Fire-fighting evacuation indication method and system based on parallel Dikstra algorithm

Abstract

The invention belongs to the technical field of fire-fighting evacuation indication, and provides a fire-fighting evacuation indication method and system based on a parallelization Dikstra algorithm, fire-fighting evacuation indication is performed by means of a building three-dimensional model, and a recommended route can be visually indicated. Meanwhile, the optimal paths from all the vertexes to other vertexes are obtained through the parallelization Dikstra algorithm, the pressure of mass data processing is reduced, the shortest distance, the shortest time and the highest safety are taken as targets through the parallelization Dikstra algorithm, and the optimal path is obtained through the parallelization Dikstra algorithm. Three pre-selected paths between the vertexes are determined, the final optimal path is determined on the basis, and on the basis of avoiding the pressure of mass data processing, the problem that it cannot be guaranteed that personnel safely arrive at an exit when only a single factor is considered is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of fire evacuation indication, and in particular relates to a fire evacuation indication method and system based on a parallelized Dijkstra algorithm. Background Art

[0002] With the rapid development of society, the firefighting situation is extremely severe. The information level of traditional firefighting work is relatively backward, and there are problems such as untimely data feedback and poor intuitiveness. At the same time, due to the complex building structure and multiple emergency exits, it is impossible to adjust the evacuation plan in time according to the congestion inside the building and the location of the fire after the fire occurs.

[0003] At present, fire evacuation instructions can be made with the help of Dijkstra algorithm to improve the accuracy of fire evacuation plans; however, when using Dijkstra algorithm for fire evacuation instructions, there is a certain data processing pressure when processing a large amount of data on fire points and destinations, and only a single factor of the shortest distance or shortest time from the departure point to the exit is considered, which cannot guarantee that people can reach the exit safely. Summary of the invention

[0004] In order to solve the above problems, the present invention proposes a fire evacuation indication method and system based on a parallelized Dijkstra algorithm. The present invention obtains the optimal paths from all vertices to other vertices at the same time through the parallelized Dijkstra algorithm, thereby reducing the pressure of large-scale data processing. The parallelized Dijkstra algorithm takes the shortest distance, the shortest time and the highest safety as the goals respectively, and determines three pre-selected paths between vertices through the parallelized Dijkstra algorithm, and determines the final optimal path based on this. On the basis of avoiding the pressure of large-scale data processing, the problem that people cannot be guaranteed to reach the exit safely when only a single factor is considered is solved.

[0005] In order to achieve the above object, the present invention is implemented through the following technical solutions:

[0006] In a first aspect, the present invention provides a fire evacuation indication method based on a parallelized Dijkstra algorithm, comprising:

[0007] Get the locations of all emergency signs in the building as vertices;

[0008] By parallelizing the Dijkstra algorithm, the optimal path from all vertices to other vertices is obtained; when determining the optimal path between vertices, the shortest distance, shortest time and highest security are taken as the goals respectively, and three pre-selected paths between vertices are determined by the parallelized Dijkstra algorithm; if the three pre-selected paths overlap, the overlapping path is the optimal path, otherwise, the optimal path is determined among the three pre-selected paths in the order of highest security, shortest time and shortest distance;

[0009] The optimal path is indicated in the preset 3D building model.

[0010] Furthermore, the distances of all vertices are initialized to infinity, and the distance of the starting vertex is initialized to; in each iteration, the unvisited vertex closest to the starting vertex is selected, and a binary heap is used as a priority queue to obtain the first time complexity; for each selected vertex, the distances of its adjacent vertices are updated, and a binary heap is used as a priority queue to obtain the total second time complexity; the first time complexity and the second time complexity are added together to obtain the total time complexity of the Dijkstra algorithm; the Dijkstra algorithm considers all accessible paths, and determines the optimal path with the shortest distance, shortest time and highest safety as the goals.

[0011] Furthermore, the graph data in the three-dimensional model of the building is divided into multiple subgraphs or node sets, each of which is processed in parallel by different processor cores; in each iteration step, another emergency sign that is currently closest to the emergency sign is searched in parallel among all unprocessed nodes; after determining the nearest emergency sign, all distance and predecessor node information is updated in parallel; locks or other synchronization mechanisms are used to avoid data competition; and repeated processing is performed until all nodes have been processed.

[0012] Furthermore, each emergency sign source point corresponds to a priority queue for storing the nodes to be processed starting from the emergency sign source point and the current shortest path length.

[0013] Furthermore, the safest path refers to the path farthest from the spread coordinates of the fire feature point.

[0014] Furthermore, the fire spread formula and preset parameters are used to determine the speed of the fire under the combined effect of wind speed and slope, as well as the speed in the opposite direction of the fire head; based on the fire spread speed and time step, the coordinates of the next fire feature point spread are obtained.

[0015] In a second aspect, the present invention further provides a fire evacuation indication system based on a parallelized Dijkstra algorithm, comprising:

[0016] The data acquisition module is configured to: obtain the locations of all emergency signs in the building as vertices;

[0017] The optimal path determination module is configured as follows: by parallelizing the Dijkstra algorithm, the optimal paths from all vertices to other vertices are obtained; when determining the optimal path between vertices, the shortest distance, the shortest time and the highest security are respectively taken as the goals, and three pre-selected paths between vertices are determined by the parallelizing Dijkstra algorithm; if the three pre-selected paths overlap, the overlapping path is the optimal path, otherwise, the optimal path is determined from the three pre-selected paths in the order of highest security, shortest time and shortest distance;

[0018] The indication module is configured to indicate the optimal path in a preset three-dimensional building model.

[0019] In a third aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the fire evacuation indication method based on the parallelized Dijkstra algorithm described in the first aspect.

[0020] In a fourth aspect, the present invention further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein when the processor executes the program, the steps of the fire evacuation indication method based on the parallelized Dijkstra algorithm described in the first aspect are implemented.

[0021] In a fifth aspect, the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the fire evacuation indication method based on the parallelized Dijkstra algorithm described in the first aspect are implemented.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] The present invention uses a three-dimensional building model to perform fire evacuation instructions, and can intuitively indicate recommended routes; at the same time, the optimal paths from all vertices to other vertices are obtained simultaneously through the parallelization of the Dijkstra algorithm, which reduces the pressure of large-scale data processing, and the parallelization of the Dijkstra algorithm takes the shortest distance, the shortest time and the highest safety as the goals, and the parallelization of the Dijkstra algorithm is used to determine three pre-selected paths between vertices, and the final optimal path is determined based on this, which avoids the pressure of large-scale data processing and solves the problem that people cannot be guaranteed to reach the exit safely when only a single factor is considered. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings in the specification that constitute a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments of this embodiment and their descriptions are used to explain this embodiment and do not constitute improper limitations on this embodiment.

[0025] Figure 1This is a schematic diagram of the method flow of Example 1 of the present invention;

[0026] Figure 2 This is an indication diagram under the three-dimensional model of Example 1 of the present invention. DETAILED DESCRIPTION

[0027] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0028] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0029] Embodiment 1:

[0030] This embodiment provides a fire evacuation indication method based on the parallelized Dijkstra algorithm, which realizes real-time monitoring of the fire scene, dynamic evacuation indication and optimal path planning through three-dimensional visualization, data integration and simulation analysis of the building three-dimensional model, thereby improving evacuation efficiency and safety.

[0031] S1. 3D modeling and proportional model construction.

[0032] Optionally, use a 3D scanning device to collect the structural data of the building, and use BIM software to build an accurate 3D model of the building. Integrate various building information in the BIM model, including spatial layout, fire protection facilities, evacuation routes, personnel distribution, etc. Import the CAD file into the software, process the units and grid lines to ensure that they are consistent with the CAD drawing, and draw walls, beams, plates, columns and other components in the software according to the geometric information in the CAD file to form a preliminary 3D model. Assign material, size, color and other attributes to each element in the model to ensure the authenticity and accuracy of the model. Use algorithms to perform structural analysis and energy consumption simulation on the model, output analysis results, and help optimize the design and construction plan. Convert the 3D model into the floor plan, elevation, etc. required for construction to ensure the accuracy and efficiency of construction.

[0033] Applying BIM technology to intelligent fire evacuation path indication and path optimization can effectively guide the intelligent fire evacuation path, realize the positioning function of people in the building, and combine with smoke and temperature sensors to determine whether the building is congested or dangerous, and calculate the optimal evacuation path, so that trapped people can evacuate quickly and safely in the shortest time, effectively avoiding stampedes caused by congestion and improving the safety factor of the building.

[0034] S2. Installation of video surveillance and IoT equipment at key locations.

[0035] The installation of video surveillance and IoT equipment in key areas includes preliminary planning, equipment selection, installation and commissioning, and post-maintenance. The specific contents are as follows:

[0036] S2.1. Preliminary planning:

[0037] Demand analysis: clarify the application scenarios and purposes of monitoring and IoT devices, such as security monitoring, environmental monitoring, equipment management, etc.; determine the key parts that need to be monitored, such as entrances and exits, corridors, and important equipment areas. Site survey: survey the installation site to understand the infrastructure conditions such as environmental layout, light conditions, power supply and network interface; determine the location and angle of equipment installation to ensure that the monitoring range is comprehensive and has no blind spots. Design plan: design the installation plan for video surveillance and IoT devices based on the demand analysis and site survey results.

[0038] S2.2, Equipment selection:

[0039] Video surveillance equipment: Select cameras suitable for monitoring scenarios, such as fixed cameras, PTZ cameras, infrared cameras, etc. IoT devices: Select appropriate IoT devices according to the objects or environmental parameters that need to be monitored, such as temperature sensors, humidity sensors, smoke detectors, access control systems, etc. Ensure that IoT devices have stable and reliable performance and easy-to-integrate interfaces.

[0040] S2.3, Installation and debugging:

[0041] Equipment installation: Install video surveillance equipment and IoT equipment to designated locations according to the design plan; adjust the angle and focal length of the camera to ensure that the surveillance image is clear and the range is appropriate. System debugging: Perform system debugging on the installed equipment, including testing of network connection, video transmission, equipment control and other functions; ensure that all equipment can work normally and meet monitoring requirements.

[0042] S2.4, Post-maintenance:

[0043] Regular inspection: Regularly inspect and maintain video surveillance and IoT equipment, including cleaning the lens, checking the power supply and network connection, etc.; promptly discover and handle equipment failures or abnormalities. Data storage and management: Set up data backup and recovery strategies as needed to ensure the safe storage and management of surveillance video and IoT data, and prevent data loss or leakage. System upgrade and optimization: Pay attention to the technological development trends of video surveillance and IoT equipment, and promptly upgrade and optimize the system; improve the stability and security of the system to meet the ever-changing monitoring needs.

[0044] S3. Collect information about equipment where fire occurs.

[0045] S3.1. Fire alarm system information:

[0046] Status information of the fire alarm controller and the fire linkage controller, including power supply, operating status, manual / automatic switching status, faults, etc. Calculate the slope and slope information of the fire point location and return it to the input data interface. Input parameters include fire point location information, wind speed, wind direction, dried combustible content, dried particle density, surface area to volume ratio, combustible moisture content, combustible extinguishing moisture content, etc. Use the fire spread formula to calculate these parameters one by one, and finally obtain the fire spread speed under windless and slopeless conditions. Calculate the speed of the fire under the combined force of wind speed and slope, as well as the speed in the opposite direction of the fire head. Obtain the coordinates of the next fire feature point spread based on the fire spread speed and time step.

[0047] S3.2, Fire equipment status information:

[0048] Status information of fire water supply systems such as fire pumps, fire hydrants, and fire water tanks, including water level, pressure, start / stop status, etc. Status information of fixed fire extinguishing systems such as automatic sprinkler systems and gas fire extinguishing systems, including the working status and action information of water flow indicators, alarm valves, and pressure switches, etc. Status information of smoke exhaust systems, including manual / automatic, start / stop, power supply, and fault information of fan control cabinets, as well as opening and closing action signals of air supply vents, smoke exhaust vents, smoke exhaust windows, or smoke exhaust valves.

[0049] S3.3, Video surveillance information:

[0050] The images captured by video surveillance cameras installed in key locations are used to monitor the fire scene in real time and provide intuitive image support for firefighting and rescue.

[0051] S3.4, IoT device information:

[0052] Environmental parameter information collected by various sensors, such as temperature, humidity, smoke concentration, etc., is used to assess the severity and spread trend of the fire. Select the appropriate sensor according to the environmental parameters that need to be monitored. For example, the DHT11 sensor can be used for temperature and humidity, the MQ-2 smoke sensor can be used for smoke concentration, and the carbon monoxide sensor can be used for carbon monoxide concentration. The signals collected by the sensor need to be processed. Analog sensors such as DHT11 output analog electrical signals, which need to be amplified, filtered, and processed before they can be correctly read by the microcontroller. Digital sensors such as MQ-2 smoke sensors can directly output digital signals, and the processing is relatively simple. After obtaining the temperature, humidity, and smoke concentration data, they will be compared according to the set minimum or maximum thresholds. If the calculated temperature, humidity, and smoke concentration data exceed the specified threshold range, an early warning will be issued according to different types of temperature, humidity, and smoke concentration, including when the temperature or humidity exceeds the threshold range, the temperature or humidity equipment can be remotely controlled to meet the standards.

[0053] S4. Calculate the optimal path based on the BIM model.

[0054] Optionally, obtain the locations of all emergency signs in the building as vertices; obtain the optimal paths from all vertices to other vertices through a parallelized Dijkstra algorithm; wherein, when determining the optimal path between vertices, take the shortest distance, shortest time and highest safety as the goals respectively, and determine three pre-selected paths between vertices through a parallelized Dijkstra algorithm; if the three pre-selected paths overlap, the overlapping path is the optimal path, otherwise, determine the optimal path among the three pre-selected paths in the order of highest safety, shortest time and shortest distance; and indicate the optimal path in a preset three-dimensional building model.

[0055] Input the spatial information and obstacle information in the BIM model into the selected Dijkstra algorithm for path calculation. The distances of all vertices need to be initialized to infinity, and the distance of the starting vertex needs to be initialized to 0. The time complexity of this step is O(V). Select the vertex with the minimum distance: In each iteration, you need to select the unvisited vertex that is currently closest to the starting vertex. Using a binary heap as a priority queue can complete this operation in O(logV) time, and a total of V selections are required, so the time complexity is O(VlogV). For each selected vertex, the distances of its adjacent vertices need to be updated. When using a binary heap as a priority queue, the adjacent vertices of each vertex will be visited at most once, so a total of E update operations are required. The time complexity of each update operation is O(logV), so the total time complexity is O(ElogV).

[0056] Adding the time complexity of the above steps, the total time complexity of the Dijkstra algorithm is O((V+E)logV). The algorithm considers all possible paths and selects the optimal path based on specific optimization goals (such as shortest distance, shortest time, highest safety, etc.). In this embodiment, the path with the highest safety refers to the path farthest from the spread coordinates of the fire feature point; in other embodiments, the path with the highest safety can also be defined by conventional techniques.

[0057] The parallel multi-label Dijkstra algorithm is an efficient algorithm used in graph theory to solve the single-source shortest path problem. Especially when dealing with large amounts of data in complex buildings, parallelization can significantly improve the execution speed of the algorithm, providing valuable time for people to escape from the fire scene. The standard Dijkstra algorithm is optimized using a greedy strategy or heap optimization, and its parallelization is realized, while processing multiple labels (i.e., the shortest path calculation from multiple source points to other vertices).

[0058] S4.1. Parallelized Dijkstra algorithm:

[0059] The parallelized Dijkstra algorithm mainly utilizes the parallel processing capabilities of multi-core processors to simultaneously process the locations of multiple emergency signs in the graph to accelerate the calculation of the shortest path. The advantage of the Dijkstra algorithm is that it can find the shortest path from the starting vertex to all other vertices, which is suitable for solving the shortest path problem in weighted graphs. Specific steps may include:

[0060] S4.1.1. Data partitioning: Divide the graph data in the three-dimensional building model into multiple sub-graphs or node sets, each of which can be processed in parallel by different processor cores.

[0061] S4.1.2. Parallel search for the minimum distance node: In each iteration, search for the node closest to the source point in all unprocessed nodes in parallel. This can be achieved through multi-threading or distributed computing.

[0062] S4.1.3. Update adjacent nodes: Once the node closest to the source point is found, update the distances and predecessor node information of all its adjacent nodes in parallel.

[0063] S4.1.4 Synchronization operations: Ensure data consistency between all parallel operations, which may require the use of locks or other synchronization mechanisms to avoid data contention.

[0064] S4.1.5. Repeat iteration: Repeat steps S4.1.2 to S4.1.4 until all nodes have been processed, that is, the shortest paths of all nodes have been determined.

[0065] S4.2, multi-label processing:

[0066] For multi-label processing, that is, calculating the shortest paths from multiple emergency sign sources to other emergency sign vertices at the same time, the following adjustments can be made based on the parallel Dijkstra algorithm:

[0067] Maintain a priority queue for each emergency sign source point: Each emergency sign source point corresponds to a priority queue, which is used to store the nodes to be processed starting from the emergency sign source point and their current shortest path length.

[0068] Execute multiple Dijkstra instances in parallel: Run multiple instances of the Dijkstra algorithm simultaneously, one for each emergency marker source. These instances can be executed in parallel on different processors or threads.

[0069] To improve and optimize the "Dijkstra algorithm", greedy strategy optimization and heap optimization can be used to solve Dijkstra's algorithm problems.

[0070] S5. Push BIM model images.

[0071] The finalized left and right paths will be pushed and displayed in the form of pictures.

[0072] Embodiment 2:

[0073] This embodiment provides a fire evacuation indication system based on a parallelized Dijkstra algorithm, including:

[0074] The data acquisition module is configured to: obtain the locations of all emergency signs in the building as vertices;

[0075] The optimal path determination module is configured as follows: by parallelizing the Dijkstra algorithm, the optimal paths from all vertices to other vertices are obtained; when determining the optimal path between vertices, the shortest distance, the shortest time and the highest security are respectively taken as the goals, and three pre-selected paths between vertices are determined by the parallelizing Dijkstra algorithm; if the three pre-selected paths overlap, the overlapping path is the optimal path, otherwise, the optimal path is determined from the three pre-selected paths in the order of highest security, shortest time and shortest distance;

[0076] The indication module is configured to indicate the optimal path in a preset three-dimensional building model.

[0077] The working method of the system is the same as the fire evacuation indication method based on the parallelized Dijkstra algorithm in Example 1, and will not be repeated here.

[0078] Embodiment 3:

[0079] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the fire evacuation indication method based on the parallelized Dijkstra algorithm described in Example 1 are implemented.

[0080] Embodiment 4:

[0081] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the program, the steps of the fire evacuation indication method based on the parallelized Dijkstra algorithm described in Example 1 are implemented.

[0082] Embodiment 5:

[0083] This embodiment provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the fire evacuation indication method based on the parallelized Dijkstra algorithm described in Example 1 are implemented.

[0084] The above description is only a preferred embodiment of the present embodiment and is not intended to limit the present embodiment. For those skilled in the art, the present embodiment may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present embodiment shall be included in the protection scope of the present embodiment.

Claims

1. A fire evacuation indication method based on a parallelized Dijkstra algorithm, characterized in that: include: Get the locations of all emergency signs in the building as vertices; By parallelizing the Dijkstra algorithm, the optimal path from all vertices to other vertices is obtained; when determining the optimal path between vertices, the shortest distance, shortest time and highest security are taken as the goals respectively, and three pre-selected paths between vertices are determined by the parallelized Dijkstra algorithm; if the three pre-selected paths overlap, the overlapping path is the optimal path, otherwise, the optimal path is determined among the three pre-selected paths in the order of highest security, shortest time and shortest distance; The optimal path is indicated in the preset 3D building model.

2. The fire evacuation indication method based on the parallelized Dijkstra algorithm according to claim 1, characterized in that: Initialize the distances of all vertices to infinity and the distance of the starting vertex to; In each iteration, select the unvisited vertex closest to the starting vertex, use a binary heap as a priority queue, and get the first time complexity; for each selected vertex, update the distance to its adjacent vertices, use a binary heap as a priority queue, and get the total second time complexity; add the first time complexity and the second time complexity to get the total time complexity of the Feldkirch algorithm; the Feldkirch algorithm considers all accessible paths, and determines the optimal path with the shortest distance, shortest time, and highest safety as the goals.

3. The fire evacuation indication method based on the parallelized Dijkstra algorithm according to claim 1, characterized in that: The graph data in the three-dimensional model of the building is divided into multiple subgraphs or node sets, each of which is processed in parallel by different processor cores; in each iteration, another emergency sign that is currently closest to the emergency sign is searched in parallel among all unprocessed nodes; After determining the nearest emergency marker, update all distance and predecessor node information in parallel; use locks or other synchronization mechanisms to avoid data competition; repeat the process until all nodes have been processed.

4. The fire evacuation indication method based on the parallelized Dijkstra algorithm according to claim 1, characterized in that: Each emergency sign source point corresponds to a priority queue, which is used to store the nodes to be processed starting from the emergency sign source point and their current shortest path length.

5. The fire evacuation indication method based on the parallelized Dijkstra algorithm according to claim 1, characterized in that: The safest path is the path farthest from the fire feature point spread coordinates.

6. The fire evacuation indication method based on the parallelized Dijkstra algorithm according to claim 5, characterized in that: Using the fire spread formula and preset parameters, determine the speed of the fire under the combined effect of wind speed and slope, as well as the speed in the opposite direction of the fire head; based on the fire spread speed and time step, obtain the coordinates of the next fire feature point spread.

7. A fire evacuation indication system based on the parallelized Dijkstra algorithm, characterized in that: include: The data acquisition module is configured to: obtain the locations of all emergency signs in the building as vertices; The optimal path determination module is configured as follows: by parallelizing the Dijkstra algorithm, the optimal paths from all vertices to other vertices are obtained; when determining the optimal path between vertices, the shortest distance, the shortest time and the highest security are respectively taken as the goals, and three pre-selected paths between vertices are determined by the parallelizing Dijkstra algorithm; if the three pre-selected paths overlap, the overlapping path is the optimal path, otherwise, the optimal path is determined from the three pre-selected paths in the order of highest security, shortest time and shortest distance; The indication module is configured to indicate the optimal path in a preset three-dimensional building model.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the fire evacuation indication method based on the parallelized Dijkstra algorithm as described in any one of claims 1 to 6 are implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: When the processor executes the program, the steps of the fire evacuation indication method based on the parallelized Dijkstra algorithm as described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the fire evacuation indication method based on the parallelized Dijkstra algorithm as described in any one of claims 1 to 6 are implemented.

Images