Cloud platform-based flood and drought disaster prevention management system and method

Abstract

The invention provides a flood and drought disaster prevention management system and method based on a cloud platform, and the method comprises the steps: a data collection module is used for collecting type data related to flood and drought disasters, and carrying out the preprocessing of the type data through a calculation formula, so as to obtain standard data; the data transmission module is used for transmitting the standard data acquired by the data acquisition module to the cloud platform processing module; the cloud platform processing module is used for deeply processing and analyzing the received standard data and then establishing a flood and drought disaster prediction model; the information sharing module is used for sharing the flood and drought disaster prediction model with each related department; and the decision support module is used for providing an anti-disaster scheme for the flood and drought disaster prevention decision according to the flood and drought disaster prediction model. According to the method, the type data is preprocessed through the calculation formula, so that weights are given to different types of data, weighted integration can be carried out according to the importance and relevance of the type data, and the data formats of different devices and the integration and transmission efficiency when the communication difference is large are improved.

Description

Technical Field

[0001] The present invention relates to the field of disaster prevention technology, and in particular to a flood and drought disaster prevention management system and method based on a cloud platform. Background Art

[0002] Traditional flood and drought disaster prevention and control systems lack data processing and analysis capabilities. Faced with massive amounts of flood and drought-related data, including meteorological, hydrological, and geographic information data, traditional processing systems have limited computing resources and are unable to rapidly perform complex data processing and in-depth analysis. For example, before a flood strikes, a large amount of hydrological flow data needs to be predicted and analyzed, but existing systems often take hours or even days to complete the calculations, missing the optimal opportunity for disaster warning and prevention. Furthermore, information sharing and collaboration are difficult in traditional flood and drought disaster prevention and control. Flood and drought disaster prevention involves multiple departments, such as water conservancy, meteorology, and emergency management. However, the information systems of these departments are independent and lack effective information sharing mechanisms, resulting in inefficient collaborative work. For example, after the meteorological department predicts heavy rainfall, it cannot promptly and accurately transmit this information to the water conservancy department for flood risk assessment. This results in each department operating independently in disaster prevention and control, preventing them from forming an effective synergistic force. Furthermore, existing flood and drought data collection equipment is scattered and the data formats and communication protocols vary widely, making efficient data integration and transmission difficult. For example, rainfall monitoring stations in some remote areas use older analog signal transmission methods, which are susceptible to interference and make it difficult to guarantee accuracy and real-time performance.

[0003] In summary, the technical problem actually solved by the present invention is how to improve the efficient integration of data. Summary of the Invention

[0004] In order to overcome the technical defects in the above-mentioned prior art that data is difficult to efficiently integrate and transmit due to the large differences in data formats and communication protocols of different devices, the purpose of the present invention is to provide a flood and drought disaster prevention management system and method based on a cloud platform, which pre-processes type data through calculation formulas to assign weights to different types of data, and can perform weighted integration according to the importance and relevance of type data, so as to improve the integration and transmission efficiency when the data formats and communication protocols of different devices are greatly different.

[0005] The present invention discloses a flood and drought disaster prevention management system based on a cloud platform, comprising a data acquisition module, a data transmission module, a cloud platform processing module, an information sharing module and a decision support module; wherein,

[0006] The data acquisition module is used to collect type data related to flood and drought disasters, and pre-process the type data through calculation formula to obtain standard data. The calculation formula is:

[0007]

[0008] Among them, D processed is the standard data, D i is the original collected data of type i, w i is the weight corresponding to the i-th type of data, and n is the number of types of data;

[0009] The data transmission module is used to transmit the standard data acquired by the data acquisition module to the cloud platform processing module;

[0010] The cloud platform processing module is used to conduct in-depth processing and analysis of the received standard data and then establish a flood and drought disaster prediction model;

[0011] The information sharing module is used to share flood and drought disaster prediction models with relevant departments;

[0012] The decision support module is used to provide disaster prevention plans for flood and drought disaster prevention decisions based on the flood and drought disaster prediction model.

[0013] Preferably, the data acquisition module includes at least one acquisition unit, and the acquisition unit is provided with a meteorological data monitoring device, and the meteorological data monitoring device is used to acquire the aforementioned type of data.

[0014] Preferably, the data acquisition module includes a correction unit, which modifies the original collected data D by a correction calculation formula. i Correction, the correction calculation formula is:

[0015]

[0016] Among them, k i is the calibration coefficient of the i-th acquisition unit.

[0017] Preferably, the data transmission module adopts wireless communication technology and / or wired communication technology to transmit standard data, the wireless communication technology includes 4G and 5G communication, and the wired communication technology includes optical fiber communication.

[0018] Preferably, the cloud platform processing module adopts a distributed computing architecture, which includes a number of computing nodes, and each computing node independently performs in-depth processing and analysis on part of the standard data.

[0019] Preferably, the distributed computing architecture includes a task scheduling algorithm, which calculates the task carrying capacity evaluation value E of each computing node. The calculation formula for calculating the task carrying capacity evaluation value E of each settlement node is:

[0020]

[0021] Among them, α is the weight coefficient, and 0<α<1, j is the computing node, L CPU is the CPU usage, L Memory is the memory usage.

[0022] Preferably, the decision support module includes a decision model library, which includes at least a flood control scheduling model and a drought relief water allocation model. When the decision support module provides disaster relief plans for flood and drought disaster prevention decisions, it provides disaster relief plans based on the flood control scheduling model and / or the drought relief water allocation model.

[0023] In view of this, a second object of the present invention is to provide a flood and drought disaster prevention management method based on a cloud platform, comprising the following steps:

[0024] Based on the data acquisition module, the type data related to floods and droughts are collected, and the type data are preprocessed through the calculation formula to obtain standard data. The calculation formula is:

[0025]

[0026] Among them, D processed is the standard data, D i is the original collected data of type i, w i is the weight corresponding to the i-th type of data, and n is the number of types of data;

[0027] Transmit the standard data to the cloud platform processing module through the data transmission module;

[0028] The cloud platform processes and analyzes standard data in depth to establish a flood and drought disaster prediction model;

[0029] Share flood and drought disaster prediction models among various departments through information sharing modules;

[0030] Provide disaster prevention plans for flood and drought disaster decision-making based on flood and drought disaster prediction models.

[0031] Preferably, in the step of establishing a flood and drought disaster prediction model after the cloud platform performs in-depth processing and analysis on the standard data, a machine learning algorithm is used to establish the flood and drought disaster prediction model.

[0032] Compared to existing technologies, the above-mentioned technical solution has the following advantages: It pre-processes data types through a computational formula to assign weights to different data types, enabling weighted integration based on their importance and relevance, thereby improving integration and transmission efficiency when data formats and communication protocols differ significantly across devices. The data transmission module transmits pre-processed standard data to the cloud platform processing module. Combining wired and wireless communication technologies, such as fiber optic + 5G in cities and 4G in remote mountainous areas, it avoids geographical restrictions and interference in data transmission, ensuring real-time and accurate data transmission. Compared to traditional transmission methods, it reduces data loss and errors, improves data transmission efficiency and reliability, and provides a solid foundation for subsequent data processing and analysis. The information sharing module enables data sharing among relevant departments, such as water conservancy, meteorology, and emergency management, and utilizes blockchain technology to ensure data security and immutability. This changes the traditional situation of independent information systems and a lack of sharing mechanisms among departments, enabling each department to obtain comprehensive disaster information in a timely manner. For example, rainfall forecast data from the meteorological department can be promptly transmitted to the water conservancy department for flood risk assessment, promoting collaborative work among departments, forming a joint disaster prevention force, and improving the overall efficiency of disaster prevention efforts. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a system diagram of a flood and drought disaster prevention management system and method based on a cloud platform of the present invention;

[0034] Figure 2 This is a schematic diagram of the method steps of a flood and drought disaster prevention management system and method based on a cloud platform of the present invention. DETAILED DESCRIPTION

[0035] The advantages of the present invention are further described below with reference to the accompanying drawings and specific embodiments.

[0036] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0037] The terms used in this disclosure are for the purpose of describing specific embodiments only and are not intended to limit the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0038] It should be understood that although the terms first, second, third, etc. may be used in this disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of this disclosure, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining."

[0039] In the description of the present invention, it should be understood that the terms "longitudinal", "transverse", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying 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.

[0040] In the description of the present invention, unless otherwise specified and limited, it should be noted that the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a mechanical connection or an electrical connection, or it can be the internal communication between two components. It can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to the specific circumstances.

[0041] In the following description, the suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present invention and have no specific meaning. Therefore, "module" and "component" can be used interchangeably.

[0042] This embodiment discloses a flood and drought disaster prevention and management system based on a cloud platform, comprising a data acquisition module, a data transmission module, a cloud platform processing module, an information sharing module, and a decision support module. The data acquisition module is used to collect type data related to flood and drought disasters and pre-process the type data to obtain standard data using a calculation formula. The calculation formula is:

[0043]

[0044] Among them, D processed is the standard data, D i is the original collected data of type i, w iis the weight corresponding to the i-th type of data, and n is the number of types of data; the data transmission module is used to transmit the standard data obtained by the data acquisition module to the cloud platform processing module; the cloud platform processing module is used to establish a flood and drought disaster prediction model after in-depth processing and analysis of the received standard data; the information sharing module is used to share the flood and drought disaster prediction model with relevant departments; the decision support module is used to provide disaster prevention plans for flood and drought disaster prevention decisions based on the flood and drought disaster prediction model.

[0045] See Figure 1 As shown, this embodiment will provide a detailed description of a flood and drought disaster prevention and management system based on a cloud platform. The system includes a data acquisition module, a data transmission module, a cloud platform processing module, an information sharing module, and a decision support module. The details are as follows:

[0046] Data collection module: The data collection module is used to collect various types of data, including but not limited to meteorological information, hydrological information, geographic information, etc., and pre-process each type of data collected through a calculation formula to perform weighted processing on the type of data to obtain standard data. The calculation formula is:

[0047]

[0048] Among them, D processed is the standard data, D i is the original collected data of type i, w i is the weight corresponding to the i-th type of data, and n is the number of data types. This mathematical formula is based on a weighted summation. By assigning appropriate weights to different types of data, it can highlight the role of data that has a significant impact on disaster assessment. For example, in flood disaster monitoring, rainfall and river water level data have a greater impact on flood formation and development and can be assigned higher weights; while data such as wind speed have a relatively smaller direct impact on floods and can be assigned lower weights. In this way, multiple types of data are integrated into a comprehensive standard data set, providing more valuable input for subsequent analysis and processing.

[0049] Data transmission module: The data transmission module is responsible for transmitting the pre-processed type data to the cloud platform processing module, that is, transmitting the standard data to the cloud platform processing module.

[0050] Cloud Platform Processing Module: Leveraging powerful computing and storage resources, the Cloud Platform Processing Module deeply processes standard data to build flood and drought prediction models. Employing a distributed computing and storage architecture, the Cloud Platform Processing Module rapidly processes massive amounts of standard data and supports a variety of data analysis algorithms and models.

[0051] Information Sharing Module: This module is used to share established flood and drought disaster prediction models across multiple departments. For example, the meteorological department, hydrological department, and geographic department can each view the shared flood and drought disaster prediction model. The information sharing module uses a standardized data interface to ensure that flood and drought disaster prediction models can be accurately shared.

[0052] Decision support module: The decision support module makes intelligent decision recommendations through the visual display of flood and drought disaster prediction models, helping decision makers quickly understand the disaster situation and thus formulate reasonable defense strategies.

[0053] Furthermore, the data acquisition module includes at least one acquisition unit, and the acquisition unit is equipped with a meteorological data monitoring device, which is used to collect type data.

[0054] In this embodiment, the data acquisition module is described in detail. The data acquisition module includes at least one acquisition unit, and the meteorological data monitoring device is used to detect type data. It should be noted that the meteorological data monitoring device includes, but is not limited to, a rainfall sensor, a wind speed sensor, and an air temperature sensor; the hydrological data sensors include a water level sensor, a flow sensor, a terrain sensor, and a soil type sensor.

[0055] Among them, the rain sensor uses a tipping bucket rain gauge. It collects rainfall in a bucket that flips when it reaches a certain level of water. The generated pulse signal measures rainfall with an accuracy of up to 0.1 mm. The wind speed sensor uses the relationship between the rotation speed of the three-cup wind cup and wind speed. An internal photoelectric encoder converts the cup rotation signal into an electrical signal to measure wind speed, typically within a range of 0-60 m / s. The temperature sensor typically uses a thermistor, whose resistance changes with temperature. The temperature is calculated by measuring this resistance with an accuracy of ±0.5°C. The terrain sensor uses lidar technology to transmit a laser beam to the ground, measure the time from emission to reflection, and calculate the three-dimensional coordinates of the ground point, thereby obtaining terrain information with centimeter-level accuracy. The soil type sensor determines soil type by measuring parameters such as conductivity, pH, and water content, combined with a soil classification model.

[0056] For example, when collecting data on a small mountainous watershed, rainfall sensors are deployed at various locations, such as mountaintops and valleys, to monitor rainfall distribution in real time. Water level sensors and flow sensors are installed at key river sections to monitor changes in water level and flow. Topographic sensors are used to scan the entire watershed to obtain topographic data. Soil type sensors are installed in different soil areas to understand soil characteristics. These sensors work together to comprehensively collect meteorological, hydrological, and geographic information data for the watershed, providing accurate data support for flood and drought prevention.

[0057] Furthermore, the data acquisition module includes a correction unit, which modifies the original collected data D by a correction calculation formula. i Correction, the correction calculation formula is: Among them, k i is the calibration coefficient of the i-th acquisition unit.

[0058] In this embodiment, the data acquisition module will be described in detail again. In order to collect data more accurately and improve the effect of preprocessing, a sensor error correction mechanism, namely a correction unit, is introduced into the data module. Since in actual applications, sensors may have systematic errors and random errors, which affect the accuracy of the collected raw data and interfere with subsequent calculations. In this embodiment, the raw data is error corrected by taking the average after multiple measurements and introducing calibration coefficients. Assume that m measurements are taken for the i-th type of data, and the measurement value D is obtained. i1 、D i2 ..., D im , then the corrected calculation formula is: Among them, k i is the calibration coefficient of the i-th type of acquisition unit, which can be obtained by comparing it with high-precision marking equipment. After error correction, it is substituted into the original preprocessing calculation formula At this time, D i It is the mean value after correction, which improves the accuracy of standard data, improves data quality, and enhances the reliability of the system in predicting water and drought disasters.

[0059] Furthermore, the data transmission module adopts wireless communication technology and / or wired communication technology to transmit standard data, the wireless communication technology includes 4G and 5G communication, and the wired communication technology includes optical fiber communication.

[0060] In this embodiment, the data transmission module will be described in detail. In cities and densely populated areas, fiber optic communication is preferred due to the well-developed communication infrastructure. Fiber optic communication has the advantages of high transmission rate, large bandwidth, and strong anti-interference ability, and can quickly and stably transmit large amounts of data. For example, at a hydrological monitoring station in a city, the collected data is transmitted to a nearby data center by laying optical fiber, with transmission rates exceeding 1Gbps, ensuring the real-time and accuracy of the data. The data from the data center is then transmitted to the cloud platform processing module using 5G communication. 5G communication has the characteristics of low latency and high reliability, which can meet the needs of real-time data transmission.

[0061] 4G communications are primarily used in remote mountainous areas and outdoor areas with weak communications infrastructure. 4G communications offer wide coverage, providing signal coverage in most areas. For example, at a meteorological monitoring station in a mountainous area, 4G communication modules transmit collected data directly to a cloud platform processing module. While the transmission rate is lower than that of fiber-optic communications, it ensures data transmission is completed within a reasonable timeframe, meeting the basic requirements of disaster monitoring. Furthermore, to improve data transmission reliability, the data transmission module utilizes technologies such as data compression and error correction coding to reduce data transmission volume and lower the error rate during data transmission.

[0062] Furthermore, the cloud platform processing module adopts a distributed computing architecture, which includes several computing nodes, each of which performs in-depth processing and analysis on part of the standard data.

[0063] The cloud platform processing module utilizes distributed computing architectures such as Hadoop and Spark to store preprocessed data in a distributed file system (such as HDFS). Upon receiving standard data from the data transmission module, it distributes this data to different compute nodes for processing based on its type, source, and other characteristics. For example, meteorological data could be assigned to one group of compute nodes, while hydrological data could be assigned to another. Each compute node possesses independent computing and storage capabilities, enabling simultaneous preprocessing of the assigned data.

[0064] When processing large-scale hydrological data, such as analyzing multi-year water level and flow data from multiple sites within a river basin, a distributed computing architecture can be used to segment the data into multiple blocks, each stored on different computing nodes. Each computing node simultaneously performs calculations on its local data block, such as calculating the average water level and flow rate trends. The distributed computing framework's communication mechanism then aggregates and integrates the results from each node, ultimately yielding a hydrological analysis for the entire river basin. Compared to traditional stand-alone computing methods, a distributed computing architecture can reduce data processing time from hours or even days to minutes, significantly improving data processing efficiency and ensuring timely and accurate flood and drought forecasting.

[0065] Furthermore, the distributed computing architecture includes a task scheduling algorithm, which calculates the task carrying capacity evaluation value E of each computing node. The calculation formula for calculating the task carrying capacity evaluation value E of each settlement node is: Among them, α is the weight coefficient, and 0<α<1, j is the computing node, L CPU is the CPU usage, L Memory is the memory usage.

[0066] In this embodiment, the cloud platform processing module will be described in detail again. In the distributed computing architecture of the cloud platform processing module, a task scheduling algorithm is introduced in the distributed computing architecture to reasonably allocate computing tasks and improve computing resource utilization. The task scheduling algorithm calculates the current load of the node (such as CPU usage L CPU , memory usage L Memory ) and computing power (such as the number of CPU cores C, computing speed V) and other factors, calculate the task carrying capacity evaluation value E of each computing node. The calculation formula is Among them, α is the weight coefficient, and 0<α<1, j is the computing node, L CPU is the CPU usage, L Memory is the memory usage rate. The weight coefficient α will be adjusted according to the degree of influence of CPU and memory on the computing task in the actual application scenario. When allocating standard data processing tasks, the tasks are preferentially allocated to the computing nodes with larger task carrying capacity evaluation value E. In some embodiments, for a batch of standard data, the task carrying capacity evaluation value E of each computing node is calculated according to the above calculation formula, and the standard data is allocated in descending order so that the computing tasks are evenly distributed on each computing node, avoiding the situation where some computing nodes are overloaded and some computing nodes are idle, thereby improving the overall data processing efficiency of the distributed computing architecture and further accelerating the establishment speed of the flood and drought disaster prediction model.

[0067] Furthermore, the decision support module includes a decision model library, which includes at least a flood control scheduling model and a drought relief water allocation model. When the decision support module provides disaster relief plans for flood and drought disaster prevention decisions, it provides disaster relief plans based on the flood control scheduling model and / or the drought relief water allocation model.

[0068] In this embodiment, the decision support module will be described in detail. The decision support module includes a decision model library, which includes a flood control scheduling model and a drought relief water allocation model.

[0069] The flood control scheduling model is based on theories of hydraulics and operations research, and incorporates the characteristics and functions of water conservancy facilities such as reservoirs, river channels, and levees within a river basin to establish a data model. Aiming to protect people's lives and property and reduce disaster losses, the model comprehensively considers factors such as rainfall, water levels, flow rates, reservoir storage capacity, and flood discharge capacity, and uses an optimization algorithm to determine the optimal flood control scheduling plan. For example, before a flood arrives, the flood control scheduling model uses real-time rainfall forecasts and water level monitoring data to calculate the appropriate flood discharge volume and timing for each reservoir, minimizing the risk of dam failure caused by over-accumulation. It also regulates river flows to alleviate flood control pressures in downstream areas.

[0070] The drought-resistance water allocation model aims to rationally allocate and efficiently utilize water resources. It considers factors such as crop water requirements, soil moisture, and water reserves, and uses optimization methods such as linear programming and dynamic programming to develop a scientific drought-resistance water allocation plan. During droughts, this model rationally allocates limited water resources based on the crop planting structure and water requirements of different regions, prioritizing the irrigation needs of grain crops and important cash crops, improving water utilization efficiency, and reducing drought losses.

[0071] This embodiment also provides a flood and drought disaster prevention and management method based on a cloud platform, comprising the following steps:

[0072] Based on the data acquisition module, the type data related to floods and droughts are collected, and the type data are preprocessed through the calculation formula to obtain standard data. The calculation formula is:

[0073]

[0074] Among them, D processed is the standard data, D i is the original collected data of type i, w i is the weight corresponding to the i-th type of data, and n is the number of types of data; the standard data is transmitted to the cloud platform processing module through the data transmission module; the cloud platform processes and analyzes the standard data in depth and then establishes a flood and drought disaster prediction model; the flood and drought disaster prediction model is shared among various departments through the information sharing module; and disaster prevention plans are provided for flood and drought disaster decision-making based on the flood and drought disaster prediction model.

[0075] It should also be noted that the information sharing module uses blockchain technology to ensure the security and non-tamperability of the flood and drought disaster prediction model during the sharing process. Blockchain technology is a decentralized distributed ledger technology with the characteristics of data non-tamperability, traceability, security and reliability. The information sharing module uses the distributed storage and consensus mechanism of blockchain to store the data shared by various departments on multiple nodes, each of which maintains a complete copy of the ledger. When the water conservancy department uploads real-time water level data, the data is packaged into a data block and timestamped. It is then verified and disseminated in the blockchain network through consensus algorithms (such as proof of work, proof of stake, etc.). When other departments obtain data, they verify the integrity and authenticity of the data through the blockchain's hash algorithm to ensure that the data has not been tampered with during transmission and storage.

[0076] Blockchain technology also enables data access control and permission management. Each department can set different data access permissions based on its needs and responsibilities. For example, the emergency management department can view all disaster response-related data, while the agricultural department can only view meteorological and hydrological data related to agricultural production. This approach ensures data security and privacy while ensuring data sharing.

[0077] See Figure 2 As shown, this embodiment will describe in detail a flood and drought disaster prevention and management method based on a cloud platform, which specifically includes the following steps:

[0078] Step S100: In this step, the data acquisition module quickly collects data such as typhoon paths, rainfall, river and lake water levels, and coastal tide levels, and pre-processes them according to the calculation formula to obtain standard data, highlighting the impact of key data. The calculation formula is:

[0079]

[0080] Step S200: In this step, the processed data is quickly transmitted to the cloud platform processing module by combining wired optical fiber and wireless 5G communication.

[0081] Step S300: In this step, the cloud platform processing module uses machine learning algorithms to analyze standard data and establish a flood and drought disaster prediction model. For example, a prediction model for typhoon-induced flood disasters can be established to predict the flood inundation range, flood peak arrival time, and other information.

[0082] Step S400: In this step, the flood and drought disaster prediction model established in step S300 is shared with water conservancy, meteorological and other departments so that relevant departments can understand flood and drought disasters in a timely manner.

[0083] Step S500: In this step, intelligent decision-making recommendations are made through the visual display of the flood and drought disaster prediction model to help decision makers quickly understand the disaster situation and thus formulate reasonable defense strategies.

[0084] Preferably, in the step of establishing a flood and drought disaster prediction model after the cloud platform performs in-depth processing and analysis on the standard data, a machine learning algorithm is used to establish the flood and drought disaster prediction model.

[0085] In this embodiment, the cloud platform processing will be described in detail. When the cloud platform processes and analyzes standard data in depth to establish a flood and drought disaster prediction model, a machine learning algorithm is used. The machine learning algorithm includes but is not limited to a neural network algorithm and a support vector machine algorithm.

[0086] Neural network algorithms mimic the structure and working principles of neurons in the human brain and possess powerful nonlinear mapping and self-learning capabilities. When building a flood prediction model, a large amount of historical flood data, including rainfall, water levels, flow rates, and topography, is first collected as training samples. This data is then fed into the neural network model, and by adjusting the model's parameters (such as the connection weights and thresholds between neurons), the model learns the inherent patterns and relationships between the data. Once training is complete, the real-time data is fed into the model, enabling it to predict information such as the probability of flood occurrence, peak flow rates, and flood arrival times.

[0087] The support vector machine (SVM) algorithm is a classification and regression algorithm based on statistical learning theory. It can find the optimal classification hyperplane or regression function in high-dimensional space. In drought prediction, the SVM algorithm is used to train models using historical data such as temperature, rainfall, evaporation, and soil moisture as input and drought occurrence as output. The trained model can predict the development trend and impact of droughts based on real-time meteorological and hydrological data, providing a basis for drought prevention and control decisions.

[0088] It should be noted that the embodiments of the present invention have better practicability and do not impose any form of limitation on the present invention. Any technician familiar with the field may use the technical content disclosed above to change or modify it into an equivalent effective embodiment. However, any modification or equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A flood and drought disaster prevention and management system based on a cloud platform, characterized in that: It includes data acquisition module, data transmission module, cloud platform processing module, information sharing module and decision support module; among them, The data acquisition module is used to collect type data related to flood and drought disasters, and pre-process the type data to obtain standard data through a calculation formula. The calculation formula is: Among them, D processed is the standard data, D i is the original collected data of type i, w i is the weight corresponding to the i-th type of data, and n is the number of data of that type; The data transmission module is used to transmit the standard data acquired by the data acquisition module to the cloud platform processing module; The cloud platform processing module is used to establish a flood and drought disaster prediction model after in-depth processing and analysis of the received standard data; The information sharing module is used to share the flood and drought disaster prediction model with relevant departments; The decision support module is used to provide disaster prevention solutions for flood and drought disaster prevention decisions based on the flood and drought disaster prediction model.

2. The flood and drought disaster prevention management system based on the cloud platform according to claim 1 is characterized in that: The data acquisition module includes at least one acquisition unit, and the acquisition unit is equipped with a meteorological data monitoring device, and the meteorological data monitoring device is used to acquire the type of data.

3. The flood and drought disaster prevention management system based on the cloud platform according to claim 2 is characterized in that: The data acquisition module includes a correction unit, which modifies the original collected data D by a correction calculation formula. i Correction, the correction calculation formula is: Among them, k i is the calibration coefficient of the i-th acquisition unit.

4. The flood and drought disaster prevention and management system based on a cloud platform according to claim 1, characterized in that: The data transmission module adopts wireless communication technology and / or wired communication technology to transmit the standard data, the wireless communication technology includes 4G and 5G communication, and the wired communication technology includes optical fiber communication.

5. The flood and drought disaster prevention management system based on a cloud platform according to claim 1, characterized in that: The cloud platform processing module adopts a distributed computing architecture, which includes a number of computing nodes, and each computing node independently performs in-depth processing and analysis on part of the standard data.

6. The flood and drought disaster prevention and management system based on a cloud platform according to claim 5, characterized in that: The distributed computing architecture includes a task scheduling algorithm, which calculates the task carrying capacity evaluation value E of each computing node. The calculation formula for calculating the task carrying capacity evaluation value E of each settlement node is: Among them, α is the weight coefficient, and 0<α<1, j is the computing node, L CPU is the CPU usage, L Memory is the memory usage.

7. The flood and drought disaster prevention and management system based on a cloud platform according to claim 1, characterized in that: The decision support module includes a decision model library, which includes at least a flood control scheduling model and a drought relief water allocation model. When the decision support module provides disaster relief plans for flood and drought disaster prevention decisions, it provides disaster relief plans based on the flood control scheduling model and / or the drought relief water allocation model.

8. A flood and drought disaster prevention and management method based on a cloud platform, characterized in that: The following steps are involved: The data acquisition module collects flood- and drought-related data, and pre-processes the data to obtain standard data using a calculation formula. The calculation formula is: Among them, D processed is the standard data, D i is the original collected data of type i, w i is the weight corresponding to the i-th type of data, and n is the number of data of that type; Transmitting the standard data to the cloud platform processing module through the data transmission module; The cloud platform processes and analyzes the standard data in depth to establish a flood and drought disaster prediction model; Sharing the flood and drought disaster prediction model among various departments through an information sharing module; According to the flood and drought disaster prediction model, a disaster prevention plan is provided for flood and drought disaster decision-making.

9. The flood and drought disaster prevention and management method based on a cloud platform according to claim 8, characterized in that: In the step of establishing a flood and drought disaster prediction model after the cloud platform performs in-depth processing and analysis on the standard data, a machine learning algorithm is used to establish the flood and drought disaster prediction model.

Images