Population evacuation path optimization method and system based on AI intelligence

Abstract

The invention discloses a population evacuation path optimization method and system based on AI intellectualization, and belongs to the field of population evacuation. Path safety analysis is performed according to obtained specific data of disasters and basic information of a path arriving at an evacuation position; and selecting an optimal evacuation path according to an evacuation position safety evaluation result and a path safety analysis result. According to the method and the device, the safety of the nearby evacuation position after a disaster occurs is accurately estimated by integrating disaster data and basic information of the nearby evacuation position; and then the safety of the paths and the nearby evacuation positions is evaluated by integrating the basic information of the paths arriving at the evacuation positions, and the nearby safest evacuation position and the corresponding path are selected, so that the accuracy and safety of evacuation path optimization are improved.

Description

Technical Field

[0001] The present application relates to the field of population evacuation, and specifically to an AI-based intelligent population evacuation path optimization method and system. Background Art

[0002] When geological disasters such as earthquakes, tsunamis, and volcanic eruptions occur, the victims need to be evacuated to a safe evacuation location in a timely manner. During the evacuation process, if the victims do not have a correct and safe evacuation path, they will be evacuated to the wrong location, which will aggravate the disaster. Therefore, it is very necessary to optimize the evacuation path of the disaster population safely and accurately. When planning population evacuation routes, the existing technologies usually only select the nearest evacuation location and evacuation route, while ignoring the negative impact of disasters on the evacuation location and evacuation route. It is impossible to comprehensively estimate the safety of nearby evacuation locations after a disaster by combining disaster data and basic information of nearby evacuation locations, resulting in low accuracy and safety of route planning. Most of the existing technologies have the above problems. In order to solve the problems raised by this background technology, this application designs an AI-based intelligent population evacuation path optimization method and system. Summary of the invention

[0003] In response to the shortcomings of the existing technology, the present application proposes an AI-based intelligent population evacuation route optimization method and system. The present application comprehensively combines disaster data and basic information of nearby evacuation locations to accurately estimate the safety of nearby evacuation locations after a disaster occurs, and then comprehensively evaluates the safety of the path and nearby evacuation locations based on the basic information of the path to the evacuation location, selects the safest nearby evacuation location and its corresponding path, and improves the accuracy and safety of evacuation route optimization.

[0004] To achieve the above objectives, the present application provides the following technical solutions: In the first aspect, the present application provides an AI-based intelligent population evacuation path optimization method, which includes the following specific steps: S1. Obtain basic information of nearby evacuation locations, basic information of routes to the evacuation locations, and specific disaster data; S2. Evaluate the safety of nearby evacuation locations based on specific disaster data and basic information of nearby evacuation locations; S3. Perform path safety analysis based on the acquired disaster specific data and basic information of the path to the evacuation location; S4. Select the optimal evacuation route based on the evacuation location safety assessment results and the route safety analysis results.

[0005] As a preferred technical solution for the method of optimizing the population evacuation path based on AI intelligence, the specific contents of obtaining the basic information of the nearby evacuation locations, obtaining the basic information of the path to the evacuation locations, and obtaining the specific data of the disaster are: S11. Obtain disaster level data and disaster intensity through a disaster information acquisition terminal; S12. Obtain basic information of all nearby evacuation locations within a specified distance, including the construction age, disaster resistance level data of the evacuation location, and building surface damage data of the evacuation location before the disaster. Because the buildings at the evacuation location have weathered over time, it is definitely impossible to evaluate whether they can withstand the current disaster based on the disaster resistance status during the construction period. It is necessary to re-evaluate the disaster resistance capacity of the building based on the building surface damage data and construction age of the current evacuation location; S13. Obtain arrival path data of all nearby evacuation locations within a specified distance range, wherein the arrival path data includes path surface damage data and road surface disaster resistance grade data.

[0006] As a preferred technical solution for the method of optimizing the population evacuation path based on AI intelligence, the safety assessment of the nearby evacuation locations based on the specific data of the disaster and the basic information of the nearby evacuation locations includes the following specific steps: S21, obtaining corresponding disaster level data and disaster intensity, and at the same time obtaining the construction years of the evacuation location, the disaster resistance level data of the evacuation location, and the building surface damage data of the evacuation location before the disaster; S22. Based on the building surface damage data of the evacuation location before the disaster, the building danger level of the building at the evacuation location is evaluated. There are multiple ways to evaluate the safety of the building itself through the building surface damage data. The building danger level can be evaluated by considering the size and depth of the building surface damage, or by considering the size, depth and clustering of the building surface damage; S23. Analyze the danger of the building under the disaster based on the danger of the building itself, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data. The danger analysis method of the building under the disaster can be based on the historical corresponding disaster level data and disaster intensity, different disaster resistance level data, the danger of the building itself and the construction age of the building to build a deep learning neural network model, train the model and then predict the danger of the building under the disaster. It should be noted that the specific method of building the deep learning neural network model is: S231, obtaining the danger level of the building itself, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data during the historical disaster process, and obtaining the building danger level data after the disaster occurs, and constructing a deep learning neural network model whose input is the danger level of the building itself, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data during the disaster process, and whose output is the building danger level data after the disaster occurs; S232, extracting the danger degree of the building itself, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data during the historical disaster process, and obtaining the building danger level data after the disaster, and setting the parameter training set and the parameter test set in a ratio of 9:1; inputting 90% of the parameter training set into the deep learning neural network model for training to obtain an initial deep learning neural network model; using 10% of the parameter test set to test the initial deep learning neural network model, and outputting the initial deep learning neural network model that meets the accuracy of judging the building danger level after the maximum disaster occurs as the deep learning neural network model, in which the five inputs of the input layer of the neural network are: the danger degree of the building itself, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data during the disaster process, and the output of the output layer is the building danger level data after the disaster occurs; S233, input the acquired danger level of the building itself at each evacuation location, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data into the constructed deep learning neural network model, and output the building danger level data of each evacuation location after the disaster occurs; As a preferred technical solution for the population evacuation path optimization method based on AI intelligence, the path safety analysis based on the acquired specific disaster data and the basic information of the path to the evacuation location includes the following specific steps: S31, obtaining disaster level data, and simultaneously obtaining path surface damage data and road surface disaster resistance level data; S32. Evaluate the road hazard level under the influence of disasters based on the disaster level data, the path surface damage data and the road surface disaster resistance level data.

[0007] As a preferred technical solution for the population evacuation path optimization method based on AI intelligence, the selection of the optimal evacuation path according to the evacuation location safety assessment results and the path safety analysis results includes the following specific contents: Obtain the building hazard level after the disaster occurs at each evacuation location and the road hazard level under the influence of the disaster to each evacuation location, multiply the building hazard level by the building hazard weight to obtain the building hazard coefficient, multiply the road hazard level under the influence of the disaster by the road hazard weight to obtain the road hazard coefficient, add the building hazard coefficient of the corresponding evacuation location and the road hazard coefficient of the corresponding path of the corresponding evacuation location to obtain the overall hazard value of the corresponding evacuation location and the corresponding path, arrange the overall hazard values ​​of the nearby evacuation locations and the corresponding paths in descending order, and set the evacuation location and corresponding path corresponding to the smallest overall hazard value as the optimal evacuation path, and automatically generate the optimal evacuation path for the rescue personnel.

[0008] In the second aspect, the present application provides an AI-based intelligent population evacuation path optimization system, which is implemented based on the above-mentioned AI-based intelligent population evacuation path optimization method, and specifically includes a data acquisition module, an evacuation location safety assessment module, a path safety analysis module, and an optimal evacuation path selection module; The data acquisition module is used to acquire basic information of nearby evacuation locations, basic information of the paths to the evacuation locations, and specific data of the disaster; The evacuation location safety assessment module is used to assess the safety of nearby evacuation locations based on specific disaster data and basic information of nearby evacuation locations; The path safety analysis module is used to perform path safety analysis based on the acquired disaster specific data and basic information of the path to the evacuation location; The optimal evacuation path selection module is used to select the optimal evacuation path according to the evacuation location safety assessment result and the path safety analysis result; A control module may also be included, and the control module is used to control the operation of the data acquisition module, the evacuation location safety assessment module, the path safety analysis module and the optimal evacuation path selection module.

[0009] In a third aspect, the present application provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the above-mentioned AI-based intelligent population evacuation path optimization method by calling the computer program stored in the memory.

[0010] In a fourth aspect, the present application provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute the above-mentioned AI-based intelligent population evacuation path optimization method.

[0011] Compared with the prior art, the beneficial effects of this application are: The present application obtains basic information of nearby evacuation locations, obtains basic information of paths to the evacuation locations, and obtains specific data of disasters, evaluates the safety of nearby evacuation locations based on the specific data of disasters and the basic information of paths to the evacuation locations, performs path safety analysis based on the obtained specific data of disasters and the basic information of paths to the evacuation locations, and selects the optimal evacuation path based on the evacuation location safety assessment results and the path safety analysis results. The present application combines the disaster data and the basic information of nearby evacuation locations to accurately estimate the safety of nearby evacuation locations after a disaster occurs, then combines the basic information of paths to the evacuation locations to evaluate the safety of paths and nearby evacuation locations, selects the safest nearby evacuation location and its corresponding path, and improves the accuracy and safety of evacuation path optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings; Figure 1 This is a schematic diagram of the overall process of the population evacuation path optimization method based on AI intelligence in this application; Figure 2 This is a schematic diagram of step S2 of the population evacuation path optimization method based on AI intelligence in this application; Figure 3 This is a schematic diagram of step S3 of the population evacuation path optimization method based on AI intelligence in this application; Figure 4 This is a schematic diagram of the overall framework of the AI-based intelligent population evacuation path optimization system for this application. DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and is by no means intended to limit the present application and its application or use.

[0014] Example 1

[0015] In order to solve the technical problems raised in the background technology, the present application provides a preferred embodiment: Figure 1 - Figure 3 As shown, the population evacuation path optimization method based on AI intelligence includes the following specific steps: S1. Obtain basic information of nearby evacuation locations, basic information of routes to the evacuation locations, and specific disaster data; In one specific embodiment, the basic information of the nearby evacuation location is obtained, the basic information of the path to the evacuation location is obtained, and the specific content of the disaster data is obtained as follows: S11, obtaining disaster level data and disaster intensity through a disaster information acquisition terminal, taking earthquake as an example, for example, the earthquake level is 1-10; S12. Obtain basic information of all nearby evacuation locations within a specified distance, including the construction age, disaster resistance level data of the evacuation location, and building surface damage data of the evacuation location before the disaster. Because the buildings at the evacuation location have weathered over time, it is definitely impossible to evaluate whether they can withstand the current disaster based on the disaster resistance status during the construction period. It is necessary to re-evaluate the disaster resistance capacity of the building based on the building surface damage data and construction age of the current evacuation location. For example, the earthquake-resistant shelter is set up to withstand a magnitude 8 earthquake; S13, obtaining arrival path data of all nearby evacuation locations within a specified distance range, wherein the arrival path data includes path surface damage data and road surface disaster resistance grade data; S2. Evaluate the safety of nearby evacuation locations based on specific disaster data and basic information of nearby evacuation locations; In one specific embodiment, evaluating the safety of nearby evacuation locations based on specific disaster data and basic information of nearby evacuation locations includes the following specific steps: S21, obtaining corresponding disaster level data and disaster intensity, and at the same time obtaining the construction years of the evacuation location, the disaster resistance level data of the evacuation location, and the building surface damage data of the evacuation location before the disaster; S22. Evaluate the building danger of the building at the evacuation location based on the building surface damage data at the time before the disaster. There are many ways to evaluate the safety of the building itself through the building surface damage data. The building danger can be evaluated by considering the size and depth of the building surface damage, or by considering the size and depth of the building surface damage and the clustering of the damage. The formula for evaluating the building danger considering the size and depth of the building surface damage and the clustering of the damage can be: In this formula, M is the number of damages on the building surface, Lm is the set damage safety distance, L is the average distance between damages, si is the area of ​​the ith damage, di is the maximum depth of the ith damage, and Vm is the volume of the building; this formula takes into account the size, depth and clustering of damages on the building surface to assess the risk of the building itself. It is relatively simple to assess the risk of the building itself by only considering the size and depth of damages on the building surface. The calculation formula can be: ; S23. Analyze the danger of the building under the disaster based on the danger of the building itself, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data. The danger analysis method of the building under the disaster can be based on the historical corresponding disaster level data and disaster intensity, different disaster resistance level data, the danger of the building itself and the construction age of the building to build a deep learning neural network model, train the model and then predict the danger of the building under the disaster. It should be noted that the specific method of building the deep learning neural network model is: S231, obtaining the danger level of the building itself, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data during the historical disaster process, and obtaining the building danger level data after the disaster occurs, and constructing a deep learning neural network model whose input is the danger level of the building itself, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data during the disaster process, and whose output is the building danger level data after the disaster occurs; S232. The danger degree of the building itself, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data during the historical disaster process are extracted, and the building danger level data after the disaster is obtained, and the parameter training set and the parameter test set are set in a ratio of 9:1; 90% of the parameter training set is input into the deep learning neural network model for training to obtain an initial deep learning neural network model; 10% of the parameter test set is used to test the initial deep learning neural network model, and the initial deep learning neural network model that meets the maximum building danger level judgment accuracy after the disaster is output as the deep learning neural network model, wherein the output strategy formula of the s-th neuron of the m-th layer in the deep learning neural network model is: ,in is the output of the sth neuron in layer m, is the connection weight between the cth neuron in the m-1th layer and the sth neuron in the mth layer, represents the input of the cth neuron in the m-1th layer, represents the bias of the linear relationship between the c-th neuron in the m-1th layer and the s-th neuron in the m-1th layer, Sig() represents the Sigmoid activation function, and w is the number of neurons in the m-1th layer; in this embodiment, it should be noted that the five inputs of the input layer in this neural network are: the danger level of the building itself during the disaster, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location, and the construction age data, and the output of the output layer is the building danger level data after the disaster occurs; S233, input the acquired danger level of the building itself at each evacuation location, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data into the constructed deep learning neural network model, and output the building danger level data of each evacuation location after the disaster occurs; It should be noted that in this embodiment, the reason why the data after the disaster is not selected for direct calculation is that a large number of electronic devices will fail after the disaster, so it is impossible to obtain the specific information of the evacuation location and evacuation path in the disaster-stricken area in the first place. Therefore, this solution estimates the damage of the evacuation location and evacuation path by the disaster based on the specific information of the evacuation location and evacuation path stored before the disaster, so as to accurately estimate the safety of each evacuation location and evacuation path; At the same time, it should be specifically explained in this embodiment that the danger level here is classified according to national standards: The following is a common way of classifying building danger levels: Grade A (Safety): The building is structurally intact, with no obvious damage or danger points, and all systems (such as electrical, heating, drainage, etc.) are operating normally and meet safety standards. Grade A is rated as 1; Class B (Basic Safety): The structure of the building is basically intact, but there may be some minor damage or defects. These damage or defects usually do not pose a serious threat to the overall safety of the building, but still need to be repaired or maintained. Class B is rated as Level 2; Class C (moderate danger): There are certain safety hazards in the structure of the building. Some load-bearing structures or components may not meet the requirements of normal use. Such buildings may need to be reinforced or renovated to ensure their safety. Class C corresponds to level 3. Grade D (highly dangerous): The structure of the building has serious safety hazards, and part or all of the load-bearing structure may no longer meet the requirements of normal use. Such buildings are usually regarded as dangerous buildings and need to be repaired or demolished immediately. Grade D corresponds to level 4; S3. Perform path safety analysis based on the acquired disaster specific data and basic information of the path to the evacuation location; In one specific embodiment, performing path safety analysis based on the acquired specific disaster data and basic information of the path to the evacuation location includes the following specific steps: S31, obtaining disaster level data, and simultaneously obtaining path surface damage data and road surface disaster resistance level data; S32, based on the disaster level data, the path surface damage data and the road surface disaster resistance level data, the road hazard degree under the influence of the disaster is evaluated, wherein the road hazard degree under the influence of the disaster is calculated by the formula: , where Xi is the disaster level data, Xz is the road surface disaster resistance level data, C is the average number of damages on each section of the path, Lz is the area of ​​the zth damage, Dz is the area of ​​the zth damage, Dm is the area of ​​the road plane, and Lc is the thickness of the road. It should be noted that the meaning that needs to be expressed in this formula is that the higher the disaster level, the more serious the damage to the road, and at the same time, the degree of danger of roads with different damage under the damage of the disaster is also different. In this way, the road danger is proportional to the road damage, and the road danger is also proportional to the disaster level data, so as to analyze the degree of danger on the road when arriving at the evacuation location from the disaster area; S4. Selecting the optimal evacuation route based on the evacuation location safety assessment results and the route safety analysis results; In one specific embodiment, selecting the optimal evacuation path according to the evacuation location safety assessment result and the path safety analysis result includes the following specific contents: Obtain the building hazard level after the disaster occurs at each evacuation location and the road hazard level under the influence of the disaster to each evacuation location, multiply the building hazard level by the building hazard weight to obtain the building hazard coefficient, multiply the road hazard level under the influence of the disaster by the road hazard weight to obtain the road hazard coefficient, add the building hazard coefficient of the corresponding evacuation location and the road hazard coefficient of the corresponding path of the corresponding evacuation location to obtain the overall hazard value of the corresponding evacuation location and the corresponding path, arrange the overall hazard values ​​of the nearby evacuation locations and the corresponding paths in descending order, and set the evacuation location and corresponding path corresponding to the smallest overall hazard value as the optimal evacuation path, and automatically generate the optimal evacuation path for the rescue personnel.

[0016] It should also be noted in the present embodiment that the setting parameters in the present embodiment, such as the road hazard weight and the building hazard weight, are obtained in the following manner: basic information of 500 groups of nearby evacuation locations is obtained, and at the same time, basic information of the paths to the evacuation locations and specific disaster data are obtained, and the overall hazard values ​​of the corresponding evacuation locations and the corresponding paths are calculated, and the expert's selection and judgment results for the optimal evacuation path are obtained. The overall hazard values ​​and selection and judgment results of the corresponding evacuation locations and the corresponding paths are imported into the fitting software, and the values ​​of parameters such as the road hazard weight and the building hazard weight that meet the maximum judgment accuracy are output.

[0017] The advantages of this embodiment over the prior art are as follows: basic information of nearby evacuation locations is obtained, basic information of paths to the evacuation locations is obtained, and specific data of disasters is obtained, the safety of nearby evacuation locations is evaluated based on the specific data of disasters and the basic information of nearby evacuation locations, path safety analysis is performed based on the obtained specific data of disasters and the basic information of paths to the evacuation locations, and the optimal evacuation path is selected based on the evacuation location safety assessment results and the path safety analysis results. This application combines disaster data and basic information of nearby evacuation locations to accurately estimate the safety of nearby evacuation locations after a disaster occurs, and then combines the basic information of paths to the evacuation locations to evaluate the safety of paths and nearby evacuation locations, selects the safest nearby evacuation location and its corresponding path, and improves the accuracy and safety of evacuation path optimization.

[0018] Example 2

[0019] like Figure 4 As shown, the population evacuation path optimization system based on AI intelligence is implemented based on the above-mentioned population evacuation path optimization method based on AI intelligence, which specifically includes a data acquisition module, an evacuation location safety assessment module, a path safety analysis module and an optimal evacuation path selection module; Among them, the data acquisition module is used to obtain basic information of nearby evacuation locations, basic information of the path to the evacuation location, and specific data of the disaster; the evacuation location safety assessment module is used to assess the safety of nearby evacuation locations based on the specific data of the disaster and the basic information of the nearby evacuation locations; the path safety analysis module is used to perform path safety analysis based on the acquired specific data of the disaster and the basic information of the path to the evacuation location; the optimal evacuation path selection module is used to select the optimal evacuation path based on the evacuation location safety assessment result and the path safety analysis result; and it may also include a control module, the control module is used to control the operation of the data acquisition module, the evacuation location safety assessment module, the path safety analysis module and the optimal evacuation path selection module; Figure 4 The direction of the arrow in the figure represents the direction of data transmission.

[0020] Example 3

[0021] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes the above-mentioned AI-based intelligent population evacuation path optimization method by calling the computer program stored in the memory.

[0022] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement the AI-based intelligent population evacuation path optimization method provided in the above method embodiment. The electronic device may also include other components for implementing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0023] Example 4

[0024] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon; When the computer program runs on a computer device, the computer device executes the above-mentioned AI-based intelligent population evacuation path optimization method.

[0025] For example, the computer readable storage medium can be a read-only memory, a random access memory, a read-only CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0026] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0027] The terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article, or apparatus.

[0028] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of application involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the aforementioned application concept. For example, the above features are replaced with (but not limited to) technical features with similar functions applied in the present application.

Claims

1. The method for optimizing the population evacuation path based on AI intelligence is characterized by: It includes the following specific steps: S1. Obtain basic information of nearby evacuation locations, basic information of routes to the evacuation locations, and specific disaster data; S2. Evaluate the safety of nearby evacuation locations based on specific disaster data and basic information of nearby evacuation locations; S3. Perform path safety analysis based on the acquired disaster specific data and basic information of the path to the evacuation location; S4. Select the optimal evacuation route based on the evacuation location safety assessment results and the route safety analysis results.

2. The method for optimizing the population evacuation path based on AI intelligence as claimed in claim 1, characterized in that: The specific contents of obtaining the basic information of the nearby evacuation location, obtaining the basic information of the path to the evacuation location, and obtaining the specific data of the disaster are: S11. Obtain disaster level data and disaster intensity through a disaster information acquisition terminal; S12, obtaining basic information of all nearby evacuation locations within a specified distance range, including the construction age, disaster resistance level data of the evacuation location, and building surface damage data of the evacuation location before the disaster; S13. Obtain arrival path data of all nearby evacuation locations within a specified distance range, wherein the arrival path data includes path surface damage data and road surface disaster resistance grade data.

3. The method for optimizing the population evacuation path based on AI intelligence as claimed in claim 1, characterized in that: The safety assessment of nearby evacuation locations based on the specific disaster data and basic information of nearby evacuation locations includes the following specific steps: S21, obtaining corresponding disaster level data and disaster intensity, and at the same time obtaining the construction years of the evacuation location, the disaster resistance level data of the evacuation location, and the building surface damage data of the evacuation location before the disaster; S22, assessing the danger level of the building itself at the evacuation location based on the building surface damage data at the evacuation location before the disaster; S23. Analyze the danger level of the building under disaster based on the danger level of the building itself, the corresponding disaster level data, disaster intensity, disaster resistance level data of the evacuation location and the construction age data.

4. The method for optimizing the population evacuation path based on AI intelligence as claimed in claim 3, characterized in that: The analysis of the danger level of a building under the influence of a disaster based on the danger level of the building itself, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data includes the following specific steps: S231, obtaining the danger level of the building itself, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data during the historical disaster process, and obtaining the building danger level data after the disaster occurs, and constructing a deep learning neural network model whose input is the danger level of the building itself, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data during the disaster process, and whose output is the building danger level data after the disaster occurs; S232, extracting the danger level of the building itself, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data during the historical disaster process, and obtaining the building danger level data after the disaster, and setting the parameter training set and the parameter test set in a ratio of 9:1; inputting 90% of the parameter training set into the deep learning neural network model for training to obtain an initial deep learning neural network model; using 10% of the parameter test set to test the initial deep learning neural network model, and outputting the initial deep learning neural network model that meets the accuracy of judging the building danger level after the maximum disaster as the deep learning neural network model; S233. Input the acquired danger level of the building itself at each evacuation location, the corresponding disaster level data, the disaster intensity, the disaster resistance level data of the evacuation location and the construction age data into the constructed deep learning neural network model, and output the building danger level data of each evacuation location after the disaster occurs.

5. The method for optimizing the population evacuation path based on AI intelligence as claimed in claim 4, characterized in that: The path safety analysis based on the acquired specific disaster data and basic information of the path to the evacuation location includes the following specific steps: S31, obtaining disaster level data, and simultaneously obtaining path surface damage data and road surface disaster resistance level data; S32. Evaluate the road hazard level under the influence of disasters based on the disaster level data, the path surface damage data and the road surface disaster resistance level data.

6. The method for optimizing the population evacuation path based on AI intelligence as claimed in claim 5, characterized in that: The selection of the optimal evacuation path according to the evacuation location safety assessment result and the path safety analysis result includes the following specific contents: Obtain the building hazard level after the disaster occurs at each evacuation location and the road hazard level under the influence of the disaster to each evacuation location, multiply the building hazard level by the building hazard weight to obtain the building hazard coefficient, multiply the road hazard level under the influence of the disaster by the road hazard weight to obtain the road hazard coefficient, add the building hazard coefficient of the corresponding evacuation location and the road hazard coefficient of the corresponding path of the corresponding evacuation location to obtain the overall hazard value of the corresponding evacuation location and the corresponding path, arrange the overall hazard values ​​of the nearby evacuation locations and the corresponding paths in descending order, and set the evacuation location and corresponding path corresponding to the smallest overall hazard value as the optimal evacuation path, and automatically generate the optimal evacuation path for the rescue personnel.

7. An AI-based intelligent population evacuation path optimization system, which is implemented based on the AI-based intelligent population evacuation path optimization method according to any one of claims 1 to 6, characterized in that: It specifically includes a data acquisition module, an evacuation location safety assessment module, a path safety analysis module and an optimal evacuation path selection module; The data acquisition module is used to acquire basic information of nearby evacuation locations, basic information of the paths to the evacuation locations, and specific disaster data; The evacuation location safety assessment module is used to assess the safety of nearby evacuation locations based on specific disaster data and basic information of nearby evacuation locations; The path safety analysis module is used to perform path safety analysis based on the acquired disaster specific data and basic information of the path to the evacuation location; The optimal evacuation path selection module is used to select the optimal evacuation path according to the evacuation location safety assessment result and the path safety analysis result.

8. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; It is characterized in that the processor executes the AI ​​intelligent population evacuation path optimization method as described in any one of claims 1 to 6 by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes the population evacuation path optimization method based on AI intelligence as described in any one of claims 1 to 6.

Images