Multi-data fusion water-containing soil burying personnel rescue monitoring and early warning system

Abstract

The invention discloses a multi-data fusion water and soil buried personnel rescue monitoring and early warning system, which relates to the technical field of emergency rescue and comprises a vital sign monitoring module, a rescue equipment safety state monitoring module, a rescue environment safety monitoring module, a data fusion and algorithm analysis module and a safety monitoring, evaluating and early warning module. According to the invention, comprehensive monitoring and early warning are carried out on the vital signs of buried personnel and rescue personnel, the safety state of rescue equipment and the safety of a rescue environment, the safety state of the rescue environment is monitored in real time to ensure that the rescue personnel carry out rescue actions in a safe environment, and the rescue efficiency and safety are improved; the safety state of the rescue equipment is monitored, so that secondary injury or accidents caused by equipment problems in the rescue process are avoided, various data sources such as vital sign data, environment data and equipment data are integrated, and a scientific basis is provided for rescue decision making; and powerful data support is provided for post-disaster evaluation, disaster cause analysis and future disaster early warning.

Description

Technical Field

[0001] The present invention relates to the field of emergency rescue technology, and in particular to a multi-data fusion water-containing soil buried personnel rescue monitoring and early warning system. Background Art

[0002] The rescue of buried personnel in water-containing soil environments during natural disasters and man-made accidents faces many challenges. At present, the forecasting and early warning technology for geological disasters such as landslides and mud-rock flows based on multiple parameters is relatively mature, and mainly relies on indicators such as rainfall, displacement, and strain for calculation and analysis. Due to the influence of complex factors such as rock and soil properties, terrain conditions, and rainfall characteristics, the disaster chain early warning is difficult. Most of the current early warning platforms provide advance warning for disasters, and there is almost no monitoring and early warning after the disaster occurs. The existing technology lacks a secondary disaster early warning platform designed for emergency rescue personnel that can comprehensively monitor vital signs, the safety status of rescue equipment, and the safety of the rescue environment.

[0003] The defects of the rescue early warning system in the prior art are:

[0004] 1. Patent document US20080137589A1 discloses a wireless mine tracking, monitoring and rescue communication system. The rescue communication system cannot comprehensively monitor and warn the vital signs of buried personnel and rescue personnel, the safety status of rescue equipment and the safety of the rescue environment, and cannot ensure that rescue personnel carry out rescue operations in a safe environment. The rescue risk is high and the rescue efficiency is low.

[0005] 2. Patent document CN116400348A discloses a slope safety monitoring and early warning device and method for rescuing buried persons in water-containing soil. The monitoring and early warning device cannot comprehensively monitor and warn the vital signs of buried persons and rescuers, the safety status of rescue equipment, and the safety of the rescue environment. It cannot ensure that rescuers carry out rescue operations in a safe environment, resulting in high rescue risks and low rescue efficiency.

[0006] 3. Patent document CN115862263B discloses a comprehensive monitoring and early warning equipment for the rescue safety of people buried in water-containing soil. The monitoring and early warning equipment cannot adapt to changes in data and cannot make accurate predictions and decisions in complex rescue environments. It is not conducive to assessing the impact of disasters, optimizing rescue plans and reducing disaster losses, and the rescue efficiency and quality are poor.

[0007] 4. Patent document CN112419644A discloses a forest fire emergency rescue wind speed and direction monitoring and early warning system and method. The monitoring and early warning system cannot adapt to data changes and cannot make accurate predictions and decisions in complex rescue environments. It is not conducive to assessing the impact of disasters, optimizing rescue plans and reducing disaster losses, and the rescue efficiency and quality are poor. Summary of the invention

[0008] The purpose of the present invention is to provide a multi-data fusion water-containing soil buried personnel rescue monitoring and early warning system to solve the problems raised in the above background technology.

[0009] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a multi-data fusion water-containing soil buried personnel rescue monitoring and early warning system, including a vital signs monitoring module, a rescue equipment safety status monitoring module, a rescue environment safety monitoring module, a data fusion and algorithm analysis module and a safety monitoring assessment and early warning module;

[0010] The data fusion and algorithm analysis module fuses the data of the vital signs monitoring module, the rescue equipment safety status monitoring module and the rescue environment safety monitoring module, and uses random forest, isolation forest and ARIMA+GRU algorithms for analysis.

[0011] Preferably, the vital signs monitoring module includes a vital signs monitoring sensor and a signal processing module. The vital signs monitoring module is used to continuously monitor the four major vital signs of the trapped person and the rescue personnel, namely, body temperature, pulse, respiration, and blood pressure, and to confirm the safety status characteristic parameters and thresholds of the vital signs of people at different physiological stages to ensure the accuracy and real-time nature of the data.

[0012] Preferably, the rescue equipment safety status monitoring module adopts a high-precision, high-sensitivity inclination sensor, combined with a three-dimensional dynamic simulation analysis method to monitor the stability status of the rescue equipment in real time.

[0013] Preferably, the rescue equipment safety status monitoring module further includes a tilt sensor calibration module, and the tilt sensor calibration module is used to ensure the accuracy of the tilt sensor data.

[0014] Preferably, the rescue environment safety monitoring module adopts sensor array technology to integrate slope deformation monitoring sensors, slope secondary collapse monitoring sensors, meteorological environment monitoring sensors, soil moisture content change monitoring sensors and dangerous gas type and concentration monitoring sensors to monitor the safety status of the rescue environment in real time.

[0015] Preferably, the rescue environment safety monitoring module also includes a data processing module, and the data processing module is used to preprocess and extract features of sensor data.

[0016] Preferably, the data fusion and algorithm analysis module also includes a data quality control module for ensuring the integrity and reliability of the data.

[0017] Preferably, a random forest algorithm is used to determine the classification of hazard sources, and the random forest algorithm formula is as follows:

[0018] Gini(U)=∑p(ui)*(1-p(ui))

[0019] Where p(ui) represents the probability that a random sample belongs to category i. When constructing each tree, the random forest will randomly extract samples from the original training data set with replacement and randomly select features for division. In the random forest, each tree will classify the input samples and finally decide the final classification result by voting.

[0020] Preferably, an isolation forest algorithm is used to identify anomalies in the vital signs of buried personnel and the safety status of rescue equipment. The isolation forest algorithm formula is as follows:

[0021] s(x,n)=2(-c(n)Eh(x))

[0022]

[0023] Where s(x,n) represents the anomaly score of sample x, Eh(x) is the expected value of the path length of x in multiple trees, c(n) is the average path length of the tree in a dataset containing n samples, which is used to standardize the path length of x; n represents the number of samples used to generate each tree.

[0024] Preferably, the ARIMA+GRU algorithm is used to predict the rescue environment, and the ARIMA+GRU algorithm formula is as follows:

[0025] ARIMA(p,d,q)=AR(p)+I(d)+MA(q)

[0026] Where AR(p) represents the autoregressive model, I(d) represents the difference model, and MA(q) represents the moving average model;

[0027]

[0028] where h t is the hidden state at the current time step, is a candidate hidden state, W h and U h is the weight matrix, b h is the bias term, tanh is the hyperbolic tangent activation function, ⊙ represents element-by-element multiplication, r t is the output of the reset gate, x t is the input of the current time step, z t is the output of the update gate.

[0029] Preferably, the safety monitoring and evaluation early warning module is established based on the analysis data and is used to issue early warning information in real time. The safety monitoring and evaluation early warning model also includes an early warning information push unit, which is used to send early warning information to commanders and rescue personnel in real time.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] 1. The present invention conducts comprehensive monitoring and early warning of the vital signs of buried personnel and rescue personnel, the safety status of rescue equipment and the safety of the rescue environment. It monitors the safety status of the rescue environment in real time to ensure that rescue personnel carry out rescue operations in a safe environment, protect the lives of rescue personnel, and improve rescue efficiency and safety. The system can monitor the vital signs of buried personnel and rescue personnel in real time, provide timely information support for rescue operations, thereby improving rescue efficiency and reducing rescue risks, and monitor the safety status of rescue equipment to avoid secondary injuries or accidents caused by equipment problems during the rescue process. The system integrates multiple data sources such as vital signs data, environmental data, equipment data, etc., to provide a scientific basis for rescue decisions, improve the accuracy and effectiveness of decisions, and provide strong data support for post-disaster assessment, disaster cause analysis and future disaster warnings.

[0032] 2. The present invention fuses the collected data through the data fusion and algorithm analysis module and adopts random forest, isolation forest and ARIMA+GRU algorithms for analysis. The random forest algorithm significantly reduces the overfitting risk of a single decision tree, thereby improving the stability and prediction accuracy of the overall model, helping to more accurately determine the classification of hazardous sources and provide strong support for emergency rescue. The isolation forest algorithm is fast in processing big data and can identify abnormalities in the vital signs of buried personnel and the safety status of rescue equipment in real time, which is helpful for rapid response and disposal at disaster sites with limited resources. The ARIMA+GRU algorithm can capture different types of time series features by adjusting parameters and adapt to data changes, which is helpful for making accurate predictions and decisions in complex rescue environments, enabling emergency rescue personnel to quickly understand the situation at the disaster site, make correct decisions and actions, and help to assess the impact of disasters, optimize rescue plans, reduce disaster losses, and improve rescue efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic diagram of the system working process of the present invention;

[0034] Figure 2 It is the technical roadmap of the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] In the description of the present invention, it should be noted that the terms "upper", "lower", "inner", "outer", "front end", "rear end", "two ends", "one end", "the other end" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0037] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "provided with", "connected", etc. should be understood in a broad sense. For example, "connected" can be a fixed connection or a movable connection, or a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0038] Embodiment 1, an embodiment provided by the present invention: a multi-data fusion water-containing soil buried personnel rescue monitoring and early warning system, including a vital signs monitoring module, a rescue equipment safety status monitoring module, a rescue environment safety monitoring module and a safety monitoring assessment and early warning module;

[0039] The vital signs monitoring module includes a vital signs monitoring sensor and a signal processing module. The vital signs monitoring module is used to continuously monitor the four major vital signs of the trapped person and the rescuer, namely, body temperature, pulse, respiration, and blood pressure, and to confirm the safety status characteristic parameters and thresholds of the vital signs of people at different physiological stages, to ensure the accuracy and real-time nature of the data.

[0040] The rescue equipment safety status monitoring module uses a high-precision, high-sensitivity inclination sensor, combined with a three-dimensional dynamic simulation analysis method to monitor the stability of the rescue equipment in real time. The rescue equipment safety status monitoring module also includes a inclination sensor calibration module, which is used to ensure the accuracy of the inclination sensor data;

[0041] The rescue environment safety monitoring module adopts sensor array technology to integrate slope deformation monitoring sensors, slope secondary collapse monitoring sensors, meteorological environment monitoring sensors, soil moisture content change monitoring sensors and dangerous gas type and concentration monitoring sensors to monitor the safety status of the rescue environment in real time. The rescue environment safety monitoring module also includes a data processing module, which is used to pre-process and extract features from sensor data;

[0042] The safety monitoring and evaluation early warning module is established based on the analysis data and is used to issue early warning information in real time. The safety monitoring and evaluation early warning model also includes an early warning information push unit, which is used to send early warning information to commanders and rescue personnel in real time.

[0043] Embodiment 2, an embodiment provided by the present invention: a multi-data fusion water-containing soil buried personnel rescue monitoring and early warning system, including a vital signs monitoring module, a data fusion and algorithm analysis module and a safety monitoring assessment and early warning module;

[0044] The vital signs monitoring module includes a vital signs monitoring sensor and a signal processing module. The vital signs monitoring module is used to continuously monitor the four major vital signs of the trapped person and the rescuer, namely, body temperature, pulse, respiration, and blood pressure, and to confirm the safety status characteristic parameters and thresholds of the vital signs of people at different physiological stages, to ensure the accuracy and real-time nature of the data.

[0045] The data fusion and algorithm analysis module receives the data from the vital signs monitoring module and analyzes it using the random forest algorithm. The data fusion and algorithm analysis module also includes a data quality control module to ensure the integrity and reliability of the data;

[0046] The random forest algorithm is used to determine the classification of hazard sources. The formula of the random forest algorithm is as follows:

[0047] Gini(U)=∑p(ui)*(1-p(ui))

[0048] Where p(ui) represents the probability that a random sample belongs to category i. When constructing each tree, the random forest randomly extracts samples from the original training data set with replacement and randomly selects features for division. In the random forest, each tree will classify the input sample, and finally decide the final classification result by voting.

[0049] The safety monitoring and evaluation early warning module is established based on the analysis data and is used to issue early warning information in real time. The safety monitoring and evaluation early warning model also includes an early warning information push unit, which is used to send early warning information to commanders and rescue personnel in real time.

[0050] Embodiment 3, an embodiment provided by the present invention: a multi-data fusion water-containing soil buried personnel rescue monitoring and early warning system, including a rescue equipment safety status monitoring module, a data fusion and algorithm analysis module and a safety monitoring assessment and early warning module;

[0051] The rescue equipment safety status monitoring module uses a high-precision, high-sensitivity inclination sensor, combined with a three-dimensional dynamic simulation analysis method to monitor the stability of the rescue equipment in real time. The rescue equipment safety status monitoring module also includes a inclination sensor calibration module, which is used to ensure the accuracy of the inclination sensor data;

[0052] The data fusion and algorithm analysis module receives the data from the rescue equipment safety status monitoring module and uses the isolation forest algorithm to analyze it. The data fusion and algorithm analysis module also includes a data quality control module to ensure the integrity and reliability of the data;

[0053] The isolation forest algorithm is used to identify anomalies in the vital signs of buried personnel and the safety status of rescue equipment. The isolation forest algorithm formula is as follows:

[0054] s(x,n)=2(-c(n)Eh(x))

[0055]

[0056] Where s(x,n) represents the anomaly score of sample x, Eh(x) is the expected value of the path length of x in multiple trees, c(n) is the average path length of the tree in the dataset containing n samples, which is used to standardize the path length of x; n represents the number of samples used to generate each tree;

[0057] The safety monitoring and evaluation early warning module is established based on the analysis data and is used to issue early warning information in real time. The safety monitoring and evaluation early warning model also includes an early warning information push unit, which is used to send early warning information to commanders and rescue personnel in real time.

[0058] Embodiment 4, an embodiment provided by the present invention: a multi-data fusion water-containing soil buried personnel rescue monitoring and early warning system, including a rescue environment safety monitoring module, a data fusion and algorithm analysis module and a safety monitoring assessment and early warning module;

[0059] The rescue environment safety monitoring module adopts sensor array technology to integrate slope deformation monitoring sensors, slope secondary collapse monitoring sensors, meteorological environment monitoring sensors, soil moisture content change monitoring sensors and dangerous gas type and concentration monitoring sensors to monitor the safety status of the rescue environment in real time. The rescue environment safety monitoring module also includes a data processing module, which is used to pre-process and extract features from sensor data;

[0060] The data fusion and algorithm analysis module receives the data transmitted by the rescue environment safety monitoring module and uses the ARIMA+GRU algorithm to analyze it. The data fusion and algorithm analysis module also includes a data quality control module to ensure the integrity and reliability of the data;

[0061] The ARIMA+GRU algorithm is used to predict the rescue environment. The ARIMA+GRU algorithm formula is as follows:

[0062] ARIMA(p,d,q)=AR(p)+I(d)+Mp(q)

[0063] Where AR(p) represents the autoregressive model, I(d) represents the difference model, and MA(q) represents the moving average model;

[0064]

[0065]

[0066] where h t is the hidden state at the current time step, is a candidate hidden state, W h and U h is the weight matrix, b h is the bias term, tanh is the hyperbolic tangent activation function, ⊙ represents element-by-element multiplication, r t is the output of the reset gate, x t is the input of the current time step, z t is the output of the update gate;

[0067] The safety monitoring and evaluation early warning module is established based on the analysis data and is used to issue early warning information in real time. The safety monitoring and evaluation early warning model also includes an early warning information push unit, which is used to send early warning information to commanders and rescue personnel in real time.

[0068] Embodiment 5, an embodiment provided by the present invention: a multi-data fusion water-containing soil buried personnel rescue monitoring and early warning system, including a vital signs monitoring module, a rescue equipment safety status monitoring module, a rescue environment safety monitoring module, a data fusion and algorithm analysis module and a safety monitoring assessment and early warning module;

[0069] The vital signs monitoring module includes a vital signs monitoring sensor and a signal processing module. The vital signs monitoring module is used to continuously monitor the four major vital signs of the trapped person and the rescuer, namely, body temperature, pulse, respiration, and blood pressure, and to confirm the safety status characteristic parameters and thresholds of the vital signs of people at different physiological stages, to ensure the accuracy and real-time nature of the data.

[0070] The rescue equipment safety status monitoring module uses a high-precision, high-sensitivity inclination sensor, combined with a three-dimensional dynamic simulation analysis method to monitor the stability of the rescue equipment in real time. The rescue equipment safety status monitoring module also includes a inclination sensor calibration module, which is used to ensure the accuracy of the inclination sensor data;

[0071] The rescue environment safety monitoring module adopts sensor array technology to integrate slope deformation monitoring sensors, slope secondary collapse monitoring sensors, meteorological environment monitoring sensors, soil moisture content change monitoring sensors and dangerous gas type and concentration monitoring sensors to monitor the safety status of the rescue environment in real time. The rescue environment safety monitoring module also includes a data processing module, which is used to pre-process and extract features from sensor data;

[0072] The data fusion and algorithm analysis module integrates the data of the vital signs monitoring module, the rescue equipment safety status monitoring module and the rescue environment safety monitoring module, and uses the random forest, isolation forest and ARIMA+GRU algorithms for analysis. The data fusion and algorithm analysis module also includes a data quality control module to ensure the integrity and reliability of the data;

[0073] The random forest algorithm is used to determine the classification of hazard sources. The formula of the random forest algorithm is as follows:

[0074] Gini(U)=∑p(ui)*(1-p(ui))

[0075] Where p(ui) represents the probability that a random sample belongs to category i. When constructing each tree, the random forest randomly extracts samples from the original training data set with replacement and randomly selects features for division. In the random forest, each tree will classify the input sample, and finally decide the final classification result by voting.

[0076] The isolation forest algorithm is used to identify anomalies in the vital signs of buried personnel and the safety status of rescue equipment. The isolation forest algorithm formula is as follows:

[0077] S(x,n)=2(-c(n)Eh(x))

[0078]

[0079] Where s(x,n) represents the anomaly score of sample x, Eh(x) is the expected value of the path length of x in multiple trees, c(n) is the average path length of the tree in the dataset containing n samples, which is used to standardize the path length of x; n represents the number of samples used to generate each tree;

[0080] The ARIMA+GRU algorithm is used to predict the rescue environment. The ARIMA+GRU algorithm formula is as follows:

[0081] ARIMA(p,d,q)=AR(p)+I(d)+MA(q)

[0082] Where AR(p) represents the autoregressive model, I(d) represents the difference model, and MA(q) represents the moving average model;

[0083]

[0084] where h t is the hidden state at the current time step, is a candidate hidden state, W h and U h is the weight matrix, b h is the bias term, tanh is the hyperbolic tangent activation function, ⊙ represents element-by-element multiplication, r t is the output of the reset gate, x t is the input of the current time step, z t is the output of the update gate;

[0085] The safety monitoring and evaluation early warning module is established based on the analysis data and is used to issue early warning information in real time. The safety monitoring and evaluation early warning model also includes an early warning information push unit, which is used to send early warning information to commanders and rescue personnel in real time.

[0086] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A multi-data fusion water-bearing soil buried personnel rescue monitoring and early warning system, characterized by: It includes vital signs monitoring module, rescue equipment safety status monitoring module, rescue environment safety monitoring module, data fusion and algorithm analysis module and safety monitoring assessment and early warning module; The data fusion and algorithm analysis module fuses the data of the vital signs monitoring module, the rescue equipment safety status monitoring module and the rescue environment safety monitoring module, and uses random forest, isolation forest and ARIMA+GRU algorithms for analysis.

2. The multi-data fusion water-bearing soil buried personnel rescue monitoring and early warning system according to claim 1 is characterized by: The vital signs monitoring module includes a vital signs monitoring sensor and a signal processing module. The vital signs monitoring module is used to continuously monitor the four major vital signs of the trapped person and the rescue personnel, namely, body temperature, pulse, respiration, and blood pressure, and to confirm the safety status characteristic parameters and thresholds of the vital signs of people at different physiological stages to ensure the accuracy and real-time nature of the data.

3. The multi-data fusion water-bearing soil buried personnel rescue monitoring and early warning system according to claim 1 is characterized by: The rescue equipment safety status monitoring module adopts a high-precision, high-sensitivity tilt sensor and combines it with a three-dimensional dynamic simulation analysis method to monitor the stability of the rescue equipment in real time.

4. The multi-data fusion water-bearing soil buried personnel rescue monitoring and early warning system according to claim 1 is characterized by: The rescue equipment safety status monitoring module also includes a tilt sensor calibration module, and the tilt sensor calibration module is used to ensure the accuracy of the tilt sensor data.

5. The multi-data fusion water-bearing soil buried personnel rescue monitoring and early warning system according to claim 1 is characterized by: The rescue environment safety monitoring module adopts sensor array technology to integrate slope deformation monitoring sensors, slope secondary collapse monitoring sensors, meteorological environment monitoring sensors, soil moisture content change monitoring sensors and dangerous gas type and concentration monitoring sensors to monitor the safety status of the rescue environment in real time.

6. The multi-data fusion water-bearing soil buried personnel rescue monitoring and early warning system according to claim 1 is characterized by: The rescue environment safety monitoring module also includes a data processing module, which is used to preprocess and extract features from sensor data.

7. The multi-data fusion water-bearing soil buried personnel rescue monitoring and early warning system according to claim 1 is characterized by: The data fusion and algorithm analysis module also includes a data quality control module for ensuring the integrity and reliability of the data.

8. The multi-data fusion water-bearing soil buried personnel rescue monitoring and early warning system according to claim 1 is characterized by: The random forest algorithm is used to determine the classification of hazard sources. The formula of the random forest algorithm is as follows: Gini(U)=∑p(ui)*(1_p(ui)) Where p(ui) represents the probability that a random sample belongs to category i. When constructing each tree, the random forest will randomly extract samples from the original training data set with replacement and randomly select features for division. In the random forest, each tree will classify the input samples and finally decide the final classification result by voting.

9. The multi-data fusion water-bearing soil buried personnel rescue monitoring and early warning system according to claim 1 is characterized by: The isolation forest algorithm is used to identify the anomalies of the vital signs of buried personnel and the safety status of rescue equipment. The isolation forest algorithm formula is as follows: s(x,n)=2(-c(n)Eh(x)) Where s(x,n) represents the anomaly score of sample x, Eh(x) is the expected value of the path length of x in multiple trees, c(n) is the average path length of the tree in a dataset containing n samples, which is used to standardize the path length of x; n represents the number of samples used to generate each tree.

10. The multi-data fusion water-bearing soil buried personnel rescue monitoring and early warning system according to claim 1, characterized in that: The ARIMA+GRU algorithm is used to predict the rescue environment. The ARIMA+GRU algorithm formula is as follows: ARIMA(p,d,q)=AR(p)+I(d)+MA(q) Where AR(p) represents the autoregressive model, I(d) represents the difference model, and MA(q) represents the moving average model; where h t is the hidden state at the current time step, is a candidate hidden state, W h and U h is the weight matrix, b h is the bias term, tanh is the hyperbolic tangent activation function, ⊙ represents element-by-element multiplication, r t is the output of the reset gate, x t is the input of the current time step, z t is the output of the update gate.

11. The multi-data fusion water-bearing soil buried personnel rescue monitoring and early warning system according to claim 1, characterized in that: The safety monitoring and evaluation early warning module is established based on the analysis data and is used to issue early warning information in real time. The safety monitoring and evaluation early warning model also includes an early warning information push unit, which is used to send early warning information to commanders and rescue personnel in real time.

Images