Mountain torrent prediction method and system based on hyper-fusion, terminal and storage medium

Abstract

The invention relates to the technical field of data processing, and particularly provides a super-fusion-based mountain torrent prediction method and system, a terminal and a storage medium, and the method comprises the steps: constructing a super-fusion platform based on kubernetes and a distributed storage technology, a weather forecast system, a hydrological monitoring system, an inspection data management system, a plan management system and an external communication system are deployed on the hyper-fusion platform; a business layer of the hyper-fusion platform obtains meteorological data from a meteorological forecasting system, and generates a mountain torrent prediction event based on the meteorological data; and the business layer obtains water regimen forecast from the hydrological monitoring system, generates disaster forecast if the water regimen forecast is matched with the mountain torrent forecast event, and performs disaster analysis and early warning release through the inspection data management system, the plan management system and the external communication system based on the disaster forecast. By constructing the hyper-fusion platform, the meteorological data and the hydrological data are fused, accurate prediction of the mountain torrents is realized, and the accuracy of mountain torrent prediction is improved.

Description

Technical Field

[0001] The present invention belongs to the field of data processing technology, and specifically relates to a flash flood prediction method, system, terminal and storage medium based on hyper-convergence. Background Art

[0002] Flash flood prediction technology is an important area of ​​disaster prediction. The current flash flood prediction technology includes prediction based on hydrological data and prediction based on meteorological data. Among them, the prediction methods based on hydrological data include: GIS hydrological analysis Q (ArcHydro, Spatial Analysist and other modules) is an important tool for basin hydrological simulation modeling, which can automatically extract and calculate basin boundaries, river networks, flow directions, confluence times and other basin characteristic parameters. Hec _RAS software is a typical flood inundation hazard analysis model, which has been widely used in the research, planning and production of flood risk management worldwide and has broad prospects. Combining ArcGIS with Hec RAS software can well realize the numerical simulation of flash flood runoff process and flood inundation. The prediction methods based on meteorological data include: monitoring rainfall, and once the rainfall reaches the set threshold, a flash flood prediction event is generated.

[0003] Existing flash flood prediction methods are unable to combine hydrological data and meteorological data. Flash flood prediction methods based on hydrological data will miss some sudden flash floods in arid mountainous areas; while prediction methods based on meteorological data are relatively rough and cannot locate flash flood outbreak areas, and the prediction results are not accurate. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides a flash flood prediction method, system, terminal and storage medium based on hyper-convergence to solve the above-mentioned technical problems.

[0005] In a first aspect, the present invention provides a flash flood prediction method based on hyper-convergence, comprising: Build a hyper-convergence platform based on Kubernetes and distributed storage technology, and deploy a weather forecast system, a hydrological monitoring system, an inspection data management system, a plan management system, and an external communication system on the hyper-convergence platform; Acquire meteorological data from a meteorological forecast system, and generate a flash flood forecast event based on the meteorological data; Obtaining a water situation forecast from a hydrological monitoring system, and generating a disaster forecast if the water situation forecast matches the flash flood forecast event; Acquire inspection data from an inspection data management system, verify the disaster forecast based on the inspection data, generate a disaster warning, and retrieve a matching plan for the disaster warning from a plan management system; Warning information is generated based on disaster warnings and matching plans, and the warning information is broadcast to terminals in corresponding areas through an external communication system.

[0006] In an optional implementation, a hyper-convergence platform is constructed based on Kubernetes and distributed storage technology, and a weather forecast system, a hydrological monitoring system, an inspection data management system, a plan management system, and an external communication system are deployed on the hyper-convergence platform, including: Build multiple container groups through kubernetes, and deploy the meteorological forecast system, hydrological monitoring system, inspection data management system, emergency plan management system and external communication system in multiple container groups in a one-to-one correspondence manner. The number of containers in the container group is not less than 2; Assign a group ID to the container group, and bind the group ID to the name of the system deployed in the container group; Use the Kubernetes resource monitoring component to monitor the available resources of each container group. If the available resources are lower than the preset threshold, add containers to the corresponding container group. Use a distributed file system to build a storage layer and allocate storage resources to each container group; Configure the nacos or REST API communication protocol for the container group.

[0007] In an optional implementation, obtaining meteorological data from a meteorological forecast system, and generating a flash flood prediction event based on the meteorological data, includes: Acquire meteorological data from a meteorological forecast system, wherein the meteorological data includes rainfall in each minimum area; The minimum areas are grouped according to the watersheds to which they belong, and a plurality of watershed groups are obtained; Collecting historical data of each smallest area in the watershed group, the historical data including previous flash floods and rainfall in the flash flood outbreak area and upstream area; Using association rule algorithm to mine the association relationship between rainfall and flash floods in the basin group based on the historical data; The correlation between the meteorological data corresponding to the river basin group and the flash flood outbreak is calculated based on the correlation relationship, and when the correlation reaches a set threshold, a flash flood prediction event is generated for the corresponding area within the river basin group.

[0008] In an optional implementation, a water situation forecast is obtained from a hydrological monitoring system, and if the water situation forecast matches the flash flood prediction event, a disaster forecast is generated, including: The watershed corresponding to the flash flood forecast event is taken as the target watershed; Obtaining a water situation forecast for a target river basin from the hydrological monitoring system, wherein the water situation forecast includes river water level and flood peak flow prediction data, and the hydrological monitoring system adopts an ArcGIS model; Determine whether the river water level and the flood peak flow forecast data reach a preset corresponding threshold value, and if so, upgrade the flash flood forecast event to a disaster forecast; Based on the disaster forecast, an inspection task is issued to the inspection data management system.

[0009] In a second aspect, the present invention provides a flash flood prediction system based on hyper-convergence, comprising: Basic building blocks, used to build a hyper-converged platform based on Kubernetes and distributed storage technology, and deploy a meteorological forecast system, a hydrological monitoring system, an inspection data management system, a plan management system, and an external communication system on the hyper-converged platform; A prediction generation module, used for acquiring meteorological data from a meteorological forecast system and generating a flash flood prediction event based on the meteorological data; A forecast generation module, used to obtain a water situation forecast from a hydrological monitoring system, and generate a disaster forecast if the water situation forecast matches the flash flood prediction event; An early warning generation module is used to obtain inspection data from an inspection data management system, verify the disaster forecast based on the inspection data, generate a disaster early warning, and retrieve a matching plan for the disaster early warning from a plan management system; The warning release module is used to generate warning information based on disaster warnings and matching plans, and broadcast the warning information to terminals in the corresponding area through an external communication system.

[0010] In an optional embodiment, the basic building blocks include: A container construction unit is used to construct multiple container groups through kubernetes, and deploy a meteorological forecast system, a hydrological monitoring system, an inspection data management system, a plan management system, and an external communication system in multiple container groups in a one-to-one correspondence manner. The number of containers in the container group is not less than 2; An identification management unit, used to assign a group identification to a container group and bind the group identification to a name of a system deployed in the container group; The container scheduling unit is used to monitor the available resources of each container group by using the resource monitoring component of Kubernetes. If the available resources are lower than a preset threshold, a container is added to the corresponding container group. A storage allocation unit, which is used to construct a storage layer using a distributed file system and allocate storage resources to each container group; The communication configuration unit is used to configure the nacos or REST API communication protocol for the container group.

[0011] In an optional embodiment, the prediction generation module includes: A meteorological acquisition unit, used for acquiring meteorological data from a meteorological forecast system, wherein the meteorological data includes the rainfall in each minimum area; A watershed division unit, used for grouping the minimum areas according to the watersheds to which the minimum areas belong, to obtain a plurality of watershed groups; A data collection unit, used to collect historical data of each minimum area in the watershed group, wherein the historical data includes the rainfall in the flash floods and the flash flood outbreak area and the upstream area; An association mining unit, used for mining the association relationship between the rainfall in the watershed group and the flash flood outbreak based on the historical data by using an association rule algorithm; The flash flood prediction unit is used to calculate the correlation between the meteorological data corresponding to the watershed group and the flash flood outbreak based on the correlation relationship, and generate a flash flood prediction event for the corresponding area in the watershed group when the correlation reaches a set threshold.

[0012] In an optional implementation, the forecast generation module includes: A target determination unit, used for taking the watershed corresponding to the flash flood prediction event as the target watershed; A data retrieval unit, used for obtaining a water situation forecast of a target river basin from the hydrological monitoring system, wherein the water situation forecast includes river water level and flood peak flow prediction data, and the hydrological monitoring system adopts an ArcGIS model; A disaster upgrade unit, used to determine whether the river water level and the flood peak flow forecast data have reached a preset corresponding threshold value, and if so, upgrade the flash flood forecast event to a disaster forecast; A task issuing unit is used to issue inspection tasks to the inspection data management system based on the disaster forecast.

[0013] In a third aspect, a terminal is provided, including: processor, memory, wherein: The memory is used to store computer programs. The processor is used to call and run the computer program from the memory, so that the terminal executes the above-mentioned terminal method.

[0014] According to a fourth aspect, a computer storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the computer executes the methods described in the above aspects.

[0015] The beneficial effect of the present invention lies in that the flash flood prediction method, system, terminal and storage medium based on hyper-convergence provided by the present invention, by building a hyper-convergence platform, integrates meteorological data and hydrological data, realizes accurate prediction of flash floods, improves the accuracy of flash flood prediction, and also realizes scientific management and control of disaster handling process by connecting to some disaster relief related systems.

[0016] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.

[0019] Figure 2 It is a schematic principle diagram of a method according to an embodiment of the present invention.

[0020] Figure 3 is a schematic block diagram of a system according to an embodiment of the present invention.

[0021] Figure 4 A schematic diagram of the structure of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0024] The flash flood prediction method based on hyper-convergence provided in the embodiment of the present invention is executed by a computer device, and accordingly, the flash flood prediction system based on hyper-convergence runs in the computer device.

[0025] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution subject may be a flash flood prediction system based on hyper-convergence. According to different requirements, the order of the steps in the flowchart may be changed, and some may be omitted.

[0026] like Figure 1As shown, the method includes: Step 110, building a hyper-convergence platform based on Kubernetes and distributed storage technology, and deploying a weather forecast system, a hydrological monitoring system, an inspection data management system, a plan management system, and an external communication system on the hyper-convergence platform; Step 120, obtaining meteorological data from a meteorological forecast system, and generating a flash flood prediction event based on the meteorological data; Step 130, obtaining a water situation forecast from a hydrological monitoring system, and generating a disaster forecast if the water situation forecast matches the flash flood prediction event; Step 140, obtaining inspection data from the inspection data management system, verifying the disaster forecast based on the inspection data, generating a disaster warning, and retrieving a matching plan for the disaster warning from the plan management system; Step 150: Generate warning information based on the disaster warning and the matching plan, and broadcast the warning information to the terminals in the corresponding area through the external communication system.

[0027] To facilitate understanding of the present invention, the flash flood prediction method based on hyper-convergence provided by the present invention is further described below based on the principle of the flash flood prediction method based on hyper-convergence of the present invention and the process of predicting and processing flash floods in the embodiments.

[0028] For details, please refer to Figure 2 , the flash flood prediction method based on hyper-convergence includes: S1. Build a hyper-convergence platform based on Kubernetes and distributed storage technology, and deploy a meteorological forecast system, a hydrological monitoring system, an inspection data management system, a plan management system, and an external communication system on the hyper-convergence platform.

[0029] Multiple container groups are constructed through kubernetes, and a meteorological forecast system, a hydrological monitoring system, an inspection data management system, a plan management system and an external communication system are deployed in the multiple container groups in a one-to-one manner. The number of containers in the container group is not less than 2; a group identifier is assigned to the container group, and the group identifier is bound to the name of the system deployed in the container group; the resource monitoring component of kubernetes is used to monitor the available resources of each container group. If the available resources are lower than the preset threshold, containers are added to the corresponding container group; a storage layer is constructed using a distributed file system, and storage resources are allocated to each container group; and nacos or REST API communication protocols are configured for the container group.

[0030] Specifically, they include: (1) Build a container image First, build Docker container images for the weather forecast system, hydrological monitoring system, inspection data management system, emergency plan management system, and external communication system. These images should contain all the dependencies and configuration files required to run each system.

[0031] (2) Create Kubernetes deployment files Use Kubernetes' Deployment resource object to define the deployment configuration of a container group. Each system should have at least two replicas (Pods) to ensure high availability and fault tolerance.

[0032] In the Deployment file, specify the container image, resource requests and limits, port mapping, etc. for each system.

[0033] Assign a unique label to each Deployment, which will be used as the group identifier and bound to the name of the system deployed in the container group.

[0034] (3) Deploy container group Use the kubectl command or the Kubernetes API to apply the Deployment file to the cluster. This will trigger the Kubernetes scheduler to create Pods on the nodes in the cluster.

[0035] (4) Monitoring container group resources Use Kubernetes' resource monitoring components (such as Prometheus, Metrics Server, etc.) to monitor the available resources (such as CPU, memory) of each container group.

[0036] Configure alert rules to trigger alerts when the amount of available resources falls below a preset threshold.

[0037] (5) Horizontal automatic expansion Use Kubernetes’ Horizontal Pod Autoscaler (HPA) to automatically scale the number of Pods up or down based on resource usage.

[0038] Configure HPA for each Deployment, specifying the minimum and maximum number of Pods, resource monitoring metrics, and scaling policies.

[0039] (6) Building the storage layer Build your storage layer using a distributed file system such as NFS, Ceph, GlusterFS, or Kubernetes-native PersistentVolume and PersistentVolumeClaims.

[0040] Allocating storage resources to each container group can be achieved by creating PersistentVolumeClaims and mounting them to the corresponding directories of the Pod.

[0041] (7) Configure the communication protocol Configure service discovery and communication protocols for container groups. Since nacos or REST API is mentioned, you can choose to use nacos as the service registration and discovery center, or use Kubernetes' built-in service (Service) and Ingress resources to implement external access to the REST API.

[0042] For nacos, you can deploy the nacos server in the Kubernetes cluster and register the services of each system in nacos.

[0043] For REST API, you can create a Kubernetes Service resource to expose the Pod's port, and use the Ingress resource to implement routing and load balancing for external access.

[0044] (8) Network configuration Make sure the network in your Kubernetes cluster is configured correctly so that container groups can communicate with each other and with the outside world.

[0045] You can use Kubernetes network plug-ins (such as Calico, Flannel, etc.) to configure the network.

[0046] (9) Logging and monitoring Configure log collection and monitoring solutions (such as Elasticsearch, Kibana, Fluentd, etc.) to collect and analyze logs and performance metrics for container groups.

[0047] (10) Backup and recovery Implement backup and recovery strategies to ensure rapid restoration of service in the event of failure or data loss.

[0048] (11) Continuous Integration and Continuous Deployment (CI / CD) Use CI / CD tools (such as Jenkins, GitLab CI, etc.) to automate the build, test, and deployment process to be able to respond quickly to code changes and changing requirements.

[0049] S2. Acquire meteorological data from a meteorological forecast system, and generate a flash flood prediction event based on the meteorological data.

[0050] Acquire meteorological data from a meteorological forecast system, the meteorological data including the rainfall in each minimum area; group the minimum areas according to the watersheds to which they belong to obtain a plurality of watershed groups; collect historical data of each minimum area in the watershed group, the historical data including the rainfall in previous flash floods and flash flood outbreak areas and upstream areas; utilize an association rule algorithm to mine the correlation between the rainfall in the watershed group and the flash flood outbreak based on the historical data; calculate the correlation between the meteorological data corresponding to the watershed group and the flash flood outbreak based on the correlation, and generate a flash flood prediction event for the corresponding area in the watershed group when the correlation reaches a set threshold.

[0051] Specifically, the following steps are included: (1) Acquisition of meteorological data First, obtain real-time meteorological data from the weather forecast system. These data should contain rainfall information for each minimum area, and are usually updated at time intervals (such as every hour, every day, etc.).

[0052] (2) River basin grouping The smallest areas are grouped into multiple watershed groups based on their geographical locations and watershed information. A watershed refers to the geographical area where water flows from the source to the downstream, usually with clear boundaries and watershed characteristics.

[0053] (3) Collection of historical data Next, collect historical data for each smallest area in the basin group. This data should include information on previous flash floods and rainfall in the flash flood outbreak area and upstream areas. Historical data is an important basis for analyzing the correlation between rainfall and flash flood outbreaks.

[0054] (4) Data preprocessing The collected historical data is preprocessed, including data cleaning, missing value filling, outlier processing, etc. The purpose of this step is to ensure the quality and accuracy of the data and provide a reliable data foundation for subsequent association rule mining and association degree calculation.

[0055] (5) Association rule mining Association rule algorithms (such as Apriori, FP-Growth, etc.) are used to mine historical data to find the correlation between rainfall and flash floods within the basin group. Association rule algorithms can identify the possibility and pattern of flash floods under different rainfall conditions.

[0056] (6) Correlation calculation Based on the mined association rules, the correlation between the meteorological data corresponding to the watershed group and the flash flood outbreak is calculated. The correlation is a quantitative indicator used to measure the degree of correlation between rainfall and flash flood outbreak. The correlation can be calculated based on the statistical results of historical data and the output results of the association rule algorithm.

[0057] (7) Threshold setting In order to determine when to generate a flash flood prediction event, a correlation threshold needs to be set. This threshold can be determined based on the analysis results of historical data, expert experience or actual needs. When the correlation between the meteorological data corresponding to the basin group and the flash flood outbreak reaches or exceeds the set threshold, the system will generate a corresponding flash flood prediction event.

[0058] (8) Flash flood forecast event generation When the correlation reaches the set threshold, the system will generate flash flood forecast events for the corresponding areas within the basin group based on the forecast results. These forecast events will include information such as the predicted flash flood outbreak time, location, and possible impact range, so that relevant departments and personnel can take timely measures to prevent and respond.

[0059] (9) Result evaluation and optimization The generated flash flood forecast events are evaluated, including the accuracy, timeliness and practicality of the forecast. Based on the evaluation results, the forecast algorithms and models are optimized and improved to improve the accuracy and reliability of the forecast.

[0060] S3. Obtain a water situation forecast from a hydrological monitoring system. If the water situation forecast matches the flash flood prediction event, generate a disaster forecast.

[0061] The river basin corresponding to the flash flood prediction event is taken as the target river basin; the water situation forecast of the target river basin is obtained from the hydrological monitoring system, the water situation forecast includes river water level and flood peak flow prediction data, and the hydrological monitoring system adopts the ArcGIS model; it is determined whether the river water level and the flood peak flow prediction data reach the corresponding preset thresholds, and if the corresponding thresholds are reached, the flash flood prediction event is upgraded to a disaster forecast; and inspection tasks are issued to the inspection data management system based on the disaster forecast.

[0062] Specifically, they include: (1) Obtaining water situation forecasts from the hydrological monitoring system Use ArcGIS models or other advanced hydrological simulation tools to obtain water forecasts for the target basin from the hydrological monitoring system. These forecast data should include but are not limited to key indicators such as river water levels and peak flow. ArcGIS models can simulate and predict hydrological processes based on the basin's geographic information and historical data.

[0063] (2) Analysis of water forecast data The acquired river water level and peak flow forecast data are analyzed in detail, including comparison with the corresponding pre-set thresholds to determine whether the current water situation forecast has reached the critical value that may cause disasters.

[0064] (3) Disaster forecast upgrade If any one or more of the river water level or peak flow forecast data reaches the pre-set threshold, it means that the target basin faces a high risk of flash flood disasters. At this time, the original flash flood forecast event should be upgraded to a disaster forecast, and its urgency and possible impact range should be indicated. In addition, by setting multi-level thresholds, the obtained hydrological data can be compared with the multi-level thresholds to determine the disaster level.

[0065] (4) Release inspection tasks to the inspection data management system Send disaster forecasts to the inspection data management system, including disaster levels and disaster locations. The inspection data management system generates inspection tasks based on the disaster forecasts. The inspection data management system sends the inspection tasks to the mobile terminals of the inspection personnel and receives the inspection data fed back by the mobile terminals.

[0066] S4. Obtain inspection data from the inspection data management system, verify the disaster forecast based on the inspection data, generate a disaster warning, and retrieve a matching plan for the disaster warning from the plan management system.

[0067] (1) Acquisition of inspection data. The business layer first obtains the latest inspection data from the inspection data management system. This data may include field inspection results, photos, videos, sensor readings, etc., which provide important field information for the approval of disaster warnings.

[0068] (2) Analysis of inspection data. The business layer will conduct a detailed analysis of the inspection data obtained. This includes data authenticity verification, integrity check, and comparison with other relevant data. Through analysis, the business layer can assess the actual situation of the disaster and understand the scope of the disaster and potential risks.

[0069] (3) Approval of disaster forecasts. Based on the analysis results of the inspection data, the business layer will review the previously generated disaster forecasts. If the inspection data verifies the accuracy of the disaster forecast, the business layer will retain the forecast; if the inspection data provides new information or finds that the forecast is biased, the business layer will adjust the disaster forecast to ensure its accuracy and reliability.

[0070] (4) Generation of disaster warnings. Approved disaster forecasts will be converted into disaster warnings. Disaster warnings are formal notifications to the public and relevant departments, which contain information such as the type of disaster, expected time of occurrence, scope of impact, potential risks, and response measures. The business layer needs to ensure that disaster warnings are clear, accurate, and timely so that relevant departments and the public can be prepared for response.

[0071] (5) Retrieval of matching plans. The business layer will retrieve the plans that match the disaster warning from the plan management system. The plan is a pre-made plan and program for dealing with disasters. It includes the emergency response process, resource allocation, personnel division of labor, etc. The business layer needs to select the most appropriate plan for retrieval based on the specific situation of the disaster warning.

[0072] (6) Evaluation and adjustment of the plan. After the plan is retrieved, the business layer needs to evaluate and adjust the plan. The purpose of the evaluation is to ensure the feasibility and effectiveness of the plan and whether it is in line with the current disaster situation. If the plan needs to be adjusted, the business layer will make necessary modifications and improvements based on the actual situation.

[0073] S5. Generate warning information based on the disaster warning and matching plan, and broadcast the warning information to terminals in corresponding areas through an external communication system.

[0074] Pre-set text prompt templates corresponding to flash flood prediction, flash flood forecast and flash flood warning. When generating a flash flood prediction, flash flood forecast or flash flood warning, extract the corresponding text prompt template to generate a prompt SMS, and send the prompt SMS to all mobile terminals in the area through the base station at the corresponding location.

[0075] In addition, combined with converged communication technology, through telephone, SMS, instant messaging, video surveillance, information sharing, etc., to achieve unified information, collaboration, interactive system, real-time and near real-time communication related personnel, including: flash flood leaders, villages, bay groups, local people, etc., to inform the warning information and assist the relevant leaders to make remote advance control arrangements, transfer routes, etc. Converged communication provides rapid command and dispatch support from a real-time perspective.

[0076] Among them, the optimization method for real-time video is as follows: 1. Video compression technology: Using H.264 High Profile technology, high-definition encoding and decoding can be achieved with low bandwidth. Only 512K bandwidth is required to achieve 720P full-motion video compression, and only 1M is required for 1080P. At the same time, it has high anti-code capabilities and can withstand 33% packet loss.

[0077] 2. Audio processing technology: 1) Using AEC (acoustic echo cancellation technology) and linear echo cancellation algorithm, through precise acquisition and calculation analysis, it can achieve 500ms echo tail suppression capability, and the voice convergence time is less than 30ms, completely eliminating residual noise; 2) Using AGC (automatic gain control technology) to ensure that the volume of the voice will not change due to the distance of the sound source within 5 meters; 3) Utilize ANS (automatic noise reduction technology) to effectively eliminate 18db static noise and 20db dynamic noise throughout the process, ensuring normal voice quality and volume. 3. Large-scale networking technology: The tree-like distributed networking structure enables unlimited downward expansion of access points, and can easily build a video communication system with more than 1,000 points.

[0078] In some embodiments, the flash flood prediction system based on hyper-convergence may include multiple functional modules composed of computer program segments. The computer program of each program segment in the flash flood prediction system based on hyper-convergence may be stored in the memory of a computer device and executed by at least one processor to perform (see Figure 1 Description) Flash flood prediction function based on hyper-convergence.

[0079] In this embodiment, the flash flood prediction system based on hyper-convergence can be divided into multiple functional modules according to the functions it performs, such as Figure 3 As shown. The functional modules of the system 300 may include: a basic construction module 310, a prediction generation module 320, a forecast generation module 330, an early warning generation module 340 and an early warning release module 350. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0080] Basic building blocks, used to build a hyper-converged platform based on Kubernetes and distributed storage technology, and deploy a meteorological forecast system, a hydrological monitoring system, an inspection data management system, a plan management system, and an external communication system on the hyper-converged platform; A prediction generation module, used for acquiring meteorological data from a meteorological forecast system and generating a flash flood prediction event based on the meteorological data; A forecast generation module, used to obtain a water situation forecast from a hydrological monitoring system, and generate a disaster forecast if the water situation forecast matches the flash flood prediction event; An early warning generation module is used to obtain inspection data from an inspection data management system, verify the disaster forecast based on the inspection data, generate a disaster early warning, and retrieve a matching plan for the disaster early warning from a plan management system; The warning release module is used to generate warning information based on disaster warnings and matching plans, and broadcast the warning information to terminals in the corresponding area through an external communication system.

[0081] Optionally, as an embodiment of the present invention, the basic building block includes: A container construction unit is used to construct multiple container groups through kubernetes, and deploy a meteorological forecast system, a hydrological monitoring system, an inspection data management system, a plan management system, and an external communication system in multiple container groups in a one-to-one correspondence manner. The number of containers in the container group is not less than 2; An identification management unit, used to assign a group identification to a container group and bind the group identification to a name of a system deployed in the container group; The container scheduling unit is used to monitor the available resources of each container group by using the resource monitoring component of Kubernetes. If the available resources are lower than a preset threshold, a container is added to the corresponding container group. A storage allocation unit, which is used to construct a storage layer using a distributed file system and allocate storage resources to each container group; The communication configuration unit is used to configure the nacos or REST API communication protocol for the container group.

[0082] Optionally, as an embodiment of the present invention, the prediction generation module includes: A meteorological acquisition unit, used for acquiring meteorological data from a meteorological forecast system, wherein the meteorological data includes the rainfall in each minimum area; A watershed division unit is used to group the minimum areas according to the watersheds to which the minimum areas belong, so as to obtain a plurality of watershed groups; A data collection unit, used to collect historical data of each minimum area in the watershed group, wherein the historical data includes the rainfall in the flash floods and the flash flood outbreak area and the upstream area; An association mining unit, used for mining the association relationship between the rainfall in the watershed group and the flash flood outbreak based on the historical data by using an association rule algorithm; The flash flood prediction unit is used to calculate the correlation between the meteorological data corresponding to the watershed group and the flash flood outbreak based on the correlation relationship, and generate a flash flood prediction event for the corresponding area in the watershed group when the correlation reaches a set threshold.

[0083] Optionally, as an embodiment of the present invention, the forecast generation module includes: A target determination unit, used for taking the watershed corresponding to the flash flood prediction event as the target watershed; A data retrieval unit, used for obtaining a water situation forecast of a target river basin from the hydrological monitoring system, wherein the water situation forecast includes river water level and flood peak flow prediction data, and the hydrological monitoring system adopts an ArcGIS model; A disaster upgrade unit, used to determine whether the river water level and the flood peak flow forecast data have reached a preset corresponding threshold value, and if so, upgrade the flash flood forecast event to a disaster forecast; A task issuing unit is used to issue inspection tasks to the inspection data management system based on the disaster forecast.

[0084] Figure 4 A schematic diagram of the structure of a terminal 400 provided in an embodiment of the present invention. The terminal 400 can be used to execute the flash flood prediction method based on hyper-convergence provided in an embodiment of the present invention.

[0085] The terminal 400 may include: a processor 410, a memory 420 and a communication unit 430. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention, and it may be a bus structure or a star structure, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0086] The memory 420 can be used to store the execution instructions of the processor 410, and the memory 420 can be implemented by any type of volatile or non-volatile storage terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. When the execution instructions in the memory 420 are executed by the processor 410, the terminal 400 can perform some or all of the steps in the following method embodiments.

[0087] The processor 410 is the control center of the storage terminal, and uses various interfaces and lines to connect various parts of the entire electronic terminal. It runs or executes software programs and / or modules stored in the memory 420, and calls data stored in the memory to perform various functions of the electronic terminal and / or process data. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of multiple packaged ICs with the same or different functions. For example, the processor 410 can include only a central processing unit (CPU). In the embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.

[0088] The communication unit 430 is used to establish a communication channel so that the storage terminal can communicate with other terminals, receive user data sent by other terminals or send user data to other terminals.

[0089] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and when the program is executed, the program may include some or all of the steps in each embodiment provided by the present invention. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0090] Therefore, the present invention integrates meteorological data and hydrological data by building a hyper-convergence platform to achieve accurate prediction of flash floods and improve the accuracy of flash flood prediction. In addition, it also realizes scientific management and control of disaster handling processes by connecting to some disaster relief related systems. The technical effects that can be achieved by this embodiment can be found in the description above and will not be repeated here.

[0091] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present invention, in essence or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes, including several instructions for enabling a computer terminal (which can be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention.

[0092] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the terminal embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

[0093] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, which can be electrical, mechanical or other forms.

[0094] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0095] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0096] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.

Claims

1. A flash flood prediction method based on hyper-convergence, characterized in that: include: Build a hyper-convergence platform based on Kubernetes and distributed storage technology, and deploy a weather forecast system, a hydrological monitoring system, an inspection data management system, a plan management system, and an external communication system on the hyper-convergence platform; Acquire meteorological data from a meteorological forecast system, and generate a flash flood forecast event based on the meteorological data; Obtaining a water situation forecast from a hydrological monitoring system, and generating a disaster forecast if the water situation forecast matches the flash flood forecast event; Acquire inspection data from an inspection data management system, verify the disaster forecast based on the inspection data, generate a disaster warning, and retrieve a matching plan for the disaster warning from a plan management system; Warning information is generated based on disaster warnings and matching plans, and the warning information is broadcast to terminals in corresponding areas through an external communication system.

2. The method according to claim 1, characterized in that A hyper-convergence platform is built based on Kubernetes and distributed storage technology, and a weather forecast system, a hydrological monitoring system, an inspection data management system, a plan management system, and an external communication system are deployed on the hyper-convergence platform, including: Build multiple container groups through kubernetes, and deploy the meteorological forecast system, hydrological monitoring system, inspection data management system, emergency plan management system and external communication system in multiple container groups in a one-to-one correspondence manner. The number of containers in the container group is not less than 2; Assign a group ID to the container group, and bind the group ID to the name of the system deployed in the container group; Use the Kubernetes resource monitoring component to monitor the available resources of each container group. If the available resources are lower than the preset threshold, add containers to the corresponding container group. Use a distributed file system to build a storage layer and allocate storage resources to each container group; Configure the nacos or REST API communication protocol for the container group.

3. The method according to claim 1, characterized in that Acquiring meteorological data from a meteorological forecast system and generating a flash flood forecast event based on the meteorological data, including: Acquire meteorological data from a meteorological forecast system, wherein the meteorological data includes rainfall in each minimum area; The minimum areas are grouped according to the watersheds to which they belong, and a plurality of watershed groups are obtained; Collecting historical data of each smallest area in the watershed group, the historical data including previous flash floods and rainfall in the flash flood outbreak area and upstream area; Using association rule algorithm to mine the association relationship between rainfall and flash floods in the basin group based on the historical data; The correlation between the meteorological data corresponding to the watershed group and the flash flood outbreak is calculated based on the correlation relationship, and when the correlation reaches a set threshold, a flash flood prediction event is generated for the corresponding area within the watershed group.

4. The method according to claim 1, characterized in that: Obtaining a water situation forecast from a hydrological monitoring system, and if the water situation forecast matches the flash flood forecast event, generating a disaster forecast, including: The watershed corresponding to the flash flood forecast event is taken as the target watershed; Obtaining a water situation forecast for a target river basin from the hydrological monitoring system, wherein the water situation forecast includes river water level and flood peak flow prediction data, and the hydrological monitoring system adopts an ArcGIS model; Determine whether the river water level and the flood peak flow forecast data reach a preset corresponding threshold value, and if so, upgrade the flash flood forecast event to a disaster forecast; Based on the disaster forecast, an inspection task is issued to the inspection data management system.

5. A flash flood prediction system based on hyper-convergence, characterized in that: include: Basic building blocks, used to build a hyper-converged platform based on Kubernetes and distributed storage technology, and deploy a meteorological forecast system, a hydrological monitoring system, an inspection data management system, a plan management system, and an external communication system on the hyper-converged platform; A prediction generation module, used for acquiring meteorological data from a meteorological forecast system and generating a flash flood prediction event based on the meteorological data; A forecast generation module, used to obtain a water situation forecast from a hydrological monitoring system, and generate a disaster forecast if the water situation forecast matches the flash flood prediction event; An early warning generation module is used to obtain inspection data from an inspection data management system, verify the disaster forecast based on the inspection data, generate a disaster early warning, and retrieve a matching plan for the disaster early warning from a plan management system; The warning release module is used to generate warning information based on disaster warnings and matching plans, and broadcast the warning information to terminals in the corresponding area through an external communication system.

6. The system according to claim 5, characterized in that The basic building blocks include: A container construction unit is used to construct multiple container groups through kubernetes, and deploy a meteorological forecast system, a hydrological monitoring system, an inspection data management system, a plan management system, and an external communication system in multiple container groups in a one-to-one correspondence manner. The number of containers in the container group is not less than 2; An identification management unit, used to assign a group identification to a container group and bind the group identification to a name of a system deployed in the container group; The container scheduling unit is used to monitor the available resources of each container group by using the resource monitoring component of Kubernetes. If the available resources are lower than a preset threshold, a container is added to the corresponding container group. A storage allocation unit, which is used to construct a storage layer using a distributed file system and allocate storage resources to each container group; The communication configuration unit is used to configure the nacos or REST API communication protocol for the container group.

7. The system according to claim 5, characterized in that The prediction generation module comprises: A meteorological acquisition unit, used for acquiring meteorological data from a meteorological forecast system, wherein the meteorological data includes the rainfall in each minimum area; A watershed division unit is used to group the minimum areas according to the watersheds to which the minimum areas belong, so as to obtain a plurality of watershed groups; A data collection unit, used to collect historical data of each minimum area in the watershed group, wherein the historical data includes the rainfall in the flash floods and the flash flood outbreak area and the upstream area; An association mining unit, used for mining the association relationship between the rainfall in the watershed group and the flash flood outbreak based on the historical data by using an association rule algorithm; The flash flood prediction unit is used to calculate the correlation between the meteorological data corresponding to the watershed group and the flash flood outbreak based on the correlation relationship, and generate a flash flood prediction event for the corresponding area in the watershed group when the correlation reaches a set threshold.

8. The system according to claim 5, characterized in that The forecast generation module comprises: A target determination unit, used for taking the watershed corresponding to the flash flood prediction event as the target watershed; A data retrieval unit, used for obtaining a water situation forecast of a target river basin from the hydrological monitoring system, wherein the water situation forecast includes river water level and flood peak flow prediction data, and the hydrological monitoring system adopts an ArcGIS model; A disaster upgrade unit, used to determine whether the river water level and the flood peak flow forecast data have reached a preset corresponding threshold value, and if so, upgrade the flash flood forecast event to a disaster forecast; A task issuing unit is used to issue inspection tasks to the inspection data management system based on the disaster forecast.

9. A terminal, characterized in that: include: A memory, used for storing a flash flood prediction program based on hyper-convergence; A processor is used to implement the steps of the flash flood prediction method based on hyper-convergence as described in any one of claims 1-4 when executing the flash flood prediction program based on hyper-convergence.

10. A computer-readable storage medium storing a computer program, characterized in that: The readable storage medium stores a flash flood prediction program based on hyper-convergence, and when the flash flood prediction program based on hyper-convergence is executed by a processor, the steps of the flash flood prediction method based on hyper-convergence as described in any one of claims 1-4 are implemented.

Images