network and the refuge place position information matched with the person, wherein the target node is a road intersection closest to the refuge place position matched with the person;
determining a first danger avoiding path according to the starting node, the destination node and the first road network, wherein the first danger avoiding path is the shortest path between the personnel and the refuge place;
determining m sub-optimal risk avoiding paths according to the starting node, the destination node and the first network, wherein the sub-optimal risk avoiding paths are risk avoiding paths except the first risk avoiding path;
sequencing the first risk avoiding path and the m sub-optimal risk avoiding paths according to the path length to obtain f front optimal risk avoiding paths;
wherein f is less than or equal to m.
Optionally, determining the suboptimal risk-avoiding path as a risk-avoiding path other than the first risk-avoiding path according to the departure node, the destination node, and the first road network, includes:
an obtaining step, namely deleting one piece of road information in a first road network to obtain a second road network;
determining a second risk avoiding path according to the starting node, the destination node and a second road network, wherein the second risk avoiding path is the shortest path from the starting node to the destination node in the second road network;
and circularly executing the obtaining step and the determining step, and deleting other road information in the first road network in sequence until m shortest risk avoidance paths are obtained.
As can be seen from the above, the method and apparatus for planning disaster prevention and risk avoidance paths in cities based on AI provided in the embodiments of the present invention includes: obtaining urban personnel information, refuge place information and map information, and matching a refuge place for each person according to the urban personnel information, the refuge place information and the map information; determining a first road network corresponding to the personnel according to the personnel information, the matched refuge place information and the map information, wherein the first road network is all road information between the personnel and the matched refuge places; and f optimal refuge paths for the people to reach the refuge are determined according to the personnel information, the matched refuge place information and the first road network, wherein f is a positive integer. The device includes: the matching module is used for acquiring urban personnel information, refuge place information and map information and matching a refuge place for each person according to the urban personnel information, the refuge place information and the map information; the first determining module is used for determining a first road network corresponding to the personnel according to the personnel information, the matched refuge place information and the map information, wherein the first road network is all road information between the personnel and the matched refuge places; and the second determining module is used for determining f optimal refuge paths for the people to reach the refuge according to the personnel information, the matched refuge information and the first road network, wherein f is a positive integer.
By applying the embodiment of the invention, urban personnel can be effectively and quickly guided to arrive at the refuge place, and a plurality of danger avoiding paths can be provided for the urban personnel for the selection of the people. Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.
The innovation points of the embodiment of the invention comprise:
1. when a city encounters a natural disaster, orderly urban personnel evacuation and escape are reasonably arranged, and the urban disaster prevention and escape method is an important link of urban disaster prevention and avoidance. In the embodiment of the invention, the danger avoiding path is pushed to the mobile terminal carried by urban personnel at any time, so that people can effectively and quickly escape to a refuge place with a clear target at the time of danger, the escape efficiency of the urban personnel is greatly improved, and the harm to the people caused by natural disasters is reduced as much as possible.
2. In the prior art, the Dijkstra algorithm is applied to obtain the shortest path from the starting point to the destination, but the algorithm can only provide one path. In real life, due to the influence of some factors, the shortest path is often not the best path, especially after a disaster, various unexpected situations occur, so that a plurality of risk avoiding paths need to be provided for urban personnel for people to select. In the embodiment of the invention, a K optimal path algorithm is introduced on the basis of a Dijkstra algorithm, so that a plurality of escape paths are obtained, and urban personnel can quickly and safely arrive at a refuge place.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is to be understood that the drawings in the following description are merely exemplary of some embodiments of the invention. For a person skilled in the art, without inventive effort, further figures can be obtained from these figures.
Fig. 1 is a schematic flow chart of an AI-based urban disaster prevention and risk avoidance path planning method according to an embodiment of the present invention;
fig. 2 is another schematic flow chart of the method for planning the urban disaster prevention and risk avoidance path based on the AI according to the embodiment of the present invention;
fig. 3 is a schematic structural diagram of an AI-based urban disaster prevention and risk avoidance path planning device according to an embodiment of the present invention.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the described embodiments are merely a few embodiments of the invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
It is to be noted that the terms "comprises" and "comprising" and any variations thereof in the embodiments and drawings of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
The invention provides an AI-based urban disaster prevention and risk avoidance path planning method and device. The following provides a detailed description of embodiments of the invention.
Fig. 1 is a schematic flow chart of an AI-based urban disaster prevention and risk avoidance path planning method according to an embodiment of the present invention. The method may comprise the steps of:
s101: urban personnel information, refuge place information and map information are obtained, and one refuge place is matched for each person according to the urban personnel information, the refuge place information and the map information.
Under the condition that a city encounters natural disasters such as flood, earthquake, fire and the like, the citizens need to be reasonably evacuated and escape routes of the citizens need to be guided. In the process of guiding the citizens to escape, the escape route map can be issued to the mobile phone of each citizen, so that the citizens can effectively and quickly escape to the refuge place according to the escape route map.
Herein, urban people refer to all people in a certain city, i.e., urban citizens. The city personnel information includes, but is not limited to, the total number of the city population, the distribution of the city population, the real-time location information of each citizen, and the like. Refuge places include, but are not limited to, urban greenbelts, such as parks, squares, and the like, but may also be exhibition centers, stadiums, and the like where large numbers of people can temporarily be accommodated to avoid disasters. The map information includes, but is not limited to, high-precision map information, real-time traffic information, and when a natural disaster occurs, a part of the road may be blocked or may not be accessible, for example, after inland inundation occurs, a part of the road is submerged. Therefore, road information which cannot pass through temporarily in real-time road conditions needs to be acquired so as to match suitable refuge places for citizens.
It should be noted that, if the current position of the citizen coincides with the position of the refuge place, only the indication information that the citizen can stay in place needs to be sent to the cell phone of the citizen, and the refuge path does not need to be pushed.
In an optional embodiment, the total number of urban people, the distribution information of urban people, and the refuge place information includes: the position information of the refuge, the accommodation capacity of the refuge and the number of the refuge.
It should be noted that the distribution information of the urban staff includes real-time location information of each citizen. And comprehensively judging according to factors such as urban personnel information, refuge place information, real-time map information and the like, and corresponding to a refuge place which is closer to the current position of the citizen and is more reasonable for each citizen.
S102: and determining a first road network corresponding to the person according to the person information, the matched refuge place information and the map information, wherein the first road network is all road information between the person and the matched refuge place.
The map information comprises all large and small roads and all road intersection information in a city, and the first road network is the information synthesis of all the roads and road intersections between the citizen and the matched refuge place, such as the position information of each road intersection, the position information of each road, the width and the length of each road, the number of the roads and the like. There may be multiple routes between each citizen's current location and its matching refuge location from the citizen's current location to the refuge. That is, in the first road network, there may be a plurality of paths for citizens to reach the refuge.
In an optional embodiment, the first road network includes all road intersection information and each piece of road information between the people and the matched refuge, wherein the number of the roads in the first road network is m, and m is a positive integer.
It should be noted that each piece of road information includes position information of each road and length information of each road.
S103: and determining f optimal refuge paths for the personnel to reach the refuge according to the personnel information, the refuge information matched with the personnel information and the first road network, wherein f is a positive integer.
Because various emergencies are easy to occur after a disaster comes, more than one danger avoiding path is provided for citizens, and the method is more favorable for quickly escaping to a safe place under complex and emergency conditions. It should be noted that the danger avoiding path and the escape route in the present application have the same meaning.
In an optional embodiment, a departure node is determined according to the first road network and the departure position information of the person, wherein the departure node is a road intersection closest to the departure position of the person in the first road network.
And determining a target node according to the first road network and the refuge place position information matched with the person, wherein the target node is a road intersection closest to the refuge place position matched with the person.
And determining a first danger avoiding path according to the starting node, the destination node and the first road network, wherein the first danger avoiding path is the shortest path between the personnel and the refuge place.
And determining m sub-optimal risk avoiding paths according to the starting node, the destination node and the first path network, wherein the sub-optimal risk avoiding paths are risk avoiding paths except the first risk avoiding path.
And sequencing the first risk avoiding path and the m sub-optimal risk avoiding paths according to the path length to obtain f front optimal risk avoiding paths, wherein f is less than or equal to m.
It should be noted that the road intersection in the first road network includes a departure node and a destination node. The shortest path between the citizens and the refuge place may be the optimal path for the citizens to reach the refuge place, but considering the congestion of partial road traffic and the complex practical situation of the alternate transformation of the main road and the auxiliary road of the road traffic, the shortest path is probably not the optimal escape path, so that other high-quality refuge paths besides the shortest path need to be provided. When there is only one path between the citizen and the refuge place, the steps related to the suboptimal refuge path are not required to be executed. The suboptimal risk avoidance path may be the shortest path in use, or may be the shortest path in a new road network graph obtained after deleting one road in the first road network.
In an optional embodiment, the obtaining step deletes one piece of road information in the first road network to obtain the second road network.
And a determining step, namely determining a second risk avoiding path according to the starting node, the destination node and the second network information, wherein the second risk avoiding path is the shortest path from the starting node to the destination node in the second network.
And circularly executing the obtaining step and the determining step, and deleting the information of other roads in the first road network in sequence until m shortest risk-avoiding paths are obtained.
The first road network includes m roads, 1 of the m roads is deleted, a new road network, that is, a second road network is obtained, and it should be noted that the second road network includes a departure node and a destination node. In one embodiment, the second road network may be obtained by sequentially deleting 1 road from the departure node. Each second road network is a road network obtained by deleting only 1 road from the first road network, that is, each second road network has m-1 roads, and m second road networks can be obtained because the first road network has m roads. And aiming at each second road network, calculating the shortest risk avoiding path in the second road network, obtaining the shortest path in each second road network, and finally obtaining m shortest risk avoiding paths.
Fig. 2 is another schematic flow chart of the method for planning an AI-based urban disaster prevention and risk avoidance path according to the embodiment of the present invention, where the method includes the following steps:
s201: urban personnel information, refuge place information and map information are obtained, and one refuge place is matched for each person according to the urban personnel information, the refuge place information and the map information.
When a natural disaster comes, the danger avoiding path can be pushed to the mobile terminal carried by the citizen at any time so as to guide the citizen to escape quickly. Each citizen can be allocated with a refuge place with a short distance according to the real-time map information, the real-time position information of the urban personnel and the like.
S202: and determining a first road network corresponding to the person according to the person information, the matched refuge place information and the map information, wherein the first road network is all road information between the person and the matched refuge place.
The most common path planning algorithm in the existing path planning algorithms at present is Dijkstra (Dijkstra) algorithm, which obtains the shortest path from a starting node to a target node by searching a road network formed by nodes and edge networks. The method specifically comprises the steps of carrying out repeated iterative computation based on a transfer length matrix between a starting node and a target node and list information of the shortest distance and the path between the currently searched starting node and the target node, and finally obtaining the shortest path between the starting node and the target node.
However, when encountering natural disasters, the actual situations of people are very complicated, so that only one risk avoiding path is provided, which is not beneficial to effective risk avoiding and escaping of citizens. Therefore, on the basis of the Dijkstra Algorithm, a K-short Path Algorithm (K-Algorithm) can be used for providing multiple danger avoiding paths for citizens to select.
And K, the optimal path algorithm can calculate a plurality of optimal paths, wherein the calculated optimal paths are K paths which are the paths with the minimum path length, the second smallest path length and the Kth smallest path length from the starting point to the end point, and a plurality of relatively optimal paths are obtained to form an optimal path set to meet the requirements of paths with different grades.
In the present embodiment, a weighted graph G ═ V ═ W where V denotes a set of all road intersections from the citizen departure position to the corresponding evacuation location position, and V ═ W1,v2,v3,…,vnN represents the total quantity of road intersections, n is more than or equal to 0, v1V is the road intersection closest to the citizen's departure position, i.e. the road intersection closest to the citizen's current positionnAt the intersection of the roads closest to the evacuation location corresponding to the citizen, E represents the set of all roads from the citizen's departure location to the corresponding evacuation location, W represents the set of all roads from the citizen's departure location to the corresponding evacuation location, and W is initialized to empty. In addition, sets P and D are set, the set P representing the slave v1To vnThe set of all nodes contained in a certain route, all the nodes are sequentially stored in the set according to the passing sequence, and the initialization is as follows: p ═ v1D denotes the slave node v1To vnIs initialized to D0And (0), obtaining the directed weighted graph according to the Dijkstra algorithm, namely the first road network.
S203: determining a departure node according to the first road network and the departure position information of the personnel, wherein the departure node is a road intersection closest to the departure position of the personnel in the first road network; and determining a target node according to the first road network and the refuge place position information matched with the person, wherein the target node is a road intersection closest to the refuge place position matched with the person.
For example, when a natural disaster occurs, a citizen is in a residential building, and a route in the residential building does not need to be planned, so that a danger avoiding path needs to take a road intersection closest to the citizen in a first road network as a starting point, current position information of the citizen is determined through a positioning system, and a starting node, namely v, is determined through the current position information of the citizen and the first road network1Is the starting node. Similarly, the road intersection nearest to the refuge is the destination node, i.e. vnFor the destination nodeThat is, the destination node is a node corresponding to the evacuation place in the first road network.
S204: and determining a first danger avoiding path according to the starting node, the destination node and the first road network, wherein the first danger avoiding path is the shortest path between the personnel and the refuge place.
In the directed weighted graph G, the secondary node v can be obtained according to the Dijkstra algorithm1To node vnThe shortest path of (2) is a path with the shortest distance from the starting position of a citizen to an evacuation place matched with the citizen, and the shortest path is a first danger avoiding path. However, in an emergency, there is a high possibility of other accidents, so that only one escape route is provided, which is not beneficial for citizens to avoid disasters, and multiple escape routes need to be provided, and 3 routes are generally selected.
Counting the number k of the shortest path, namely the edge of the first hedge path passing through the directed weighted G graph in turn0And the length of the first hedge path is D01I.e. the total length of all edges in the traversed directed weighted graph G, and at the same time, all nodes traversed are placed in the set P, and all edges traversed are sequentially stored in the set W.
S205: and deleting one piece of road information in the first road network to obtain a second road network.
In the first road network, there are m roads in total, starting from the departure node v1And firstly, deleting one road in the first road network in sequence to obtain a second road network with one less road relative to the first road network. Therefore, the ith (i ═ 1,2, …, m) road of the m roads is deleted, and the original network G graph, i.e., the first network directed weighted graph G, is changed to the directed weighted graph Gi。
S206: and determining a second risk avoiding path according to the starting node, the destination node and the second road network, wherein the second risk avoiding path is the shortest path from the starting node to the destination node in the second road network.
In directed weighted graph GiIn the method, a secondary node v is solved by utilizing a Dijkstra algorithm1To node vnThe shortest path of (a) to (b),and obtaining the second risk avoiding paths, and obtaining m second risk avoiding paths. Recording all nodes contained in the path and the length of the path, namely counting the directed weighted G of the second hedge path in sequenceiNumber of edges k traversed in the figureiAnd the length of the second hedge path is DiI.e. the traversed directed weighted graph GiThe total length of all edges, and at the same time, all nodes passing through are placed in the set P, and all edges passing through are sequentially stored in the set W.
S207: and circularly executing the obtaining step and the determining step, and deleting the information of other roads in the first road network in sequence until m shortest risk-avoiding paths are obtained.
The other roads in the set W are deleted in sequence, and steps S205 and S206 are repeated until the mth road is deleted. M directed weighted graphs G can be obtainediEach directed weighted graph GiCorresponding to 1 second risk avoiding path, namely, m second risk avoiding paths are arranged in the corresponding directed weighted graph GiThe shortest risk avoidance path in (1).
S208: and sequencing the first risk avoiding path and the m sub-optimal risk avoiding paths according to the path length to obtain the front f optimal risk avoiding paths.
And sequencing the first risk avoiding path and the other m sub-optimal risk avoiding paths, wherein the sub-optimal risk avoiding path is the second risk avoiding path, namely sequencing the m +1 optimal paths. The first f optimal paths with the shortest path may be selected. For example, the path with the top three ranking can be selected to be provided to the citizen as the escape path of the citizen, that is, f is 3, and f may also be other positive integers as long as the f number is not greater than the m number.
Corresponding to the method embodiment, the embodiment of the invention provides an AI-based urban disaster prevention and risk avoidance path planning device.
Fig. 3 is a schematic structural diagram of an AI-based urban disaster prevention and risk avoidance path planning device according to an embodiment of the present invention, where the device includes:
the matching module S301 is used for acquiring urban personnel information, refuge place information and map information, and matching a refuge place for each person according to the urban personnel information, the refuge place information and the map information.
Herein, urban people refer to all people in a certain city, i.e., urban citizens. The city personnel information includes, but is not limited to, the total number of the city population, the distribution of the city population, the real-time location information of each citizen, and the like. Refuge places include, but are not limited to, urban greenbelts, such as parks, squares, and the like, but may also be exhibition centers, stadiums, and the like where large numbers of people can temporarily be accommodated to avoid disasters. The map information includes, but is not limited to, high-precision map information, real-time traffic information, and when a natural disaster occurs, a part of the road may be blocked or may not be accessible, for example, after inland inundation occurs, a part of the road is submerged. Therefore, it is necessary to acquire information of roads that cannot pass through temporarily in real-time road conditions so as to match suitable refuge places for citizens around the roads that cannot pass through.
It should be noted that if the current position of the citizen coincides with the refuge place, only the indication information that the citizen can stay in place needs to be sent to the cell phone of the citizen, and the refuge path does not need to be pushed.
In an optional embodiment, the total number of urban people, the distribution information of urban people, and the refuge place information includes: the position information of the refuge, the accommodation capacity of the refuge and the number of the refuge.
It should be noted that the distribution information of the urban staff includes real-time location information of each citizen. According to the comprehensive judgment of the factors such as urban personnel information, refuge place information, namely real-time map information and the like, each citizen corresponds to a refuge place which is closer to the current position of the citizen and is more reasonable.
A first determining module S302, configured to determine, according to the person information, the evacuation location information matched with the person information, and the map information, a first road network corresponding to the person, where the first road network is all road information between the person and the evacuation location matched with the person.
The map information comprises all large and small roads and all road intersection information in a city, and the first road network is the information synthesis of all the roads and road intersections between the citizen and the matched refuge place, such as the position information of each road intersection, the position information of each road, the width and the length of each road, the number of the roads and the like. There may be multiple routes between each citizen's current location and its matching refuge location from the citizen's current location to the refuge. That is, in the first road network, there may be a plurality of paths for citizens to reach the refuge.
In an optional embodiment, the first road network includes all road intersection information and each piece of road information between the people and the matched refuge, wherein the number of the roads in the first road network is m, m is a positive integer
It should be noted that each piece of road information includes position information of each road and length information of each road.
A second determining module S303, configured to determine f optimal risk avoidance paths for the people to reach the refuge place according to the people information, the refuge place information matched with the people information, and the first road network, where f is a positive integer.
Because various emergencies are easy to occur after a disaster comes, more than one danger avoiding path is provided for citizens, and the method is more favorable for quickly escaping to a safe place under complex and emergency conditions. It should be noted that the danger avoiding path and the escape route in the present application have the same meaning.
In an optional embodiment, the second determining module is configured to determine a departure node according to the first road network and the departure location information of the person, where the departure node is a road intersection closest to the departure location of the person in the first road network.
And determining a target node according to the first road network and the refuge place position information matched with the person, wherein the target node is a road intersection closest to the refuge place position matched with the person.
And determining a first danger avoiding path according to the starting node, the destination node and the first road network, wherein the first danger avoiding path is the shortest path between the personnel and the refuge place.
And determining m sub-optimal risk avoiding paths according to the starting node, the destination node and the first path network, wherein the sub-optimal risk avoiding paths are risk avoiding paths except the first risk avoiding path.
And sequencing the first risk avoiding path and the m sub-optimal risk avoiding paths according to the path length to obtain f front optimal risk avoiding paths, wherein f is less than or equal to m.
It should be noted that the road intersection in the first road network includes a departure node and a destination node. The shortest path between the citizens and the refuge place may be the optimal path for the citizens to reach the refuge place, but considering the congestion of partial road traffic and the complex practical situation of the alternate transformation of the main road and the auxiliary road of the road traffic, the shortest path is probably not the optimal escape path, so that other high-quality refuge paths besides the shortest path need to be provided. When there is only one path between the citizen and the refuge place, the steps related to the suboptimal refuge path are not required to be executed. The suboptimal risk avoidance path may be the shortest path in use, or may be the shortest path in a new road network graph obtained after deleting one road in the first road network.
In an optional embodiment, the obtaining step deletes one piece of road information in the first road network to obtain the second road network.
And a determining step, namely determining a second risk avoiding path according to the starting node, the destination node and the second network information, wherein the second risk avoiding path is the shortest path from the starting node to the destination node in the second network.
And circularly executing the obtaining step and the determining step, and deleting the information of other roads in the first road network in sequence until m shortest risk-avoiding paths are obtained.
The first road network includes m roads, 1 of the m roads is deleted, a new road network, that is, a second road network is obtained, and it should be noted that the second road network includes a departure node and a destination node. In one embodiment, the second road network may be obtained by sequentially deleting 1 road from the departure node. Each second road network is a road network obtained by deleting only 1 road from the first road network, that is, each second road network has m-1 roads, and m second road networks can be obtained because the first road network has m roads. And aiming at each second road network, calculating the shortest risk avoiding path in the second road network, obtaining the shortest path in each second road network, and finally obtaining m shortest risk avoiding paths.
The system and apparatus embodiments correspond to the system embodiments, and have the same technical effects as the method embodiments, and for the specific description, refer to the method embodiments. The device embodiment is obtained based on the method embodiment, and for specific description, reference may be made to the method embodiment section, which is not described herein again. Those of ordinary skill in the art will understand that: the figures are merely schematic representations of one embodiment, and the blocks or flow diagrams in the figures are not necessarily required to practice the present invention.
Those of ordinary skill in the art will understand that: modules in the devices in the embodiments may be distributed in the devices in the embodiments according to the description of the embodiments, or may be located in one or more devices different from the embodiments with corresponding changes. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An AI-based urban disaster prevention risk avoidance path planning method is characterized by comprising the following steps:
obtaining urban personnel information, refuge place information and map information, and matching a refuge place for each person according to the urban personnel information, the refuge place information and the map information;
determining a first road network corresponding to the person according to the person information, the matched refuge place information and the map information, wherein the first road network is all road information between the person and the matched refuge place;
and determining f optimal refuge paths for the personnel to reach the refuge according to the personnel information, the refuge information matched with the personnel information and the first road network, wherein f is a positive integer.
2. The method of claim 1, wherein the people information comprises: the total number of urban personnel and urban personnel distribution information, and the refuge place information comprises: the position information of the refuge, the accommodation capacity of the refuge and the number of the refuge.
3. The method of claim 1, wherein said first road network comprises information of all road intersections between said persons and their matching refuges, information of each road, wherein the number of roads in said first road network is m, and m is a positive integer.
4. The method according to claim 1, wherein the determining f optimal refuge paths for the people to reach the refuge according to the people information and the matching refuge information thereof and the first road network, wherein f is a positive integer, comprises:
determining a departure node according to the first road network and the departure position information of the personnel, wherein the departure node is a road intersection closest to the departure position of the personnel in the first road network;
determining a target node according to the first road network and the refuge place position information matched with the person, wherein the target node is a road intersection closest to the refuge place position matched with the person;
determining a first danger avoiding path according to the starting node, the destination node and the first road network, wherein the first danger avoiding path is the shortest path between the personnel and the refuge place;
determining m sub-optimal risk avoiding paths according to the starting node, the destination node and the first network, wherein the sub-optimal risk avoiding paths are risk avoiding paths except the first risk avoiding path;
sequencing the first risk avoiding path and the m sub-optimal risk avoiding paths according to the path length to obtain f front optimal risk avoiding paths;
wherein f is less than or equal to m.
5. The method of claim 4, wherein determining the sub-optimal hedge path as a hedge path other than a first hedge path according to the departure node, the destination node, and the first road network comprises:
an obtaining step, namely deleting one piece of road information in the first road network to obtain a second road network;
determining a second risk avoiding path according to the starting node, the destination node and the second road network, wherein the second risk avoiding path is the shortest path from the starting node to the destination node in the second road network;
and circularly executing the obtaining step and the determining step, and deleting the information of other roads in the first road network in sequence until m shortest risk-avoiding paths are obtained.
6. An AI-based urban disaster prevention risk-avoiding path planning device, characterized in that the device comprises:
the matching module is used for acquiring urban personnel information, refuge place information and map information and matching a refuge place for each person according to the urban personnel information, the refuge place information and the map information;
the first determining module is used for determining a first road network corresponding to the person according to the person information, the matched refuge place information and the map information, wherein the first road network is all road information between the person and the matched refuge place;
and the second determining module is used for determining f optimal refuge paths for the personnel to reach the refuge according to the personnel information, the matched refuge place information and the first road network, wherein f is a positive integer.
7. The apparatus of claim 6, wherein the people information comprises: the total number of urban personnel and urban personnel distribution information, and the refuge place information comprises: the position information of the refuge, the accommodation capacity of the refuge and the number of the refuge.
8. The apparatus of claim 6, wherein said first road network comprises information of all road intersections between said persons and their matching refuges, information of each road, wherein the number of roads in said first road network is m, and m is a positive integer.
9. The apparatus of claim 6, wherein the second determination module is to:
determining a departure node according to the first road network and the departure position information of the personnel, wherein the departure node is a road intersection closest to the departure position of the personnel in the first road network;
determining a target node according to the first road network and the refuge place position information matched with the person, wherein the target node is a road intersection closest to the refuge place position matched with the person;
determining a first danger avoiding path according to the starting node, the destination node and the first road network, wherein the first danger avoiding path is the shortest path between the personnel and the refuge place;
determining m sub-optimal risk avoiding paths according to the starting node, the destination node and the first network, wherein the sub-optimal risk avoiding paths are risk avoiding paths except the first risk avoiding path;
sequencing the first risk avoiding path and the m sub-optimal risk avoiding paths according to the path length to obtain f front optimal risk avoiding paths;
wherein f is less than or equal to m.
10. The apparatus of claim 9, wherein the determining, according to the departure node, the destination node, and the first path network, that the sub-optimal hedge path is a hedge path other than a first hedge path comprises:
an obtaining step, namely deleting one piece of road information in the first road network to obtain a second road network;
determining a second risk avoiding path according to the starting node, the destination node and the second road network, wherein the second risk avoiding path is the shortest path from the starting node to the destination node in the second road network;
and circularly executing the obtaining step and the determining step, and deleting the information of other roads in the first road network in sequence until m shortest risk-avoiding paths are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111060937.4A CN113865605A (en) | 2021-09-10 | 2021-09-10 | AI-based urban disaster prevention risk avoidance path planning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111060937.4A CN113865605A (en) | 2021-09-10 | 2021-09-10 | AI-based urban disaster prevention risk avoidance path planning method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113865605A true CN113865605A (en) | 2021-12-31 |
Family
ID=78995270
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111060937.4A Pending CN113865605A (en) | 2021-09-10 | 2021-09-10 | AI-based urban disaster prevention risk avoidance path planning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113865605A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04326499A (en) * | 1991-04-26 | 1992-11-16 | Toshiba Corp | System for supporting escape guide |
| JP2006292402A (en) * | 2005-04-06 | 2006-10-26 | Xanavi Informatics Corp | Navigation device |
| JP2006323569A (en) * | 2005-05-18 | 2006-11-30 | Foundation Of River & Basin Integrated Communications Japan | Disaster prevention/evacuation action simulation system |
| WO2007018305A1 (en) * | 2005-08-08 | 2007-02-15 | Nec Corporation | Evacuation route information providing system, evacuation route information providing apparatus, evacuation route information providing method, and evacuation route information providing program |
| CN101183445A (en) * | 2007-12-20 | 2008-05-21 | 浙江大学 | Personnel evacuation method for municipal traffic under calamity outburst surroundings |
| CN103020744A (en) * | 2012-12-31 | 2013-04-03 | 中国科学技术大学 | Method for finding optimal traffic route under disastrous environments |
| CN103337162A (en) * | 2013-07-16 | 2013-10-02 | 四川大学 | Real-time planning and dynamic scheduling system for urban emergency rescue channel |
| CN104750895A (en) * | 2013-12-30 | 2015-07-01 | 深圳先进技术研究院 | Real-time city emergency evacuation simulating method and system based on mobile phone data |
| JP2016050922A (en) * | 2014-09-02 | 2016-04-11 | 日産自動車株式会社 | Disaster-time route providing apparatus and disaster-time route providing method |
| JP2018045519A (en) * | 2016-09-15 | 2018-03-22 | 株式会社日立製作所 | Evacuation guidance information provision device and evacuation guidance information provision method |
| CN111504298A (en) * | 2020-03-16 | 2020-08-07 | 深圳市城市公共安全技术研究院有限公司 | Emergency shelter guiding system and guiding method |
| JP2020173687A (en) * | 2019-04-12 | 2020-10-22 | アイシン・エィ・ダブリュ株式会社 | Evacuation route information providing device, communication terminal and computer program |
-
2021
- 2021-09-10 CN CN202111060937.4A patent/CN113865605A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH04326499A (en) * | 1991-04-26 | 1992-11-16 | Toshiba Corp | System for supporting escape guide |
| JP2006292402A (en) * | 2005-04-06 | 2006-10-26 | Xanavi Informatics Corp | Navigation device |
| JP2006323569A (en) * | 2005-05-18 | 2006-11-30 | Foundation Of River & Basin Integrated Communications Japan | Disaster prevention/evacuation action simulation system |
| WO2007018305A1 (en) * | 2005-08-08 | 2007-02-15 | Nec Corporation | Evacuation route information providing system, evacuation route information providing apparatus, evacuation route information providing method, and evacuation route information providing program |
| CN101183445A (en) * | 2007-12-20 | 2008-05-21 | 浙江大学 | Personnel evacuation method for municipal traffic under calamity outburst surroundings |
| CN103020744A (en) * | 2012-12-31 | 2013-04-03 | 中国科学技术大学 | Method for finding optimal traffic route under disastrous environments |
| CN103337162A (en) * | 2013-07-16 | 2013-10-02 | 四川大学 | Real-time planning and dynamic scheduling system for urban emergency rescue channel |
| CN104750895A (en) * | 2013-12-30 | 2015-07-01 | 深圳先进技术研究院 | Real-time city emergency evacuation simulating method and system based on mobile phone data |
| JP2016050922A (en) * | 2014-09-02 | 2016-04-11 | 日産自動車株式会社 | Disaster-time route providing apparatus and disaster-time route providing method |
| JP2018045519A (en) * | 2016-09-15 | 2018-03-22 | 株式会社日立製作所 | Evacuation guidance information provision device and evacuation guidance information provision method |
| JP2020173687A (en) * | 2019-04-12 | 2020-10-22 | アイシン・エィ・ダブリュ株式会社 | Evacuation route information providing device, communication terminal and computer program |
| CN111504298A (en) * | 2020-03-16 | 2020-08-07 | 深圳市城市公共安全技术研究院有限公司 | Emergency shelter guiding system and guiding method |
Non-Patent Citations (2)
| Title |
|---|
| 吴健宏 等: "基于GIS和Multi-Agent的城市应急疏散", 清华大学学报(自然科学版), vol. 50, no. 8 * |
| 周亚飞 等: "基于多目标规划的城市避难场所选址研究", 安全与环境学报, vol. 10, no. 3 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bayram et al. | Compromising system and user interests in shelter location and evacuation planning | |
| Cova et al. | Modelling community evacuation vulnerability using GIS | |
| JP6619714B2 (en) | Evacuation guidance information providing apparatus and evacuation guidance information providing method | |
| CN109033718B (en) | Dynamic emergency evacuation method for urban rail transit line failure | |
| CN105590289B (en) | A kind of URBAN EARTHQUAKE emergency evacuation Site Selection method | |
| Usman et al. | Application of agent-based model simulation for tsunami evacuation in Pacitan, Indonesia | |
| Borowska-Stefańska et al. | Changes concerning commute traffic distribution on a road network following the occurrence of a natural disaster–The example of a flood in the Mazovian Voivodeship (Eastern Poland) | |
| CN113486880A (en) | Image acquisition equipment arrangement method and device, electronic equipment and storage medium | |
| Hasnat et al. | EMERGENCY RESPONSE DURING DISASTROUS SITUATION IN DENSELY POPULATED URBAN AREAS: A GIS BASED APPROACH. | |
| Rathore et al. | A routing model for emergency vehicles using the real time traffic data | |
| CN113865605A (en) | AI-based urban disaster prevention risk avoidance path planning method and device | |
| CN110807287B (en) | Construction method for dividing service grids in emergency repair point arrangement scene based on finite element grids | |
| Baharmand et al. | A Framework for Shelter Location Decisions by Ant Colony Optimization. | |
| Hirokawa et al. | Access time of emergency vehicles under the condition of street blockages after a large earthquake | |
| JP2003044969A (en) | Network system for emergency countermeasure | |
| Hailin et al. | Modeling of evacuations to no-notice event by public transit system | |
| CN112465265A (en) | Digital map-based fire station construction site selection method | |
| Yao et al. | The Emergency Accessibility Analysis based on Traffic Big Data and Flood Scenario Simulation in the context of Shanghai Hotel industry | |
| Thanh et al. | Comparative study on going to evacuation shelters in school districts and the nearest shelter in the city-A case study of Kanazawa city, Japan | |
| CN104851283B (en) | The method and apparatus that urban transportation strategical planning scheme is automatically generated | |
| Mazur | Hypothetical accident in Polish nuclear power plant. Worst case scenario for main Polish cities | |
| KR102443937B1 (en) | Optimal Area Analysis Method and Device for Responding to Forest Fires, and Medium Being Recorded with Program for Executing the Method | |
| Davoodi et al. | A GIS based fire station site selection using network analysis and set covering location problem (case study: Tehran, Iran) | |
| Kurniawan et al. | Tsunami Evacuation Planning as a tool for Tsunami Risk Reduction: A case study in Palu Bay, Central Sulawesi | |
| Urfalı et al. | Determining smart intersections for smart city applications using multi-criteria decision-making techniques |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |