A rescue response situation analysis display method, system, medium and product

Abstract

A rescue response situation analysis and display method, system, medium and product, which relate to the field of situation display, and include: obtaining real-time perception data and historical rescue data of the rescue area; determining obstacle information of the rescue area based on drone image data and satellite image data; generating dynamic environmental situation of the rescue area according to obstacle type, obstacle location and sensor data; determining multiple rescue path plans based on obstacle distribution changes and weather environment changes; predicting resource allocation plans for each rescue path according to the rescue path, historical rescue path data and historical resource allocation data; associating resource allocation plans with rescue path plans for visual display. Implementing this method can improve rescue efficiency.

Description

Technical Field

[0001] The present application relates to the field of situation display, and in particular to a rescue response situation analysis display method, system, medium and product. Background Art

[0002] As global climate change intensifies, natural disasters such as earthquakes, floods, and forest fires occur more frequently, which puts higher demands on emergency rescue. The key to the success of rescue operations lies in whether the disaster situation can be assessed quickly and accurately and rescue plans can be deployed effectively. Therefore, how to quickly obtain real-time data in the disaster area for efficient rescue management has become the core of improving rescue efficiency and success rate.

[0003] At present, rescue response systems mainly rely on geographic information system (GIS) technology to obtain geographical information of the disaster area, including topography, building distribution, etc., as well as manually collecting disaster data. In addition, some rescue response systems integrate GPS technology to track the location of rescue teams and ensure the coordination of rescue operations.

[0004] Although the rescue response system in the relevant technology can achieve basic rescue route planning and resource allocation when dealing with large-scale disasters, it has obvious limitations when coping with rapidly changing disaster environments. It is difficult to determine the dynamic changes in the disaster area environment based on real-time conditions, resulting in low rescue efficiency and waste of resources. Summary of the invention

[0005] The present application provides a rescue response situation analysis display method, system, medium and product for improving rescue efficiency.

[0006] In a first aspect, the present application provides a rescue response situation analysis and display method, which is applied to a rescue response system, and the method includes: obtaining real-time perception data and historical rescue data of a rescue area, the real-time perception data including drone image data, satellite image data and sensor data, and the historical rescue data including historical rescue path data and historical resource allocation data; based on the drone image data and the satellite image data, determining obstacle information of the rescue area, the obstacle information including obstacle type and obstacle position; based on the obstacle type, the obstacle position and the sensor data, generating a dynamic environmental situation of the rescue area, the dynamic environmental situation including obstacle distribution changes and weather environment changes; based on the obstacle distribution changes and the weather environment changes, determining multiple rescue path plans, the rescue path plan including the safety factor, time duration and resource consumption of the rescue path; based on the rescue path, the historical rescue path data and the historical resource allocation data, predicting the resource allocation plan of each rescue path; associating the resource allocation plan with the rescue path plan for visual display.

[0007] By adopting the above technical solutions, first, the rescue response system integrates multi-source real-time perception data such as drone image data, satellite image data and sensor data to fully grasp the dynamic environmental situation of the rescue area. Secondly, the rescue response system plans multiple rescue path plans that take into account safety factors, timeliness and resource consumption according to the dynamic environmental situation. Then, the rescue response system predicts the resource allocation plan for each rescue path based on historical rescue path data and historical resource allocation data, and visualizes the resource allocation plan and rescue path plan, so that rescue commanders can make decisions quickly. This rescue response situation analysis and display method significantly improves the intelligence level of rescue response, reduces the workload of manual analysis, and improves rescue efficiency and resource utilization.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the dynamic environmental situation of the rescue area is generated based on the obstacle type, the obstacle position and the sensor data, and the dynamic environmental situation includes changes in obstacle distribution and weather environment changes, specifically including: determining fixed obstacles and mobile obstacles based on the obstacle type; performing time series analysis on the drone image data and the satellite image data to obtain a motion trajectory prediction result of the mobile obstacle; establishing a grid environment model of the rescue area based on the ground sensor data, the fixed obstacle and the motion trajectory prediction result of the mobile obstacle, the grid environment model of the rescue area including multiple grid units, the state of the grid unit is passable or impassable, and the sensor data includes the ground sensor data; constructing a weather change prediction model based on the weather sensor data, the sensor data includes the weather sensor data; the dynamic changes of the grid environment model of the rescue area and the weather change prediction model are integrated to generate the dynamic environmental situation, and the dynamic environmental situation includes changes in obstacle distribution and weather environment changes.

[0009] By adopting the above technical solutions, the rescue response system classifies obstacles into fixed and mobile types, and combines time series analysis to predict the movement trajectory of mobile obstacles, thereby establishing a dynamic grid environment model of the rescue area. The rescue response system integrates ground sensor data and weather change prediction models to update the traffic status of each grid unit in the grid environment model of the rescue area in real time, thereby accurately reflecting the dynamic changes in the rescue area. This grid-based dynamic environment modeling method enables the rescue response system to accurately grasp the real-time status of the rescue environment, provide reliable environmental information support for subsequent path planning, effectively avoid risks that may be encountered during the rescue process, and improve the safety and reliability of rescue operations.

[0010] In combination with some embodiments of the first aspect, in some embodiments, based on the changes in the obstacle distribution and the weather environment, multiple rescue path plans are determined, and the rescue path plan includes the safety factor, time duration and resource consumption of the rescue path, specifically including: dividing the rescue process of the rescue area into multiple time segments; based on the target time segment, establishing a target path planning network layer, and the target path planning network layer includes the target obstacle area and target weather environment of the target time segment; searching for multiple target candidate paths from the starting point to the end point in the target path planning network layer, and the target candidate paths avoid the target obstacle area in the target time segment; optimizing the target candidate paths to generate a target rescue path plan, and the optimization goals of the optimization processing are minimizing the total path length, maximizing the safety factor, minimizing the time duration and minimizing the resource consumption.

[0011] By adopting the above technical solution, the rescue response system divides the rescue process into multiple time segments and establishes an independent path planning network layer for each time segment, taking into account the specific obstacle distribution and weather environment changes of the time segment. By searching for candidate paths in each path planning network layer and performing multi-objective optimization processing, the rescue response system can simultaneously balance multiple key factors such as the total path length, safety factor, duration, and resource consumption. This multi-level path planning method based on time segments not only ensures the real-time and dynamic adaptability of the planning scheme, but also ensures the overall optimization of the rescue path, greatly improving the execution effect and success rate of the rescue operation.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the resource allocation plan for each rescue path is predicted based on the rescue path, the historical rescue path data and the historical resource allocation data, specifically including: training a preset model through the historical rescue path data and the historical resource allocation data to obtain a rescue resource allocation model, and the rescue resource allocation model is used to output resource allocation information based on the rescue path information; inputting the rescue path into the rescue resource allocation model to obtain a resource allocation plan for each rescue path.

[0013] By adopting the above technical solutions, the rescue response system uses historical rescue path data and historical resource allocation data to train the preset model and establish an intelligent rescue resource allocation model. This data-driven model can learn the optimal resource allocation strategy from historical experience and automatically predict the required resource allocation plan based on the characteristics of the new rescue path. It not only avoids the subjectivity and uncertainty that may exist in traditional manual experience allocation, but also makes more scientific and accurate resource allocation decisions based on statistical analysis of a large amount of historical data, effectively improving the efficiency of rescue resource use, reducing resource waste, and ensuring the smooth implementation of rescue operations.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of acquiring real-time perception data and historical rescue data of the rescue area, the real-time perception data includes drone image data, satellite image data and sensor data, and the historical rescue data includes historical rescue path data and historical resource allocation data, the method also includes: performing image segmentation and feature extraction on the drone image data and the satellite image data to identify the source of danger; determining the influence coefficient of weather conditions based on the sensor data; dividing the rescue area based on the overall area and the preset area of ​​the rescue area to obtain multiple rescue sub-areas; and calculating the danger coefficient of the rescue sub-area based on the type of the source of danger and the influence coefficient of the weather condition.

[0015] By adopting the above technical solutions, the rescue response system conducts intelligent analysis of drone image data and satellite image data to identify danger sources, and combines sensor data to evaluate the influence coefficient of weather conditions, thus realizing refined management of the rescue area. By dividing the large rescue area into multiple small rescue sub-areas and calculating the danger coefficient for each rescue sub-area, the rescue response system can carry out rescue planning and resource allocation in a more targeted manner. This method based on the identification and regional division of danger sources and weather condition influence coefficients enables rescue commanders to quickly grasp the degree of danger of each rescue sub-area, give priority to high-risk rescue sub-areas, and realize the rational allocation of rescue resources, which significantly improves the accuracy and efficiency of rescue operations and reduces the safety risks faced by rescue personnel.

[0016] In combination with some embodiments of the first aspect, in some embodiments, the method also includes: constructing a multi-level situation display interface, the multi-level situation display interface includes a macro layer, a meso layer and a micro layer, the macro layer is used to display a hazard factor distribution heat map of the entire rescue area, the hazard factor distribution heat map is used to represent the hazard factor of each rescue sub-area, the meso layer is used to display the hazard source and weather condition influence coefficient in the rescue sub-area, and the micro layer is used to display the monitoring data collected by cameras installed at each preset position in the rescue area.

[0017] By adopting the above technical solutions, the rescue response system has built a situation display interface at three levels: macro, meso and micro, realizing multi-dimensional visualization of rescue information. The macro level intuitively displays the hazard coefficient of each rescue sub-area through the hazard coefficient distribution heat map, the meso level displays the specific hazard sources and weather conditions in detail, and the micro level displays monitoring data in real time. This hierarchical display method enables commanders to quickly switch information views of different dimensions as needed, so that they can grasp the overall situation and pay attention to local details, which greatly improves the intuitiveness and accuracy of rescue command and provides all-round information support for scientific decision-making.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of constructing a multi-level situation display interface, the method also includes: collecting location data and vital signs data of the rescuer, the location data is used to indicate the rescue sub-area where the rescuer is located, and the vital signs data include heart rate, blood oxygen and body temperature; calculating the fatigue of the rescuer based on the danger factor of the rescue sub-area and the vital signs data: when the fatigue of the rescuer exceeds a preset fatigue threshold, triggering a personnel rotation reminder in the multi-level situation display interface.

[0019] By adopting the above technical solutions, the rescue response system collects and monitors the location data and vital signs data of rescuers in real time, and establishes an intelligent personnel fatigue assessment and rotation reminder mechanism in combination with the risk factor of the rescue sub-area. The rescue response system can automatically calculate the fatigue level of rescuers and trigger rotation reminders in time when the fatigue level exceeds the preset fatigue threshold. This data-based personnel management method effectively prevents the potential safety hazards caused by excessive fatigue of rescuers, ensures the physical and mental health of rescuers, improves the continuity and safety of rescue operations, and also optimizes the efficiency of human resource deployment.

[0020] In a second aspect, an embodiment of the present application provides a rescue response system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the rescue response system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions. When the computer program product is run on a rescue response system, the rescue response system executes the method described in the first aspect and any possible implementation manner of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions, which, when executed on a rescue response system, enable the rescue response system to execute the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] It can be understood that the rescue response system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0025] 1. By adopting the above technical solution, first, the rescue response system integrates multi-source real-time perception data such as drone image data, satellite image data and sensor data to fully grasp the dynamic environmental situation of the rescue area. Secondly, the rescue response system plans multiple rescue path plans that take into account safety factors, timeliness and resource consumption according to the dynamic environmental situation. Then, the rescue response system predicts the resource allocation plan for each rescue path based on historical rescue path data and historical resource allocation data, and visualizes the resource allocation plan and rescue path plan, so that rescue commanders can make decisions quickly. This rescue response situation analysis and display method significantly improves the intelligence level of rescue response, reduces the workload of manual analysis, and improves rescue efficiency and resource utilization.

[0026] 2. By adopting the above technical solution, the rescue response system divides the rescue process into multiple time segments and establishes an independent path planning network layer for each time segment, taking into account the specific obstacle distribution and weather environment changes of the time segment. By searching for candidate paths in each path planning network layer and performing multi-objective optimization processing, the rescue response system can simultaneously balance multiple key factors such as the total path length, safety factor, duration and resource consumption. This multi-level path planning method based on time segments not only ensures the real-time and dynamic adaptability of the planning scheme, but also ensures the overall optimization of the rescue path, greatly improving the execution effect and success rate of the rescue operation.

[0027] 3. By adopting the above technical solutions, the rescue response system conducts intelligent analysis of drone image data and satellite image data to identify danger sources, and combines sensor data to evaluate the influence coefficient of weather conditions, thereby realizing refined management of the rescue area. By dividing the large rescue area into multiple small rescue sub-areas and calculating the danger coefficient for each rescue sub-area, the rescue response system can carry out rescue planning and resource allocation in a more targeted manner. This method based on the identification and regional division of danger sources and weather condition influence coefficients enables rescue commanders to quickly grasp the degree of danger of each rescue sub-area, give priority to high-risk rescue sub-areas, and realize the rational allocation of rescue resources, which significantly improves the accuracy and efficiency of rescue operations and reduces the safety risks faced by rescue personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 This is a flowchart of a rescue response situation analysis and display method in an embodiment of the present application;

[0029] Figure 2This is another flowchart of the rescue response situation analysis display method in the embodiment of the present application;

[0030] Figure 3 It is a schematic diagram of a physical device structure of a rescue response system in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0032] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0033] The following is a description of the process of the method provided by this implementation. Figure 1 , which is a flow chart of the rescue response situation analysis display method in an embodiment of the present application.

[0034] S101, acquiring real-time perception data and historical rescue data of the rescue area, wherein the real-time perception data includes drone image data, satellite image data, and sensor data, and the historical rescue data includes historical rescue path data and historical resource allocation data;

[0035] Among them, the rescue area refers to the geographical scope where rescue activities need to be carried out, which can be the site of a natural disaster, an accident site, etc.; real-time perception data refers to the rescue area status information obtained in real time through various data acquisition devices; drone image data refers to aerial images of the rescue area collected by the camera equipment carried by the drone; satellite image data refers to image data obtained by remote sensing imaging of the rescue area by a satellite; sensor data refers to parameters such as temperature, humidity, wind direction, vibration, etc. collected by various sensors; historical rescue path data refers to the specific rescue route information adopted by past rescue operations in the rescue area; historical resource allocation data refers to the specific configuration plans of personnel, materials, equipment and other resources in historical rescue paths in previous rescue operations.

[0036] Specifically, the rescue response system dispatches drones to cruise around the area to obtain real-time aerial images, namely, drone image data. At the same time, the rescue response system accesses the satellite remote sensing system to obtain regional satellite images, namely, satellite image data. Various sensors deployed in the rescue area continuously collect sensor data and transmit it to the rescue response system. The rescue response system will also retrieve the path planning and resource allocation records of previous rescue operations in the rescue area or similar areas, namely, historical rescue path data and historical resource allocation data.

[0037] S102, determining obstacle information of the rescue area based on the drone image data and the satellite image data, where the obstacle information includes obstacle type and obstacle location;

[0038] Among them, obstacle information refers to the characteristic description of various obstructing objects in the rescue area that may affect the implementation of rescue operations; obstacle type refers to the specific attribute classification of obstacles, such as building debris, broken roads, flooded areas, etc.; obstacle location refers to the specific geographical coordinates and spatial distribution of each obstacle in the rescue area.

[0039] Specifically, first, the rescue response system inputs the drone image data and satellite image data into the image recognition model to automatically detect and locate each obstacle in the image data. Then, the rescue response system analyzes the specific attributes of each obstacle through the feature extraction algorithm to determine the obstacle type. At the same time, the rescue response system combines the geographic information and positioning information of the image data to determine the precise spatial location of each obstacle, that is, the obstacle location. Finally, the rescue response system stores the identified obstacle type and obstacle location in a structured manner.

[0040] S103, generating a dynamic environmental situation of the rescue area according to the obstacle type, the obstacle position and the sensor data, the dynamic environmental situation including obstacle distribution changes and weather environment changes;

[0041] Among them, the dynamic environmental situation refers to the real-time status of environmental elements in the rescue area and their changing trends; the change in obstacle distribution refers to the dynamic changes in the location, range and other spatial characteristics of obstacles over time; the change in weather environment refers to the dynamic changes in meteorological elements such as temperature, precipitation and wind direction over time.

[0042] Specifically, first, the rescue response system integrates obstacle information and sensor data, and combined with the analysis of historical data sequences, the rescue response system calculates the movement trajectory and diffusion trend of obstacles to obtain the changes in obstacle distribution. At the same time, based on meteorological sensor data, the rescue response system predicts weather and environmental changes in the future. Then, the rescue response system fuses the obstacle distribution changes and weather and environmental changes to generate a complete dynamic environmental situation. The dynamic environmental situation will be continuously updated as new data is continuously accessed to ensure the real-time and accuracy of the situation prediction.

[0043] Optionally, in general, the dynamic environmental situation of the rescue area is generated according to the obstacle type, the obstacle location and the sensor data. The dynamic environmental situation includes changes in obstacle distribution and weather environment changes. This can be achieved in the following ways, which are not limited here: determining fixed obstacles and mobile obstacles according to the obstacle type; performing time series analysis on the drone image data and the satellite image data to obtain a motion trajectory prediction result of the mobile obstacle; establishing a grid environment model of the rescue area according to the ground sensor data, the fixed obstacle and the motion trajectory prediction result of the mobile obstacle, the grid environment model of the rescue area includes multiple grid units, and the state of the grid unit is passable or impassable, and the sensor data includes the ground sensor data; constructing a weather change prediction model according to the weather sensor data, and the sensor data includes the weather sensor data; fusing the dynamic changes of the grid environment model of the rescue area with the weather change prediction model to generate the dynamic environmental situation, which includes changes in obstacle distribution and weather environment changes.

[0044] S104, determining a plurality of rescue path plans based on the change in the obstacle distribution and the change in the weather environment, wherein the rescue path plans include a safety factor, a time duration, and a resource consumption of the rescue path;

[0045] Among them, the rescue route plan refers to a complete description of the feasible route from the rescue starting point to the end point and its related evaluation indicators; the safety factor refers to the assessment value of the danger level of the rescue route, taking into account factors such as obstacle threats and weather influences; the time required refers to the estimated time required to complete the rescue route; and the resource consumption refers to the amount of human, material and other resources estimated to be required to execute the rescue route.

[0046] Specifically, the rescue response system divides the rescue process into time segments and establishes a path planning network layer for each time segment. In each path planning network layer, the rescue response system uses the improved A* algorithm to search for feasible candidate paths while avoiding predicted obstacle areas. For each candidate path, the rescue response system calculates its safety factor (taking into account factors such as obstacle distance and weather impact), estimates the duration (based on path length and traffic conditions), and evaluates resource consumption (including personnel, equipment, materials, etc.). Finally, the response system uses a multi-objective optimization algorithm to seek the optimal balance among the goals of shortest total path length, highest safety factor, shortest duration, and lowest resource consumption, and determines multiple optional rescue path solutions.

[0047] Optionally, in general, based on the changes in the obstacle distribution and the weather environment, multiple rescue path plans are determined, and the rescue path plan includes the safety factor, time duration and resource consumption of the rescue path, which can be achieved in the following ways, which are not limited here: dividing the rescue process of the rescue area into multiple time segments; based on the target time segment, establishing a target path planning network layer, and the target path planning network layer includes the target obstacle area and target weather environment of the target time segment; searching for multiple target candidate paths from the starting point to the end point in the target path planning network layer, and the target candidate paths avoid the target obstacle area in the target time segment; optimizing the target candidate paths to generate a target rescue path plan, and the optimization goals of the optimization processing are minimizing the total path length, maximizing the safety factor, minimizing the time duration and minimizing the resource consumption.

[0048] S105, predicting a resource allocation scheme for each rescue path according to the rescue path, the historical rescue path data, and the historical resource allocation data;

[0049] Among them, the resource allocation plan refers to the specific configuration plan for various types of resources required for a specific rescue path; resource type refers to different types of resources such as personnel, vehicles, equipment, and materials required for rescue.

[0050] Specifically, first, the rescue response system cleans and extracts features from historical rescue data to build a training data set containing path features and resource allocation relationships; then, the rescue response system uses machine learning algorithms (such as random forests, neural networks, etc.) to train resource allocation prediction models; the new rescue path is input into the trained resource allocation prediction model to predict the number of various resources required for the rescue path. The rescue response system will also consider the current available resources and make appropriate adjustments to the prediction results. Finally, the rescue path data generates a detailed resource allocation plan, including the number of rescue personnel, professional types, required equipment models, and types and quantities of supplies.

[0051] Optionally, under normal circumstances, based on the rescue path, the historical rescue path data and the historical resource allocation data, predicting the resource allocation plan for each rescue path can be achieved in the following manner, which is not limited here: training a preset model through the historical rescue path data and the historical resource allocation data to obtain a rescue resource allocation model, which is used to output resource allocation information based on the rescue path information; inputting the rescue path into the rescue resource allocation model to obtain a resource allocation plan for each rescue path.

[0052] The steps to build a deep learning-based rescue resource allocation model are as follows:

[0053] First, the rescue response system collects historical rescue path data and historical resource allocation data. Historical rescue path data refers to the specific rescue route information adopted by past rescue operations in the rescue area; historical resource allocation data refers to the specific configuration plan of personnel, materials, equipment and other resources in the historical rescue path of previous rescue operations. The rescue response system stores the collected historical rescue path data and historical resource allocation data in data set D in chronological order, and the format of each data is (historical rescue path data, historical resource allocation data). Among them, historical rescue path data is the input feature of model training, and historical resource allocation data is the output feature of model training.

[0054] Then, the rescue response system builds a LSTM-based recurrent neural network, which includes an input layer, two LSTM hidden layers, a fully connected layer, and an output layer. The input layer inputs historical rescue path data, the number of hidden layer nodes is set to 64, and the number of fully connected layer nodes is set to 32. The output layer outputs historical resource allocation data.

[0055] Next, the rescue response system uses the Adam optimizer, the learning rate is set to 0.001, and the training batch size is 32. It can also be set according to the actual situation and is not limited here. 80% of the historical data is divided into a training set and 20% is divided into a validation set. 100 epochs are trained and the model with the highest accuracy of the validation set is saved. It can also be set according to the actual situation and is not limited here. Epoch is the process in which the training data set passes through the neural network once. In machine learning and deep learning, epoch is a unit used to measure the number of times the entire training set is repeatedly learned. Specifically, when the neural network completes a forward calculation and back propagation process, that is, all data has been processed by the network once, this completes an epoch. The rescue response system uses binary cross entropy as the loss function and Early Stopping to prevent overfitting. When the value of the loss function exceeds the preset function threshold, the model training is determined to be completed and the rescue resource allocation model is obtained. Early Stopping is a technology in deep learning and machine learning to prevent model overfitting. It determines when to stop training by monitoring the performance of the model on the validation set.

[0056] Finally, the rescue response system inputs the input features in the validation set into the rescue resource allocation model, and then obtains the predicted output of the rescue resource allocation model. The predicted output of the rescue resource allocation model is compared with the actual output features in the validation set, and some performance indicators such as accuracy, precision, recall, F1 score, mean square error (MSE), etc. are used to evaluate the performance of the rescue resource allocation model. According to the performance of the rescue resource allocation model on the validation set, the parameters of the rescue resource allocation model are adjusted, including adjusting the learning rate, changing the model complexity (such as increasing or decreasing the number of layers or nodes of the neural network), modifying the regularization strength, etc. This process may require multiple iterations, each adjustment based on the previous learning results, so as to optimize the rescue resource allocation model.

[0057] S106: Associating the resource allocation plan with the rescue path plan and performing visual display.

[0058] Among them, association refers to pairing the resource allocation plan and the rescue path plan; visualization means intuitively presenting various information of the rescue plan in a graphical way.

[0059] Specifically, the rescue response system displays the resource allocation plan and the rescue path plan in association on a tablet or touch screen interface. When the user clicks on one of the rescue path plans, the touch screen will display the detailed information of the rescue path and the corresponding resource allocation plan. The user can also put forward specific requirements, and the rescue response system will filter the resource allocation plan and the rescue path plan according to the user's specific requirements and display the filtering results.

[0060] By adopting the above technical solutions, first, the rescue response system integrates multi-source real-time perception data such as drone image data, satellite image data and sensor data to fully grasp the dynamic environmental situation of the rescue area. Secondly, the rescue response system plans multiple rescue path plans that take into account safety factors, timeliness and resource consumption according to the dynamic environmental situation. Then, the rescue response system predicts the resource allocation plan for each rescue path based on historical rescue path data and historical resource allocation data, and visualizes the resource allocation plan and rescue path plan, so that rescue commanders can make decisions quickly. This rescue response situation analysis and display method significantly improves the intelligence level of rescue response, reduces the workload of manual analysis, and improves rescue efficiency and resource utilization.

[0061] The following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the rescue response situation analysis display method in an embodiment of the present application.

[0062] S201, acquiring real-time perception data and historical rescue data of the rescue area, wherein the real-time perception data includes drone image data, satellite image data, and sensor data, and the historical rescue data includes historical rescue path data and historical resource allocation data;

[0063] For details, please refer to step S101, which will not be described in detail here.

[0064] S202, performing image segmentation and feature extraction on the drone image data and the satellite image data to identify danger sources;

[0065] Among them, image segmentation refers to the process of dividing an image into multiple regions with semantic meanings; feature extraction refers to extracting numerical features from an image that can characterize the characteristics of the target; hazard sources refer to various types of dangerous factors that may pose a threat to rescue operations, such as building collapse points, ground collapse, and leakage of hazardous materials.

[0066] Specifically, first, the rescue response system uses deep learning segmentation algorithms (such as U-Net, Mask R-CNN, etc.) to perform semantic segmentation on drone images and satellite images, dividing the images into different target areas; then, the rescue response system uses SIFT, HOG and other algorithms to extract visual features such as texture, shape, and color of each target area; then, the rescue response system compares the extracted visual features with the preset hazard source database to determine whether there is a hazard source in each area. The rescue response system will also fuse the recognition results of the two image sources to improve the reliability of recognition. Finally, the rescue response system stores the identified hazard sources in a structured form, including location coordinates, type labels, degree of hazard and other attributes.

[0067] S203, determining a weather condition influence coefficient according to the sensor data;

[0068] Among them, the weather condition impact coefficient refers to the quantitative indicator of the impact of different weather factors on rescue operations; sensor data refers to weather condition parameters such as temperature, humidity, wind speed, etc. collected by meteorological sensors.

[0069] Specifically, first, the rescue response system standardizes the data of various meteorological sensors. Then, the rescue response system determines the weight coefficients of various weather condition parameters based on expert experience. Next, the rescue response system multiplies the standardized data with the weight coefficients and sums them to obtain a comprehensive impact index. The rescue response system also considers the sensitivity of different types of rescue activities to weather conditions, dynamically adjusts the impact coefficients, and obtains the final weather condition impact parameters.

[0070] S204, dividing the rescue area based on the overall area and the preset area of ​​the rescue area to obtain a plurality of rescue sub-areas;

[0071] Among them, the preset area refers to a pre-defined range used to divide the entire rescue area to facilitate rescue personnel to carry out rescue work; the rescue sub-area refers to a part of the rescue area, and the rescue area includes multiple rescue sub-areas.

[0072] Specifically, the rescue response system divides the overall area of ​​the rescue area by the preset area to obtain the number of rescue sub-areas. The rescue response system divides the rescue area from the preset position to obtain the location information of the multiple rescue sub-areas.

[0073] S205, calculating the risk factor of the rescue sub-area according to the type of the risk source and the weather condition influence coefficient;

[0074] Among them, the danger coefficient is a numerical indicator that quantitatively expresses the overall danger level of the rescue sub-area; the danger source type refers to the attribute classification of different types of danger sources.

[0075] Specifically, first, the rescue response system determines the risk source coefficient according to the type of risk source. Then, the rescue response system determines the weight corresponding to the risk source coefficient and the weight of the weather condition influence coefficient according to the preset risk factor calculation weight table. Then, the rescue response system performs weighted summation based on the weight corresponding to the risk source coefficient and the weight of the weather condition influence coefficient to obtain the risk coefficient of the rescue sub-area.

[0076] S206. Determine obstacle information of the rescue area based on the drone image data and the satellite image data, where the obstacle information includes obstacle type and obstacle location;

[0077] For details, please refer to step S102, which will not be described in detail here.

[0078] S207, generating a dynamic environmental situation of the rescue area according to the obstacle type, the obstacle position and the sensor data, the dynamic environmental situation including obstacle distribution changes and weather environment changes;

[0079] For details, please refer to step S103, which will not be described in detail here.

[0080] S208, determining a plurality of rescue path plans based on the change in the obstacle distribution and the change in the weather environment, wherein the rescue path plans include a safety factor, a time duration, and a resource consumption of the rescue path;

[0081] For details, please refer to step S104, which will not be described in detail here.

[0082] S209, predicting a resource allocation scheme for each rescue path according to the rescue path, the historical rescue path data, and the historical resource allocation data;

[0083] For details, please refer to step S105, which will not be described in detail here.

[0084] S210, associating the resource allocation plan with the rescue path plan and performing visual display;

[0085] For details, please refer to step S106, which will not be described in detail here.

[0086] S211, constructing a multi-level situation display interface, the multi-level situation display interface includes a macro layer, a meso layer and a micro layer, the macro layer is used to display a heat map of the hazard coefficient distribution of the entire rescue area, the hazard coefficient distribution heat map is used to represent the hazard coefficient of each rescue sub-area, the meso layer is used to display the hazard source and weather condition influence coefficient in the rescue sub-area, and the micro layer is used to display the monitoring data collected by the cameras installed at each preset position in the rescue area;

[0087] Among them, the multi-level situation display interface refers to a visualization system with different spatial scales and information granularity; the macro layer refers to the overall situation view covering the entire rescue area; the meso layer refers to the detailed information display for a single rescue sub-area; the micro layer refers to the real-time data display of specific monitoring points; the heat map refers to a visualization graphic that uses different shades of color to represent the risk factor; the preset position refers to a fixed monitoring point planned and deployed in advance; the monitoring data is used to represent the real-time video stream collected by the camera and its analysis results.

[0088] Specifically, the rescue response system uses GIS maps as the base map at the macro level, and displays the distribution of hazard factors of each rescue sub-area through a hazard factor distribution heat map, with colors from green to red indicating increasing hazard factors; at the meso level, detailed information of the selected rescue sub-area is displayed, including the location, type, and impact range of the hazard source, as well as the value and change trend of the coefficient of weather conditions; at the micro level, the video images of each fixed monitoring point are displayed in real time, and the results of intelligent analysis, such as abnormal event detection and target tracking, are superimposed; the rescue response system supports seamless switching and linkage between multiple levels. Clicking an area on the hazard factor distribution heat map allows you to drill down to view the meso information of the rescue sub-area, and clicking a monitoring point on the meso map allows you to call up real-time video images.

[0089] S212, collecting location data and vital sign data of the rescuer, where the location data is used to indicate the rescue sub-area where the rescuer is located, and the vital sign data includes heart rate, blood oxygen and body temperature;

[0090] Among them, location data refers to the real-time geographic coordinate information of the rescuers; vital signs data refers to the physiological indicators of the rescuers' physical condition; heart rate is used to indicate the number of heart beats per minute; blood oxygen indicates the percentage of oxygen saturation in the blood; and body temperature refers to the temperature value measured on the human body surface.

[0091] Specifically, first, the rescue response system obtains the location data of the rescuer through the positioning terminal (such as Beidou, GPS equipment) carried by the rescuer. Then, the rescue response system spatially matches the location data with the location data of the rescue sub-area to determine the rescue sub-area where the rescuer is located. At the same time, the rescue response system continuously collects vital signs data such as heart rate, blood oxygen, and body temperature through wearable devices such as smart bracelets.

[0092] S213. Calculate the rescuer's fatigue level according to the risk factor of the rescue sub-area and the vital sign data:

[0093] Among them, fatigue level is a quantitative indicator of the rescue workers' physical exertion and fatigue state; the risk factor refers to the degree of danger of the working environment; the fatigue calculation model is a mathematical model used to evaluate the fatigue level of personnel; the physiological indicator threshold represents the normal range boundary of vital signs; the fatigue warning level refers to the different warning levels divided according to the fatigue level.

[0094] Specifically, first, the rescue response system compares the vital sign data with the normal value range and calculates the degree of deviation of each indicator. Next, the rescue response system determines the impact of the risk factor of the rescue sub-area on physical exertion from historical data. Then, the rescue response system calculates the fatigue score based on the working hours, the risk factor of the rescue sub-area and the degree of deviation of each indicator. The rescue response system will take into account individual physical differences and historical data to personalize the fatigue calculation results.

[0095] S214: When the fatigue level of the rescuer exceeds a preset fatigue level threshold, a personnel rotation reminder is triggered in the multi-level situation display interface.

[0096] Among them, the preset fatigue threshold refers to the fatigue level standard for personnel rotation; the personnel rotation reminder refers to the warning information issued by the rescue response system to replace rescue personnel.

[0097] Specifically, the rescue response system compares the calculated fatigue level with the preset fatigue threshold in real time. When it is detected that the fatigue level exceeds the preset fatigue threshold, a warning window pops up at the corresponding position of the multi-level situation display interface. The warning information in the warning window includes the personnel number, location, fatigue level, duration exceeding the preset fatigue threshold, etc. The rescue response system also sends rotation notifications to the on-site commander and backup personnel.

[0098] The following describes the rescue response system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of a rescue response system in an embodiment of the present application.

[0099] It should be noted that Figure 3 The structure of the rescue response system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0100] like Figure 3 As shown, the rescue response system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In the RAM 303, various programs and data required for the operation of the rescue response system are also stored. The CPU 301, the ROM 302 and the RAM 303 are connected to each other through the bus 304. The input / output (I / O) interface 305 is also connected to the bus 304.

[0101] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0102] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0103] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0104] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0105] Specifically, the rescue response system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the rescue response situation analysis and display method provided in the above embodiment is implemented.

[0106] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the rescue response system described in the above embodiment; or may exist independently without being assembled into the rescue response system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the rescue response system, the rescue response system implements the rescue response situation analysis and display method provided in the above embodiment.

[0107] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0108] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0109] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A rescue response situation analysis and display method, characterized in that: Applied to a rescue response system, the method comprises: Acquire real-time perception data and historical rescue data of the rescue area, wherein the real-time perception data includes drone image data, satellite image data, and sensor data, and the historical rescue data includes historical rescue path data and historical resource allocation data; Determine obstacle information of the rescue area based on the drone image data and the satellite image data, wherein the obstacle information includes obstacle type and obstacle location; Generate a dynamic environmental situation of the rescue area according to the obstacle type, the obstacle position and the sensor data, wherein the dynamic environmental situation includes a change in obstacle distribution and a change in weather environment; Based on the change in the obstacle distribution and the change in the weather environment, determine multiple rescue path plans, wherein the rescue path plans include a safety factor, a time duration, and a resource consumption of the rescue path; Predicting a resource allocation scheme for each rescue path according to the rescue path, the historical rescue path data, and the historical resource allocation data; Associating the resource allocation plan with the rescue path plan and performing visual display; Based on the change in the obstacle distribution and the change in the weather environment, multiple rescue path plans are determined, and the rescue path plans include the safety factor, time duration and resource consumption of the rescue path. Specifically, the rescue process of the rescue area is divided into multiple time segments; based on the target time segment, a target path planning network layer is established, and the target path planning network layer includes the target obstacle area and target weather environment of the target time segment; multiple target candidate paths from the starting point to the end point are searched in the target path planning network layer, and the target candidate paths avoid the target obstacle area in the target time segment; the target candidate paths are optimized to generate a target rescue path plan, and the optimization goals of the optimization process are minimizing the total path length, maximizing the safety factor, minimizing the time duration and minimizing the resource consumption.

2. The method according to claim 1, characterized in that: The generating of the dynamic environmental situation of the rescue area according to the obstacle type, the obstacle position and the sensor data, wherein the dynamic environmental situation includes the change of obstacle distribution and the change of weather environment, specifically includes: Determining fixed obstacles and mobile obstacles according to the obstacle type; Performing time series analysis on the drone image data and the satellite image data to obtain a motion trajectory prediction result of the moving obstacle; Establishing a grid environment model of a rescue area according to the ground sensor data, the prediction results of the motion trajectories of the fixed obstacles and the mobile obstacles, wherein the grid environment model of the rescue area includes a plurality of grid cells, and the status of the grid cells is passable or impassable, and the sensor data includes the ground sensor data; constructing a weather change prediction model based on weather sensor data, wherein the sensor data includes the weather sensor data; The dynamic changes of the gridded environment model of the rescue area and the weather change prediction model are integrated to generate the dynamic environment situation, which includes the changes in obstacle distribution and weather environment changes.

3. The method according to claim 1, characterized in that The predicting of a resource allocation scheme for each rescue path according to the rescue path, the historical rescue path data and the historical resource allocation data specifically includes: The preset model is trained by using the historical rescue path data and the historical resource allocation data to obtain a rescue resource allocation model, wherein the rescue resource allocation model is used to output resource allocation information according to the rescue path information; The rescue path is input into the rescue resource allocation model to obtain a resource allocation plan for each rescue path.

4. The method according to claim 1, characterized in that After the step of acquiring real-time perception data and historical rescue data of the rescue area, wherein the real-time perception data includes drone image data, satellite image data, and sensor data, and the historical rescue data includes historical rescue path data and historical resource allocation data, the method further includes: Performing image segmentation and feature extraction on the drone image data and the satellite image data to identify danger sources; Determining a weather condition influence coefficient based on the sensor data; Based on the overall area and the preset area of ​​the rescue area, the rescue area is divided to obtain a plurality of rescue sub-areas; The danger coefficient of the rescue sub-area is calculated according to the type of the danger source and the weather condition influence coefficient.

5. The method according to claim 4, characterized in that The method further comprises: A multi-level situation display interface is constructed, which includes a macro layer, a meso layer and a micro layer. The macro layer is used to display a heat map of the hazard coefficient distribution of the entire rescue area. The heat map of the hazard coefficient distribution is used to represent the hazard coefficient of each rescue sub-area. The meso layer is used to display the hazard sources and weather conditions in the rescue sub-area. The micro layer is used to display the monitoring data collected by cameras installed at each preset position in the rescue area.

6. The method according to claim 5, characterized in that After the step of constructing a multi-level situation display interface, the method further includes: Collecting location data and vital sign data of the rescuer, wherein the location data is used to indicate the rescue sub-area where the rescuer is located, and the vital sign data includes heart rate, blood oxygen and body temperature; The fatigue degree of the rescuer is calculated according to the risk factor of the rescue sub-area and the vital sign data: When the fatigue level of the rescuer exceeds a preset fatigue threshold, a personnel rotation reminder is triggered in the multi-level situation display interface.

7. A rescue response system, characterized in that: The rescue response system comprises: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code comprises computer instructions, and the one or more processors call the computer instructions so that the rescue response system executes the method as described in any one of claims 1-6.

8. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a rescue response system, the rescue response system is caused to execute the method according to any one of claims 1 to 6.

9. A computer program product, characterized in that When the computer program product is run on a rescue response system, the rescue response system is caused to execute the method according to any one of claims 1 to 6.

Images