Disaster emergency monitoring system

By combining personnel feedback and prediction models in the disaster emergency monitoring system, work tasks and scheduling arrangements are updated in real time, the problem of prediction deviation in the existing system is solved, and the accuracy and efficiency of disaster emergency monitoring are improved.

CN119091584APending Publication Date: 2024-12-06GUANGDONG ACAD OF FORESTRY +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411073262.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing disaster emergency monitoring system lacks staff feedback, resulting in disaster prediction deviations and inability to effectively schedule and arrange personnel, affecting the accuracy of forecasting and system efficiency.

Method used

A disaster emergency monitoring system was designed, including data acquisition module, network service module, processing module, scheduling module and execution module. By combining the personnel scheduling system, the prediction model and feedback data can be used to update work tasks and scheduling schedules in real time to improve prediction. Accuracy and system efficiency.

Benefits of technology

By using historical monitoring data, current monitoring values ​​and work task feedback, the accuracy and execution efficiency of response strategies are improved, and the losses caused by disasters are reduced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119091584A_ABST
    Figure CN119091584A_ABST
Patent Text Reader

Abstract

The invention discloses a disaster emergency monitoring system, and the system comprises a data collection module which is used for collecting the monitoring data of a monitoring region; the processing module is used for performing data interaction on the monitoring data and submitting a data interaction result to the scheduling module; the scheduling module is used for formulating a work task and finishing scheduling arrangement of related workers according to the data interaction result and in combination with a personnel scheduling system; the execution module is used for receiving execution feedback after related workers execute the work task, and the execution module sends the execution feedback to the processing module; the processing module continuously updates the current monitoring value of the monitoring area and performs feedback in combination so as to update a data interaction result; the processing module stores a prediction model. A monitoring area is evaluated and predicted by adopting a prediction model and using historical monitoring data, a current monitoring value and execution feedback of a work task as input so as to make a coping strategy as early as possible and schedule and execute the strategy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of disaster emergency response, and in particular to a disaster emergency monitoring system. Background Art

[0002] With the development of cities and the deteriorating environment, natural emergency disasters have occurred frequently, causing great losses of life and property. In order to protect the safety of public life and property and reduce the losses caused by disasters, disaster emergency management came into being.

[0003] The disaster emergency monitoring system is a comprehensive emergency management system based on advanced technology. It aims to provide fast, accurate and efficient response measures through real-time monitoring and analysis of data information, prediction and early warning, resource scheduling, command and decision-making of various disaster events, so as to protect the safety of public life and property and reduce the losses caused by disasters.

[0004] However, the existing disaster emergency monitoring systems focus more on predicting and analyzing the occurrence of disasters, and rarely mention personnel scheduling and work arrangements. Due to the lack of feedback from staff, actual predictions are biased, such as disaster intensity. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a disaster emergency monitoring system that can effectively combine the feedback of staff, thereby improving the accuracy of prediction and the efficiency of the disaster emergency monitoring system, providing a basis for subsequent system improvement.

[0006] According to the disaster emergency monitoring system of the first aspect of the present invention, the disaster emergency monitoring system includes a data acquisition module, a network service module, a processing module, a scheduling module and an execution module; wherein,

[0007] The data acquisition module is constructed to include a field data acquisition unit and a remote sensing data acquisition unit, which are used to collect monitoring data of the monitoring area and send the monitoring data to the network service module through network communication;

[0008] The network service module is configured to realize transmission and protection of the monitoring data;

[0009] The processing module is configured to perform data interaction on the monitoring data and submit the data interaction result to the scheduling module;

[0010] The scheduling module is configured to formulate work tasks and complete the scheduling of relevant staff members according to the data interaction results and in combination with the staff scheduling system;

[0011] The execution module is configured to receive the work tasks assigned by the scheduling module and the execution feedback of the relevant staff after the work tasks are executed, including the execution time and the actual implementation situation, and the execution module sends the execution feedback to the processing module;

[0012] The processing module continuously updates the current monitoring value of the monitoring area and combines it with the execution feedback to update the data interaction result; the processing module stores a prediction model; by inputting historical monitoring data into the prediction model, a first prediction value corresponding to the current time is obtained; and by inputting historical monitoring data and the current monitoring value into the prediction model, a second prediction value corresponding to the future time is obtained; based on comparing the first prediction value with the current monitoring value, and based on comparing the second prediction value with the future monitoring value, whether the status of the monitoring area is healthy or whether the progress is completed, or further issuing early warning information; and based on the difference between the above two values, updating work tasks and scheduling arrangements.

[0013] The disaster emergency monitoring system according to the embodiment of the present invention has at least the following beneficial effects: by adopting a prediction model, using historical monitoring data, current monitoring values ​​and execution feedback of work tasks as input, the monitoring area is evaluated and predicted, so as to make a response strategy as early as possible and schedule the execution of the strategy.

[0014] According to some embodiments of the present invention, the execution steps of the disaster emergency monitoring system include:

[0015] S100, data reception, receiving the monitoring data collected by the data collection module in a first period T1;

[0016] S200, the processing module performs historical monitoring data analysis and obtains a first prediction value, compares the first prediction value with the current monitoring value, obtains a first difference value, and formulates a first work task and a first scheduling arrangement according to the first difference value;

[0017] S300, sending the first work task and the first scheduling arrangement to relevant personnel or departments for execution, and receiving corresponding execution feedback;

[0018] S400, the processing module analyzes historical monitoring data, current monitoring values, and execution feedback to obtain a second prediction value;

[0019] S500. At a specified time in the future, compare the second predicted value with the future monitored value to obtain a second difference value, and evaluate the execution result of the first work task according to the second difference value.

[0020] According to some embodiments of the present invention, step S200 includes:

[0021] The historical monitoring data and the current monitoring values ​​are input into the preset fault node model to obtain the fault node that matches the fault node model; the geographical location corresponding to the fault node is analyzed, and the early warning area of ​​the specified range is delineated; the fault node model is set by relevant technical personnel according to the standard range of environmental parameters in different sections of the monitoring area.

[0022] According to some embodiments of the present invention, step S200 further includes adjusting the monitoring time of the warning area to a second period T2, and making T2<T1.

[0023] According to some embodiments of the present invention, in step S300, historical monitoring data, current monitoring values, first prediction values, second prediction values, fault nodes, geographical locations corresponding to fault nodes, warning areas and other information are saved in the network service module, and one or more of the above information is displayed when relevant individuals or units require it.

[0024] According to some embodiments of the present invention, the workflow of the scheduling module and the execution module includes the following steps:

[0025] W100, the scheduling module sends the first work task and the first scheduling arrangement to the execution module of the corresponding partition management unit;

[0026] W200, after receiving the corresponding control instruction, the execution module of the zoning management unit dispatches staff to work on the warning area based on the first work task according to the first scheduling arrangement;

[0027] W300. After the work is completed, the staff sends the execution feedback to the network service module through the execution module, and the network service module records and stores the execution feedback.

[0028] According to some embodiments of the present invention, the network service module includes:

[0029] An Internet of Things gateway, configured to solve the data collection and processing problems of sensors in a plurality of said data collection modules;

[0030] The server is configured to handle data flow and cache, and includes a database for storing monitoring data.

[0031] According to some embodiments of the present invention, the prediction model includes a gray prediction model, a regression prediction model, a time series analysis model, a Kalman filter prediction model, a fuzzy mathematical model, a supervised machine learning model, a residual network-based machine learning model, a weight-based machine learning model or a generative adversarial network-based machine learning model, or any combination of two or more of these models.

[0032] According to some embodiments of the present invention, the field data acquisition unit includes one or more of a strain gauge, a piezometer, a stress gauge, a water level gauge, an earth pressure gauge, a weir gauge, an inclinometer, an anemometer and a barometer.

[0033] According to some embodiments of the present invention, the remote sensing data acquisition unit includes one or more satellite images of a meteorological satellite, an earth satellite, a land satellite, and an ocean satellite.

[0034] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The present invention will be further described below with reference to the accompanying drawings and embodiments, wherein:

[0036] Figure 1 A schematic diagram of a disaster emergency monitoring system according to an embodiment of the present invention;

[0037] Figure 2 It is a schematic diagram for explaining each prediction data in the embodiment of the present invention, wherein Figure (A) is the calculation of the first prediction value X′ using historical monitoring data, and Figure (B) is the calculation of the second prediction value Y′ using historical monitoring data and current monitoring data. DETAILED DESCRIPTION

[0038] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0039] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying 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 should not be understood as a limitation on the present invention.

[0040] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0041] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0042] Reference Figure 1 and Figure 2 According to the disaster emergency monitoring system of the embodiment of the present invention, the disaster emergency monitoring system includes a data acquisition module, a network service module, a processing module, a scheduling module and an execution module; wherein,

[0043] The data acquisition module is constructed to include a field data acquisition unit and a remote sensing data acquisition unit, which are used to collect monitoring data of the monitoring area and send the monitoring data to the network service module through network communication;

[0044] The network service module is configured to realize transmission and protection of the monitoring data;

[0045] The processing module is configured to perform data interaction on the monitoring data and submit the data interaction result to the scheduling module;

[0046] The scheduling module is configured to formulate work tasks and complete the scheduling of relevant staff members according to the data interaction results and in combination with the staff scheduling system;

[0047] The execution module is configured to receive the work tasks assigned by the scheduling module and the execution feedback of the relevant staff after the work tasks are executed, including the execution time and the actual implementation situation, and the execution module sends the execution feedback to the processing module;

[0048] The processing module continuously updates the current monitoring value of the monitoring area and combines it with the execution feedback to update the data interaction result; the processing module stores a prediction model; by inputting historical monitoring data into the prediction model, a first prediction value corresponding to the current time is obtained; and by inputting historical monitoring data and the current monitoring value into the prediction model, a second prediction value corresponding to the future time is obtained; based on comparing the first prediction value with the current monitoring value, and based on comparing the second prediction value with the future monitoring value, whether the status of the monitoring area is healthy or whether the progress is completed, or further issuing early warning information; and based on the difference between the above two values, updating work tasks and scheduling arrangements.

[0049] Specifically, there are multiple data acquisition modules, the field data acquisition unit includes multiple sensors, and the multiple sensors are configured at the monitoring site of the monitoring area to collect the field monitoring data of the monitoring area; the remote sensing data acquisition unit collects the remote sensing monitoring data of the monitoring area by adopting remote sensing monitoring technology;

[0050] The network service module is based on the Internet or the intranet of the relevant emergency management department, and adopts the Internet of Things gateway and the corresponding server to realize the transmission and protection of various data. The execution feedback sent by the execution module to the processing module is transmitted through the network service module;

[0051] The data interaction includes processing, exchanging, analyzing, sharing and saving the collected monitoring data.

[0052] By adopting a predictive model, using historical monitoring data, current monitoring values, and execution feedback of work tasks as input, the monitoring area is evaluated and predicted so that a response strategy can be made as early as possible and the execution of the strategy can be scheduled.

[0053] According to some embodiments of the present invention, the execution steps of the disaster emergency monitoring system include:

[0054] S100, data reception, receiving the monitoring data collected by the data collection module in a first period T1;

[0055] S200, the processing module performs historical monitoring data analysis and obtains a first prediction value, compares the first prediction value with the current monitoring value, obtains a first difference value, and formulates a first work task and a first scheduling arrangement according to the first difference value;

[0056] S300, sending the first work task and the first scheduling arrangement to relevant personnel or departments for execution, and receiving corresponding execution feedback;

[0057] S400, the processing module analyzes historical monitoring data, current monitoring values, and execution feedback to obtain a second prediction value;

[0058] S500. At a specified time in the future, compare the second predicted value with the future monitored value to obtain a second difference value, and evaluate the execution result of the first work task according to the second difference value.

[0059] According to some preferred embodiments of the present invention, step S200 includes:

[0060] The historical monitoring data and the current monitoring values ​​are input into the preset fault node model to obtain the fault node that matches the fault node model; the geographical location corresponding to the fault node is analyzed, and the early warning area of ​​the specified range is delineated; the fault node model is set by relevant technical personnel according to the standard range of environmental parameters in different sections of the monitoring area.

[0061] According to some preferred embodiments of the present invention, step S200 further includes adjusting the monitoring time of the warning area to a second period T2, and making T2<T1.

[0062] According to some embodiments of the present invention, in step S300, historical monitoring data, current monitoring values, first prediction values, second prediction values, fault nodes, geographical locations corresponding to fault nodes, warning areas and other information are saved in the network service module, and one or more of the above information is displayed when relevant individuals or units require it.

[0063] According to some embodiments of the present invention, the workflow of the scheduling module and the execution module includes the following steps:

[0064] W100, the scheduling module sends the first work task and the first scheduling arrangement to the execution module of the corresponding partition management unit;

[0065] W200, after receiving the corresponding control instruction, the execution module of the zoning management unit dispatches staff to work on the warning area based on the first work task according to the first scheduling arrangement;

[0066] W300. After the work is completed, the staff sends the execution feedback to the network service module through the execution module, and the network service module records and stores the execution feedback.

[0067] According to some embodiments of the present invention, the network service module includes:

[0068] An Internet of Things gateway, configured to solve the data collection and processing problems of sensors in a plurality of said data collection modules;

[0069] The server is configured to handle data flow and cache, and includes a database for storing monitoring data.

[0070] Through the system intranet of the disaster emergency department, the Internet of Things gateway and the corresponding server, the processing module works together to improve the flow and unified processing of collected data, analyzed data, managed data and displayed data in the network;

[0071] According to some embodiments of the present invention, the data acquisition module includes a field data acquisition unit, and the field data acquisition unit includes one or more of a strain gauge, a piezometer, a stress gauge, a water level gauge, an earth pressure gauge, a water weir gauge, an inclinometer, an anemometer, and a barometer. According to different actual monitoring areas, different sensors are selected to be configured on site, and field monitoring data is collected momentarily, and then the data is collected through the equipment console or a dedicated control box (PLZ);

[0072] According to some embodiments of the present invention, remote sensing technology can be used to conduct long-distance non-contact monitoring of large-scale monitoring areas; remote sensing technology utilizes the characteristics of light spectrum information collection, and uses different remote sensing bands composed of various wavelengths such as ultraviolet, visible light, infrared, far infrared and even radar to reflect various types of light reflection information on the ground or in space; these data information of different bands, after computer processing and information extraction, will generate a large amount of various professional information, such as a wide range of understanding of water bodies, vegetation, water systems, geology, disasters, ground structures, soil erosion, coastal erosion, etc., as well as all-weather water conditions, climate change, flood monitoring, etc., and the remote sensing data acquisition unit includes one or more satellite images of meteorological satellites, earth satellites, land satellites, and ocean satellites. According to the actual monitoring area, different satellites or multiple satellites are selected to match to collect remote sensing monitoring data in real time.

[0073] Combining on-site monitoring data and remote sensing monitoring data, the monitoring area can be monitored in multiple dimensions from macro to micro, achieving comprehensive and highly informationized data collection;

[0074] In some embodiments, the network service module, processing module, scheduling module and execution module can be based on one or more cloud computing servers, and a cloud management platform can be established; the cloud management platform integrates the basis of data collection, exchange, service, sharing and utilization, and includes standards such as data collection and storage, exchange and service interfaces, as well as components such as data services, repositories, and identity codes. The application of cloud technology is to connect and control remote server clusters through networking, and to process computing programs online. It can realize dynamic management of the monitoring area, collect and organize data, videos, location information, etc. of the monitoring area in real time, and transmit them to the corresponding modules in the cloud platform for analysis, processing, storage, backup and summary in a timely manner. The safety production management information control system can download and call the data in the database at any time to realize safety monitoring of the monitoring area, real-time query of monitoring area information, data exchange, disaster warning, disaster emergency rescue and accident investigation and processing, etc., promote the technical improvement and reform of the disaster emergency management level of the emergency management department, and realize the comprehensive and scientific management of emergency disasters.

[0075] In the past, monitoring of monitoring areas required technicians to closely and continuously monitor changes in multiple monitoring data manually. The relevant technicians needed a lot of professional knowledge and timely identify possible problems in the monitoring area and determine appropriate response measures;

[0076] With the development of information technology, the application of big data algorithms and machine learning technology can be used to establish a prediction model using machine learning to predict future monitoring data based on historical monitoring data and current monitoring data;

[0077] An exemplary implementation of establishing the prediction model based on machine learning is as follows:

[0078] S410, receiving a monitoring data set, and dividing it into a training set and a validation set;

[0079] S420, generating a eigenvalue corresponding to the eigenvector based on the monitoring data set;

[0080] S430, using machine learning to perform prediction model training on the training set;

[0081] S440, use the validation set to evaluate the model and perform model optimization.

[0082] Wherein, in step S410, the processing module receives a monitoring data set for training the prediction model, which includes a plurality of historical monitoring data of a plurality of monitoring areas divided in time series; these data are historical monitoring data accumulated over time; the type of monitoring data may include climate data, such as temperature, wind speed, and light; it may also include a plurality of index data about fluid, such as flow rate, flow velocity, flow direction, clarity, etc.; further, it may include a plurality of index data about soil, such as soil moisture content, soil pressure value, soil inclination, etc.; further, it may include image data of the monitoring area, such as reflected light illumination; and further include remote sensing data;

[0083] In step S420, based on the received monitoring data set, the relevant technical personnel define each monitoring indicator in the monitoring data set as a feature vector, and generate a set of feature values ​​of each feature vector based on the monitoring data set;

[0084] In step S430 and step S440, in some embodiments, the monitoring data set is divided into a training set and a validation set; wherein the training set is used to train the model, and the validation set is used to optimize the parameters of multiple weight values ​​in the model.

[0085] Furthermore, the prediction model may include one or more statistical or machine learning models; according to some embodiments of the present invention, the prediction model includes a gray prediction model, a regression prediction model, a time series analysis model, a Kalman filter prediction model, a fuzzy mathematical model, a supervised machine learning model, a residual network-based machine learning model, a weight-based machine learning model or a generative adversarial network-based machine learning model, or any combination of two or more of these models.

[0086] In some embodiments, the grey prediction model identifies the degree of difference in the development trends between system factors, that is, performs correlation analysis, and generates and processes the original data to find the law of system changes, generates a data sequence with strong regularity, and then establishes a corresponding differential equation model. It constructs a grey prediction model with a series of quantitative values ​​reflecting the characteristics of the prediction object observed at equal time intervals, predicts the characteristic quantity at a certain moment in the future, or the time to reach a certain characteristic quantity;

[0087] In some embodiments, the regression prediction model includes a nonlinear regression model, which includes a high-dimensional nonlinear parameter function; given the history of multiple characteristic values ​​of similar monitoring areas at different implementation locations, including geographical locations, climate conditions, etc., the model parameters can be adjusted to better predict future characteristic values;

[0088] In some embodiments, the weight-based machine learning model includes learning and predicting the weights of the process-driven model and the data-driven model; in order to predict the time series of specified features, the machine learning model may use a set of deep neural networks, the structure of which may be an artificial recurrent neural network (RNN) or a long short-term memory (LSTM) architecture; these models may also include convolutional neural networks (ZNN) to process various image-based data;

[0089] In some embodiments, the machine learning model based on the generative adversarial network includes two groups of machine learning models; one model takes the historical monitoring data of some features of the monitored area as input to generate predicted data; and the other model is used to distinguish between predicted data and observed data; the two models are iteratively trained so that the predicted data of the model used to predict data is closer to the actual data; both models can be trained using deep neural networks, nonlinear parameterized functions, or functions of related disaster emergency calculations whose weights can be iteratively adjusted.

[0090] The analysis of monitoring data and the prediction of future data based on the prediction model can be implemented through the following exemplary description, referring to Figure 2 As shown;

[0091] For each monitoring area, the disaster emergency monitoring system can obtain multiple data sets, including: a current monitoring value X obtained by monitoring at the current time, a first prediction value X′ based on the predicted data at the current time, a second prediction value Y′ predicted at a specified future time, and an estimated target Z at a specified future time; each of these data sets will be described below; and these data sets are at least partially based on the prediction model;

[0092] Among them, the current monitoring value X is the value of a certain feature obtained by monitoring the monitoring area at the current time (for example, specific data at a certain time node, or the average value of this day, this week, this month, etc.); this data set can be obtained by the data acquisition module described in this article;

[0093] The first predicted value X' refers to the value of a certain feature at the current time predicted by the disaster emergency monitoring system based on the historical monitoring data obtained by the past monitoring of the monitoring area; and according to a preferred embodiment of the present invention, the first predicted value X' can be obtained using the prediction model; the disaster emergency monitoring system can correspond to multiple past moments [..., T n-3 , T n-2 , T n-1 ] as an input feature and input into the prediction model; the prediction model can predict and output the value at time Tn, that is, the first prediction value X'; in some embodiments, the predicted first prediction value X' can be interpreted as "what the monitoring data should look like now";

[0094] The second predicted value Y' refers to the output characteristic value of a certain feature predicted by the disaster emergency monitoring system based on the historical monitoring data obtained from the past monitoring of the monitoring area and the current measured data; and according to a preferred embodiment of the present invention, the second predicted value Y' can be obtained using the prediction model; the system can calculate the output characteristic value of a certain feature in the future time corresponding to multiple past moments and the current moment [..., T n-3 , T n-2 , T n-1 , T n ] as the input feature of the monitoring data set, and input it into the prediction model; the prediction model can output the prediction at the future time T n+1 The predicted data, i.e., the second predicted value Y′; in some embodiments, the second predicted value Y′ can be interpreted as “what the monitored data will look like in the future”;

[0095] The expected future time target Z refers to the value of the process of monitoring data changing between one or more future times, so as to evaluate the progress of the change in the realization of the work task; for example, given a set of work tasks (for example, achieving specified indicator data within a month), the disaster emergency monitoring system can determine what the characteristic value of the indicator data should reach every week; in some embodiments, the expected future time target Z can be interpreted as "what the process of the monitoring area from now to the future time should be like";

[0096] Furthermore, the processing module can evaluate the results of the task objectives from the above values, and can perform process inspection to ensure that the work tasks in the process are changing according to the established trajectory, and timely update the first task objective and the first scheduling arrangement to the second task objective and the second scheduling arrangement;

[0097] Furthermore, the disaster emergency monitoring system presents a series of data using images to achieve a more intuitive monitoring data display effect.

[0098] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in the relevant technical field without departing from the purpose of the present invention.

Claims

1. A disaster emergency monitoring system, characterized in that: The disaster emergency monitoring system includes a data acquisition module, a network service module, a processing module, a scheduling module and an execution module; wherein, The data acquisition module is constructed to include a field data acquisition unit and a remote sensing data acquisition unit, which are used to collect monitoring data of the monitoring area and send the monitoring data to the network service module through network communication; The network service module is configured to realize transmission and protection of the monitoring data; The processing module is configured to perform data interaction on the monitoring data and submit the data interaction result to the scheduling module; The scheduling module is configured to formulate work tasks and complete the scheduling of relevant staff members according to the data interaction results and in combination with the staff scheduling system; The execution module is configured to receive the work tasks assigned by the scheduling module and the execution feedback of the relevant staff after the work tasks are executed, including the execution time and the actual implementation situation, and the execution module sends the execution feedback to the processing module; The processing module continuously updates the current monitoring value of the monitoring area and combines it with the execution feedback to update the data interaction result; the processing module stores a prediction model; by inputting historical monitoring data into the prediction model, a first prediction value corresponding to the current time is obtained; and by inputting historical monitoring data and the current monitoring value into the prediction model, a second prediction value corresponding to the future time is obtained; based on comparing the first prediction value with the current monitoring value, and based on comparing the second prediction value with the future monitoring value, whether the status of the monitoring area is healthy or whether the progress is completed, or further issuing early warning information; and based on the difference between the above two values, updating work tasks and scheduling arrangements.

2. The disaster emergency monitoring system according to claim 1, characterized in that: The execution steps of the disaster emergency monitoring system include: S100, data reception, receiving the monitoring data collected by the data collection module in a first period T1; S200, the processing module performs historical monitoring data analysis and obtains a first prediction value, compares the first prediction value with the current monitoring value, obtains a first difference value, and formulates a first work task and a first scheduling arrangement according to the first difference value; S300, sending the first work task and the first scheduling arrangement to relevant personnel or departments for execution, and receiving corresponding execution feedback; S400, the processing module analyzes historical monitoring data, current monitoring values, and execution feedback to obtain a second prediction value; S500. At a specified time in the future, compare the second predicted value with the future monitored value to obtain a second difference value, and evaluate the execution result of the first work task according to the second difference value.

3. The disaster emergency monitoring system according to claim 2, characterized in that: The step S200 includes: The historical monitoring data and the current monitoring values ​​are input into the preset fault node model to obtain the fault node that matches the fault node model; the geographical location corresponding to the fault node is analyzed, and the early warning area of ​​the specified range is delineated; the fault node model is set by relevant technical personnel according to the standard range of environmental parameters in different sections of the monitoring area.

4. The disaster emergency monitoring system according to claim 3, characterized in that: The step S200 further includes adjusting the monitoring time of the warning area to a second period T2, and making T2<T1.

5. The disaster emergency monitoring system according to claim 3, characterized in that: In step S300, historical monitoring data, current monitoring values, first prediction values, second prediction values, fault nodes, geographical locations corresponding to fault nodes, warning areas and other information are saved in the network service module, and one or more of the above information is displayed when required by relevant individuals or units.

6. The disaster emergency monitoring system according to claim 5, characterized in that: The workflow of the scheduling module and the execution module includes the following steps: W100, the scheduling module sends the first work task and the first scheduling arrangement to the execution module of the corresponding partition management unit; W200, after receiving the corresponding control instruction, the execution module of the zoning management unit dispatches staff to work on the warning area based on the first work task according to the first scheduling arrangement; W300. After the work is completed, the staff sends the execution feedback to the network service module through the execution module, and the network service module records and stores the execution feedback.

7. The disaster emergency monitoring system according to claim 6, characterized in that: The network service module includes: An Internet of Things gateway, configured to solve the data collection and processing problems of sensors in a plurality of said data collection modules; The server is configured to handle data flow and cache, and includes a database for storing monitoring data.

8. The disaster emergency monitoring system according to claim 1, characterized in that: The prediction model includes a grey prediction model, a regression prediction model, a time series analysis model, a Kalman filter prediction model, a fuzzy mathematical model, a supervised machine learning model, a residual network-based machine learning model, a weight-based machine learning model or a generative adversarial network-based machine learning model, or any combination of two or more of these models.

9. The disaster emergency monitoring system according to claim 1, characterized in that: The field data acquisition unit includes one or more of a strain gauge, a piezometer, a stress gauge, a water level gauge, an earth pressure gauge, a water weir gauge, an inclinometer, an anemometer and a barometer.

10. The disaster emergency monitoring system according to claim 1, characterized in that: The remote sensing data acquisition unit includes one or more satellite images of meteorological satellites, earth satellites, land satellites, and ocean satellites.