Flood disaster prediction method and device, equipment and storage medium

By building a dialogue group of multiple agents, the full process automation of flood disaster analysis and loss calculation is achieved, the problems of complexity and manual intervention in traditional flood scenario analysis are solved, and the efficiency and accuracy of flood prevention work are improved.

CN118886331AActive Publication Date: 2024-11-01CHINA INST OF WATER RESOURCES & HYDROPOWER RES

Patent Information

Application Number
CN202411306181.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-19
Publication Date
2024-11-01
Estimated Expiration
2044-09-19

AI Technical Summary

Technical Problem

The current flood scenarios are complex and changeable, involving multiple types of composite flood events. The traditional water conservancy model call process requires a lot of manual intervention, which consumes high labor costs, and lacks automatic monitoring of the entire process, which affects the efficiency of flood prevention work and the accuracy of results.

Method used

By building a dialogue group of multiple agents, we can automate the flood disaster analysis process, including obtaining analysis requirements, determining water conservancy and hydrological models, obtaining and processing data, generating water conservancy and hydrological results, and calling the disaster loss model for calculations, so as to achieve flood disaster assessment and loss assessment and loss Automation of the entire process of computing.

Benefits of technology

It improves the efficiency and accuracy of flood disaster prediction, is suitable for a variety of composite flood scenarios, reduces operational complexity and technical thresholds, and ensures the reliability and flexibility of results. It is suitable for urban floods, mountain torrents, tidal floods, etc.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118886331A_ABST
    Figure CN118886331A_ABST
Patent Text Reader

Abstract

The invention provides a flood disaster prediction method and device, equipment and a storage medium, and the method comprises the steps: constructing a dialogue group which comprises a plurality of agents, and the agents are used for executing corresponding model service tasks; acquiring a flood disaster analysis demand, and determining a water conservancy hydrological model and a corresponding first intelligent agent required for analysis according to the flood disaster analysis demand; obtaining water conservancy and hydrological data according to the water conservancy and hydrological model required for analysis and the first intelligent agent; using the first agent to call the water conservancy and hydrology model required for analysis to process the water conservancy and hydrology data, and generating a water conservancy and hydrology result; and calling a disaster loss model for calculation by using the second agent according to the water conservancy and hydrology result to obtain the flood disaster loss.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of flood disaster prediction, and in particular to a flood disaster prediction method, device, equipment and storage medium. Background Art

[0002] Affected by the complexity of multiple types of composite flood scenarios, current flood scenarios are not only complex and changeable, but also often involve multiple types of composite flood events. These scenarios include but are not limited to mountain torrent basin floods, tidal offshore propagation and urban floods. When constructing a hydraulic model calling process tailored to the differences in various regions, a lot of manual intervention is often required, which requires high labor costs. Summary of the invention

[0003] The embodiments of the present application provide a flood disaster prediction method, device, equipment and storage medium to solve the problems existing in the related technologies. The technical solutions are as follows: In a first aspect, an embodiment of the present application provides a method for predicting flood damage, comprising: Constructing a dialogue group, wherein the dialogue group includes a plurality of intelligent agents, and the intelligent agents are used to perform corresponding model service tasks; Obtaining flood disaster analysis requirements, and determining a water conservancy and hydrological model required for analysis and a corresponding first intelligent agent according to the flood disaster analysis requirements; Acquiring water conservancy and hydrology data according to the water conservancy and hydrology model required for the analysis and the first intelligent agent; Using the first intelligent agent to call the water conservancy and hydrology model required for the analysis to process the water conservancy and hydrology data to generate a water conservancy and hydrology result; The second intelligent agent is used to call the disaster loss model according to the water conservancy and hydrological results to calculate the flood disaster losses.

[0004] In one implementation, the using the first agent to call the water conservancy and hydrology model required for the analysis to process the water conservancy and hydrology data to generate water conservancy and hydrology results includes: Using the first intelligent agent to call the water conservancy and hydrology model required for the analysis to process the water conservancy and hydrology data to generate preliminary water conservancy and hydrology results; Using a third agent to perform precision analysis on the preliminary water conservancy and hydrology results according to the precision index, and obtaining water conservancy and hydrology results when the preliminary water conservancy and hydrology results meet the precision requirements; In the case where the preliminary water conservancy and hydrology results do not meet the accuracy requirements, the third agent is used to adjust the water conservancy and hydrology data and the first agent is used again to call the water conservancy and hydrology model required for the analysis to process the adjusted water conservancy and hydrology data to obtain the adjusted preliminary water conservancy and hydrology results; When the adjusted preliminary water conservancy and hydrology results meet the accuracy requirements, obtaining water conservancy and hydrology results; When the adjusted preliminary water conservancy and hydrology results do not meet the accuracy requirements, the third intelligent agent is reused to adjust the water conservancy and hydrology data until the adjusted preliminary water conservancy and hydrology results obtained after processing by the first proxy user meet the accuracy requirements or the water conservancy and hydrology data are adjusted a maximum number of times.

[0005] In one implementation, the constructing a dialogue group includes: Calling a toolkit or a data interface to create a first dialogue group; configuring basic parameters of the initial dialogue group to obtain a second dialogue group; Adding each agent to the conversation list of the second conversation group by corresponding identification to generate a third conversation group; All agents in the third dialogue group are verified, and a dialogue group is obtained when all agents in the third dialogue group pass the verification.

[0006] In one embodiment, when all agents in the third dialogue group pass the verification, obtaining the dialogue group further includes: When all agents in the third dialogue group pass the verification, a dialogue group information management is created in the third dialogue group to obtain a dialogue group, and the dialogue information management is used to manage the dialogues between the agents and call each agent to perform corresponding tasks.

[0007] In one embodiment, the determining of the water conservancy and hydrological model required for analysis and the corresponding first agent according to the flood damage analysis requirements includes: According to the needs of flood damage analysis, the dialogue information management creates an initial task to be added to the dialogue group; When receiving the initial task, the dialogue group analyzes the initial task and determines the water conservancy and hydrology model required for the analysis and the corresponding first intelligent agent.

[0008] In one embodiment, obtaining water conservancy and hydrology data according to the water conservancy and hydrology model required for the analysis and the first agent includes: Utilizing the first agent to analyze the water conservancy and hydrology model required for the analysis of the initial task, and determining the data required for the water conservancy and hydrology model; The interface of the first intelligent agent is called to obtain the data required by the water conservancy and hydrology model to obtain the water conservancy and hydrology data.

[0009] In one embodiment, it further includes: A visual diagram is generated based on the flood damage and an execution report is generated based on the content of the dialogue group.

[0010] In a second aspect, an embodiment of the present application provides a flood disaster prediction device, comprising: A construction module, used to construct a dialogue group, wherein the dialogue group includes a plurality of intelligent agents, and the intelligent agents are used to perform corresponding model service tasks; A first acquisition module is used to obtain flood damage analysis requirements, and determine the water conservancy and hydrological model required for analysis and the corresponding first intelligent agent according to the flood damage analysis requirements; A second acquisition module, used for acquiring water conservancy and hydrology data according to the water conservancy and hydrology model required for the analysis and the first intelligent agent; A generation module, used to use the first agent to call the water conservancy and hydrology model required for the analysis to process the water conservancy and hydrology data and generate water conservancy and hydrology results; The module is used to use the second intelligent agent to call the disaster loss model according to the water conservancy and hydrology results to calculate and obtain the flood disaster losses.

[0011] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising: a memory and a processor. The memory and the processor communicate with each other through an internal connection path, the memory is used to store instructions, the processor is used to execute the instructions stored in the memory, and when the processor executes the instructions stored in the memory, the processor executes the method in any one of the above-mentioned embodiments.

[0012] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a computer, the method in any one of the above-mentioned embodiments is executed.

[0013] The advantages or beneficial effects of the above technical solution include at least: The technical solution of the disclosed embodiment, the flood disaster prediction method includes: constructing a dialogue group, the dialogue group includes multiple agents, the agents are used to perform corresponding model service tasks; obtaining flood disaster analysis requirements, and determining the water conservancy and hydrological model required for analysis and the corresponding first agent according to the flood disaster analysis requirements; obtaining water conservancy and hydrological data according to the water conservancy and hydrological model required for analysis and the first agent; using the first agent to call the water conservancy and hydrological model required for analysis to process the water conservancy and hydrological data and generate water conservancy and hydrological results; using the second agent to call the disaster loss model according to the water conservancy and hydrological results to calculate and obtain the flood disaster loss. Through the flood disaster prediction method of this embodiment, by establishing a dialogue group including multiple types of agents, the full process automation of flood disaster assessment and loss calculation is realized. Each proxy user is used to perform complex water conservancy model calling and calculation tasks, refine the analysis requirements, and generate accurate evaluation results. Ensure the efficient collaboration of each link and the reliability of the results, suitable for various complex flood scenes such as urban floods, mountain torrents, tidal floods, etc., to improve the efficiency and accuracy of flood prevention work.

[0014] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present application will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar parts or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in the present application and should not be regarded as limiting the scope of the present application.

[0016] Figure 1 A flowchart of a flood disaster prediction method according to an embodiment of the present application; Figure 2 A structural block diagram of a flood disaster prediction device according to an embodiment of the present invention is shown; Figure 3 A structural block diagram of an electronic device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0017] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present application. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0018] The technology of this embodiment is applicable to complex flood scenarios under multiple influencing factors, including but not limited to: Urban flooding and rainstorm waterlogging: When the drainage system is overloaded due to rainstorm in the city, the technology of this embodiment can evaluate the degree of flooding and economic losses to urban roads, residential areas, commercial areas, etc.

[0019] River overflow: When the water level of a river near a city rises due to prolonged rainfall or flood discharge from an upstream reservoir, the technology of this embodiment can assess the impact of the flood on the city's infrastructure and residents' lives.

[0020] Flash floods and heavy rains in mountainous areas: When sudden heavy rains in mountainous areas trigger flash floods, the technology of this embodiment can quickly assess the degree of damage and economic losses caused by flash floods to mountain villages, roads, bridges, etc.

[0021] Debris flow accompanied by flood: Mountain torrents carry a large amount of mud, sand and rocks. The technology of this embodiment can assess the degree of disaster and related losses to downstream areas.

[0022] River flooding and large-scale rainfall: When long-term, large-scale rainfall causes the river water level to continue to rise, the technology of this embodiment can assess the impact of river bank breaches or rising water levels on downstream farmland, residential areas, and industrial and commercial areas; Dam breach flood: When a river dam breaks, the technology of this embodiment can quickly assess the flood spread and the economic losses caused.

[0023] Tidal flooding and storm surge: When a storm surge occurs in a coastal area, the technology of this embodiment can assess the impact of the tide on coastal cities, ports, fishing villages, etc.

[0024] Affected by the complexity of multi-type composite flood scenarios, current flood scenarios are not only complex and changeable, but also often involve multiple types of composite flood events. These scenarios include but are not limited to mountain torrent basin floods, tidal offshore propagation and urban floods. Each flood type has its own unique physical and hydrological characteristics, so it is necessary to call on a variety of different models for accurate simulation and evaluation.

[0025] At the same time, when constructing the water conservancy model calling process for different regions, a lot of manual intervention and adjustment is often required. This is not only time-consuming and labor-intensive, but also requires operators to have high professional knowledge and technical thresholds. This situation seriously affects the efficiency and response capabilities of flood control workers. Specific problems include: Complex process construction: The terrain, climate, and hydrological conditions of each region are different. Traditional model calling processes are difficult to quickly adapt to these differences and often need to be readjusted and configured; High operational difficulty: Flood control workers need to master the use of multiple models and parameter settings, which requires a high level of technical skills and increases the complexity of actual operations; Lack of flexibility: The lack of flexible automation tools makes it difficult to quickly adjust and optimize the model calling process according to actual conditions.

[0026] In addition, during the flood simulation process, the hydraulic model that calculates key parameters such as water depth is affected by many factors, such as the water seepage capacity of the underlying surface and the roughness of the surface. Changes in these factors may cause errors in model calculations and affect the final evaluation results. In addition, there is currently a lack of observation methods for automated monitoring of the entire flood calculation process. Specific problems include: Parameter sensitivity: The model is highly sensitive to certain parameters, for example, changes in the water permeability and roughness of the underlying surface may lead to significant changes in the simulation results; Data docking problem: The data formats and interfaces between different models may be inconsistent, and problems are prone to occur during data transmission and docking, requiring complex data conversion and processing; Lack of full-process monitoring: Current technical means make it difficult to achieve automated monitoring of the entire flood simulation process, and are unable to promptly detect and correct problems in the calculation, affecting the accuracy and reliability of the results.

[0027] Figure 1 FIG. 1 is a flow chart showing a method for predicting flood damage according to an embodiment of the present application. Figure 1 As shown, this embodiment provides a flood disaster prediction method, which may include: S110: constructing a dialogue group, wherein the dialogue group includes a plurality of intelligent agents, and the intelligent agents are used to perform corresponding model service tasks; S120: Obtaining flood disaster analysis requirements, and determining a water conservancy and hydrological model required for analysis and a corresponding first intelligent agent according to the flood disaster analysis requirements; S130: Acquire water conservancy and hydrology data according to the water conservancy and hydrology model required for the analysis and the first intelligent agent; S140: Using the first agent to call the water conservancy and hydrology model required for the analysis to process the water conservancy and hydrology data to generate a water conservancy and hydrology result; S150: Using the second intelligent agent to call the disaster loss model according to the water conservancy and hydrology results to calculate the flood disaster losses.

[0028] The technical solution of the disclosed embodiment, the flood disaster prediction method includes: constructing a dialogue group, the dialogue group includes multiple agents, the agents are used to perform corresponding model service tasks; obtaining flood disaster analysis requirements, and determining the water conservancy and hydrological model required for analysis and the corresponding first agent according to the flood disaster analysis requirements; obtaining water conservancy and hydrological data according to the water conservancy and hydrological model required for analysis and the first agent; using the first agent to call the water conservancy and hydrological model required for analysis to process the water conservancy and hydrological data and generate water conservancy and hydrological results; using the second agent to call the disaster loss model according to the water conservancy and hydrological results to calculate and obtain the flood disaster loss. Through the flood disaster prediction method of this embodiment, by establishing a dialogue group including multiple types of agents, the full process automation of flood disaster assessment and loss calculation is realized. Each proxy user is used to perform complex water conservancy model calling and calculation tasks, refine the analysis requirements, and generate accurate evaluation results. Ensure the efficient collaboration of each link and the reliability of the results, suitable for various complex flood scenes such as urban floods, mountain torrents, tidal floods, etc., to improve the efficiency and accuracy of flood prevention work.

[0029] In an embodiment of the present application, the user selects the area to be analyzed, sets the start and end dates for the flood damage analysis, and starts the flood damage analysis; the task planning agent plans which water conservancy and hydrological models need to be called to complete the simulation analysis of the flood scenario.

[0030] Water conservancy and hydrological data, for example: elevation data of the region, associated areas, future precipitation forecasts, underlying surface properties or average evaporation of the region, etc. The model in the first agent calls, for example, the current water depth, flow boundary, and elevation data of the SFINCS hydrodynamic model call function.

[0031] After completing the retrieval of the data (elevation, section information, strip height, water level) required to call the water conservancy and hydrological model in the first intelligent agent, the agent with the corresponding model service capability is called up according to the call chain of the water conservancy and hydrological model in the dialogue group, and the query result is used as the dialogue input to call the model.

[0032] b) Such as flooding range spread model In the creation of the dialogue group of this application, first of all, ModelBuilder is created to plan and coordinate all tasks, ensuring that each task is carried out efficiently in the correct order. ModelBuilder decides which hydrological and water conservancy models to use based on the input data and assigns tasks to the corresponding agents. The role and necessity of ModelBuilder is to ensure the orderliness and efficiency of the entire process and prevent errors and delays caused by operational confusion.

[0033] Taking the AutoGen framework as an example, several main processes need to be built, including process startup, task execution, and process supervision: First, create a GroupChat: Use Autogen's GroupChat to create a conversation group that includes all agents. In the AutoGen framework, in order to promote effective communication and collaboration between multiple agents, you first need to use the GroupChat function provided by AutoGen to create a dedicated conversation group. This conversation group will serve as the core platform for information transmission and task allocation, ensuring that all participating agents can receive relevant information in real time.

[0034] (1) Initial configuration: Configure the basic parameters of GroupChat, including the name of the conversation group, the member list (i.e. the identifiers of all agents), and the necessary permission settings.

[0035] (2) Create an instance: Create a GroupChat instance by calling the service API or SDK and specify the above configuration information.

[0036] (3) Wake up members: Automatically add all agents to the dialogue group member list by corresponding identifiers to ensure that they can access and participate in the dialogue group.

[0037] (4) Verification and testing: Finally, verification testing is performed to ensure that each agent can successfully access the conversation group and can receive and send messages normally.

[0038] Next, create GroupChatManager (dialogue information management): Use GroupChatManager to manage the entire process and coordinate the interaction between agents. GroupChatManager is a key component for managing the entire process and coordinating the interaction between agents. It is responsible for monitoring activities within the dialogue group, handling tasks such as task allocation and message forwarding, and ensuring the smooth progress of the process.

[0039] (1) Task scheduling: GroupChatManager maintains a task queue. According to process requirements, it takes tasks from the queue and assigns them to corresponding agents.

[0040] (2) Message forwarding: Receive messages from agents and forward them to target agents based on the message content or type.

[0041] (3) Status monitoring: Monitor the status and task execution of agents in real time to ensure that each agent is working properly and intervene when necessary.

[0042] (4) Logging: Record key information during process execution, including task assignment, execution results, abnormal situations, etc., for subsequent analysis and problem tracking.

[0043] Further configure the process start method: ModelBuilder Agent (a workflow agent, a type of intelligent agent) starts the process and assigns tasks to other agents. Process start is the starting point of the entire automation process and is the responsibility of ModelBuilder Agent. ModelBuilder Agent starts the process and assigns initial tasks based on preset rules or external trigger conditions.

[0044] (1) Trigger conditions: ModelBuilder Agent checks whether the preset trigger conditions are met (such as time arrival, receipt of specific instructions, etc.).

[0045] (2) Initialization task: Once the trigger conditions are met, ModelBuilder Agent will create the initial task and add it to the task queue of GroupChatManager.

[0046] (3) Task allocation: After receiving the initial task, GroupChatManager allocates it to appropriate agents for execution based on the task type and the capabilities of the agents.

[0047] Then configure the tasks of each agent in the task execution: after receiving the task, each professional agent performs the corresponding operation according to the task requirements and passes the result to the next agent or returns it to the ModelBuilder Agent.

[0048] (1) Task analysis: Agents first analyze the received task information and clarify the task objectives and requirements.

[0049] (2) Execute operations: Based on the task type, call the corresponding functional module or algorithm to perform operations. This may include data analysis, image processing, model prediction, and other operations.

[0050] (3) Result generation: Organize the operation results into a standard format, ready to be passed to the next agent or returned to the ModelBuilder Agent.

[0051] (4) Result delivery: Send the results to the specified agents or broadcast them to all members through GroupChat. At the same time, update the task status and task progress information.

[0052] Finally, configure the process supervisory agent ProcessSupervisor Agent (a type of agent), which is mainly responsible for supervising the execution of the entire process, ensuring that the process proceeds as expected, and intervening when necessary.

[0053] (1) Real-time monitoring: Continuously monitor the status of agents, task execution, and process progress.

[0054] (2) Anomaly detection: Detect potential anomalies or errors through log analysis, status checking, etc.

[0055] (3) Intervention measures: Once an anomaly or error is detected, timely intervention measures are taken, such as reallocating tasks, restarting agents, adjusting process parameters, etc.

[0056] (4) Report generation: After the process is completed, a detailed execution report is generated, including task completion status, exception records, performance indicators, etc., for subsequent analysis and improvement.

[0057] If the user does not specify a fixed model call chain, the ModelBuilder Agent will work with multiple functional assistant agents to plan the task, that is, to build a model call chain for the current task through a non-fixed process.

[0058] When building an agent member (agent) of the AssistantAgent type, you need to consider the following configuration aspects: (1) Type: AssistantAgent or UserProxyAgent AssistantAgent is used to perform specific tasks or assist in managing the overall process, and has a certain degree of intelligence and decision-making capabilities. This type of agent is responsible for processing unstructured and semi-structured data, not limited to structured SQL databases. AssistantAgent can directly undertake analysis tasks without creating a dedicated AnalysisAgent.

[0059] UserProxyAgent is responsible for coordinating the entire conversation and task execution process. When errors occur during task execution, UserProxyAgent is responsible for error handling and recovery processes. It can also automate decision-making processes, such as when to end a conversation, when more information is needed, etc. In situations where human input is required, UserProxyAgent acts as an interface between human users and AI systems and model platforms. In complex tasks involving multiple AssistantAgents, UserProxyAgent is responsible for coordinating interactions between different agents.

[0060] (2) Capability description: Each AssistantAgent needs to clarify its specific capabilities, such as task planning, data processing, model execution, result analysis, etc. These capabilities determine the role and responsibilities of the agent in the system.

[0061] (3) Prompt configuration: The prompt of the agent is the key to its receiving instructions and executing tasks. The prompt should be clear and guide the agent on how to perform corresponding operations based on the received input.

[0062] “As an AssistantAgent, your task is to assist in processing flood model output data and generating flood maps. Please generate a visual flood map based on the input model data to ensure that the map information accurately reflects the actual situation.” (4) Other configuration requirements: Interaction mode: defines the interaction methods and collaboration mechanisms between agents and other agents or users, such as chat groups, messaging formats, etc.

[0063] Supervision and management: Whether it is necessary to add a mechanism to supervise or manage the intelligent agent in the system to ensure the correctness of task execution and the stability of the system.

[0064] Data Interface: Does the agent require a specific data interface or format to handle input and output data?

[0065] 3. Flood damage analysis agent (agent) configuration (1) Workflow Management Agent (ModelBuilder) Type: AssistantAgent Abilities: Task planning, process coordination, decision making Prompt configuration: Set as a workflow manager, responsible for overall process coordination, task allocation, ensuring that the operation sequence is reasonable and efficient, and deciding which models to use based on the input data.

[0066] Description: ModelBuilder is the commander of the entire workflow. It is responsible for planning and coordinating all tasks, ensuring that each task is carried out efficiently in the correct order. ModelBuilder decides which models to use based on the input data and assigns tasks to the corresponding agents. Its role and necessity lies in ensuring the orderliness and efficiency of the entire process and preventing errors and delays caused by operational confusion.

[0067] (2) Compound Flood Scenario Agent Type: AssistantAgent Capabilities: data integration, scenario construction, multi-model coordination Prompt configuration: "Your task is to create composite flood scenarios, integrate various flood model data, and build comprehensive flood scenarios. Ensure the compatibility of different model outputs and provide detailed scenario descriptions and data support." Description: CompoundScenario is responsible for creating composite flood scenarios, integrating data from different models to build comprehensive flood scenarios. It ensures the compatibility of various flood model outputs and provides detailed scenario descriptions and data support. Its role and necessity lies in comprehensively considering multiple flood types and their impacts, and providing accurate and comprehensive basic data for the entire assessment process.

[0068] Description: CompoundScenario focuses on creating composite flood scenarios, integrating data from different flood models to build comprehensive flood scenarios. Its role is to provide a comprehensive flood prediction and assessment platform, ensure that the outputs of various models are compatible with each other, and provide detailed flood impact analysis for system users.

[0069] (3) Two-dimensional hydrodynamic flood model Agent (2DHydroModel) Type: UserProxyAgent Capabilities: Execute 2D hydrodynamic models, process model input and output Prompt configuration: "As an interface to a 2D hydrodynamic flood model, you need to accept input parameters, run the model, and return results in a specific format. Ensure the accuracy of the model calculations and the reliability of the output." Description: 2DHydroModel is an agent that is specifically responsible for executing a two-dimensional hydrodynamic flood model. It receives input parameters, simulates water flow, water level changes, etc., and outputs model prediction results. Its existence enables the system to accurately simulate the propagation and impact of floods in two-dimensional space, providing important support for flood management and early warning.

[0070] (4) Urban Model Agent (UrbanModel) Type: UserProxyAgent Ability: Simulate urban drainage system Prompt configuration: "Specialized in urban drainage system simulation, accepting urban parameter input, running urban drainage model, and outputting results. Ensure that the model can accurately reflect urban flooding conditions." Description: UrbanModel is another agent-based agent that focuses on simulating the operation of urban drainage systems. It receives parameter inputs of urban structures and drainage facilities, simulates the impact of floods on urban infrastructure and residents' lives, and provides support for urban flood prevention planning and emergency response.

[0071] (5) FlashFloodModel Agent Type: UserProxyAgent Capabilities: Simulate flash flood conditions Prompt configuration: "Focus on flash flood simulation, process terrain and rainfall data, run flash flood models, and provide flash flood prediction results. Ensure that the model's simulation of flash floods is accurate and reliable." Description: FlashFloodModel specializes in flash flood simulations. It processes terrain and rainfall data to predict possible sudden floods in mountainous areas. Its role is to provide timely warnings and accurately predict the scale and impact range of mountain floods, and provide flood risk management strategies for mountain residents and relevant departments.

[0072] (6) Coastal Model Agent (CoastalModel) Type: UserProxyAgent Capabilities: Simulate coastal flooding conditions Prompt configuration: "For coastal flood simulation, process ocean and meteorological data, run coastal flood models, and output coastal flood forecasts. Ensure that the simulation results can accurately reflect coastal flood conditions." Description: CoastalModel focuses on simulating flood conditions in coastal areas, processing ocean and meteorological data, and predicting the possible impact of waves and storm surges on coastal areas. Its existence enables the system to effectively respond to coastal flood risks and provide corresponding protection recommendations and emergency response strategies.

[0073] (7) Flood Map Generator Type: AssistantAgent Abilities: data visualization, map generation, GIS processing Prompt configuration: "Specialized in flood map generation, processing model output into visual formats, creating various flood maps. Ensures accuracy and readability of maps, making them easy for users to understand and use." Description: FloodMapGenerator is responsible for converting the output data of various flood models into visual flood maps. Its role is to convert abstract model data into intuitive map displays, providing decision makers and the public with intuitive understanding and spatial distribution information of flood impacts.

[0074] (8) Deterministic Flood Map Agent (DeterministicFloodMap) Type: AssistantAgent Capabilities: Generation of deterministic flood maps, geographic information processing Prompt configuration: "Focus on generating deterministic flood maps, processing geographic data, and creating clear and accurate deterministic flood extent maps. Ensure that the charts are intuitive and easy to understand and reflect the real situation." Description: DeterministicFloodMap focuses on generating deterministic flood range maps. By processing geographic information data, it accurately describes the areas that may be covered by floods and the degree of impact, providing a scientific basis for risk assessment and emergency plans.

[0075] (9) Flood Risk Map Agent (FloodRiskMap) Type: AssistantAgent Abilities: risk assessment, probability analysis, map generation Prompt configuration: "Responsible for generating flood risk maps, assessing flood risks by combining multiple factors, and creating intuitive risk distribution maps. Ensure the comprehensiveness and accuracy of risk assessments." Description: FloodRiskMap is responsible for assessing and displaying flood risks. Combining probability analysis and geographic information processing, it generates flood risk distribution maps to help decision makers understand the degree of flood risk in different areas and take corresponding risk management measures.

[0076] (10) Damage Risk Model Agent (ImpactModel) Type: AssistantAgent Capabilities: risk assessment, impact analysis, vulnerability assessment Prompt configuration: "Assess flood impacts, analyze infrastructure and community vulnerability, quantify potential losses, and provide risk assessments and recommendations. Ensure that assessment results are scientific and reliable to facilitate decision-making." Description: ImpactModel assesses the impact of floods on infrastructure and communities, analyzes vulnerability and potential losses, and provides necessary decision support for post-disaster recovery and disaster preparedness through quantitative analysis.

[0077] (11) Agent (ExternalForcing) Type: UserProxyAgent Ability: Processing external environment data Prompt configuration: "Specially handles data of external factors such as storms and tides, and pre-processes these data for use by other models. Ensures the accuracy and timeliness of data to support model calculations." Description: ExternalForcing focuses on processing external environmental data, such as storms, tides and other factors. It preprocesses these data and provides input for other flood models to ensure the accuracy and real-time performance of model calculations.

[0078] (12) Model Input Agent (ModelInput) Type: UserProxyAgent Ability: data preparation, format conversion Prompt configuration: "Responsible for preparing the input data required for various models, including data collection, cleaning, formatting, etc. Ensure that the data quality and format meet the model requirements." Description: ModelInput is responsible for preparing and managing the input data required by various flood models. It collects, cleans and formats the data to ensure that the model can run effectively and produce reliable prediction results.

[0079] (13) Accuracy Verification Agent Type: AssistantAgent Capabilities: data analysis, quality control, accuracy assessment, parameter adjustment Prompt configuration: "Check and adjust the model calculation accuracy, perform data quality control, and ensure the reliability of the results. Find and solve errors and problems in the calculation in a timely manner." Description: AccuracyVerification is responsible for checking and adjusting the accuracy of model calculations. Through data analysis and quality control, it ensures the accuracy and reliability of model output and improves the overall performance of the decision support system.

[0080] In some embodiments, the second agent uses the disaster loss model to calculate the flood disaster loss according to the water conservancy and hydrology results, and the flood disaster loss includes: The water conservancy and hydrology result may be a flood map, and a flood map suitable for loss assessment is selected according to the flood map; According to the flood map for loss assessment, the skill of processing water accumulation depth-loss function is configured, that is, according to the flood map for loss assessment, the depth-loss function data is obtained, and the depth-loss function data is used to assess the potential economic losses of buildings, facilities and roads; According to the flood map of loss assessment, the exposure data processing skill is configured, that is, according to the flood map of loss assessment, the exposure data is obtained, and the exposure data includes the location, value and ground height of the exposed assets.

[0081] Based on the exposure data, economic loss calculation is performed, that is, the exposure data is input into the model to quickly calculate the economic impact of the flood event.

[0082] Based on the economic impact of flood events and depth-loss function data, risk assessment is carried out, that is, flood risk is assessed by combining multiple factors and a risk distribution map is generated.

[0083] After completing the model capability configuration, it is also necessary to improve the agent's self-adaptation and natural language interaction capabilities. This application provides the agent with observation, reasoning and interaction capabilities through the LLM natural language large model.

[0084] Local deployment of large LLM models: Determine the hardware and software environment required for large models, including high-performance GPUs, sufficient memory and storage space. Install necessary software, such as Docker environment, deep learning frameworks (such as TensorFlow or PyTorch), and Docker (if containerized deployment is required).

[0085] Further configure the streaming output interface: Select a suitable streaming data interface framework, such as gRPC, WebSocket, or RESTful API. Develop a server application that is responsible for receiving requests from the agent and calling the large model for reasoning.

[0086] Finally, configure the agent to call the large model service interface and configure monitoring tools (Prometheus, Grafana) to monitor the running status of each service instance.

[0087] Due to the adoption of the above technical solution, the beneficial effects of this application are as follows: (1) Automating the flood damage analysis process: This application uses multi-agent (dialogue group and agent) technology to provide a flexible, automated and intelligent flood damage assessment and loss calculation solution, which significantly improves the efficiency and accuracy of the analysis.

[0088] (2) Reducing operational complexity: By configuring UserProxyAgent to proxy users to perform model calls and calculations, the operational process is simplified, the technical threshold for model calls is lowered, and flood control workers can use complex models for flood assessment more efficiently.

[0089] (3) Improve the reliability of evaluation: Through multi-agent collaboration and monitoring mechanisms, the reliability of each step of the calculation and evaluation process is ensured. The results generated by AssistantAgent are verified and optimized by UserProxyAgent to ensure that the final evaluation results meet the expected requirements.

[0090] (4) Realize the response to multiple types of complex flood scenarios: This application is applicable to complex flood scenarios under multiple influencing factors, and can cope with various complex scenarios including urban floods, mountain torrents, tidal floods, etc., improving the applicability and flexibility of the system.

[0091] (5) Full-process automated monitoring: This solves the problem that current technical means are difficult to achieve automated monitoring of the entire flood simulation process. By monitoring the entire calculation process, problems in the calculation can be discovered and corrected in a timely manner, ensuring the accuracy and reliability of the results.

[0092] In one implementation, the using the first agent to call the water conservancy and hydrology model required for the analysis to process the water conservancy and hydrology data to generate water conservancy and hydrology results includes: Using the first intelligent agent to call the water conservancy and hydrology model required for the analysis to process the water conservancy and hydrology data to generate preliminary water conservancy and hydrology results; Using a third agent to perform precision analysis on the preliminary water conservancy and hydrology results according to the precision index, and obtaining water conservancy and hydrology results when the preliminary water conservancy and hydrology results meet the precision requirements; In the case where the preliminary water conservancy and hydrology results do not meet the accuracy requirements, the third agent is used to adjust the water conservancy and hydrology data and the first agent is used again to call the water conservancy and hydrology model required for the analysis to process the adjusted water conservancy and hydrology data to obtain the adjusted preliminary water conservancy and hydrology results; When the adjusted preliminary water conservancy and hydrology results meet the accuracy requirements, obtaining water conservancy and hydrology results; When the adjusted preliminary water conservancy and hydrology results do not meet the accuracy requirements, the third intelligent agent is reused to adjust the water conservancy and hydrology data until the adjusted preliminary water conservancy and hydrology results obtained after processing by the first proxy user meet the accuracy requirements or the water conservancy and hydrology data are adjusted a maximum number of times.

[0093] In this embodiment, after the model calculation in the first agent is completed, the AccuracyVerification precision check is used to check the accuracy of the water conservancy and hydrology results obtained by the model. Whether the calculation result reaches the specified accuracy. After the dialogue is completed, the passed content is returned to the task planning. Due to the maximum number of dialogue rounds, the precision check agent will not repeat the result correction instructions endlessly, and a more accurate water level result can be obtained.

[0094] Specifically, the model calculation in the first agent relies on water conservancy and hydrological data, and parameters such as soil roughness need to be adjusted to make the model calculation in the first agent more accurate. The precision observation agent stores the average water depth and average parameters of the X-year return period as an accuracy indicator to observe whether the water conservancy model calculation deviates too much from the true value.

[0095] If there is a deviation, the hydrological and water conservancy data will be modified by the third agent and re-calculated in the first agent until an exact solution is obtained or the maximum number of dialogue rounds is reached, and accurate hydrological and water conservancy results are obtained.

[0096] In one implementation, the constructing a dialogue group includes: Calling a toolkit or a data interface to create a first dialogue group; configuring basic parameters of the initial dialogue group to obtain a second dialogue group; Adding each agent to the conversation list of the second conversation group by corresponding identification to generate a third conversation group; All agents in the third dialogue group are verified, and a dialogue group is obtained when all agents in the third dialogue group pass the verification.

[0097] In this embodiment, a GroupChat instance is created by calling the service API (interface) or SDK (toolkit), and the above configuration information is specified. Initialization configuration: Configure the basic parameters of GroupChat, including the name of the conversation group, the member list (i.e., the identifiers of all agents), and the necessary permission settings. Automatically add all agents to the conversation group member list by corresponding identifiers to ensure that they can all access and participate in the conversation group. Verification and testing: Finally, perform verification tests to ensure that each agent can successfully access the conversation group and can receive and send messages normally.

[0098] The dialogue group will serve as the core platform for information transmission and task allocation, ensuring that all participating agents can receive relevant information in real time.

[0099] In one embodiment, when all agents in the third dialogue group pass the verification, obtaining the dialogue group further includes: When all agents in the third dialogue group pass the verification, a dialogue group information management is created in the third dialogue group to obtain a dialogue group, and the dialogue information management is used to manage the dialogues between the agents and call each agent to perform corresponding tasks.

[0100] In one embodiment, the determining of the water conservancy and hydrological model required for analysis and the corresponding first agent according to the flood damage analysis requirements includes: According to the needs of flood damage analysis, the dialogue information management creates an initial task to be added to the dialogue group; When receiving the initial task, the dialogue group analyzes the initial task and determines the water conservancy and hydrology model required for the analysis and the corresponding first intelligent agent.

[0101] In one embodiment, obtaining water conservancy and hydrology data according to the water conservancy and hydrology model required for the analysis and the first agent includes: Utilizing the first agent to analyze the water conservancy and hydrology model required for the analysis of the initial task, and determining the data required for the water conservancy and hydrology model; The interface of the first intelligent agent is called to obtain the data required by the water conservancy and hydrology model to obtain the water conservancy and hydrology data.

[0102] This embodiment provides a flexibly configurable loss calculation process for different types of composite flood scenarios (such as urban floods, mountain torrents, river floods, tidal floods, etc.). By automatically calling and coordinating distributed hydrological models, one-dimensional and two-dimensional hydrodynamic models, water quality and discharge models, etc., accurate assessment and loss calculation in complex scenarios are achieved.

[0103] In one embodiment, it further includes: A visual diagram is generated based on the flood damage and an execution report is generated based on the content of the dialogue group.

[0104] In this implementation, the flood damage losses can be presented through visualization and execution reports, so that the staff can understand the flood disaster situation more clearly, supervise the execution of the entire process, ensure that the process is carried out as expected, and intervene when necessary. Continuously monitor the status of agents, task execution, and process progress. Through log analysis, status checks, etc., potential anomalies or errors are discovered. Once anomalies or errors are detected, timely intervention measures are taken, such as reallocating tasks, restarting agents, adjusting process parameters, etc. After the process is completed, a detailed execution report is generated, including task completion, anomaly records, performance indicators, etc., for subsequent analysis and improvement.

[0105] In a second aspect, an embodiment of the present application provides a flood disaster prediction device, comprising: A construction module 201 is used to construct a dialogue group, wherein the dialogue group includes a plurality of agents, and the agents are used to perform corresponding model service tasks; The first acquisition module 202 is used to obtain the flood damage analysis requirements, and determine the water conservancy and hydrological model required for the analysis and the corresponding first intelligent agent according to the flood damage analysis requirements; A second acquisition module 203 is used to acquire water conservancy and hydrological data according to the water conservancy and hydrological model required for the analysis and the first agent; A generation module 204 is used to use the first agent to call the water conservancy and hydrology model required for the analysis to process the water conservancy and hydrology data and generate a water conservancy and hydrology result; The obtaining module 205 is used to use the second intelligent agent to call the disaster loss model according to the water conservancy and hydrology results to calculate and obtain the flood disaster losses.

[0106] The functions of the modules in the devices in the embodiments of the present invention can be found in the corresponding descriptions of the above methods, which will not be described in detail here.

[0107] Figure 3 FIG. 2 shows a structural block diagram of an electronic device according to an embodiment of the present invention. Figure 3 As shown, the electronic device includes: a memory 910 and a processor 920, wherein the memory 910 stores a computer program that can be run on the processor 920. When the processor 920 executes the computer program, the flood disaster prediction method in the above embodiment is implemented. The number of the memory 910 and the processor 920 can be one or more.

[0108] The electronic device / terminal / server also includes: The communication interface 930 is used to communicate with external devices and perform data exchange transmission.

[0109] If the memory 910, the processor 920 and the communication interface 930 are implemented independently, the memory 910, the processor 920 and the communication interface 930 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0110] Optionally, in a specific implementation, if the memory 910, the processor 920 and the communication interface 930 are integrated on a chip, the memory 910, the processor 920 and the communication interface 930 can communicate with each other through an internal interface.

[0111] An embodiment of the present invention provides a computer-readable storage medium storing a computer program, which implements the method provided in the embodiment of the present application when the program is executed by a processor.

[0112] An embodiment of the present application also provides a chip, which includes a processor for calling and executing instructions stored in the memory from the memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present application.

[0113] An embodiment of the present application also provides a chip, including: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided in the embodiment of the application.

[0114] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor supporting the advanced RISC machines (ARM) architecture.

[0115] Further, optionally, the above-mentioned memory may include a read-only memory and a random access memory, and may also include a non-volatile random access memory. The memory may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may include a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may include a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct rambus RAM (DR RAM).

[0116] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.

[0117] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0118] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0119] Any process or method description in the flow chart or otherwise described herein can be understood to represent a module, fragment or portion of a code including one or more executable instructions for implementing the steps of a specific logical function or process. And the scope of the preferred embodiment of the present application includes other implementations, in which the functions may not be performed in the order shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the functions involved.

[0120] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0121] It should be understood that the various parts of the present application can be implemented with hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. All or part of the steps of the above embodiment method can be completed by instructing the relevant hardware through a program, which can be stored in a computer-readable storage medium, and when the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0122] In addition, each functional unit in each embodiment of the present application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the above-mentioned integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium can be a read-only memory, a disk or an optical disk, etc.

[0123] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for predicting flood damage, characterized in that: include: Constructing a dialogue group, wherein the dialogue group includes a plurality of intelligent agents, and the intelligent agents are used to perform corresponding model service tasks; Obtaining flood disaster analysis requirements, and determining a water conservancy and hydrological model required for analysis and a corresponding first intelligent agent according to the flood disaster analysis requirements; Acquiring water conservancy and hydrology data according to the water conservancy and hydrology model required for the analysis and the first intelligent agent; Using the first intelligent agent to call the water conservancy and hydrology model required for the analysis to process the water conservancy and hydrology data to generate a water conservancy and hydrology result; The second intelligent agent is used to call the disaster loss model according to the water conservancy and hydrological results to calculate the flood disaster losses.

2. The method for predicting flood damage according to claim 1, characterized in that: The using the first intelligent agent to call the water conservancy and hydrology model required for the analysis to process the water conservancy and hydrology data to generate water conservancy and hydrology results includes: Using the first intelligent agent to call the water conservancy and hydrology model required for the analysis to process the water conservancy and hydrology data to generate preliminary water conservancy and hydrology results; Using a third agent to perform precision analysis on the preliminary water conservancy and hydrology results according to the precision index, and obtaining water conservancy and hydrology results when the preliminary water conservancy and hydrology results meet the precision requirements; In the case where the preliminary water conservancy and hydrology results do not meet the accuracy requirements, the third agent is used to adjust the water conservancy and hydrology data and the first agent is used again to call the water conservancy and hydrology model required for the analysis to process the adjusted water conservancy and hydrology data to obtain the adjusted preliminary water conservancy and hydrology results; When the adjusted preliminary water conservancy and hydrology results meet the accuracy requirements, obtaining water conservancy and hydrology results; When the adjusted preliminary water conservancy and hydrology results do not meet the accuracy requirements, the third agent is reused to adjust the water conservancy and hydrology data until the adjusted preliminary water conservancy and hydrology results obtained after processing by the first agent meet the accuracy requirements or the water conservancy and hydrology data are adjusted a maximum number of times.

3. The method for predicting flood damage according to claim 2, characterized in that: The constructing dialogue group comprises: Calling a toolkit or a data interface to create a first dialogue group; configuring basic parameters of the first dialogue group to obtain a second dialogue group; Adding each agent to the conversation list of the second conversation group by corresponding identification to generate a third conversation group; All agents in the third dialogue group are verified, and a dialogue group is obtained when all agents in the third dialogue group pass the verification.

4. The method for predicting flood damage according to claim 3, characterized in that: In the case where all agents in the third dialogue group pass the verification, obtaining the dialogue group further comprises: When all agents in the third dialogue group pass the verification, a dialogue group information management is created in the third dialogue group to obtain a dialogue group, and the dialogue information management is used to manage the dialogues between the agents and call each agent to perform corresponding tasks.

5. The method for predicting flood damage according to claim 4, characterized in that: The step of determining the water conservancy and hydrological model and the corresponding first agent required for the analysis according to the flood disaster analysis requirements includes: According to the needs of flood damage analysis, the dialogue information management creates an initial task to be added to the dialogue group; When receiving the initial task, the dialogue group analyzes the initial task and determines the water conservancy and hydrology model required for the analysis and the corresponding first intelligent agent.

6. The method for predicting flood damage according to claim 5, characterized in that: The step of obtaining water conservancy and hydrology data according to the water conservancy and hydrology model required for the analysis and the first intelligent agent includes: Utilizing the first agent to analyze the water conservancy and hydrology model required for the analysis of the initial task, and determining the data required for the water conservancy and hydrology model; The interface of the first intelligent agent is called to obtain the data required by the water conservancy and hydrology model to obtain the water conservancy and hydrology data.

7. The method for predicting flood damage according to claim 6, characterized in that: Also includes: A visual diagram is generated based on the flood damage and an execution report is generated based on the content of the dialogue group.

8. A flood disaster prediction device, characterized in that: include: A construction module, used to construct a dialogue group, wherein the dialogue group includes a plurality of intelligent agents, and the intelligent agents are used to perform corresponding model service tasks; A first acquisition module is used to obtain flood damage analysis requirements, and determine the water conservancy and hydrological model required for analysis and the corresponding first intelligent agent according to the flood damage analysis requirements; A second acquisition module, used for acquiring water conservancy and hydrology data according to the water conservancy and hydrology model required for the analysis and the first intelligent agent; A generation module, used to use the first agent to call the water conservancy and hydrology model required for the analysis to process the water conservancy and hydrology data and generate water conservancy and hydrology results; The module is used to use the second intelligent agent to call the disaster loss model according to the water conservancy and hydrology results to calculate and obtain the flood disaster losses.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Multi-sensing equipment intelligent support power grid risk disposal method

    CN117575304A

  • Semiconductor production data monitoring method and system based on multi-mode intelligent agent

    CN118197960A

  • Data processing method and device, electronic equipment and storage medium

    CN118657127A

  • KR20230083542A

Cited By

  • Method and system for automatically generating hydrological analysis service chain based on large model

    CN119691296A

  • A large model-based hydrological analysis service chain automatic generation method and system

    CN119691296B

  • Method and system for intelligently constructing two-dimensional hydrodynamic model based on large language model

    CN119989995A

  • Information processing method, program, and information processing system

    JP7769851B1