A method, device and medium for recommending historical similar flood events
Through the recommended method of historically similar flooding sequences, machine learning technology is used to match the current flooding sequences with the most similar rainfall, and corresponding measures are called from the database, which solves the problem of high artificial dependence in flood control work and improves the automation and accuracy of flood control decisions. reduces the degree of flood disasters.
Patent Information
- Application Number
- CN202410682299.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-29
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-05-29
AI Technical Summary
The existing flood situation prediction methods are too dependent on people, which leads to the limitation of the sustainability and effectiveness of flood control work, and is prone to misjudgment or judgment deviations.
The recommended method of historical similar flood scenes is adopted, and historical flood scene information is extracted by collecting and featured, training data sets are constructed, curve functions are generated, and the most similar historical flood scenes are matched based on the current rainfall data, and corresponding solutions are called from the database.
It reduces the degree of disasters caused by floods, changes the absolute dependence on expert experience, improves the automation and accuracy of flood control decisions, and assists in the designation of flood control scheduling plans.
Smart Images

Figure CN118520171B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of machine learning technology, and in particular to a method, device and medium for recommending historical similar flood events. Background Art
[0002] Most areas of my country have a monsoon climate, and the time dimension of rainfall is unevenly distributed, which is prone to relatively concentrated heavy rainfall weather, causing flood disasters and huge flood control pressure. In the face of floods that may be caused by heavy rainfall, how to deal with them and what effective measures to take to minimize the harm caused by floods have become urgent issues to be solved.
[0003] At present, in the face of floods that may be caused by heavy rainfall, experts with rich flood control experience are generally invited to hold consultations, and relevant deployment and dispatch are carried out based on expert experience and combined with the response measures of similar floods in history. However, this method is too dependent on people, which is not conducive to the sustainability of flood control work, and manual judgment is prone to misjudgment or bias, which is not conducive to the effective implementation of flood control work. Summary of the invention
[0004] The embodiment of the present invention provides a method, device and medium for recommending similar historical flood events, which are used to solve the following technical problems: the current flood situation prediction method is too dependent on humans, which is not conducive to the sustainability and effectiveness of flood prevention work.
[0005] The embodiment of the present invention adopts the following technical solution:
[0006] On the one hand, an embodiment of the present invention provides a method for recommending historical similar flood events, the method comprising: collecting historical flood event information, and performing feature extraction on the historical flood event information to construct a training data set;
[0007] Based on the training data set, generating curve functions corresponding to each historical flood event;
[0008] According to the hydrological data of the current rainfall, the corresponding real-time characteristic value is determined;
[0009] According to the real-time characteristic value, matching is performed with the curve function corresponding to each historical flood event to determine the historical flood event that is most similar to the current rainfall;
[0010] The solution corresponding to the most similar historical flood event is called in the database.
[0011] In a feasible implementation, collecting historical flood event information specifically includes:
[0012] All historical flood event information is read from the historical flood reservoir and the historical water condition database; wherein the historical flood event information includes at least: flood number, flood occurrence basin, flood start time, flood end time, rainfall center point, flood peak observation station data and flood peak flow.
[0013] In a feasible implementation, feature extraction is performed on the historical flood event information to construct a training data set, specifically including:
[0014] In the historical flood event information, preset characteristic values are calculated to complete feature extraction; wherein the preset characteristic values at least include: average rainfall in the basin, rainfall duration, rainfall center point and flood monitoring flow;
[0015] Cartesian product operation is performed on the obtained basin average rainfall and flood monitoring flow, and the basin average rainfall in each Cartesian product is grouped according to the timestamp;
[0016] Determine a group with the smallest time difference, and update the flood monitoring flow in the preset characteristic value based on the flood monitoring flow in the group;
[0017] The preset characteristic values corresponding to all historical flood events are constructed as the training data set.
[0018] In a feasible implementation manner, in the historical flood event information, a preset characteristic value is calculated to complete feature extraction, specifically including:
[0019] According to the flood peak observation station data, the rainfall in each preset time period and the cumulative rainfall of each flood peak observation station are counted, and the average rainfall of each river basin is calculated at intervals of the preset time period;
[0020] According to the rainfall timestamps of adjacent rainfall events, the rainfall duration of each rainfall event is calculated;
[0021] Two virtual variables are created, and different combinations of the two virtual variables represent different rainfall center points; wherein the value of the virtual variable is 0 or 1; and the rainfall center points include at least upstream, downstream and midstream;
[0022] Obtain the flood start time and flood end time in all flood-occurring basins and calculate the flood duration; select all rainfall data within the flood duration in the rainfall table; and obtain the flood monitoring flow within the flood duration based on the flood peak observation station data.
[0023] In a feasible implementation, based on the training data set, a curve function corresponding to each historical flood event is generated, specifically including:
[0024] Based on the training data in the training data set, the Sklearn library of Python is used to generate curve functions corresponding to each historical flood event; the curve function is used to describe the functional relationship between the monitored flow and the average rainfall in the basin, rainfall duration, and rainfall center point.
[0025] In a feasible implementation, the corresponding real-time characteristic value is determined according to the hydrological data of the current rainfall, specifically including:
[0026] The hydrological data of the current rainfall is obtained in real time, and the corresponding real-time characteristic values are calculated based on the hydrological data; wherein the real-time characteristic values include at least: the real-time average rainfall in the basin, the real-time rainfall duration, the real-time rainfall center point and the real-time flood monitoring flow.
[0027] In a feasible implementation, according to the real-time characteristic value, matching is performed with the curve function corresponding to each historical flood event to determine the historical flood event most similar to the current rainfall, specifically including:
[0028] Substitute the calculated real-time basin average rainfall, real-time rainfall history and real-time rainfall center point into the curve function corresponding to each historical flood event to calculate the corresponding flood flow value;
[0029] The three flood flow values calculated in the same historical flood event are respectively subjected to variance calculation and summation with the real-time flood detection flow to obtain the sum of variances corresponding to the historical flood event;
[0030] The historical flood event corresponding to the curve function with the smallest sum of variance is determined as the historical flood event most similar to the current rainfall.
[0031] In a feasible implementation manner, the solution corresponding to the most similar historical flood event is called in the database, specifically including:
[0032] According to the flood number corresponding to the historical flood event that is most similar to the current rainfall, the corresponding historical flood event information and corresponding solutions are searched and called in the database, and recommended to relevant personnel.
[0033] On the other hand, an embodiment of the present invention further provides a device for recommending historical similar flood events, the device comprising:
[0034] at least one processor; and,
[0035] a memory communicatively connected to the at least one processor; wherein,
[0036] The memory stores instructions that can be executed by the at least one processor, so that the at least one processor can execute the method for recommending historical similar flood events.
[0037] Finally, an embodiment of the present invention also provides a storage medium, which is a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, each of which includes instructions, and when the instructions are executed by a terminal, the terminal executes the method for recommending historical similar flood events.
[0038] Compared with the prior art, the method, device and medium for recommending similar historical flood events provided by the embodiments of the present invention have the following beneficial effects:
[0039] 1. The present invention makes full use of the existing achievements of water conservancy information construction, and combines the innovative exploration of machine learning and big data technology in flood control business, changing the original flood control mode that absolutely relies on expert experience. It can calculate and recommend similar historical floods in real time according to the current rainfall, and feedback the decision-making measures at that time, assist in flood control decision-making and scheduling plan designation, and effectively reduce the degree of disaster caused by floods.
[0040] 2. The present invention is closely related to flood prevention business and solves practical problems. The function page is simple to operate and can also provide recommendation services to the outside world, facilitating the development of flood prevention business. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:
[0042] Figure 1 A flow chart of a method for recommending historical similar flood events provided by an embodiment of the present invention;
[0043] Figure 2 An example diagram of a training data set provided by an embodiment of the present invention;
[0044] Figure 3 A schematic diagram of the structure of a device for recommending historically similar flood events provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0045] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0046] The embodiment of the present invention provides a method for recommending similar historical flood events. Figure 1 As shown, the method for recommending historical similar flood events specifically includes steps S101-S106:
[0047] S101. Collect historical flood event information.
[0048] Specifically, all historical flood event information is read from the historical flood reservoir and the historical water condition database; wherein the historical flood event information includes at least: flood number, flood basin, flood start time, flood end time, rainfall center point, flood peak observation station data and flood peak flow.
[0049] As a feasible implementation method, the training data sources include historical flood databases and historical water condition databases. All historical flood event information is read from the above two databases. The information includes the flood number, flood basin, flood start time, flood end time, rainfall center point, flood peak observation station, and flood peak flow of each historical flood event.
[0050] S102: Extract features from historical flood event information and construct a training data set.
[0051] Specifically, in the historical flood event information, preset characteristic values are calculated to complete feature extraction; wherein the preset characteristic values include at least: average rainfall in the basin, rainfall duration, rainfall center point and flood monitoring flow.
[0052] Among them, in the historical flood event information, the preset characteristic values are calculated to complete the feature extraction, which specifically includes:
[0053] First, according to the data of the flood peak observation station, the rainfall in each preset time period and the cumulative rainfall of each flood peak observation station are counted, and the average rainfall in each basin is calculated at intervals of the preset time period. Then, according to the rainfall timestamps of adjacent sessions, the rainfall duration of each rainfall is calculated. Furthermore, two virtual variables are created, and different rainfall center points are represented according to different combinations of the two virtual variables; wherein the value of the virtual variable is 0 or 1; the rainfall center points include at least the upstream, downstream and midstream. Finally, the flood start time and flood end time in all flood-occurring basins are obtained to calculate the flood duration; all rainfall data within the flood duration are selected in the rainfall table; and the flood monitoring flow within the flood duration is obtained according to the data of the flood peak observation station.
[0054] As a feasible implementation method, the basin average rainfall data is calculated by first counting the rainfall every 5 minutes according to the station dimension, then counting the cumulative rainfall at each station, and finally calculating the regional average rainfall at intervals of 5 minutes. The regional average rainfall adopts the arithmetic mean method.
[0055] Calculation of rainfall duration: rainfall duration = timestamp of the next rainfall – timestamp of the previous rainfall + duration of the previous rainfall.
[0056] Data conversion of rainfall center point: Because the rainfall center point is divided into three values, upstream, midstream and downstream, it is a dummy variable and cannot be directly brought into the function as a characteristic value. Therefore, two virtual variables A and B are taken in the present invention, and the values of the two virtual variables are 0 or 1. The variable value combination corresponding to the upstream is (1, 0), the variable value combination corresponding to the downstream is (0, 1), and the variable value combination corresponding to the midstream is (1, 1).
[0057] Flood monitoring flow acquisition: According to the basin information where the flood occurred, select all the measuring stations in the basin from the basic information table of the measuring stations, and then select the data of all the measuring stations in this time period from the rainfall table according to the start time and end time of the flood, and then select the flow information of the corresponding time period according to the flood peak observation station.
[0058] Furthermore, the average rainfall in the watershed obtained is calculated by Cartesian product with the flood monitoring flow, and the watersheds are grouped according to the timestamp of the average rainfall in each Cartesian product. The group with the smallest time difference is determined, and the flood monitoring flow in the preset characteristic value is updated based on the flood monitoring flow in the group. Finally, the preset characteristic values corresponding to all historical flood events are constructed as a training data set.
[0059] As a feasible implementation method, since the collection frequency of flow data and rainfall data is inconsistent, the data cannot correspond one to one, so it is necessary to fill flow data for part of the rainfall data. When filling flow data, first perform a Cartesian product operation on the collected rainfall data and the collected flow data. Then, in the distributed processing engine Flink, group the rainfall data according to the timestamp, take the data with the smallest time difference in the group (that is, the flow data collected closest to the rainfall data), and update the flow data in the training data set.
[0060] In one embodiment, Figure 2 An example diagram of a training data set provided by an embodiment of the present invention, such as Figure 2 As shown, the final training data includes: flood ID, basin average rainfall (DRP), rainfall duration (TM), rainfall center point (A, B), monitoring flow (Q), and rainfall duration (DURATION).
[0061] S103. Generate curve functions corresponding to various historical flood events based on the training data set.
[0062] Specifically, based on the training data in the training data set, the Sklearn library of Python is used to generate curve functions corresponding to each historical flood event; the curve function is used to describe the functional relationship between the monitored flow and the average rainfall in the basin, rainfall duration, and rainfall center point.
[0063] As a feasible implementation method, based on the prepared training data, the Sklearn library of Python is used to generate the curve function corresponding to each historical flood event. The function mainly describes the functional relationship between the monitored flow and the average rainfall in the basin, rainfall duration, and rainfall center point. There is a curve function corresponding to each monitored flow and the average rainfall in the basin, rainfall duration, and rainfall center point, so each historical flood event corresponds to four curve functions.
[0064] S104: Determine corresponding real-time characteristic values according to the hydrological data of the current rainfall.
[0065] Specifically, the hydrological data of the current rainfall is obtained in real time, and the corresponding real-time characteristic values are calculated based on the hydrological data; wherein the real-time characteristic values include at least: real-time average rainfall in the basin, real-time rainfall duration, real-time rainfall center point and real-time flood monitoring flow.
[0066] As a feasible implementation method, the corresponding basin average rainfall (drp), rainfall duration (tm), rainfall center point (a, b) and monitoring flow (q) are calculated in real time based on the current rainfall hydrological data.
[0067] S105. Match the real-time characteristic value with the curve function corresponding to each historical flood event to determine the historical flood event that is most similar to the current rainfall.
[0068] Specifically, the calculated real-time average rainfall in the basin, real-time rainfall history and real-time rainfall center point are respectively substituted into the curve function corresponding to each historical flood event to calculate the corresponding flood flow value.
[0069] Furthermore, the variances of the three flood flow values calculated in the same historical flood event are calculated and summed with the real-time flood detection flow to obtain the sum of the variances corresponding to the historical flood event.
[0070] Furthermore, the historical flood event corresponding to the curve function with the smallest sum of variance is determined as the historical flood event most similar to the current rainfall.
[0071] As a feasible implementation method, drp, tm, a, and b are substituted into the curve functions of a certain historical flood event, and the corresponding flow rates Q1, Q2, Q3, and Q4 are calculated respectively. Then the variances of Q1, Q2, Q3, and Q4 are calculated with q respectively, and the four variances are summed. The sum of the variances of the current rainfall and other historical flood events is calculated in the same way. The one with the smallest sum of variances is the historical flood event that is most similar to the current rainfall.
[0072] S106. Call the solution corresponding to the most similar historical flood event in the database.
[0073] Specifically, according to the flood number corresponding to the historical flood event that is most similar to the current rainfall, the corresponding historical flood event information and corresponding solutions are searched and called in the database, and recommended to relevant personnel.
[0074] As a feasible implementation method, corresponding flood event information and corresponding decision-making measures are found according to the flood ID of the most similar historical flood event and recommended to the user.
[0075] This method uses a machine learning algorithm to fit the multivariate linear functions corresponding to each historical flood scenario, then brings the current heavy rainfall related data into each function, calculates the function with the smallest variance, confirms that the historical flood scene corresponding to this function is the most similar historical flood scene, and recommends measures to deal with this flood.
[0076] In addition, the embodiment of the present invention also provides a device for recommending historical similar flood events, such as Figure 3 As shown in the figure, the recommended equipment for similar historical flood events includes:
[0077] at least one processor; and a memory in communication with the at least one processor; wherein,
[0078] The memory stores instructions executable by at least one processor to enable the at least one processor to perform:
[0079] Collecting historical flood event information, performing feature extraction on the historical flood event information, and constructing a training data set;
[0080] Based on the training data set, generating curve functions corresponding to each historical flood event;
[0081] According to the hydrological data of the current rainfall, the corresponding real-time characteristic value is determined;
[0082] According to the real-time characteristic value, matching is performed with the curve function corresponding to each historical flood event to determine the historical flood event that is most similar to the current rainfall;
[0083] The solution corresponding to the most similar historical flood event is called in the database.
[0084] Finally, an embodiment of the present invention further provides a storage medium, which is a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, each of which includes instructions, and when the instructions are executed by a terminal, the terminal executes:
[0085] Collecting historical flood event information, performing feature extraction on the historical flood event information, and constructing a training data set;
[0086] Based on the training data set, generating curve functions corresponding to each historical flood event;
[0087] According to the hydrological data of the current rainfall, the corresponding real-time characteristic value is determined;
[0088] According to the real-time characteristic value, matching is performed with the curve function corresponding to each historical flood event to determine the historical flood event that is most similar to the current rainfall;
[0089] The solution corresponding to the most similar historical flood event is called in the database.
[0090] The present invention solves the problems of recommending similar historical flood events in the flood prevention process, recommending flood prevention decision-making and scheduling plans, fitting historical flood event functions by machine learning, statistical analysis of current rainfall-related hydrological data, and selecting the most similar function.
[0091] The present invention is mainly used in water conservancy and flood control business scenarios. The machine learning method is used to generate functions corresponding to each historical flood event, and then Flink is used to prepare training data and calculate the current real-time rainfall data. The present invention selects the basin's cumulative surface rainfall, rainfall duration, rainfall center point, and basin flood observation point flow as characteristic values, and can automatically recommend similar historical flood events and the decision-making deployment information at the time. And provide external recommendation services for similar historical flood events. The function is clear and the operation is simple, and it can be operated and viewed directly on the browser page or mobile terminal.
[0092] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0093] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0094] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0095] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0096] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0098] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0099] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0100] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0101] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0102] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0103] Each embodiment of the present invention is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.
[0104] The above describes specific embodiments of the present invention. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0105] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for recommending similar historical flood events, characterized in that: The method comprises: Collecting historical flood event information, performing feature extraction on the historical flood event information, and constructing a training data set; Based on the training data set, generating curve functions corresponding to each historical flood event; According to the hydrological data of the current rainfall, the corresponding real-time characteristic values are determined, including: Acquire the hydrological data of current rainfall in real time, and calculate the corresponding real-time characteristic values according to the hydrological data; wherein the real-time characteristic values at least include: real-time average rainfall in the basin, real-time rainfall duration, real-time rainfall center point and real-time flood monitoring flow; According to the real-time characteristic value, matching is performed with the curve function corresponding to each historical flood event to determine the historical flood event most similar to the current rainfall, specifically including: Substitute the calculated real-time basin average rainfall, real-time rainfall history and real-time rainfall center point into the curve function corresponding to each historical flood event to calculate the corresponding flood flow value; The three flood flow values calculated in the same historical flood event are respectively subjected to variance calculation and summation with the real-time flood monitoring flow to obtain the sum of variances corresponding to the historical flood event; The historical flood event corresponding to the curve function with the smallest sum of variance is determined as the historical flood event most similar to the current rainfall; the curve function is used to describe the functional relationship between the monitored flow and the average rainfall in the basin, the rainfall duration, and the rainfall center point; The solution corresponding to the most similar historical flood event is called in the database.
2. A method for recommending historically similar flood events according to claim 1, characterized in that: Collect historical flood information, including: All historical flood event information is read from the historical flood reservoir and the historical water condition database; wherein the historical flood event information includes at least: flood number, flood occurrence basin, flood start time, flood end time, rainfall center point, flood peak observation station data and flood peak flow.
3. A method for recommending historically similar flood events according to claim 2, characterized in that: Feature extraction is performed on the historical flood event information to construct a training data set, specifically including: In the historical flood event information, preset characteristic values are calculated to complete feature extraction; wherein the preset characteristic values at least include: average rainfall in the basin, rainfall duration, rainfall center point and flood monitoring flow; Cartesian product operation is performed on the obtained basin average rainfall and flood monitoring flow, and the basin average rainfall in each Cartesian product is grouped according to the timestamp; Determine a group with the smallest time difference, and update the flood monitoring flow in the preset characteristic value based on the flood monitoring flow in the group; The preset characteristic values corresponding to all historical flood events are constructed as the training data set.
4. A method for recommending historically similar flood events according to claim 3, characterized in that: In the historical flood event information, the preset characteristic value is calculated to complete the feature extraction, which specifically includes: According to the flood peak observation station data, the rainfall in each preset time period and the cumulative rainfall of each flood peak observation station are counted, and the average rainfall of each river basin is calculated at intervals of the preset time period; According to the rainfall timestamps of adjacent rainfall events, the rainfall duration of each rainfall event is calculated; Two virtual variables are created, and different combinations of the two virtual variables represent different rainfall center points; wherein the value of the virtual variable is 0 or 1; and the rainfall center points include at least upstream, downstream and midstream; Obtain the flood start time and flood end time in all flood-occurring basins and calculate the flood duration; select all rainfall data within the flood duration in the rainfall table; and obtain the flood monitoring flow within the flood duration based on the flood peak observation station data.
5. The method for recommending historically similar flood events according to claim 1, characterized in that: Based on the training data set, a curve function corresponding to each historical flood event is generated, specifically including: Based on the training data in the training data set, the Sklearn library of Python is used to generate the curve functions corresponding to each historical flood event.
6. A method for recommending historically similar flood events according to claim 1, characterized in that: The solution corresponding to the most similar historical flood event is called in the database, specifically including: According to the flood number corresponding to the historical flood event that is most similar to the current rainfall, the corresponding historical flood event information and corresponding solutions are searched and called in the database, and recommended to relevant personnel.
7. A device for recommending historical similar flood events, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, so that the at least one processor can execute a method for recommending historical similar flood events according to any one of claims 1-6.
8. A storage medium, characterized in that: The storage medium is a non-volatile computer-readable storage medium, and the non-volatile computer-readable storage medium stores at least one program, each of which includes instructions, and when the instructions are executed by the terminal, the terminal executes a method for recommending historical similar flood events according to any one of claims 1-6.
