Rainstorm payment prediction method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a rainstorm payment prediction method and device, electronic equipment and a storage medium, and belongs to the technical field of financial science and technology. The method comprises the following steps: receiving insuring area information and current precipitation; obtaining a target historical precipitation amount of the insuring area and historical precipitation time information of the target historical precipitation amount according to the insuring area information; according to the historical precipitation time information, performing recurrence period calculation on the target historical precipitation amount to obtain a precipitation recurrence period of each target historical precipitation amount; performing precipitation interval division on the target historical precipitation according to the precipitation reproduction period to obtain precipitation partitions and the partition number of the precipitation partitions; performing compensation data prediction according to preset compensation constraint data and the number of the partitions to obtain target compensation prediction data of each precipitation partition; and screening rainstorm compensation prediction data from the target compensation prediction data according to the precipitation partition and the current precipitation. According to the embodiment of the invention, the accuracy of rainstorm payment prediction can be improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to a method and device for predicting rainstorm compensation, an electronic device and a storage medium. Background Art

[0002] In the insurance field, there are more and more types of insurance products, and the problem of the rationality of insurance compensation has arisen. If the insurance compensation is unreasonable, it will affect the insurance rate and insurance service income. Therefore, how to make more accurate insurance compensation has become a focus of attention in the insurance field. For example, in the heavy rain compensation scenario, the compensation structure of heavy rain is generally formulated based on manual experience, and the manually formulated compensation structure is not objective. People with different experiences formulate different compensation structures, resulting in inconsistent compensation structures, which affects the accuracy of heavy rain compensation predictions. Therefore, how to improve the accuracy of heavy rain compensation predictions has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The main purpose of the embodiments of the present application is to propose a rainstorm compensation prediction method and device, electronic equipment and storage medium, aiming to improve the accuracy of rainstorm compensation prediction.

[0004] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a rainstorm compensation prediction method, the method comprising:

[0005] Receiving a rainstorm compensation request; wherein the rainstorm compensation request includes: insured area information and current precipitation;

[0006] Acquire historical heavy rainfall data of the insured area according to the insured area information; wherein the historical heavy rainfall data includes: target historical rainfall amount and historical rainfall time information of the target historical rainfall amount;

[0007] Calculating the recurrence period of the target historical precipitation according to the historical precipitation time information to obtain the precipitation recurrence period of each target historical precipitation;

[0008] Dividing the target historical precipitation into precipitation intervals according to the precipitation recurrence period to obtain precipitation partitions and the number of partitions of the precipitation partitions;

[0009] Predicting compensation data according to preset compensation constraint data and the number of partitions to obtain target compensation prediction data for each precipitation partition;

[0010] The rainstorm compensation forecast data is screened out from the target compensation forecast data according to the precipitation partitions and the current precipitation.

[0011] In some embodiments, the calculating the recurrence period of the target historical precipitation according to the historical precipitation time information to obtain the precipitation recurrence period of each target historical precipitation includes:

[0012] Acquire the historical precipitation time information of the same target historical precipitation amount to obtain the selected precipitation time information;

[0013] Obtaining the time interval between two adjacent selected precipitation time information to obtain the precipitation time interval;

[0014] The recurrence period of the target historical precipitation is calculated according to the precipitation time interval to obtain the precipitation recurrence period.

[0015] In some embodiments, dividing the target historical precipitation into precipitation intervals according to the precipitation recurrence period to obtain precipitation partitions and the number of partitions of the precipitation partitions includes:

[0016] Filtering selected historical precipitation amounts in each of the preset precipitation cycle intervals from the target historical precipitation amounts according to the preset precipitation cycle intervals and the precipitation recurrence period;

[0017] Performing fitting processing on the selected historical precipitation to obtain historical precipitation fitting data;

[0018] Extracting a fitting upper limit value and a fitting lower limit value from the historical precipitation fitting data;

[0019] Perform interval construction according to the fitting upper limit value and the fitting lower limit value to obtain the precipitation partition;

[0020] The number of the precipitation partitions is obtained to obtain the number of partitions.

[0021] In some embodiments, the compensation constraint data includes: a compensation change rate limit interval, a total compensation limit rate and a total compensation limit data, wherein the compensation change rate limit interval is a change rate limit interval of the compensation forecast data between the two precipitation partitions;

[0022] The compensation data prediction is performed according to the preset compensation constraint data and the number of partitions to obtain the target compensation prediction data for each precipitation partition, including:

[0023] Compensation data prediction is performed based on the compensation change rate limit interval, the number of partitions and the total compensation limit data to obtain preliminary compensation prediction data for each precipitation partition;

[0024] The preliminary compensation prediction data is screened according to the total compensation limit rate and the total compensation limit data to obtain the target compensation prediction data.

[0025] In some embodiments, the screening process of the preliminary compensation prediction data according to the total compensation limit rate and the total compensation limit data to obtain the target compensation prediction data includes:

[0026] The preliminary compensation prediction data are spliced ​​to obtain total compensation prediction data;

[0027] Obtaining the ratio between the total compensation prediction data and the total compensation limit data to obtain a total compensation prediction rate;

[0028] The preliminary compensation prediction data is screened according to the total compensation limit rate and the total compensation prediction rate to obtain the target compensation prediction data.

[0029] In some embodiments, obtaining historical heavy rainfall data of the insured area according to the insured area information includes:

[0030] Acquire target historical precipitation data of the insured area according to the insured area information; wherein the target historical precipitation data includes: candidate historical precipitation amount and candidate precipitation time information of the candidate historical precipitation amount;

[0031] Screening the candidate historical precipitation according to a preset precipitation threshold to obtain a target historical precipitation;

[0032] The candidate precipitation time information of the target historical precipitation is acquired to obtain the historical precipitation time information.

[0033] In some embodiments, acquiring target historical precipitation data of the insured area according to the insured area information includes:

[0034] Acquire original historical precipitation data collected by an observation site and an original recurrence period of the original historical precipitation data according to the insured area information; wherein the observation site is used to observe the precipitation data of the insured area;

[0035] Filtering out maximum historical precipitation data from the original historical precipitation data according to the original recurrence period;

[0036] The maximum historical precipitation data is used as the target historical precipitation data.

[0037] To achieve the above-mentioned purpose, a second aspect of the embodiment of the present application provides a rainstorm compensation prediction device, the device comprising:

[0038] A request receiving module, used to receive a request for a rainstorm compensation; wherein the rainstorm compensation request includes: information about the insured area and current precipitation;

[0039] A data acquisition module, used for acquiring historical heavy rainfall data of the insured area according to the insured area information; wherein the historical heavy rainfall data includes: target historical precipitation and historical precipitation time information of the target historical precipitation;

[0040] A recurrence period calculation module, used to calculate the recurrence period of the target historical precipitation according to the historical precipitation time information, and obtain the precipitation recurrence period of each target historical precipitation;

[0041] An interval division module, used for dividing the target historical precipitation into precipitation intervals according to the precipitation recurrence period, and obtaining the precipitation partitions and the number of partitions of the precipitation partitions;

[0042] A compensation data prediction module, used to predict compensation data according to preset compensation constraint data and the number of partitions, and obtain target compensation prediction data for each precipitation partition;

[0043] A data screening module is used to screen out the rainstorm compensation forecast data from the target compensation forecast data according to the precipitation partition and the current precipitation.

[0044] To achieve the above objectives, a third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0045] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0046] The rainstorm compensation prediction method and device, electronic device and storage medium proposed in the present application first obtain the historical heavy precipitation data in the insured area, and the historical heavy precipitation data includes the target historical precipitation and the historical precipitation time information of the target historical precipitation. First, the recurrence period of the target historical precipitation is calculated according to the historical precipitation time information to obtain the precipitation recurrence period of each target historical precipitation, so as to determine the period of repeated occurrence of each target historical precipitation. Then, the target historical precipitation is divided into precipitation intervals according to the precipitation recurrence period to obtain the precipitation intervals and the number of partitions of the precipitation intervals, so as to realize objective precipitation interval division that conforms to the heavy rainfall situation. After the precipitation partitions are determined, the target compensation prediction data of each precipitation partition is predicted according to the compensation constraint data and the number of partitions of the precipitation partitions, so as to realize the automatic construction of the rainstorm compensation structure, and the constructed rainstorm compensation structure is objective. When making a rainstorm compensation forecast, based on the target compensation forecast data corresponding to each precipitation zone, the rainstorm compensation forecast data is screened out from the target compensation forecast data according to the current precipitation and precipitation zone, and the obtained rainstorm compensation forecast data is more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of a rainstorm compensation prediction method provided in an embodiment of the present application;

[0048] Figure 2 It is a schematic diagram of generating a heavy rain compensation request in the heavy rain compensation prediction method provided in an embodiment of the present application;

[0049] Figure 3 yes Figure 1 Flow chart of step S102 in FIG.

[0050] Figure 4 yes Figure 3 Flow chart of step S301 in FIG.

[0051] Figure 5 yes Figure 1 Flow chart of step S103 in FIG.

[0052] Figure 6 yes Figure 1 Flow chart of step S104 in FIG.

[0053] Figure 7 yes Figure 1 Flow chart of step S105 in FIG.

[0054] Figure 8 yes Figure 7 Flowchart of step S702 in FIG.

[0055] Fig. 9 It is a structural schematic diagram of a rainstorm compensation prediction device provided in an embodiment of the present application;

[0056] Fig.10 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0060] First, some nouns involved in this application are analyzed:

[0061] Artificial intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. AI is a branch of computer science that attempts to understand the essence of intelligence and produce a new type of intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robots, language recognition, image recognition, natural language processing and expert systems. AI can simulate the information process of human consciousness and thinking. AI is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0062] Observation sites: refers to fixed or mobile equipment or facilities used to obtain and record natural science data such as environment, climate, geology, biology, etc. These sites are used for scientific research, environmental monitoring, climate prediction, geological surveys, etc.

[0063] Extreme Value Theory (EVT): is a statistical method used to analyze the probability and frequency of extreme events. The theory assumes that in a given random variable, there are extreme values ​​and frequencies, which can be used to predict the probability and impact of extreme events.

[0064] Data fitting: refers to the process of using statistical models or algorithms to fit known data. The purpose is to fit the data into a mathematical model in order to predict future data or solve practical problems.

[0065] Optimization algorithm: A type of mathematical algorithm that aims to find the optimal solution to the objective function.

[0066] With the increase in the categories of insurance products, how to formulate an insurance compensation structure that meets the needs of policyholders and insurance benefits has also become a focus of attention in the insurance field. However, the traditional insurance compensation structure mainly relies on the experience of insurance experts, and insurance experts in different fields formulate different insurance compensation structures, resulting in inconsistent insurance compensation structures and affecting the insurance rate. For example, in the heavy rain compensation scenario, it is necessary to collect precipitation in the target area through multiple observation stations and make segmented compensation based on the precipitation. However, the precipitation segmentation of heavy rain compensation and the compensation data for each segment are set by manual experience, which is subjective and affects the accuracy of compensation.

[0067] Based on this, the embodiments of the present application provide a rainstorm compensation prediction method and device, an electronic device, and a storage medium, which are intended to automatically formulate precipitation partitions based on the historical heavy rainfall data of the target area, and predict the target compensation prediction data of each precipitation partition based on the compensation constraint data and the number of partitions, so that when making rainstorm compensation, the corresponding rainstorm compensation prediction data can be found in the target compensation prediction data based on the current precipitation and precipitation partition. Therefore, an objective rainstorm compensation structure is automatically formulated based on the heavy rainfall data and the compensation constraint data to achieve objective rainstorm compensation prediction and improve the accuracy of rainstorm compensation.

[0068] The rainstorm compensation prediction method and device, electronic device and storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the rainstorm compensation prediction method in the embodiments of the present application is described.

[0069] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0070] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0071] The rainstorm compensation prediction method provided in the embodiment of the present application relates to the field of financial technology technology. The rainstorm compensation prediction method provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server side, and can also be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the rainstorm compensation prediction method, etc., but is not limited to the above forms.

[0072] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can 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. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0073] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0074] Figure 1 is an optional flowchart of the rainstorm compensation prediction method provided in the embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S106.

[0075] Step S101, receiving a rainstorm compensation request; wherein the rainstorm compensation request includes: insured area information and current precipitation;

[0076] Step S102, obtaining historical heavy precipitation data of the insured area according to the insured area information; wherein the historical heavy precipitation data includes: target historical precipitation and historical precipitation time information of the target historical precipitation;

[0077] Step S103, calculating the recurrence period of the target historical precipitation according to the historical precipitation time information, and obtaining the precipitation recurrence period of each target historical precipitation;

[0078] Step S104, dividing the target historical precipitation into precipitation intervals according to the precipitation recurrence period, and obtaining precipitation partitions and the number of partitions of the precipitation partitions;

[0079] Step S105, predicting compensation data according to preset compensation constraint data and the number of partitions, and obtaining target compensation prediction data for each precipitation partition;

[0080] Step S106, filtering out rainstorm compensation prediction data from the target compensation prediction data according to the precipitation partitions and the current precipitation.

[0081] Steps S101 to S106 shown in the embodiment of the present application are to obtain the historical heavy precipitation data of the insured area corresponding to the insured area information, and the historical heavy precipitation data includes the target historical precipitation and the historical precipitation time information of the target historical precipitation, calculate the precipitation recurrence period of each target historical precipitation according to the historical precipitation time information, and determine the period of recurrence of each target historical precipitation. According to the precipitation recurrence period, the target historical precipitation is divided into precipitation intervals to obtain precipitation partitions and the number of partitions of the precipitation partitions, so as to realize the automatic setting of multiple precipitation compensation intervals. Then, the target compensation prediction data of each precipitation partition is predicted according to the compensation constraint data and the number of partitions, so as to determine the compensation prediction data corresponding to each precipitation compensation interval, and realize the automatic generation of the heavy rain compensation structure, without relying on manual experience, to obtain an objective heavy rain compensation structure that meets the precipitation conditions and compensation requirements of the insured area. Therefore, when it is necessary to predict heavy rain compensation, the heavy rain compensation prediction data is screened out from the target compensation prediction data according to the current precipitation and precipitation partition, and the automatic prediction of the heavy rain compensation data is realized to obtain objective heavy rain compensation prediction data and improve the accuracy of the heavy rain compensation prediction.

[0082] In step S101 of some embodiments, the rainstorm compensation request is a request sent by the user end or an automatically generated request for rainstorm compensation prediction. The rainstorm compensation request includes: insurance area information and current precipitation, the insurance area information represents the area insured by the insured, and the current precipitation is the current precipitation of the insurance area.

[0083] It should be noted that the rainstorm compensation prediction method is applied to the server. The insured actively sends a rainstorm compensation request to the server through the mini-program, mobile client, web page, etc. on the user side. The precipitation in the insured area can also be automatically monitored to obtain the monitored precipitation. When the monitored precipitation reaches the preset precipitation threshold, a rainstorm compensation request is automatically generated. This embodiment does not impose specific restrictions on the method of generating the rainstorm compensation request.

[0084] For example, if user A selects a rainstorm compensation product on the insurance service software and insures his area P1 to obtain a rainstorm insurance policy. The precipitation in area P1 is monitored regularly to obtain the monitored precipitation. When the monitored precipitation reaches the lowest precipitation partition in the rainstorm compensation structure, a rainstorm compensation request is automatically generated, and a rainstorm compensation forecast is performed based on the rainstorm compensation request. Figure 2 As shown in the figure, the current insured area is displayed as area P1 on the rainstorm insurance business form, and the current insurance status is "rainstorm compensation forecasting", so that the insured can understand the current compensation progress. Therefore, by automatically generating rainstorm compensation requests, the claim settlement operation can be realized without manual initiation, which improves the insured's satisfaction with the rainstorm compensation product.

[0085] In step S102 of some embodiments, the historical heavy precipitation data is data related to the heavy precipitation event when the heavy precipitation event occurs, and the heavy precipitation event is an event in which the precipitation reaches a preset precipitation threshold. It should be noted that multiple observation stations are set up in the insured area, and the observation stations are used to monitor the precipitation conditions in the insured area and record the precipitation conditions. When any observation station in the insured area monitors that the precipitation reaches the preset precipitation threshold, it is defined as the start of the heavy precipitation event, until the precipitation monitored by all observation stations in the insured area is less than the preset precipitation threshold, the end of the heavy precipitation event is defined.

[0086] See also Figure 3 In some embodiments, step S102 may include but is not limited to steps S301 to S303:

[0087] Step S301, obtaining target historical precipitation data of the insured area according to the insured area information; wherein the target historical precipitation data includes: candidate historical precipitation amount and candidate precipitation time information of the candidate historical precipitation amount;

[0088] Step S302, screening candidate historical precipitations according to a preset precipitation threshold to obtain target historical precipitation;

[0089] Step S303, obtaining candidate precipitation time information of the target historical precipitation amount, and obtaining the historical precipitation time information.

[0090] In step S301 of some embodiments, the candidate historical precipitation is all the historical precipitation of the insured area, that is, the precipitation recorded when precipitation occurred in the insured area in the past, and the candidate precipitation time information is the precipitation time corresponding to the candidate historical precipitation. In this embodiment, the historical precipitation of the insured area before the preset period is collected as the candidate historical precipitation, and the preset period setting range is relatively large, generally more than 100 years, so the collected historical heavy precipitation data is more representative, and the constructed rainstorm compensation structure is more reasonable. If the preset period setting range is small, the collected historical heavy precipitation data is not representative, then the precipitation partitions based on the small range of historical heavy precipitation data do not conform to the actual heavy rainfall situation in the insured area.

[0091] In step S302 of some embodiments, as disclosed above, this embodiment defines a precipitation event with a precipitation reaching a preset precipitation threshold as a heavy precipitation event, and the construction of the rainstorm compensation structure mainly requires the collection of precipitation when the heavy precipitation event occurs, and the precipitation corresponding to the normal precipitation event does not need to be collected. Therefore, the candidate historical precipitation that is greater than or equal to the preset precipitation threshold is used as the target historical precipitation, and the target historical precipitation is the precipitation when the heavy precipitation event occurs, that is, the precipitation that needs to be compensated. It should be noted that the preset precipitation threshold can be set by experts with rich experience in rainstorm compensation, or it can be formulated according to the precipitation corresponding to the rainstorm damage situation. This embodiment does not make specific restrictions on the preset precipitation threshold. For example, if the preset precipitation threshold is formulated based on the precipitation corresponding to the rainstorm damage situation, the rainstorm damage data corresponding to each candidate historical precipitation is first obtained, and the rainstorm damage data can be the manpower and resources consumed by rainstorm protection, as well as the resource loss caused by the rainstorm. If the rainstorm damage data reaches the preset damage threshold, the candidate historical precipitation corresponding to the rainstorm damage data is used as the preset precipitation threshold. Therefore, by judging the loss caused by precipitation and setting the preset precipitation threshold, the rainstorm compensation structure formulated based on the target historical precipitation selected by the preset precipitation threshold is more in line with the rainstorm compensation needs.

[0092] In step S303 of some embodiments, there are multiple target historical precipitation amounts, and the candidate precipitation time information corresponding to each target historical precipitation amount is used as the historical precipitation time information, that is, the time point when each heavy precipitation event occurs. It should be noted that heavy precipitation events generally occur within a time period, and in order to facilitate the division of precipitation intervals, this embodiment selects a time point in the time period when the heavy precipitation event occurs as the historical precipitation time information. Specifically, the time information when the heavy precipitation event starts can be used as the historical precipitation time information, and the time information when the heavy precipitation event ends can be used as the historical precipitation time information, or the middle time from the start to the end of the heavy precipitation event can be used as the historical precipitation time information. This embodiment does not impose specific restrictions on the selection of historical precipitation time information.

[0093] For example, if the preset precipitation threshold is 50 mm, there are 5 observation stations in the insured area, and the 5 observation stations are defined as the first observation station G1, the second observation station G2, the third observation station G3, the fourth observation station G4 and the fifth observation station G5 respectively. If the second observation station G2 observes precipitation greater than or equal to 50 mm at 20:00, even if the precipitation observed by other observation stations does not reach 50 mm, it is considered to be the beginning of a heavy precipitation event. Then at 22:00, the first observation station G1, the third observation station G3 and the fifth observation station G5 all observe precipitation greater than 50 mm. Until 06:00 the next day, the precipitation observed by all observation stations is less than 50 mm, which is defined as the end of a heavy precipitation event. Therefore, 20:00 can be used as historical precipitation time information, and one precipitation amount is selected from the multiple precipitation amounts collected by each observation station from 20:00 to 6:00 the next day as the target historical precipitation amount.

[0094] In steps S301 to S303 shown in this embodiment, the candidate historical precipitation that is greater than or equal to the preset precipitation threshold is used as the target historical precipitation, and the candidate precipitation time information corresponding to the target historical precipitation is used as the historical precipitation time information to determine the precipitation and precipitation time corresponding to the heavy precipitation event. Therefore, the precipitation partitions divided according to the target historical precipitation and the historical precipitation time information are more in line with the heavy precipitation situation, and a more objective precipitation partition is formulated, making the rainstorm compensation prediction more reasonable.

[0095] See also Figure 4 In some embodiments, step S301 may include but is not limited to steps S401 to S403:

[0096] Step S401, obtaining original historical precipitation data collected by an observation station and an original recurrence period of the original historical precipitation data according to the insured area information; wherein the observation station is used to observe the precipitation data of the insured area;

[0097] Step S402, filtering out the maximum historical precipitation data from the original historical precipitation data according to the original recurrence period;

[0098] Step S403: taking the maximum historical precipitation data as the target historical precipitation data.

[0099] In step S401 of some embodiments, as disclosed above, the precipitation conditions in the insured area are observed by multiple observation stations, and during the period of heavy precipitation events, multiple observation stations will collect multiple precipitation amounts and combine them into original historical precipitation data. It should be noted that each original historical precipitation data corresponds to a historical time information, and the time interval between two adjacent historical time information of the same original historical precipitation data is used as the original recurrence period of the original historical precipitation data. However, because the insured area is relatively large and the observation stations are relatively dispersed, the original recurrence periods corresponding to the same historical precipitation data collected by different observation stations are different, and it is necessary to select target historical precipitation data that is representative of rainstorm compensation.

[0100] In some embodiments, in step S402 to step S403, because the observation sites are distributed in different areas, there are multiple original historical precipitation data corresponding to the same original recurrence period. By taking the largest original historical precipitation data in the same original recurrence period as the target historical precipitation data, the rainstorm compensation structure constructed according to the target historical precipitation data is more in line with the insurance benefits. Specifically, this embodiment uses extreme value estimation to select the target historical precipitation data from the original historical precipitation data, that is, divide the multiple original historical precipitation data into original historical precipitation data groups according to the original recurrence period, and then select the maximum value in each original historical precipitation data group as the target historical precipitation data.

[0101] For example, if the first observation station G1 observes 80 mm of precipitation with an original recurrence period of 3 years, the second observation station G2 observes 85 mm of precipitation with an original recurrence period of 3 years, the third observation station G3 observes 90 mm of precipitation with an original recurrence period of 3 years, the fourth observation station G4 observes 70 mm of precipitation with an original recurrence period of 3 years, and the fifth observation station G5 observes 75 mm of precipitation with an original recurrence period of 3 years. It can be seen that the precipitation observed by different observation stations in the same insured area with the same original recurrence period is different. In order to facilitate the construction of the rainstorm compensation structure of the insured area, the maximum 90 mm observed by the third observation station G3 is used as the target historical precipitation data with an original recurrence period of 3 years, so as to facilitate the subsequent screening of more stable historical heavy precipitation data based on the target historical precipitation data.

[0102] In steps S401 to S403 illustrated in the present embodiment, by acquiring the original historical precipitation data of multiple observation sites and the original recurrence period of the original historical precipitation data, the largest original historical precipitation data in the same original recurrence period is used as the target historical precipitation data. Then, based on the target historical precipitation data, stable and representative historical heavy precipitation data can be extracted to construct a stable rainstorm compensation structure.

[0103] See also Figure 5In some embodiments, step S103 may include but is not limited to steps S501 to S503:

[0104] Step S501, obtaining historical precipitation time information of the same target historical precipitation amount to obtain selected precipitation time information;

[0105] Step S502, obtaining the time interval between two adjacent selected precipitation time information to obtain the precipitation time interval;

[0106] Step S503, calculating the recurrence period of the target historical precipitation according to the precipitation time interval to obtain the precipitation recurrence period.

[0107] In step S501 of some embodiments, there are multiple target historical precipitation amounts, and the historical precipitation time information of the same target historical precipitation amount is different. The historical precipitation time information corresponding to the same target historical precipitation amount is used as the selected precipitation time information, and there are also multiple selected precipitation time information.

[0108] In step S502 of some embodiments, multiple selected precipitation time information are sorted in time order, and the time interval between two adjacent selected precipitation time information is used as the precipitation time interval. It should be noted that, because there are multiple selected precipitation time information, there are also multiple precipitation time intervals. In this example, the average value of multiple precipitation time intervals can be calculated to obtain the final precipitation time interval, or the minimum or maximum precipitation time interval from multiple precipitation time intervals can be taken as the final precipitation time interval, and this embodiment does not specifically limit the determination of the precipitation time interval.

[0109] In step S503 of some embodiments, the recurrence period of the target historical precipitation is calculated according to the precipitation time interval, that is, the precipitation time interval is used as the precipitation recurrence period to determine the period of recurrence of each target historical precipitation. It should be noted that the probability of occurrence of each target historical precipitation within a year can be determined according to the precipitation time interval, and the precipitation recurrence period can be determined according to the inverse of the occurrence probability. Specifically, if the probability of occurrence of the target historical precipitation within a year is defined as P, the precipitation recurrence period is N, and the relationship between the precipitation recurrence period and the occurrence probability can be expressed as shown in formula (1):

[0110]

[0111] It can be seen from formula (1) that the longer the precipitation recurrence period, the lower the frequency of occurrence of the target historical precipitation in a year. For example, if the target historical precipitation is 100 mm and occurs twice in 50 years, the precipitation recurrence period of the target historical precipitation of 100 mm is determined to be 25 years, and the probability of occurrence in a year is 4%. If the target historical precipitation is 200 mm and occurs only once in 100 years, the precipitation recurrence period of the target historical precipitation of 200 mm is determined to be 100 years, and the probability of occurrence in a year is 1%. Therefore, the probability of occurrence of each target historical precipitation in a year can be known through the precipitation recurrence period, so dividing the precipitation zone according to the precipitation recurrence period will also be more in line with the economic benefits of rainstorm compensation.

[0112] In steps S501 to S503 shown in this embodiment, the time interval corresponding to the same target historical precipitation is determined as the precipitation time interval, and the precipitation time interval is determined as the precipitation recurrence period of each target historical precipitation, so as to determine the probability of occurrence of each target historical precipitation according to the precipitation recurrence period. Then, dividing the precipitation into zones according to the precipitation recurrence period will be more in line with the economic benefits of heavy rain compensation prediction, and a more objective and accurate heavy rain compensation structure will be obtained.

[0113] See also Figure 6 In some embodiments, step S104 may include but is not limited to steps S601 to S605:

[0114] Step S601, selecting selected historical precipitation in each preset precipitation period interval from the target historical precipitation according to the preset precipitation period interval and the precipitation recurrence period;

[0115] Step S602, performing fitting processing on the selected historical precipitation to obtain historical precipitation fitting data;

[0116] Step S603, extracting a fitting upper limit value and a fitting lower limit value from the historical precipitation fitting data;

[0117] Step S604, constructing intervals according to the fitting upper limit value and the fitting lower limit value to obtain precipitation partitions;

[0118] Step S605, obtaining the number of precipitation partitions to obtain the number of partitions.

[0119] In step S601 of some embodiments, the preset precipitation cycle interval is a pre-set cycle interval, and can also be defined as a cycle divided by a precipitation recurrence period. It should be noted that at least two preset precipitation cycle intervals are set to achieve multiple compensation level settings for a rainstorm compensation structure. Specifically, each precipitation recurrence period corresponds to a target historical precipitation, and the target historical precipitation whose precipitation recurrence period is within the preset precipitation cycle interval is used as the selected historical precipitation to achieve interval division of the target historical precipitation.

[0120] For example, if the preset precipitation period intervals are set to 11, the 11 preset precipitation period intervals are shown in Table 1:

[0121]

[0122]

[0123] Table 1

[0124] Where R is year, and 2-3 years is defined as the first preset precipitation cycle interval, 3-5 years as the second preset precipitation cycle interval, and so on, the last preset time period interval is more than 250 years. If the target historical precipitation with a precipitation recurrence period of 2 years is 60 mm, and the target historical precipitation with a precipitation recurrence period of 3 years is 80 mm, the target historical precipitation corresponding to the precipitation recurrence period within 2-3 years is selected as the selected historical precipitation, and multiple selected historical precipitations are combined into a selected historical precipitation sequence.

[0125] In steps S602 to S604 of some embodiments, because there are multiple selected historical precipitations and they increase in chronological order, in order to output more accurate precipitation partitions, multiple selected historical precipitations in each selected historical precipitation sequence are fitted into historical precipitation fitting data. It should be noted that each preset precipitation cycle interval corresponds to a historical precipitation fitting data, so the fitting upper limit value and the fitting lower limit value are extracted from the historical precipitation fitting data, and the precipitation partition corresponding to each preset precipitation cycle interval is constructed according to the fitting upper limit value and the fitting lower limit value, so as to divide the accurate precipitation partitions.

[0126] For example, if the first preset precipitation period interval is 2-3 years, the fitting lower limit value and the fitting upper limit value are 60mm and 80mm respectively, and the second preset precipitation period interval is 3-5 years, the fitting upper limit value and the fitting lower limit value are 80mm and 100mm respectively, then the first precipitation partition is determined to be [60mm, 80mm], and the second precipitation partition is determined to be [80mm, 100mm].

[0127] In step S605 of some embodiments, as disclosed above, the precipitation partitions are set according to the preset precipitation cycle intervals, so the number of precipitation partitions is also the number of the preset precipitation cycle intervals.

[0128] In steps S601 to S605 illustrated in the present embodiment, the target historical precipitation is divided into selected historical precipitation corresponding to each preset precipitation cycle interval by using preset precipitation cycle intervals and precipitation recurrence periods, and then the selected historical precipitation is fitted into historical precipitation fitting data corresponding to each preset precipitation cycle interval, and precipitation partitions are constructed based on the fitting upper limit value and the fitting lower limit value of the historical precipitation fitting data, so as to construct precipitation partitions that are accurate and conform to the heavy precipitation situation.

[0129] In step S105 of some embodiments, the compensation constraint data is used to constrain the compensation prediction data of each precipitation partition to solve the optimal compensation prediction data of each precipitation partition. It should be noted that the compensation constraint data is pre-set, and can be pre-set by experts with rich experience in insurance compensation, or can be set based on historical compensation data, compensation satisfaction and insurance income data. This embodiment does not impose specific restrictions on the compensation constraint data.

[0130] It should be noted that the compensation constraint data includes: compensation change rate limit interval, total compensation limit rate and total compensation limit data. The compensation change rate limit interval is the change rate limit interval of the compensation forecast data between two precipitation partitions. The total compensation limit rate is also called the expected compensation rate, which is the compensation rate corresponding to all precipitation partitions. The total compensation limit data is the limit of the sum of all compensation forecast data.

[0131] See also Figure 7 In some embodiments, step S105 includes but is not limited to steps S701 to S702:

[0132] Step S701, predicting compensation data according to the compensation change rate limit interval, the number of partitions and the total compensation limit data, and obtaining preliminary compensation prediction data for each precipitation partition;

[0133] Step S702, screening and processing the preliminary compensation prediction data according to the total compensation limit rate and the total compensation limit data to obtain target compensation prediction data.

[0134] In step S701 of some embodiments, this embodiment constructs a payout relationship function according to the payout change rate limit interval, the total payout limit data and the number of partitions, and solves the payout relationship function according to the optimization algorithm to obtain preliminary payout prediction data for each precipitation partition. Specifically, the payout change rate limit interval is to limit the payout change rate between two adjacent precipitation partitions, and the two upper and lower limits of the payout change rate limit interval are defined as the first payout change rate and the second payout change rate, respectively, and the second payout change rate is greater than the first payout change rate. In this embodiment, the candidate payout prediction data is first calculated based on the total payout limit data and the number of partitions, and then the candidate payout prediction data is adjusted according to the first payout change rate and the second payout change rate to obtain preliminary payout prediction data.

[0135] For example, if the first payout change rate is 1.5 times, the second payout change rate is 5 times, the total payout limit data is 30,000, and the number of partitions is 11, first calculate and divide 11 data intervals with increasing data based on 30,000, and then adjust the data interval according to the change rate of 1.5 to 5 to obtain the preliminary payout forecast data.

[0136] In step S702 of some embodiments, there are multiple preliminary compensation prediction data corresponding to each precipitation zone. In order to achieve better compensation prediction, the preliminary compensation prediction data is further screened according to the total compensation limit rate and the total compensation limit data to screen out better target compensation prediction data.

[0137] In steps S701 to S702 shown in the present embodiment, preliminary compensation forecast data corresponding to each precipitation partition is obtained by first predicting the compensation data according to the compensation change rate limit interval, the number of partitions and the total compensation limit data, and then the target compensation forecast data is screened out from the preliminary compensation forecast data according to the total compensation limit rate and the total compensation limit data to obtain more optimized compensation forecast data. Then, a more optimal rainstorm compensation structure is constructed based on the target compensation forecast data and precipitation partitions.

[0138] See also Figure 8 In some embodiments, step S702 may include but is not limited to steps S801 to S803:

[0139] Step S801, concatenating the preliminary compensation prediction data to obtain total compensation prediction data;

[0140] Step S802, obtaining the ratio between the total compensation prediction data and the total compensation limit data to obtain the total compensation prediction rate;

[0141] Step S803, screening and processing the preliminary claim prediction data according to the total claim limit rate and the total claim prediction rate to obtain target claim prediction data.

[0142] In step S801 of some embodiments, the preliminary compensation prediction data corresponding to each precipitation interval is spliced ​​into the total compensation prediction data. It should be noted that there are multiple preliminary compensation prediction data in each precipitation interval, so there are also multiple total compensation prediction data spliced. In this embodiment, the preliminary compensation prediction data is spliced ​​by summing, so as to judge whether the preliminary compensation prediction data corresponding to each precipitation partition meets the set constraint conditions through the total compensation prediction data.

[0143] In step S802 of some embodiments, the total payout prediction rate is obtained by acquiring the ratio between the total payout prediction data and the total payout limit data, and one total payout prediction data corresponds to one total payout prediction rate, and the larger the total payout prediction rate, the larger the total payout prediction data.

[0144] In step S803 of some embodiments, the preliminary claim prediction data is screened according to the total claim limit rate and the total claim prediction rate, that is, the preliminary claim prediction data with a total claim prediction rate less than or equal to the total claim limit rate is selected as the target claim prediction data. It should be noted that if there are multiple preliminary claim prediction data with a total claim prediction rate less than or equal to the total claim limit rate, the preliminary claim prediction data corresponding to the minimum total claim prediction rate is selected as the target claim prediction data.

[0145] For example, the target compensation forecast data corresponding to each precipitation partition is calculated through the above disclosure, and the target compensation forecast data can be the compensation amount, then a rainstorm compensation structure is constructed according to the precipitation partition and the target compensation forecast data, and the rainstorm compensation structure is shown in Table 2:

[0146] Precipitation zone (unit: mm) Compensation amount (unit: 10,000 yuan) 60≤Y＜80 200 80≤Y＜100 300 100≤Y＜130 500 130≤Y＜160 800 160≤Y＜180 1200 180≤Y＜190 2000 190≤Y＜200 3500 200≤Y＜220 6000 220≤Y＜230 8000 Y≥230 11000

[0147] Table 2

[0148] Among them, Y is the rainfall. It can be seen from Table 2 that as the precipitation increases, the compensation amount also increases, so as to achieve an objective prediction of heavy rain compensation.

[0149] In steps S801 to S803 shown in the present embodiment, the preliminary compensation prediction data of each precipitation interval are aggregated into total compensation prediction data, and then the total compensation prediction rate of each total compensation prediction data is calculated based on the total compensation prediction data and the total compensation limit data. Then, the preliminary compensation prediction data corresponding to the total compensation prediction rate being less than or equal to the total compensation limit rate is obtained as the target compensation prediction data, so as to obtain the optimal compensation prediction data that meets the pre-set constraints, so as to construct a more objective and accurate rainstorm compensation structure.

[0150] In step S106 of some embodiments, as disclosed above, after the rainstorm compensation structure is constructed, the target compensation prediction data corresponding to each precipitation partition is set. If rainstorm compensation is required, the current precipitation of the insured area is directly obtained, and the target partition is selected from the precipitation partition according to the current precipitation, and the target compensation prediction data corresponding to the target partition is used as the rainstorm compensation prediction data to achieve an objective and accurate rainstorm compensation prediction. For example, if the current precipitation is 140, it can be seen from Table 2 that the compensation amount is 800.

[0151] The embodiment of the present application receives a rainstorm compensation request sent from a user terminal, and the rainstorm compensation request includes the insured area information and the current precipitation. The original historical precipitation data and the original recurrence period of the original historical precipitation data collected by each observation station in the insured area are obtained according to the insured area information. The original historical precipitation data with the largest original recurrence period is used as the target historical precipitation data to achieve one original recurrence period corresponding to one target historical precipitation data, so as to facilitate the subsequent precipitation zoning. Furthermore, the target historical precipitation data includes: candidate historical precipitation and candidate precipitation time information of the candidate historical precipitation. When constructing the rainstorm compensation structure, it is necessary to collect the precipitation when the heavy precipitation event occurs, and there is no need for the precipitation when the normal precipitation event occurs. Specifically, the candidate historical precipitation that is greater than or equal to the preset precipitation threshold is used as the target historical precipitation, and then the candidate precipitation time information corresponding to the target historical precipitation is obtained as the historical precipitation time information. When constructing a rainstorm compensation structure, the historical precipitation time information of the same target historical precipitation is obtained as the selected precipitation time information, the time interval between adjacent selected precipitation time information is used as the precipitation time interval, and the precipitation time interval is used as the precipitation recurrence period of each target historical precipitation.

[0152] After the precipitation recurrence period is determined, the target historical precipitation whose precipitation recurrence period is in the preset precipitation period interval is used as the selected historical precipitation in the preset precipitation period interval, and then multiple selected historical precipitations are fitted into historical precipitation fitting data in the preset precipitation period interval. The fitting lower limit value of the historical precipitation fitting data is used as the lower limit value of the precipitation partition, and the fitting upper limit value of the historical precipitation fitting data is used as the upper limit value of the precipitation partition to construct the precipitation partition corresponding to the preset precipitation period interval. After the precipitation partition division is completed, in order to predict the compensation prediction data corresponding to each precipitation partition, the candidate compensation prediction data is first calculated based on the total compensation limit data and the number of partitions, and then the candidate compensation prediction data is adjusted according to the first compensation change rate and the second compensation change rate to obtain the preliminary compensation prediction data. The preliminary compensation forecast data for each precipitation range are aggregated into total compensation forecast data, and then the total compensation forecast rate of each total compensation forecast data is calculated based on the total compensation forecast data and the total compensation limit data. Then, the preliminary compensation forecast data corresponding to the total compensation forecast rate being less than or equal to the total compensation limit rate is obtained as the target compensation forecast data, so as to obtain the optimal compensation forecast data that meets the pre-set conditions and construct a more objective and accurate rainstorm compensation structure.

[0153] When starting to make a rainstorm compensation forecast, the target partition is screened out from the precipitation partition according to the current precipitation, and the target compensation forecast data corresponding to the target partition is used as the rainstorm compensation forecast data to achieve an objective and accurate rainstorm compensation forecast.

[0154] See also Fig. 9 The embodiment of the present application also provides a rainstorm compensation prediction device, which can implement the above-mentioned rainstorm compensation prediction method, and the device includes:

[0155] The request receiving module 901 is used to receive a rainstorm compensation request; wherein the rainstorm compensation request includes: insured area information and current precipitation;

[0156] The data acquisition module 902 is used to acquire the historical heavy precipitation data of the insured area according to the insured area information; wherein the historical heavy precipitation data includes: the target historical precipitation amount and the historical precipitation time information of the target historical precipitation amount;

[0157] A recurrence period calculation module 903 is used to calculate the recurrence period of the target historical precipitation according to the historical precipitation time information to obtain the precipitation recurrence period of each target historical precipitation;

[0158] An interval division module 904 is used to divide the target historical precipitation into precipitation intervals according to the precipitation recurrence period, and obtain precipitation partitions and the number of partitions of the precipitation partitions;

[0159] The compensation data prediction module 905 is used to predict the compensation data according to the preset compensation constraint data and the number of partitions, and obtain the target compensation prediction data for each precipitation partition;

[0160] The data screening module 906 is used to screen out the rainstorm compensation prediction data from the target compensation prediction data according to the precipitation partition and the current precipitation.

[0161] The specific implementation of the heavy rain compensation prediction device is basically the same as the specific implementation of the above-mentioned heavy rain compensation prediction method, and will not be repeated here.

[0162] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned rainstorm compensation prediction method when executing the computer program. The electronic device can be any smart terminal including a tablet computer, a car computer, etc.

[0163] See also Fig.10 , Fig.10 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0164] The processor 1001 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0165] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1002, and the processor 1001 calls and executes the rainstorm compensation prediction method of the embodiment of this application;

[0166] Input / output interface 1003, used to implement information input and output;

[0167] The communication interface 1004 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WI FI, Bluetooth, etc.);

[0168] A bus 1005 , which transmits information between various components of the device (e.g., the processor 1001 , the memory 1002 , the input / output interface 1003 , and the communication interface 1004 );

[0169] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0170] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned heavy rain compensation prediction method is implemented.

[0171] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0172] The rainstorm compensation prediction method and device, electronic device and storage medium provided in the embodiment of the present application, when receiving a rainstorm compensation request, and the rainstorm compensation request includes the insured area information and the current precipitation, first obtain the historical heavy precipitation data of the insured area according to the insured area information, and the historical heavy precipitation data includes the target historical precipitation and the historical precipitation time information of the target historical precipitation. According to the historical precipitation time information, the precipitation recurrence period of each target historical precipitation is calculated to determine the period of recurrence of each target historical precipitation, and then the target historical precipitation is divided into precipitation partitions based on the precipitation recurrence period to construct precipitation partitions that are in line with the precipitation conditions of the insured area and objective. Then, according to the number of partitions of the precipitation partition and the compensation constraint data, the target compensation prediction data of each precipitation partition is predicted, and the compensation prediction data of each precipitation partition is automatically generated without consuming a lot of manpower settings. Finally, the rainstorm compensation prediction data is screened out from the target compensation prediction data according to the current precipitation and the precipitation partition, and an accurate rainstorm compensation prediction is achieved.

[0173] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0174] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0175] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0176] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0177] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0178] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0179] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0180] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0181] In addition, each functional unit in each embodiment of the present application 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-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0182] 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 present application 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, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0183] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for predicting rainstorm compensation, characterized in that: The method comprises: Receiving a rainstorm compensation request; wherein the rainstorm compensation request includes: insured area information and current precipitation; Acquire historical heavy rainfall data of the insured area according to the insured area information; wherein the historical heavy rainfall data includes: target historical rainfall amount and historical rainfall time information of the target historical rainfall amount; Calculating the recurrence period of the target historical precipitation according to the historical precipitation time information to obtain the precipitation recurrence period of each target historical precipitation; Dividing the target historical precipitation into precipitation intervals according to the precipitation recurrence period to obtain precipitation partitions and the number of partitions of the precipitation partitions; Predicting compensation data according to preset compensation constraint data and the number of partitions to obtain target compensation prediction data for each precipitation partition; The rainstorm compensation forecast data is screened out from the target compensation forecast data according to the precipitation partitions and the current precipitation.

2. The method according to claim 1, characterized in that: The step of calculating the recurrence period of the target historical precipitation according to the historical precipitation time information to obtain the precipitation recurrence period of each target historical precipitation includes: Acquire the historical precipitation time information of the same target historical precipitation amount to obtain the selected precipitation time information; Obtaining the time interval between two adjacent selected precipitation time information to obtain the precipitation time interval; The recurrence period of the target historical precipitation is calculated according to the precipitation time interval to obtain the precipitation recurrence period.

3. The method according to claim 1, characterized in that The step of dividing the target historical precipitation into precipitation intervals according to the precipitation recurrence period to obtain precipitation partitions and the number of partitions of the precipitation partitions includes: Filtering selected historical precipitation amounts in each of the preset precipitation cycle intervals from the target historical precipitation amounts according to the preset precipitation cycle interval and the precipitation recurrence period; Performing fitting processing on the selected historical precipitation to obtain historical precipitation fitting data; Extracting a fitting upper limit value and a fitting lower limit value from the historical precipitation fitting data; Performing interval construction according to the fitting upper limit value and the fitting lower limit value to obtain the precipitation partition; The number of the precipitation partitions is obtained to obtain the number of partitions.

4. The method according to any one of claims 1 to 3, characterized in that: The compensation constraint data includes: a compensation change rate limit interval, a total compensation limit rate and total compensation limit data, wherein the compensation change rate limit interval is a change rate limit interval of the compensation forecast data between the two precipitation partitions; The compensation data prediction is performed according to the preset compensation constraint data and the number of partitions to obtain the target compensation prediction data for each precipitation partition, including: Compensation data prediction is performed based on the compensation change rate limit interval, the number of partitions and the total compensation limit data to obtain preliminary compensation prediction data for each precipitation partition; The preliminary compensation prediction data is screened according to the total compensation limit rate and the total compensation limit data to obtain the target compensation prediction data.

5. The method according to claim 4, characterized in that The screening process of the preliminary compensation forecast data according to the total compensation limit rate and the total compensation limit data to obtain the target compensation forecast data includes: The preliminary compensation prediction data are spliced ​​to obtain total compensation prediction data; Obtaining the ratio between the total compensation prediction data and the total compensation limit data to obtain a total compensation prediction rate; The preliminary compensation prediction data is screened according to the total compensation limit rate and the total compensation prediction rate to obtain the target compensation prediction data.

6. The method according to any one of claims 1 to 3, characterized in that: The obtaining of historical heavy rainfall data of the insured area according to the insured area information includes: Acquire target historical precipitation data of the insured area according to the insured area information; wherein the target historical precipitation data includes: candidate historical precipitation amount and candidate precipitation time information of the candidate historical precipitation amount; Screening the candidate historical precipitation according to a preset precipitation threshold to obtain a target historical precipitation; The candidate precipitation time information of the target historical precipitation is acquired to obtain the historical precipitation time information.

7. The method according to claim 6, characterized in that The step of obtaining target historical precipitation data of the insured area according to the insured area information includes: Acquire original historical precipitation data collected by an observation site and an original recurrence period of the original historical precipitation data according to the insured area information; wherein the observation site is used to observe the precipitation data of the insured area; Filtering out maximum historical precipitation data from the original historical precipitation data according to the original recurrence period; The maximum historical precipitation data is used as the target historical precipitation data.

8. A rainstorm compensation prediction device, characterized in that: The device comprises: A request receiving module, used to receive a request for a rainstorm compensation; wherein the rainstorm compensation request includes: information about the insured area and current precipitation; A data acquisition module, used for acquiring historical heavy rainfall data of the insured area according to the insured area information; wherein the historical heavy rainfall data includes: target historical precipitation and historical precipitation time information of the target historical precipitation; A recurrence period calculation module, used to calculate the recurrence period of the target historical precipitation according to the historical precipitation time information, and obtain the precipitation recurrence period of each target historical precipitation; An interval division module, used for dividing the target historical precipitation into precipitation intervals according to the precipitation recurrence period, and obtaining the precipitation partitions and the number of partitions of the precipitation partitions; A compensation data prediction module, used to predict compensation data according to preset compensation constraint data and the number of partitions, and obtain target compensation prediction data for each precipitation partition; A data screening module is used to screen out the rainstorm compensation forecast data from the target compensation forecast data according to the precipitation partition and the current precipitation.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images