Real-time typhoon evaluation method and device for similar disaster-causing typhoons

Abstract

The invention provides a real-time typhoon evaluation method and device for similar disaster-causing typhoons, and relates to the technical field of typhoon evaluation, and the method comprises the steps: obtaining historical typhoon parameters and rainfall parameters, and storing the parameters; associating the rainfall parameters of the historical typhoons with the historical typhoon parameters; the typhoon data of the current typhoon are acquired for multiple times at regular time Performing similarity detection and sorting according to the typhoon data of the current typhoon and the historical typhoon parameters, and synchronously updating along with the typhoon data of the current typhoon obtained each time; and matching the most similar historical typhoon according to the sorting result, and calling the corresponding rainfall parameters. The method has the beneficial effects that through combination of historical typhoon data and real-time data and by utilizing the knowledge graph and the machine learning algorithm, the similarity of typhoons can be analyzed more accurately, the accuracy of disaster early warning is improved, and the situation that other important influence factors are ignored only depending on path similarity is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of typhoon evaluation, and in particular to a real-time typhoon evaluation method and device for similar disaster-causing typhoons. Background Art

[0002] A typhoon is a tropical cyclone that originates on the sea surface of the western and southwestern Pacific Ocean. The wind speed at the center of the typhoon can vary over time. While bringing abundant moisture to the Pacific coastal areas, typhoons usually also form severe convective weather such as heavy rain and storm surges in these areas. Therefore, typhoons are a recognized highly destructive natural phenomenon that seriously endangers human safety and socioeconomic development in coastal areas. Typhoons have also become a hot research topic today, especially the analysis of typhoon paths, in order to issue early warnings for developing typhoons and reduce casualties and property losses.

[0003] Therefore, it is necessary to issue typhoon warnings. In the typhoon disaster warning and forecasting business, the possibility and impact of disasters caused by typhoons are mainly predicted and forecasted. However, at present, when predicting typhoon disasters, only real-time monitoring of typhoon data and historical typhoon paths is carried out, and the accuracy and degree of disaster are difficult to estimate. Summary of the invention

[0004] In view of this, an embodiment of the present specification provides a real-time typhoon evaluation method for similar disaster-causing typhoons.

[0005] One or more embodiments of the present specification also relate to a real-time typhoon evaluation device for similar disaster-causing typhoons, an electronic device, a computer-readable storage medium, and a computer program product to solve the technical defects existing in the prior art.

[0006] In a first aspect, a real-time typhoon evaluation method for similar disaster-causing typhoons comprises the following steps: Obtain historical typhoon parameters and precipitation parameters for storage; Correlate the historical typhoon precipitation parameters with the historical typhoon parameters; Regularly obtain the typhoon data of the current typhoon multiple times; Perform similarity detection and sorting based on the typhoon data of the current typhoon and the historical typhoon parameters, and update them synchronously each time the typhoon data of the current typhoon is obtained; According to the sorting results, the most similar historical typhoon is matched and the corresponding precipitation parameters are retrieved.

[0007] Preferably, the historical typhoon data includes the longitude and latitude of the typhoon movement path, typhoon intensity, typhoon speed, air pressure, wind circle range, warning line data, and time.

[0008] Preferably, obtaining historical typhoon parameters and precipitation parameters for storage includes: storing the historical typhoon parameters and precipitation parameters in a graph database.

[0009] Preferably, acquiring historical typhoon parameters for storage further includes: preprocessing the historical typhoon data.

[0010] Preferably, preprocessing the historical typhoon data includes: completing missing data with the mean value of the current typhoon, and unifying the units of typhoon attribute values.

[0011] Preferably, acquiring historical typhoon parameters and precipitation parameters for storage further includes: The warning levels of different historical typhoons are graded according to the historical typhoon data.

[0012] Preferably, grading the warning levels of different historical typhoons according to the historical typhoon data includes: The disaster level of historical typhoons is divided into four levels according to the landing warning line situation, namely no impact, 48-hour impact, 24-hour impact, and disaster impact.

[0013] Preferably, associating the precipitation parameters of historical typhoons with the historical typhoon parameters includes: taking the historical typhoon wind circle as the radius, associating the rainfall stations and water level stations covered by the historical typhoons with the corresponding historical typhoons through a geospatial algorithm.

[0014] Preferably, regularly acquiring the typhoon data of the current typhoon for multiple times includes: deploying a crawler program as a scheduled task to perform data collection of the current typhoon once every set time.

[0015] Preferably, similarity detection and sorting are performed based on the typhoon data of the current typhoon and the historical typhoon parameters, and synchronously updated each time the typhoon data of the current typhoon is obtained, including: The current typhoon longitude and latitude, typhoon intensity, typhoon speed, and air pressure are input one by one into the similar typhoon algorithm of the dynamic time warping algorithm in a high-dimensional data format to calculate historical similar typhoons and sort the retrieved similar historical typhoons.

[0016] Similarity detection and sorting are performed based on the typhoon data of the current typhoon and the historical typhoon parameters, and the typhoon data of the current typhoon is updated synchronously each time it is obtained, and also includes: When the current typhoon reaches the 48-hour or 24-hour warning line, a similarity test is performed and historical typhoons that have not reached the 48-hour warning line are removed.

[0017] Preferably, calculating similar historical typhoons and sorting the retrieved similar historical typhoons further comprises: The results at different stages are merged, and the results of similarity detection at different stages of no impact, 48-hour impact, 24-hour impact, and disaster impact are weighted and merged.

[0018] In a second aspect, the present application also provides a real-time typhoon evaluation device for similar disaster-causing typhoons, comprising: An acquisition unit is configured to acquire historical typhoon parameters and precipitation parameters for storage, and to acquire typhoon data of the current typhoon multiple times at regular intervals; A correlation unit configured to correlate historical typhoon precipitation parameters and historical typhoon parameters; A matching unit is configured to perform similarity detection and sorting based on the typhoon data of the current typhoon and the historical typhoon parameters, and is synchronously updated each time the typhoon data of the current typhoon is obtained; The retrieving unit is configured to match the most similar historical typhoon according to the sorting result and retrieve the corresponding precipitation parameters.

[0019] The device includes modules / units for executing any possible design method of the first aspect. These modules / units can be implemented by hardware, or by executing corresponding software implementations by hardware.

[0020] In a third aspect, an embodiment of the present invention provides an electronic device, including a processor and a memory, wherein the memory is used to store one or more computer programs; when the one or more computer programs stored in the memory are executed by the processor, the electronic device can implement any possible design method of the first aspect.

[0021] In a fourth aspect, the present invention provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the method as described in any one of the above embodiments is implemented.

[0022] In a fifth aspect, an embodiment of the present invention further provides a computer program product, which, when executed on an electronic device, enables the electronic device to execute any possible design method of any of the above aspects.

[0023] The beneficial effects of the present invention are: By combining historical typhoon data with real-time data and using knowledge graphs and machine learning algorithms, we can more accurately analyze the similarity of typhoons, improve the accuracy of disaster warnings, and avoid relying solely on path similarity while ignoring other important influencing factors. The scheduled tasks are used to automatically collect and analyze real-time typhoon data to ensure that changes in typhoon paths can be quickly reflected in disaster warnings, greatly improving the efficiency of responding to new typhoons; Combined with historical rainfall and water level data, correlation analysis with similar typhoons was conducted, not only considering the intensity and path of the typhoon itself, but also comprehensively analyzing the hydrological disasters it may bring, thus improving the depth and breadth of disaster assessment; As the path and intensity of a typhoon change, the system can dynamically update the analysis results of similar typhoons and adjust the disaster assessment plan in real time to ensure the effectiveness and timeliness of the prediction results; Through weighted processing of different typhoon classifications, the problem of different impacts of typhoons at different stages is solved, providing a disaster impact assessment that is more in line with actual conditions and increasing the credibility of the analysis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of a framework of a real-time typhoon evaluation method for similar disaster-causing typhoons is provided for the present invention; Figure 2 A schematic flow chart of a real-time typhoon evaluation method for similar disaster-causing typhoons is provided for the present invention; Figure 3 A schematic diagram of a similarity detection process of a real-time typhoon evaluation method for similar disaster-causing typhoons is provided for the present invention; Figure 4 It is a structural schematic diagram of a real-time typhoon evaluation device for similar disaster-causing typhoons provided in an embodiment of the present application; Figure 5 This is a structural block diagram of an electronic device provided by an embodiment of the present application; Figure 6 This application Figure 3 A schematic diagram of the enlarged structure of the middle A position; Figure 7 This application Figure 3 Schematic diagram of the enlarged structure at position B in the middle. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Unless otherwise defined, the technical terms or scientific terms used herein should be understood by people with general skills in the field to which the present invention belongs. "Including" and similar words used in this article mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects.

[0026] In view of the problems existing in the existing technology, such as Figure 1As shown, an embodiment of the present invention provides a real-time typhoon evaluation method for similar disaster-causing typhoons, comprising the steps of: S101, obtaining historical typhoon parameters and precipitation parameters for storage; In some specific embodiments, the historical typhoon data includes the longitude and latitude of the typhoon movement path, typhoon intensity, typhoon speed, air pressure, wind circle range, warning line data, and time.

[0027] Specifically, the longitude and latitude of the typhoon's moving path: records the geographical locations that the typhoon passes through during its movement, providing accurate path tracking data; Typhoon intensity: The intensity parameter of a typhoon, usually expressed by indicators such as wind speed and central air pressure, is used to measure the destructive power of a typhoon; Typhoon speed: refers to the speed at which a typhoon moves, that is, the time interval between its passing through different locations, which can help predict when a typhoon may affect a specific area; Air pressure: The air pressure data at the center of a typhoon is an important reference indicator for assessing the intensity of a typhoon. Generally, the lower the air pressure, the greater the intensity of the typhoon. Wind circle range: refers to the impact range of a typhoon, usually the area extending outward from the center of the typhoon. The radius of the wind circle affects the wind conditions within this range; Warning line data: refers to the distance between a typhoon and the pre-set 24-hour and 48-hour warning lines when it passes through a certain location, used to predict the time and scope of the typhoon's possible impact; Time: The timestamp of each typhoon data point records the specific time when the typhoon passes through each geographical location, which facilitates time series analysis and similarity comparison.

[0028] Preferably, obtaining historical typhoon parameters and precipitation parameters for storage includes: storing the historical typhoon parameters and precipitation parameters in a graph database.

[0029] Specifically, the collection of historical typhoon parameters and precipitation parameters, through crawler technology or other data interfaces to collect various parameters of historical typhoons (such as path, intensity, wind speed, air pressure, etc.) and related precipitation data (such as data from rainfall monitoring stations, water level change data from water level stations); The cleaned historical typhoon parameters and precipitation parameters are stored in a graph database (such as Neo4j graph database). Graph databases can efficiently store and display complex multi-dimensional data relationships. Through their powerful graph structure, they can quickly realize the association and query of typhoon paths, precipitation monitoring points, disaster impacts and other data.

[0030] In some specific embodiments, Figure 3 , Figure 6 and Figure 7 As shown, obtaining historical typhoon parameters for storage also includes: preprocessing the historical typhoon data.

[0031] In some specific embodiments, Figure 3 , Figure 6 and Figure 7 As shown, the preprocessing of the historical typhoon data includes: completing the missing data with the mean value of the current typhoon, and unifying the units of the typhoon attribute values.

[0032] Specifically, for the missing values ​​in the historical typhoon data, a reasonable completion method is adopted. In the present embodiment, it is preferred to use the mean of the current typhoon for completion to ensure the integrity of the data, thereby improving the accuracy of the analysis. This method can avoid the analysis errors caused by missing data and ensure that the results will not be affected by incomplete data when calculating the similarity. Historical typhoon data may come from different channels, and the units of attribute values ​​(such as wind speed, distance, pressure, etc.) may be inconsistent. Therefore, the units of all typhoon attribute values ​​are uniformly processed and all converted into the same units such as kilometers, kilometers per hour, and kilopascals.

[0033] In some specific embodiments, obtaining historical typhoon parameters and precipitation parameters for storage further includes: The warning levels of different historical typhoons are graded according to the historical typhoon data.

[0034] In some specific embodiments, Figure 2 , Figure 3 , Figure 6 and Figure 7 As shown, the warning levels of different historical typhoons are classified according to the historical typhoon data, including: The disaster level of historical typhoons is divided into four levels according to the landing warning line, namely no impact, 48-hour impact (the typhoon center passes the 48-hour warning line), 24-hour impact (the typhoon center passes the 24-hour warning line), and disaster impact (the typhoon center lands).

[0035] Specifically, the classification of disaster levels is not only based on the time nodes along the typhoon's path (such as the 48-hour and 24-hour warning lines), but also combines parameters such as the typhoon's intensity, wind speed, and air pressure to ensure the accuracy and scientific nature of the classification. By grading the historical typhoon warning levels, we can better identify the degree of impact that a typhoon may bring, and provide a strong reference for current typhoon warnings. At the same time, this classification system also provides a unified standard for analyzing similar typhoons, facilitating more accurate disaster risk assessments.

[0036] S102, correlating historical typhoon precipitation parameters with historical typhoon parameters; In some specific embodiments, Figure 3As shown, the association between the precipitation parameters of historical typhoons and the historical typhoon parameters includes: taking the historical typhoon wind circle as the radius, and associating the rainfall stations and water level stations covered by the historical typhoons with the corresponding historical typhoons through geospatial algorithms.

[0037] Specifically, the historical typhoon wind circle is used as the radius. For each historical typhoon, its wind circle range (the influence radius extending outward from the center of the typhoon) is determined. Based on the wind circle radius, the area affected by the typhoon when it passes through the path is calculated. The wind circle range is usually determined based on the intensity and influence of the typhoon. Through geospatial algorithms, the geographical area covered by the typhoon path is matched with the rainfall stations and water level stations in the area using geospatial algorithms (such as GIS algorithms). The specific operation is based on the wind circle range of historical typhoons, and the monitoring stations within the influence radius are found; Associate the monitoring stations with historical typhoons. Once the rainfall stations and water level stations that match the typhoon wind circle are found, the system will associate the precipitation data and water level data of these monitoring stations with the corresponding historical typhoons; this will accurately analyze the changes in precipitation and water levels brought about by each historical typhoon; This correlation method, by combining the typhoon wind circle radius and geospatial algorithms, can accurately identify precipitation and water level change data in the typhoon-affected area.

[0038] S103, regularly acquiring typhoon data of the current typhoon multiple times; In some specific embodiments, Figure 3 , Figure 6 and Figure 7 As shown, the timing of acquiring the typhoon data of the current typhoon multiple times includes: deploying the crawler program as a timing task to perform data collection of the current typhoon once every set time.

[0039] Specifically, the deployment of the crawler program involves writing and deploying a crawler program, setting it to periodically obtain real-time data on the current typhoon from public or authorized data sources (such as meteorological websites or data interfaces). The crawler program will continuously collect data based on the latest changes in the typhoon's path, intensity, wind speed, etc. Setting of scheduled tasks: Setting the crawler program as a scheduled task, you can set the frequency of data collection according to actual needs. For example, perform a data collection task every hour or less to ensure that the system can continuously update the latest typhoon dynamics. Execute current typhoon data collection. Whenever the set time node is reached, the crawler program will run automatically to obtain the latest typhoon latitude and longitude, intensity, speed, air pressure and other data to ensure the real-time and continuity of the data. This timed data collection method can effectively track the movement and changes of typhoons, ensuring that the system can update information in time when the typhoon path and intensity change.

[0040] S104, combined Figure 2 , Figure 3 , Figure 6 and Figure 7 , perform similarity detection and sorting based on the typhoon data of the current typhoon and the historical typhoon parameters, and update them synchronously with each acquisition of the typhoon data of the current typhoon; In some specific embodiments, Figure 2 and Figure 3 As shown, similarity detection and sorting are performed based on the typhoon data of the current typhoon and the historical typhoon parameters, and the typhoon data of the current typhoon is synchronously updated each time it is obtained, including: The current typhoon longitude and latitude, typhoon intensity, typhoon speed, and air pressure are input one by one into the similar typhoon algorithm of the dynamic time warping algorithm in a high-dimensional data format to calculate historical similar typhoons and sort the retrieved similar historical typhoons.

[0041] Specifically, these extracted typhoon parameter data (latitude and longitude, intensity, speed, and air pressure) are combined in a high-dimensional data format so that data from multiple dimensions can be simultaneously input into the algorithm for calculation. These high-dimensional data can fully characterize the state and change trend of the typhoon, facilitating complex similarity analysis; Input the current typhoon data one by one into the DTW (Dynamic Time Warping) similar typhoon detection model. The DTW algorithm is good at processing time series data and can compare the similarity of two sequences at different time points. Even if the time axis of the paths or intensity changes of the two typhoons is different, the best matching relationship can be found. The algorithm can flexibly deal with the different processes of typhoon paths and characteristics on the time axis. Through the DTW algorithm, the similarity of the current typhoon and the historical typhoon's multi-dimensional data such as path, intensity, speed, and air pressure is calculated to find the historical typhoon that is most similar to the current typhoon; Based on the calculated similarity values, all matching historical typhoons are sorted from high to low according to the similarity. The higher the similarity, the closer the path and characteristics of the historical typhoon are to the current typhoon.

[0042] As each crawler task collects new current typhoon data, the system will synchronously update the analysis results of similar typhoons. The new typhoon data will be input into the DTW algorithm again, the similarity with historical typhoons will be recalculated, and the sorting results of similar typhoons will be adjusted to ensure that the analysis results are continuously updated with the changes in typhoon dynamics.

[0043] In some specific embodiments, Figure 2As shown, similarity detection and sorting are performed based on the typhoon data of the current typhoon and the historical typhoon parameters, and the typhoon data of the current typhoon is synchronously updated each time it is obtained, and it also includes: When the current typhoon reaches the 48-hour or 24-hour warning line, a similarity test is performed and historical typhoons that have not reached the 48-hour warning line are removed.

[0044] Specifically, when the current typhoon reaches the 48-hour or 24-hour warning line, in order to improve the accuracy of similarity detection, the system will automatically filter out historical typhoons that have not reached the 48-hour warning line. The reason for this is that those historical typhoons that have not reached the warning line may not have reference value for the similarity analysis of the current typhoon. Retaining these data may lead to errors in similarity calculation. After removing the historical typhoons that have not reached the warning line, the system will continue to use the DTW (Dynamic Time Warping) algorithm to perform similarity detection between the current typhoon and the remaining historical typhoons. This step of similarity detection will be more accurate because irrelevant historical typhoons have been excluded, thus ensuring that the analysis results are more focused on typhoons with the same warning characteristics; As the typhoon reaches different warning lines, the system will not only update the screening conditions for similar typhoons, but also update the similarity sorting results. Historical typhoons that reach the 48-hour or 24-hour warning line and have similar characteristics to the current typhoon will be displayed first, so as to provide more accurate historical references for disaster warnings.

[0045] S105, matching the most similar historical typhoon according to the sorting result, and retrieving its corresponding precipitation parameters.

[0046] Specifically, based on the precipitation and water level changes of historical typhoons that are most similar to the current typhoon, the system will call up the data of these historical typhoons to study the extent of the disaster that the current typhoon may bring. By analyzing the affected areas and disaster records of similar historical typhoons, the potential impact of the current typhoon can be inferred; The disaster data associated with the most similar historical typhoons (such as precipitation, water level rise, flood risk, etc.) are displayed to users. This data provides an intuitive reference for predicting the disasters of the current typhoon and can help decision makers better understand the possible impact of the current typhoon; The system performs weighted processing on historical data based on the characteristics of the typhoon and its stage (such as the 24-hour warning line or the 48-hour warning line), for example: Typhoons that reach the 48-hour or 24-hour warning line are given higher weights because they are closer to the impact stage of the current typhoon; historical typhoons with greater disaster severity (such as typhoons that caused severe rainfall and rising water levels) are given higher reference values ​​in the weighted processing. The weighted analysis can more accurately reflect the potential disaster impact of the current typhoon; Based on historical typhoon data and weighted processing results, the system will calculate the probability of disaster impact that the current typhoon may cause. This probability can help assess the disaster risk of the typhoon on its current path, such as possible precipitation intensity, flood risk, and wind impact. By combining historical typhoon data and typhoon disaster data, not only the accuracy of current typhoon similarity analysis is improved, but also the comprehensiveness of disaster warning is increased. The in-depth combination of historical data and current data enables the disaster warning system to more accurately predict the disaster risk of typhoons and better serve disaster prevention and mitigation work.

[0047] In some specific embodiments, Figure 2 , Figure 3 , Figure 6 and Figure 7 , calculate similar historical typhoons, and sort the retrieved similar historical typhoons also include: The results at different stages are merged, and the results of similarity detection at different stages of no impact, 48-hour impact, 24-hour impact, and disaster impact are weighted and merged.

[0048] Specifically, as the moving path of the new typhoon moves, the typhoon similarity analysis process may cross different warning classification groups (such as no impact, 48-hour impact, 24-hour impact, disaster impact), so there will be multiple sorting results. In order to improve the accuracy and rationality of the analysis, the typhoon path weighted algorithm is used to merge the results of different stages. The specific method is as follows: The weight coefficients are set according to the different classification groups of typhoons to reflect the different impacts of typhoons approaching or passing through the warning line: No impact: The weight coefficient is set to 1, indicating that the impact at this stage is minimal; 48-hour impact: The weight coefficient is set to 1.2, indicating that the typhoon is far from the warning line during this stage and the impact gradually increases; 24-hour impact: The weight coefficient is set to 1.3, indicating that the typhoon is approaching the 24-hour warning line and the impact is further increased; Disaster impact: The weight coefficient is set to 1.5, indicating that the typhoon has landed or is about to land, which may cause serious disasters and has the highest weight; In the process of typhoon similarity analysis, different classification groups will lead to multiple ranking results. In order to obtain a unified analysis result, weighted processing is adopted to merge the results of each classification group according to the weight coefficient. At the same time, the offset of the similarity analysis is calculated and standardized to a score range of 0 to 100, making the analysis result more intuitive and readable. In the calculation process, it is necessary to consider the influence of the typhoon in each classification group (through the preset weight) and the ranking weight of each typhoon in the classification group. Through this multiple weighted form, the system can conduct a more accurate and comprehensive analysis of the typhoon; This weighted typhoon similarity analysis can provide a more accurate and complete result. The weighted algorithm not only takes into account the warning levels of typhoons at different stages, but also reasonably combines the impacts of each stage, and finally generates a comprehensive similarity score ranging from 0 to 100. This score is more intuitive and helps decision makers assess the potential impact of the current typhoon and take corresponding disaster prevention measures based on the disaster situations of similar historical typhoons.

[0049] The present application also provides a real-time typhoon evaluation device for similar disaster-causing typhoons, such as Figure 4 As shown, including: The acquisition unit 301 is configured to acquire historical typhoon parameters and precipitation parameters for storage, and to acquire the typhoon data of the current typhoon multiple times at regular intervals; The associating unit 302 is configured to associate the historical typhoon precipitation parameters with the historical typhoon parameters; The matching unit 303 is configured to perform similarity detection and sorting based on the typhoon data of the current typhoon and the historical typhoon parameters, and is synchronously updated each time the typhoon data of the current typhoon is obtained; The retrieving unit 304 is configured to match the most similar historical typhoon according to the sorting result and retrieve the corresponding precipitation parameter.

[0050] All relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here.

[0051] In some other embodiments of the present invention, the present invention discloses an electronic device, such as Figure 5 As shown, the electronic device may include: one or more processors 401; a memory 402; a display 403; one or more applications (not shown); and one or more computer programs 404. The above components may be connected via one or more communication buses 405. The one or more computer programs 404 are stored in the above memory 402 and configured to be executed by the one or more processors 401. The one or more computer programs 404 include instructions, which may be used to execute the following: Figure 1 to Figure 2And each step in the corresponding embodiment.

[0052] Through the description of the above implementation methods, technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0053] Each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0054] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: flash memory, mobile hard disk, read-only memory, random access memory, disk or optical disk and other media that can store program codes.

[0055] The above is only a specific implementation of the embodiment of the present invention, but the protection scope of the embodiment of the present invention is not limited thereto. Any changes or substitutions within the technical scope disclosed in the embodiment of the present invention should be included in the protection scope of the embodiment of the present invention. Therefore, the protection scope of the embodiment of the present invention should be based on the protection scope of the claims.

Claims

1. A real-time typhoon evaluation method for similar disaster-causing typhoons, characterized in that: Includes steps: Obtain historical typhoon parameters and precipitation parameters for storage; Correlate the historical typhoon precipitation parameters with the historical typhoon parameters; Regularly obtain the typhoon data of the current typhoon multiple times; Perform similarity detection and sorting based on the typhoon data of the current typhoon and the historical typhoon parameters, and update them synchronously each time the typhoon data of the current typhoon is obtained; According to the sorting results, the most similar historical typhoon is matched and the corresponding precipitation parameters are retrieved.

2. The method according to claim 1, characterized in that The historical typhoon data includes the longitude and latitude of the typhoon movement path, typhoon intensity, typhoon speed, air pressure, wind circle range, warning line data, and time.

3. The method according to claim 1, characterized in that Acquiring historical typhoon parameters and precipitation parameters for storage includes: storing the historical typhoon parameters and precipitation parameters in a graph database.

4. The method according to claim 1, characterized in that: Acquiring historical typhoon parameters for storage also includes: preprocessing the historical typhoon data; The missing data are supplemented with the mean value of the current typhoon, and the units of the typhoon attribute values ​​are unified.

5. The method according to claim 2, characterized in that: Obtaining historical typhoon parameters and precipitation parameters for storage also includes: Classifying the warning levels of different historical typhoons according to the historical typhoon data; The disaster level of historical typhoons is divided into four levels according to the landing warning line situation, namely no impact, 48-hour impact, 24-hour impact, and disaster impact.

6. The method according to claim 1, characterized in that The association is made based on the precipitation parameters of historical typhoons and the historical typhoon parameters, including: taking the historical typhoon wind circle as the radius, and associating the rainfall stations and water level stations covered by the historical typhoons with the corresponding historical typhoons through geospatial algorithms.

7. The method according to claim 5, characterized in that Similarity detection and sorting are performed based on the typhoon data of the current typhoon and the historical typhoon parameters, and the typhoon data of the current typhoon is updated synchronously each time it is obtained, including: The current typhoon longitude and latitude, typhoon intensity, typhoon speed, and air pressure are input one by one into the similar typhoon algorithm of the dynamic time warping algorithm in a high-dimensional data format to calculate historical similar typhoons and sort the retrieved similar historical typhoons.

8. The method according to claim 7, characterized in that Similarity detection and sorting are performed based on the typhoon data of the current typhoon and the historical typhoon parameters, and the typhoon data of the current typhoon is updated synchronously each time it is obtained, and also includes: When the current typhoon reaches the 48-hour or 24-hour warning line, a similarity test is performed and historical typhoons that have not reached the 48-hour warning line are removed.

9. The method according to claim 7, characterized in that: Calculating historical similar typhoons and sorting the retrieved similar historical typhoons also includes: The results at different stages are merged, and the results of similarity detection at different stages of no impact, 48-hour impact, 24-hour impact, and disaster impact are weighted and merged.

10. A real-time typhoon evaluation device for similar disaster-causing typhoons, characterized in that: include: An acquisition unit, used to acquire historical typhoon parameters and precipitation parameters for storage, and to acquire the typhoon data of the current typhoon multiple times at regular intervals; A correlation unit, used for correlating historical typhoon precipitation parameters with historical typhoon parameters; A matching unit, used to perform similarity detection and sorting based on the typhoon data of the current typhoon and the historical typhoon parameters, and synchronously update each time the typhoon data of the current typhoon is obtained; The retrieval unit is used to match the most similar historical typhoon according to the sorting results and retrieve its corresponding precipitation parameters.

Images