CN114510545A - Evacuation path determination method and device, electronic equipment and storage medium - Google Patents
Evacuation path determination method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114510545A CN114510545A CN202210112873.6A CN202210112873A CN114510545A CN 114510545 A CN114510545 A CN 114510545A CN 202210112873 A CN202210112873 A CN 202210112873A CN 114510545 A CN114510545 A CN 114510545A
- Authority
- CN
- China
- Prior art keywords
- accident
- target
- information
- area
- scene
- 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 59
- 238000003860 storage Methods 0.000 title claims abstract description 19
- 230000007613 environmental effect Effects 0.000 claims description 19
- 230000008901 benefit Effects 0.000 claims description 17
- 230000015654 memory Effects 0.000 claims description 15
- 230000000875 corresponding effect Effects 0.000 claims description 14
- 230000002596 correlated effect Effects 0.000 claims description 7
- 231100001261 hazardous Toxicity 0.000 claims description 2
- 238000013528 artificial neural network Methods 0.000 description 22
- 238000004422 calculation algorithm Methods 0.000 description 19
- 230000009471 action Effects 0.000 description 14
- 238000004088 simulation Methods 0.000 description 14
- 238000012549 training Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 239000000779 smoke Substances 0.000 description 8
- 230000008859 change Effects 0.000 description 7
- 230000033001 locomotion Effects 0.000 description 7
- 230000002787 reinforcement Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000002485 combustion reaction Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000003491 array Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 230000004888 barrier function Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000005485 electric heating Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Remote Sensing (AREA)
- Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Alarm Systems (AREA)
Abstract
The embodiment of the application discloses an evacuation path determining method and device, electronic equipment and a storage medium. The evacuation path determination method includes: inputting a first model according to the building layout information and accident information of an accident site, and generating accident map information at the current moment; wherein the accident map information indicates at least whether different areas of the accident scene are passable; acquiring distribution condition information of the accident scene target and exit information of a safety exit; determining relative position information between the target and the safety exit according to the distribution condition information; and obtaining a safe evacuation path of the target leaving the accident scene according to the accident map information, the relative position information and a second model. Therefore, the safe evacuation path can be determined according to the actual situation of the accident site, the distribution condition of the target and the position of the safe exit, and the method has strong applicability.
Description
Technical Field
The present disclosure relates to the field of information technologies, and in particular, to a method and an apparatus for determining an evacuation path, an electronic device, and a storage medium.
Background
With the increasingly complex internal structure of public places and the increasingly large building scale, the safety of public places becomes a problem which cannot be ignored. Accidents such as fire, collapse and the like are one of the great disasters threatening the safety of public places, and the accidents easily cause property and personnel safety, so that the personnel in the building can be evacuated in time to at least reduce casualties.
Disclosure of Invention
In view of the above, embodiments of the present application are intended to provide an evacuation path determining method, an evacuation path determining device, an electronic device, and a storage medium.
The technical scheme of the application is realized as follows:
in a first aspect, an embodiment of the present application provides an evacuation path determining method, including:
inputting a first model according to the building layout information and accident information of an accident site, and generating accident map information at the current moment; wherein the accident map information indicates at least whether different areas of the accident scene are passable;
acquiring distribution condition information of the accident scene target and exit information of a safety exit;
determining relative position information between the target and the safety exit according to the distribution condition information;
and obtaining a safe evacuation path of the target leaving the accident scene according to the accident map information, the relative position information and a second model.
Based on the above scheme, the method further comprises:
and after the moving condition of the target according to the safe evacuation path meets a first condition, acquiring the distribution condition information of the target on the accident site again.
Based on the above scheme, the reacquiring the distribution status information of the accident scene target after the moving status of the target according to the safe evacuation path meets the first condition includes:
after the moving condition of the target according to the safe evacuation path meets the first condition, determining whether the relative position relation between the target and the safe exit meets a second condition;
and if the relative position relation between the target and the safety exit does not meet the second condition, acquiring the distribution condition information of the accident site target again.
Based on the above scheme, the method further comprises:
stopping the determination of the safe evacuation path if the relative position between the target and the safe exit satisfies the second condition.
Based on the above solution, the obtaining a safe evacuation path of the target leaving the accident scene according to the accident map information, the relative position information, and the second model includes:
according to the distribution condition information, determining environmental information of the area where the target is located from the accident map information;
and inputting the environmental information and the relative position information into the second model to obtain a safe evacuation path, which is output by the second model and used for the target to leave the accident scene.
Based on the above scheme, the inputting the environmental information and the relative position information into the second model to obtain the safe evacuation path of the target leaving the accident scene, which is output by the second model, includes:
determining a plurality of alternative moving paths meeting safety conditions according to the accident map information and the relative position information;
when a plurality of alternative moving paths exist, selecting the alternative moving path with the maximum safety benefit as the safety evacuation path; wherein the security benefits have a particular one of:
the safety benefit is negatively related to the distance from the target to the safety exit according to the corresponding alternative moving path;
the safety gains are inversely related to the accident occurrence rate predicted when the target moves to the safety exit according to the corresponding alternative moving path;
the safety gain is positively correlated with the probability that the target successfully reaches the safety exit according to the corresponding alternative moving path.
Based on the scheme, the distribution condition information of the target indicates that:
each of the target distribution locations and/or the number of targets located within the accident scene;
the environment information at least indicates the area type of an adjacent area of the position where the target is located;
the region types include: a traffic zone and a non-traffic zone outside the traffic zone.
Based on the scheme, the non-passing area comprises at least one of the following parts:
an obstacle area in which an area where obstacles are stacked to hinder passage;
accident area, area where the accident site is located;
and congestion areas, which contain areas with the target number exceeding a preset number.
Based on the above scheme, the method further comprises:
acquiring accident parameters of the accident scene;
and determining whether the adjacent area of the position where the target is located is the accident area or not according to the accident parameters.
Based on the above scheme, the accident parameter includes at least one of the following:
fire parameters;
collapse parameters;
and (4) flood parameters.
Based on the scheme, the accident scene is a fire scene;
the acquiring of the accident parameters of the accident scene comprises:
acquiring the type of a fire source of the fire scene, the spatial parameter of a space where the fire source is located and the heat release rate of the fire source, wherein the spatial parameter of the space where the fire source is located indicates the ignition point position of the fire source and/or the distribution condition of combustibles in the space where the fire source is located.
Based on the above scheme, the determining whether the adjacent area of the position where the target is located is the accident area according to the accident parameter includes:
inputting a third model according to the type of the fire source of the fire scene, the space parameters of the space where the fire source is located and the heat release rate of the fire source to obtain an output result;
acquiring the temperature and/or visibility of each area of the fire scene according to the output result;
determining a dangerous area of the fire scene according to the temperature and/or visibility;
and determining whether the adjacent area of the position where the target is located is the accident area or not according to the dangerous area.
Based on the above scheme, the determining the dangerous area of the fire scene according to the temperature and/or visibility includes:
and when the temperature exceeds a first threshold value and/or when the visibility is lower than a second threshold value, determining that the adjacent area of the position where the target is located is a dangerous area of the fire scene.
In a second aspect, an embodiment of the present application provides an evacuation path determining device, including:
the generating module is used for inputting a first model according to the building layout information and the accident information of the accident site and generating accident map information at the current moment; wherein the accident map information indicates at least whether different areas of the accident scene are passable;
the first acquisition module is used for acquiring the distribution condition information of the accident scene target and the exit information of a safety exit;
the first determining module is used for determining the relative position information between the target and the safety exit according to the distribution condition information;
and the obtaining module is used for obtaining the safe evacuation path of the target leaving the accident scene according to the accident map information, the relative position information and the second model.
In a third aspect, an embodiment of the present application provides an electronic device, including:
a memory storing computer readable instructions;
and the processor is connected with the memory and used for realizing the method provided by any technical scheme of the first aspect by executing the computer-executable instructions stored on the memory.
In a fourth aspect, an embodiment of the present application provides a computer storage medium, where the computer storage medium stores computer-executable instructions, and after the computer-executable instructions are executed, the method provided in any technical solution of the first aspect can be implemented.
The evacuation path determining method, the evacuation path determining device, the electronic equipment and the storage medium provided by the embodiment of the application can input the first model according to the building layout information and the accident information of an accident site to generate the accident map information at the current moment; wherein the accident map information indicates at least whether different areas of the accident scene are passable; acquiring distribution condition information of the accident scene target and exit information of a safety exit; determining relative position information between the target and the safety exit according to the distribution condition information; and obtaining a safe evacuation path of the target leaving the accident scene according to the accident map information, the relative position information and a second model. Therefore, according to the building layout information and the accident information of the accident site, the disaster situations of different areas in the whole building can be known through the first model, so that the optimal evacuation path can be given by combining the position of the target, the position of a safety exit and the like, and compared with the judgment of the disaster situations which can be seen by the target according to the sight of the target, the casualties caused by the fact that the target can go to the area with more serious accidents can be reduced, and the loss caused by the accidents is reduced.
Drawings
Fig. 1 is a schematic flowchart of an evacuation path determining method according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of another evacuation path determining method according to an embodiment of the present application;
fig. 3 is a schematic flowchart of a fire evacuation simulation method based on deep reinforcement learning according to an embodiment of the present application;
FIG. 4 is a schematic diagram of a fire scene model established by using fire dynamics simulation software according to an embodiment of the present application;
fig. 5 is a schematic diagram of a gridding simulation model of an evacuation scene according to an embodiment of the present application;
fig. 6 is a schematic diagram of evacuation of people according to an embodiment of the present application;
fig. 7 is a schematic diagram illustrating evacuation ending according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an evacuation path determining device according to an embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
So that the manner in which the features and aspects of the present application can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to embodiments, some of which are illustrated in the appended drawings.
As shown in fig. 1, an evacuation path determining method according to an embodiment of the present application includes:
step S110: inputting a first model according to the building layout information and accident information of an accident site, and generating accident map information at the current moment; wherein the accident map information indicates at least whether different areas of the accident scene are passable;
step S120: acquiring distribution condition information of the accident scene target and exit information of a safety exit;
step S130: determining relative position information between the target and the safety exit according to the distribution condition information;
step S140: and obtaining a safe evacuation path of the target leaving the accident scene according to the accident map information, the relative position information and a second model.
The accident scene may be a space where an accident occurs.
Illustratively, the accident scene includes, but is not limited to:
a fire scene where a fire occurs;
an earthquake site where an earthquake occurs;
a collapse site where a collapse occurs;
and (4) a flood site with abnormal water flow.
The building layout information can indicate the overall layout of the building, and can specifically indicate the positions, the orientations, the surrounding environment and the like of all facilities in the building.
For example, the building layout information may indicate the location of a safe passage in the building and/or indicate the location blocked by a wall in the building.
In the embodiment of the present application, the building layout information includes, but is not limited to: building design plans, as-built acceptance charts or data obtained by field measurements, and other information from which the overall layout of the building can be obtained.
The accident information may include any information describing the accident, for example, information indicating the process and situation in which the accident occurred and developed, for example, in the case of a fire scene, the accident information may include information on the location of a fire source, the type of the fire source, the severity of the fire, and the area covered by the fire.
The first model may specifically be an evacuation scene simulation model, and is configured to generate overall accident map information according to the input information. The first model can grid the whole accident site according to the building layout information, namely, the space of the accident site is divided into a plurality of areas, and the specific situation of each area is determined according to the input accident information, for example, each area is divided into a passing area and a non-passing area.
The communication area may be an area through which the object can safely pass;
the non-communication area may be an area where the object cannot pass or where there is a high probability of a security accident occurring.
The accident map information is used for indicating specific conditions of different areas of the accident scene, such as a passing area, a non-passing area and the like. The passing area can be an area where the target can normally pass; the non-passing area may be an area where the target cannot normally pass, such as an area blocked by an obstacle or a dangerous area caused by an accident, or may be an area with a full number of targets.
The targets may include: various movable objects, illustratively, the target may include: a living body, e.g., a human and/or a pet. Still further illustratively, the target may further include: the ground mobile robot has mobility, so that the ground mobile robot can leave in time when an accident happens, and the damage to the ground mobile robot can be reduced.
The distribution condition information of the target is used for indicating the distribution condition of the target, and the distribution condition can include: distribution location and/or distribution density, etc.
The distribution of the targets may be the number of targets, and/or the location of the targets in the accident scene.
The exit information of the fire exit is used to indicate the location of the fire exit, for example, the fire exit may include: an elevator exit from a building, a stairway exit, or an underground passageway.
The safe exit may be an evacuation stair in compliance with regulations or an exit from a scene of a safe escape accident. In the embodiment of the application, the target can safely escape from the accident scene through the safety exit.
The relative position information is used for indicating the relative position between the target and the safety exit.
The second model may specifically be a neural network model, and is configured to calculate, according to the input information, a safe evacuation path from the target to the safe exit. In the embodiment of the application, a collaborative double-depth Q network algorithm can be adopted as a neural network model for deep reinforcement learning. The cooperative double-depth Q network algorithm is formed by performing neural network input layer optimization and multi-target neural network sharing and experience sharing on the basis of the traditional independent depth Q network algorithm, and the stability of the algorithm is improved.
The safe evacuation path may be a moving path of the target through the transit area to the safe exit. In the embodiment of the application, the safe evacuation path comprises a safe evacuation path of the whole target and a safe evacuation path corresponding to each target.
In an embodiment of the present application, the method further includes:
and after the moving condition of the target according to the safe evacuation path meets a first condition, acquiring the distribution condition information of the target on the accident site again.
The movement condition is used for indicating the movement of the target, namely, is used for indicating the change of the position of the target; the movement may be a behavior in which the target changes its original position, such as walking or running or riding an indoor vehicle, etc.
The first condition may be a time the target moves or a distance moved. For example, the movement condition satisfying the first condition may include at least one of:
the target moving step number reaches a step number threshold value, and the first condition can be considered to be met;
when the target moving time length reaches a time length threshold value, the target moving time length can be considered to meet a first condition;
the length of the path which is traveled by the target reaches a path length threshold value, and the first condition can be considered to be met;
the target displacement amount reaches the displacement amount threshold, and it can be considered that the first condition is satisfied.
In the embodiment of the present application, the number of the targets and the number of the safe exits may be one or more (two or more), so that the nearest safe exits may change at any time during the moving process of the targets, and thus the optimal safe evacuation route needs to be determined again. In this way, safety and real-time performance are better by updating the safe evacuation path of the target in real time according to the time of the target moving and/or the distance of the target moving.
In this embodiment of the application, the retrieving the distribution status information of the targets at the accident scene after the moving status of the targets according to the safe evacuation path satisfies the first condition includes:
after the moving condition of the target according to the safe evacuation path meets the first condition, determining whether the relative position relation between the target and the safe exit meets a second condition;
and if the relative position relation between the target and the safety exit does not meet the second condition, acquiring the distribution condition information of the accident site target again.
The second condition may be a distance between the target and the safety vent. And if the distance between the target and the safety exit meets the second condition, the target is shown to reach the safety exit, and the distribution condition information of the target on the accident site does not need to be acquired again.
In an embodiment of the present application, the method further includes:
stopping the determination of the safe evacuation path if the relative position between the target and the safe exit satisfies the second condition.
If the distance between the target and the exit meets the second condition, the target reaches the exit or can reach the exit through one or more determined passing areas compared with the distance between the target and the exit at the last time, and the target safe evacuation path does not need to be determined, so that the calculation resources can be saved, and the safe evacuation paths of the remaining targets can be calculated more quickly.
As shown in fig. 2, the obtaining a safe evacuation path of the target leaving the accident scene according to the accident map information, the relative position information and the second model includes:
step S210: according to the distribution condition information, determining environmental information of the area where the target is located from the accident map information;
step S220: and inputting the environmental information and the relative position information into the second model to obtain a safe evacuation path, which is output by the second model and used for the target to leave the accident scene.
The environment information is used for at least indicating the area type of the adjacent area of the position where the target is located. During evacuation of the object, accidents may still be in progress, possibly causing some of the existing traffic areas to become non-traffic areas. Therefore, the safe evacuation path of the target leaving the accident scene can be better obtained by combining the environmental information of the area where the target is located. Therefore, the corresponding safe evacuation path can be calculated in real time according to the change of the accident scene, and the safety and the practicability are better.
In an embodiment of the application, the inputting the environmental information and the relative position information into the second model to obtain a safe evacuation path of the target leaving the accident site, where the safe evacuation path is output by the second model, includes:
determining a plurality of alternative moving paths meeting safety conditions according to the accident map information and the relative position information;
when a plurality of alternative moving paths exist, selecting the alternative moving path with the maximum safety benefit as the safety evacuation path; wherein the security benefits have a particular one of:
the safety benefit is negatively related to the distance from the target to the safety exit according to the corresponding alternative moving path;
the safety benefit is inversely related to the accident rate predicted when the target moves to the safety exit according to the corresponding alternative moving path;
the safety gain is positively correlated with the probability that the target successfully reaches the safety exit according to the corresponding alternative moving path.
The safety condition may be that only a traffic zone exists on the alternative movement path. And if the non-passing area exists, the target cannot move to the safety exit according to the alternative moving path, and the safety condition is not met.
The alternative moving path may be an area through which the target needs to move.
The safety benefit may be a safety benefit obtained by moving the target according to the alternative moving path. If the safety gain is increased, the safer the target is, namely, the lower the probability that the target will be casualty at the accident site.
The positive correlation may include, but is not limited to: proportional correlation, etc.
The negative correlation may include, but is not limited to: negative proportional correlation, etc.
In this embodiment of the present application, the distribution status information of the target indicates: each of the target distribution locations and/or the number of targets located within the accident scene;
the environment information at least indicates the area type of an adjacent area of the position where the target is located;
the region types include: a traffic zone and a non-traffic zone outside the traffic zone.
In an embodiment of the present application, the non-passing area includes at least one of:
an obstacle area in which an area where obstacles are stacked to hinder passage;
accident area, area where the accident site is located;
and congestion areas, which contain areas with the target number exceeding a preset number.
In the embodiment of the application, the congestion area is set in the non-traffic area in consideration of the influence of the targets, so that the number of the targets in the area is limited, the smooth escape of the targets is ensured, and the occurrence of accidents such as crowding and treading is reduced.
The preset number may be determined according to the area of the region and/or the size of the channel in the region, for example, the area of the region and the preset number may be positively correlated; or the volume of the channels in the area is positively correlated with the preset number.
In an embodiment of the present application, the method further includes:
acquiring accident parameters of the accident scene;
and determining whether the adjacent area of the position where the target is located is the accident area or not according to the accident parameters.
The accident parameter may be one of the aforementioned accident information, which is used to indicate the nature of the accident. The occurrence and possible progression of an accident can be determined by means of the accident parameters, so that the type information of the area can be updated in this way.
For example, various security devices are installed in a building, and the security devices can acquire information of an accident scene so as to obtain accident information. For example, a camera in a building can acquire an image of an accident scene, and the fire or collapse situation of a fire scene and/or a collapse scene, the target distribution situation and the like can be known through image analysis. In addition, smoke sensors and the like in the building can collect smoke information and report the smoke information to the network side. The electronic device may obtain the accident information through the network or extract the accident parameter based on the accident information, that is, the electronic device directly obtains the accident information from the network device or directly receives the accident parameter.
The accident area may be an area where an accident occurs or is affected by the accident, such as an area where a fire occurs, an area where smoke generated by the fire spreads to affect visibility, an area where a house collapses due to an earthquake, and the like.
In an embodiment of the application, the accident parameter comprises at least one of:
fire parameters;
collapse parameters;
and (4) flood parameters.
In the embodiment of the application, the accident scene is a fire scene;
the acquiring of the accident parameters of the accident scene comprises:
acquiring the type of a fire source of the fire scene, the spatial parameter of a space where the fire source is located and the heat release rate of the fire source, wherein the spatial parameter of the space where the fire source is located indicates the ignition point position of the fire source and/or the distribution condition of combustibles in the space where the fire source is located.
The fire scene may be an accident scene where a fire occurs.
The fire source may be an energy source for burning or exploding combustibles and combustion aids and some explosive substances, such as heat energy, as well as electric energy, mechanical energy, chemical energy, light energy, and the like.
The fire source can be open fire, high-temperature object, electric heating energy, chemical heat energy, mechanical heat energy, biological heat, light energy, nuclear energy and the like.
The heat release rate of the fire source can be the heat released by the combustion of the material in unit time of the fire source, and is used for indicating the propagation speed of flame generated by the combustion of the fire source.
The ignition point position of the fire source indicates the initial position at which combustion of the fire source occurs.
The distribution condition of the combustibles in the space where the fire source is located at least indicates the position and the quantity of the combustibles.
The collapse parameters may include source intensity, source depth, etc. of a source at the collapse site.
The seismic source may be a location within the earth where a formation fractures causing vibrations.
The source intensity may be a magnitude of seismic energy, which is used to indicate the severity of the earthquake.
The source depth may be a distance vertically up to the surface of the earth for indicating the location of the source. The flood parameters may include flow, level, volume, etc. of the water source at the flood site.
The source of water may be the source of water that causes a flood.
The flow rate may include an average flow rate and an instantaneous flow rate for indicating the severity and propagation speed of the flood.
The water level can be the elevation that the free water surface of the water source is higher than the fixed base level, can directly reflect the increase and decrease change of the water quantity of the water source, and is used for indicating the probability of flood.
The amount of water may be what the flow rate of the water source is.
In this embodiment of the application, the determining, according to the accident parameter, whether an adjacent area of the position where the target is located is the accident area includes:
inputting a third model according to the type of the fire source of the fire scene, the space parameters of the space where the fire source is located and the heat release rate of the fire source to obtain an output result;
acquiring the temperature and/or visibility of each area of the fire scene according to the output result;
determining a dangerous area of the fire scene according to the temperature and/or visibility;
and determining whether the adjacent area of the position where the target is located is the accident area or not according to the dangerous area.
The third model can be a fire scene model and is used for simulating the fire occurrence and development process according to the type of the input fire source, the space parameters of the space where the fire source is located and the heat release rate of the fire source to obtain an output result. Specifically, a fire dynamics simulation software is used for modeling a fire scene, and the occurrence and development process of the fire is simulated by setting the type and position of a fire source, the heat release rate and environmental parameters.
The output result may be a result obtained by processing the input information by the third model.
The temperature may be a physical quantity indicating a degree of cold and heat to indicate whether there is a fire in the area.
The visibility may be a maximum distance representing a target recognition object to indicate whether smoke is present in the area due to a fire.
The dangerous area refers to a non-passing area where the target is difficult to pass due to the occurrence and development of a fire.
In an embodiment of the present application, the determining a dangerous area of the fire scene according to the temperature and/or visibility includes:
and when the temperature exceeds a first threshold value and/or when the visibility is lower than a second threshold value, determining that the adjacent area of the position where the target is located is a dangerous area of the fire scene.
In the embodiment of the application, whether the area is affected by fire or not is judged through temperature and/or visibility. The first threshold and the second threshold may be set manually as needed. In practical applications, a sensor or other devices may be used to detect the temperature and visibility in an area, so as to determine whether the area is a dangerous area.
Based on the foregoing embodiments, the embodiments of the present application provide a fire evacuation simulation method and system based on Deep reinforcement learning, and a collaborative dual-depth Q Network algorithm is formed in a manner of performing neural Network input layer optimization and multi-mobile neural Network sharing and experience sharing on the basis of a traditional Independent Deep Q Network (IDQN) algorithm, so that the stability of the algorithm is improved, and an evacuation path of people can be planned in a dynamically changing fire scene environment. According to the embodiment of the application, the mobile body can learn the environmental data in the interaction process with the fire environment, manual input is not needed, and the safety of an evacuation path is improved.
The present application will be further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
As shown in fig. 1, an embodiment of the present application provides a schematic flow chart of a fire evacuation simulation method based on deep reinforcement learning, including:
step S310: and establishing a fire scene model by using fire dynamics simulation software, and acquiring a real-time dangerous area influenced by high temperature and fire smoke from a fire numerical simulation result, wherein the fire scene model is one of the third models, the fire numerical simulation result is one of the output results, and the real-time dangerous area is one of the dangerous areas.
Fig. 4 is a schematic diagram of a fire scene model created by using fire dynamics simulation software according to an embodiment of the present application. According to the architectural design plan, completion acceptance chart and field measurement data, a fire scene model is established by using fire dynamics simulation software, the type and position of a fire source, the heat release rate and environmental parameters are set, and the fire source type and position, the heat release rate and the environmental parameters are one of the accident parameters, and the fire source type and position, the heat release rate and the environmental parameters are simulated and simulated by using the fire dynamics simulation software.
A layer of slices is arranged at a position 1.5m away from the ground, the temperature distribution and visibility distribution conditions of the whole indoor area are observed, and an area with the temperature higher than 65 ℃ or the visibility lower than 8m is set as a fire hazard area. And acquiring the distribution condition of the dangerous area affected by high temperature and fire smoke every 1s from the beginning of the fire, wherein 65 ℃ is one of the first threshold values, and 8m is one of the second threshold values.
Step S320: and establishing an evacuation scene simulation model according to real scene information, setting information such as the number of evacuated persons and the positions of the persons, wherein the real scene information is one of the building layout information of the accident site, the evacuation scene simulation model is one of the first models, the evacuated persons are one of the targets, and the information such as the number of evacuated persons and the positions of the persons is one of the distribution condition information of the targets of the accident site.
Fig. 5 is a schematic diagram of a gridding simulation model of an evacuation scene according to an embodiment of the present application. According to real scene information such as a building design plan and the like, a gridding simulation model of an evacuation scene is established by taking 0.4m as the side length of a grid unit, the model comprises a wall, a safety exit, a fire real-time dangerous area and evacuated people, and the wall is one of the barriers.
The number and the position distribution condition of the evacuated people can be set according to the actual condition and can be changed according to the requirement. Evacuation personnel should have the following characteristics:
1. personnel need to know the position of an outlet, but do not know the distribution of obstacles and the distribution of real-time dangerous areas of the fire, and can know the situation only through learning;
2. in the evacuation process, each person occupies the space of one grid, namely, one grid can only accommodate one person at most;
3. in the evacuation process, a person can move one grid in 8 directions of upward, downward, left, right, upward left, downward left, upward right and downward right in each action, and a plurality of grids cannot be moved at one time;
4. when the next grid after the person selects the moving direction is the obstacle grid or is occupied by other people, the evacuated person stays in the original grid, and the action is regarded as staying in place.
Step S330: and leading the real-time dangerous area of the fire into an evacuation model along with the increase of evacuation time.
Immediately after the occurrence of a fire, the area of a dangerous area affected by the fire is small, and the influence on evacuation of people is small. As the evacuation time increases, the area of the dangerous area affected by the fire gradually expands, which has a great influence on the evacuation route selection after the evacuation of people has not been completed. Therefore, the evacuation scene of the evacuation model is updated in real time by taking 1s as a time interval, so that the simulation of the real evacuation scene is realized, and the reality and the safety of the personnel evacuation process are enhanced, wherein the 1s is one of the first conditions.
The influence of the introduced real-time fire hazard area on personnel evacuation is similar to that of the barrier, and when the next grid after the personnel select the moving direction is the fire hazard area grid, the evacuated personnel can stay in the original grid. However, the fire danger area is constantly changing, when the evacuation route of people coincides with the fire danger area, people are prevented from being evacuated to the exit, and even people are surrounded by the fire danger area and cannot reach the exit, which requires that the evacuation algorithm plans an optimal evacuation path on the basis of fully considering the real-time change of the fire danger area, wherein the optimal evacuation path is one of the aforementioned safe evacuation paths.
Step S340: and (4) planning the optimal path of the personnel by utilizing a collaborative double-depth Q network algorithm.
In the process of evacuating all the moving bodies, all the moving bodies which do not reach an exit are screened out according to the distance between each person and the nearest exit, each moving body collects environmental information, and performs action selection according to the current training result of the collaborative double-depth Q network algorithm. After each mobile body performs action selection, the reward value is obtained through calculation, and each mobile body enters the next state according to the selected action execution, wherein the action execution is one of the first conditions. Then, storing all the experience cell progenitors into an experience pool, selecting part of experience cell progenitors in the experience pool in a random batch sampling mode to carry out learning training, and updating the neural network parameter theta. Finally, when all the people escape from the scene or the evacuation time step reaches the set upper limit, stopping the model learning training of the round, and performing the next round of learning training until the set number of training rounds is reached, as shown in fig. 6, a people evacuation schematic diagram provided by the embodiment of the present application is provided.
Furthermore, a collaborative double-depth Q network algorithm is adopted as a neural network model for deep reinforcement learning, environment information of eight neighborhoods around the moving body is added into a neural network input layer, observation of people on the surrounding environment in a low-visibility environment is simulated, and therefore the moving body with the same configuration is built, and optimization of the neural network input layer is carried out.
The cooperative double-depth Q network algorithm utilizes the commonness of behaviors and targets among the same-configuration moving bodies to carry out neural network structure sharing and experience sharing learning, and simulates information sharing of the conditions of high temperature of fire and development and spread of toxic and harmful smoke of personnel in a real evacuation process through communication modes such as shouting and the like. The shared learning mode among the moving bodies enables the experience learned by a single moving body in each step to be popularized to other moving bodies, and each moving body can learn by using the experience knowledge of other moving bodies, so that the learning efficiency of the neural network is improved, and the speed of algorithm path planning is increased. All the moving bodies can share one shared neural network for learning, the number of the neural networks and the number of training parameters cannot change along with the increase and decrease of the number of the moving bodies, and the stability of the evacuation model is enhanced. Due to the sharing of the structures and parameters of the neural networks of all the moving bodies, the training difficulty of the neural networks is reduced, and the learning efficiency of the neural networks is further improved.
Further, the state space S of the moving body is set to { S ═ S1,s2,…,snDenotes a set of all states of the mobile body in the environment, stAnd e S represents the state of the mobile body at time step t. Wherein n is state nullThe total number of cells indicates the number of all state spaces in which the mobile body can act, except for obstacles in the environment.
Setting an operation space A of a moving body as { a }1,a2,…,amA represents a set of all selectable actions of the mobile body in the current environment, atAnd e A represents the motion of the mobile body at the time step t, and m is the total number of motion spaces.
Setting a state transition probability function P of a mobile body in an environment, S multiplied by A multiplied by S → [0,1]，P(st+1|st,at)
Indicating the state s of the moving bodytSelection action atAfter that, the state is changed to st+1The value of the probability is in the range of 0-1.
Further, a reward function of the mobile body is set. Due to the fact that the state space is large, in order to solve the sparse rewarding problem and speed up the model training, negative value rewarding is given to each action of the moving body, and when the moving body arrives at an exit, large positive value rewarding is given, and the rewarding is one of the safety benefits. The reward setting principles of different mobile bodies are the same, the joint reward of multiple mobile bodies is not set, and the specific reward setting conditions are as follows:
wherein A is1～4＝{a1,a2,a3,a4The action is to move a grid upwards, downwards, leftwards and rightwards; a. the5～8＝{a5,a6,a7,a8The action is to move a grid up and down left, up and down right by a distance A1～4Is/are as follows
Multiple, thus setting the prize to also be A1～4Is
And (4) doubling.
Wherein n is the number of outlets, dtAnd dt+1The distances between the mobile body and the nearest exit at time step t and time step t +1, respectively.
The reward setting standard is the distance change condition between the mobile body and the nearest exit, and when the distance between the mobile body and the nearest exit is reduced, a smaller negative value reward is given; when the distance between the mobile body and the nearest exit is not reduced, a large negative value is awarded.
The reason for arranging the distance between the moving body and the nearest exit to be constant and the same as the increased reward is to encourage the moving body to search for evacuation of other exits. In most cases, a constant distance between the mobile body and the nearest exit means that the mobile body is influenced by fire products, obstacles or other persons, and cannot move in a selected direction and stay in place. The same reward is set for the distance unchanged and the distance increased, and the moving body is encouraged to go to other exits to try to obtain a better path planning result when the moving body cannot pass through temporarily due to the blockage of a large number of fire products or crowding.
Further, when the mobile body performs learning training in an environment by using a collaborative dual-depth Q network algorithm, the learned experiences of several adjacent states have correlation and do not meet the independent equal distribution requirement, so that the neural network training result can be converged to a suboptimal strategy, and even the training result is oscillated and dispersed and cannot be converged. Therefore, parameter updating is carried out on the neural network in an empirical playback mode, and stability of the algorithm is improved.
The experience playback mechanism is that after the mobile body selects one action, the obtained experience primitive is used as the elementt＝(st,at,rt,st+1) Put into storage allEmpirical pool D ═ e1,e2,…,eNAnd selecting a part of experience units in the experience pool for learning in a random batch sampling mode, and updating the neural network parameter theta. In the cooperative double-depth Q network algorithm, one experience element is composed of four parameters which are respectively the current state s of a time step ttAction a performed at time step ttIn a state stPerforming action atEarned reward rtAnd in state stPerforming action atEntering the next state st+1. The number of experience meta-ancestors in the experience pool is limited, and when the number of experience pool storages reaches the upper limit, the newly added experience will replace the experience learned initially, so that the experience in the experience pool is kept updated in real time. In the process of neural network learning training, the random batch sampling method reduces the correlation among experience tuples, so that the learning experience can be repeatedly utilized, and the neural network is prevented from falling into local optimization.
Step S350: the evacuation path and evacuation time for each person are obtained.
After the training and learning of the model are finished, the evacuation path and evacuation time of each person can be obtained, and the distribution of fire hazard danger areas, the number of people finishing evacuation, and the distribution condition of the remaining persons can also be obtained at any evacuation time, as shown in fig. 7, which is a schematic diagram of finishing evacuation of persons provided by the embodiment of the present application.
The embodiment of the application considers the real-time influence of fire burning on personnel evacuation, so that the personnel evacuation process is safer and more true, and the scientific and reasonable personnel evacuation path can be planned.
The embodiment of the application adopts a cooperative double-depth Q network algorithm, so that the moving bodies can share the neural network, the learning amount of the neural network is reduced, and the training difficulty is reduced; the method has the advantages that learning experience can be shared among moving bodies, the learning efficiency of the neural network is improved, and the speed of algorithm path planning is increased.
The embodiment of the application provides a fire evacuation simulation system based on deep reinforcement learning, including:
the system comprises an initialization setting module, a scene model and a monitoring module, wherein the initialization setting module is used for initializing personnel distribution, a real-time fire hazard area, a wall and a safety exit in the scene model;
the neural network model building module is used for building a collaborative deep reinforcement learning network model, setting a reward function interacting with the environment and building a big experience pool for storing the experiences of all moving bodies;
the fire hazard zone reading module is used for acquiring a fire hazard real-time hazard zone exceeding a temperature threshold or lower than a visibility threshold from fire hazard dynamics simulation software;
and the evacuation simulation module adopts a collaborative double-depth Q network algorithm to plan the evacuation path of people, obtains the optimal evacuation path planning result of the whole crowd and respectively obtains the evacuation path of each person.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Although the embodiments of the present application have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present application, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive effort by those skilled in the art.
As shown in fig. 8, an embodiment of the present application provides an evacuation path determining apparatus, including:
the generation module 110 is configured to input a first model according to the building layout information and the accident information of the accident scene, and generate accident map information at the current moment; wherein the accident map information indicates at least whether different areas of the accident scene are passable;
a first obtaining module 120, configured to obtain distribution status information of the accident scene target and exit information of a security exit;
a first determining module 130, configured to determine, according to the distribution status information, relative location information between the target and the security exit;
an obtaining module 140, configured to obtain, according to the accident map information, the relative position information, and the second model, a safe evacuation path where the target leaves the accident site.
In some embodiments, the generating module 110, the first obtaining module 120, the first determining module 130, and the obtaining module 140 may be all program modules, and the program modules are executed by a processor and can implement the functions of the above modules.
In other embodiments, the generating module 110, the first obtaining module 120, the first determining module 130, and the obtaining module 140 may all be a soft-hard combining module; the soft and hard combining module includes but is not limited to: various programmable arrays; the field programmable array includes, but is not limited to: field programmable arrays and/or complex programmable arrays.
In still other embodiments, the generating module 110, the first obtaining module 120, the first determining module 130, and the obtaining module 140 may all be pure hardware modules; the pure hardware modules include, but are not limited to: an application specific integrated circuit.
In some embodiments, the apparatus further comprises:
and the second acquisition module is used for acquiring the distribution condition information of the targets on the accident site again after the moving condition of the targets according to the safe evacuation path meets the first condition.
In some embodiments, the retrieving the distribution condition information of the accident scene target after the moving condition of the target according to the safe evacuation path meets the first condition includes:
after the moving condition of the target according to the safe evacuation path meets the first condition, determining whether the relative position relation between the target and the safe exit meets a second condition;
and if the relative position relation between the target and the safety exit does not meet the second condition, acquiring the distribution condition information of the accident site target again.
In some embodiments, the apparatus further comprises:
a stopping module for stopping the determination of the safe evacuation path if the relative position between the target and the safe exit satisfies the second condition.
In some embodiments, the obtaining a safe evacuation path for the target to leave the accident scene according to the accident map information, the relative position information and the second model includes:
according to the distribution condition information, determining environmental information of the area where the target is located from the accident map information;
and inputting the environmental information and the relative position information into the second model to obtain a safe evacuation path, which is output by the second model and used for the target to leave the accident scene.
In some embodiments, said inputting the environmental information and the relative location information to the second model to obtain the safe evacuation path from the accident scene targeted by the second model output comprises:
determining a plurality of alternative moving paths meeting safety conditions according to the accident map information and the relative position information;
when a plurality of alternative moving paths exist, selecting the alternative moving path with the maximum safety benefit as the safety evacuation path; wherein the security benefits have a particular one of:
the safety benefit is negatively correlated with the distance from the target to the safety exit according to the corresponding alternative moving path;
the safety gains are inversely related to the accident occurrence rate predicted when the target moves to the safety exit according to the corresponding alternative moving path;
the safety gain is positively correlated with the probability that the target successfully reaches the safety exit according to the corresponding alternative moving path.
In some embodiments, the distribution status information of the target indicates:
each of the target distribution locations and/or the number of targets located within the accident scene;
the environment information at least indicates the area type of an adjacent area of the position where the target is located;
the region types include: a traffic zone and a non-traffic zone outside the traffic zone.
In some embodiments, the non-passing area includes at least one of:
an obstacle area in which an area where obstacles are stacked to hinder passage;
accident area, area where the accident site is located;
and congestion areas, which contain areas with the target number exceeding a preset number.
In some embodiments, the apparatus further comprises:
the third acquisition module is used for acquiring accident parameters of the accident scene;
and the second determination module is used for determining whether the adjacent area of the position where the target is located is the accident area.
In some embodiments, the accident parameter comprises at least one of:
fire parameters;
collapse parameters;
and (4) flood parameters.
In some embodiments, the accident scene is a fire scene;
the acquiring of the accident parameters of the accident scene comprises:
acquiring the type of a fire source of the fire scene, the spatial parameter of a space where the fire source is located and the heat release rate of the fire source, wherein the spatial parameter of the space where the fire source is located indicates the ignition point position of the fire source and/or the distribution condition of combustibles in the space where the fire source is located.
In some embodiments, the determining, according to the accident parameter, whether an area adjacent to the position of the target is the accident area includes:
inputting a third model according to the type of the fire source of the fire scene, the space parameters of the space where the fire source is located and the heat release rate of the fire source to obtain an output result;
acquiring the temperature and/or visibility of each area of the fire scene according to the output result;
determining a dangerous area of the fire scene according to the temperature and/or visibility;
and determining whether the adjacent area of the position where the target is located is the accident area or not according to the dangerous area.
In some embodiments, said determining a hazardous area of said fire scene from said temperature and/or visibility comprises:
and when the temperature exceeds a first threshold value and/or when the visibility is lower than a second threshold value, determining that the adjacent area of the position where the target is located is a dangerous area of the fire scene.
As shown in fig. 9, an embodiment of the present application provides an electronic device, including:
a memory for storing computer readable instructions;
a processor, connected to the memory, for implementing the method provided by any of the foregoing embodiments by executing the computer readable instructions, for example, the method shown in fig. 1, fig. 2 and/or fig. 3 may be executed.
The memory can be various types of memories, such as random access memory, read only memory, flash memory, and the like. The memory may be used for information storage, e.g., storing computer-executable instructions, etc. The computer-executable instructions may be various program instructions, such as object program instructions and/or source program instructions, and the like.
The processor may be various types of processors, such as a central processing unit, a microprocessor, a digital signal processor, a programmable array, a digital signal processor, an application specific integrated circuit, or an image processor, among others. The processor may be connected to the memory via a bus. The bus may be an integrated circuit bus or the like.
As shown in fig. 9, the electronic device may further include a network interface, which may be used for interacting with a peer device through a network.
Embodiments of the present application further provide a computer storage medium, where computer-executable instructions are stored, and when executed, the computer storage medium is capable of implementing the method provided in any of the foregoing embodiments, for example, the method shown in fig. 1, fig. 2, and/or fig. 3 may be executed.
The computer storage medium provided by the embodiment comprises: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all functional units in the embodiments of the present application may be integrated into one processing module, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (16)
1. An evacuation path determination method, comprising:
inputting a first model according to the building layout information and accident information of an accident site, and generating accident map information at the current moment; wherein the accident map information indicates at least whether different areas of the accident scene are passable;
acquiring distribution condition information of the accident scene target and exit information of a safety exit;
determining relative position information between the target and the safety exit according to the distribution condition information;
and obtaining a safe evacuation path of the target leaving the accident scene according to the accident map information, the relative position information and a second model.
2. The method of claim 1, further comprising:
and after the moving condition of the target according to the safe evacuation path meets a first condition, acquiring the distribution condition information of the target on the accident site again.
3. The method of claim 2, wherein the retrieving of the distribution information of the targets at the accident site after the moving status of the targets according to the safe evacuation path satisfies the first condition comprises:
after the moving condition of the target according to the safe evacuation path meets the first condition, determining whether the relative position relation between the target and the safe exit meets a second condition;
and if the relative position relation between the target and the safety exit does not meet the second condition, acquiring the distribution condition information of the accident site target again.
4. The method of claim 3, further comprising:
stopping the determination of the safe evacuation path if the relative position between the target and the safe exit satisfies the second condition.
5. The method of claim 1, wherein said deriving a safe evacuation path for the target to leave the accident site based on the accident map information and the relative location information and a second model comprises:
according to the distribution condition information, determining environmental information of the area where the target is located from the accident map information;
and inputting the environmental information and the relative position information into the second model to obtain a safe evacuation path, which is output by the second model and used for the target to leave the accident scene.
6. The method of claim 5, wherein said inputting the environmental information and the relative location information to the second model resulting in a safe evacuation path for the target of the second model output to exit the accident site comprises:
determining a plurality of alternative moving paths meeting safety conditions according to the accident map information and the relative position information;
when a plurality of alternative moving paths exist, selecting the alternative moving path with the maximum safety benefit as the safety evacuation path; wherein the security benefits have a particular one of:
the safety benefit is negatively related to the distance from the target to the safety exit according to the corresponding alternative moving path;
the safety gains are inversely related to the accident occurrence rate predicted when the target moves to the safety exit according to the corresponding alternative moving path;
the safety gain is positively correlated with the probability that the target successfully reaches the safety exit according to the corresponding alternative moving path.
7. The method of claim 5, wherein the distribution status information of the target indicates:
each of the target distribution locations and/or the number of targets located within the accident scene;
the environment information at least indicates the area type of an adjacent area of the position where the target is located;
the region types include: a traffic zone and a non-traffic zone outside the traffic zone.
8. The method of claim 7, wherein the non-passing area comprises at least one of:
an obstacle area in which an area where obstacles are stacked to hinder passage;
accident area, area where the accident point is located;
and congestion areas, which contain areas with the target number exceeding a preset number.
9. The method of claim 8, further comprising:
acquiring accident parameters of the accident scene;
and determining whether the adjacent area of the position where the target is located is the accident area or not according to the accident parameters.
10. The method of claim 9, wherein the incident parameters include at least one of:
fire parameters;
collapse parameters;
and (4) flood parameters.
11. The method of claim 9, wherein the accident site is a fire site;
the acquiring of the accident parameters of the accident scene comprises:
acquiring the type of a fire source of the fire scene, the spatial parameter of a space where the fire source is located and the heat release rate of the fire source, wherein the spatial parameter of the space where the fire source is located indicates the ignition point position of the fire source and/or the distribution condition of combustibles in the space where the fire source is located.
12. The method of claim 11, wherein the determining whether the area adjacent to the location of the target is the accident area based on the accident parameter comprises:
inputting a third model according to the type of the fire source of the fire scene, the space parameters of the space where the fire source is located and the heat release rate of the fire source to obtain an output result;
acquiring the temperature and/or visibility of each area of the fire scene according to the output result;
determining a dangerous area of the fire scene according to the temperature and/or visibility;
and determining whether the adjacent area of the position where the target is located is the accident area or not according to the dangerous area.
13. The method of claim 12, wherein said determining a hazardous area of said fire scene from said temperature and/or visibility comprises:
and when the temperature exceeds a first threshold value and/or when the visibility is lower than a second threshold value, determining that the adjacent area of the position where the target is located is a dangerous area of the fire scene.
14. An evacuation path determining apparatus, comprising:
the generating module is used for inputting a first model according to the building layout information and the accident information of the accident site and generating accident map information at the current moment; wherein the accident map information indicates at least whether different areas of the accident scene are passable;
the first acquisition module is used for acquiring the distribution condition information of the accident scene target and the exit information of a safety exit;
the first determining module is used for determining the relative position information between the target and the safety exit according to the distribution condition information;
and the obtaining module is used for obtaining the safe evacuation path of the target leaving the accident scene according to the accident map information, the relative position information and the second model.
15. An electronic device, comprising:
a memory storing computer readable instructions;
a processor coupled to the memory and configured to implement the method of any of claims 1 to 13 by executing the computer readable instructions.
16. A computer storage medium having stored thereon computer-executable instructions; the computer executable instructions, when executed by a processor, are capable of implementing the method of any one of claims 1 to 13.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210112873.6A CN114510545A (en) | 2022-01-29 | 2022-01-29 | Evacuation path determination method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210112873.6A CN114510545A (en) | 2022-01-29 | 2022-01-29 | Evacuation path determination method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114510545A true CN114510545A (en) | 2022-05-17 |
Family
ID=81551921
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210112873.6A Pending CN114510545A (en) | 2022-01-29 | 2022-01-29 | Evacuation path determination method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114510545A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116017298A (en) * | 2022-12-02 | 2023-04-25 | 东土科技(宜昌)有限公司 | Object position adjustment method and device for chemical engineering safety and electronic equipment |
-
2022
- 2022-01-29 CN CN202210112873.6A patent/CN114510545A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116017298A (en) * | 2022-12-02 | 2023-04-25 | 东土科技(宜昌)有限公司 | Object position adjustment method and device for chemical engineering safety and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shi et al. | Agent-based evacuation model of large public buildings under fire conditions | |
| KR101442658B1 (en) | System and Method for Disaster Evacuation providing Evacuation Simulation | |
| KR102209384B1 (en) | Disaster management system using 3D BIM object model and disaster management Method | |
| Wijerathne et al. | HPC enhanced large urban area evacuation simulations with vision based autonomously navigating multi agents | |
| CN114510545A (en) | Evacuation path determination method and device, electronic equipment and storage medium | |
| CN109583628A (en) | A kind of flood personnel's dynamic evacuation path analysis method based on cellular automata | |
| KR101881222B1 (en) | Urban fire simulation apparatus | |
| CN116187608A (en) | Underground traffic facility evacuation path decision method, system and equipment in flood environment | |
| CN114862070B (en) | Method, device, equipment and storage medium for predicting crowd evacuation capacity bottleneck | |
| CN112488401A (en) | Fire escape route guiding method and system | |
| CN114065348A (en) | Crowd emergency evacuation method, system, terminal and storage medium | |
| Bernardini et al. | Assessing the flood risk to evacuees in outdoor built environments and relative risk reduction strategies | |
| Ebihara et al. | A model for simulating human behavior during emergency evacuation based on classificatory reasoning and certainty value handling | |
| Mitchell et al. | Integrating wildfire spread and evacuation times to design safe triggers: Application to two rural communities using PERIL model | |
| Mysorewala et al. | Multi-scale adaptive sampling with mobile agents for mapping of forest fires | |
| Goto et al. | A Guidance System for Wide-area Complex Disaster Evacuation based on Ant Colony Optimization. | |
| CN113464197A (en) | Mine water disaster emergency management method and system | |
| Cheng et al. | A modified particle swarm optimization-based human behavior modeling for emergency evacuation simulation system | |
| Cao et al. | Indoor fire emergency evacuation path planning based on improved NavMesh algorithm | |
| Koutamanis | Multilevel analysis of fire escape routes in a virtual environment | |
| Soderlund | Characterization of wildland fires through evidence-based sensor fusion and planning | |
| Wang | Bidirectional ACO intelligent fire evacuation route optimization | |
| Le et al. | Speeding up the evaluation of casualties in multi-agent simulations with Linear Programming application to optimization of sign placement for tsunami evacuation | |
| Matsuki et al. | Identification of issues in disaster response to flooding, focusing on the time continuity between residents’ evacuation and rescue activities | |
| Tagg et al. | Use of agent-based modelling in emergency management under a range of flood hazards |
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 |