Crop meteorological index insurance pricing method and system
By constructing a meteorological disaster risk assessment data set and a prediction model data set, combined with GIS and machine learning algorithms, the problem of pricing error of single meteorological elements in the existing technology is solved, and the accurate calculation of crop insurance prices and improvement of work efficiency is achieved.
Patent Information
- Application Number
- CN202411523542.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-30
- Publication Date
- 2024-11-29
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The prior art usually only selects a single meteorological element in the insurance pricing of crop meteorological index, and fails to effectively consider the relationship between multiple meteorological elements, resulting in price calculation errors and inefficient work.
By acquiring historical meteorological databases, building meteorological disaster risk assessment data sets and prediction model data sets, using GIS to divide disaster risk levels, detect yield data in real time and integrate it with prediction model data sets, train and verify the initial output prediction algorithm, and calculate the target fee rate To determine the insurance price, random forest regression, SVR and PSO-LSTM algorithms were used for data processing and prediction.
The objective and accurate calculation of crop insurance prices is achieved, the calculation errors are eliminated, the work efficiency is improved, and the insurance price accuracy in the target production area is ensured.
Smart Images

Figure CN119048185A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a pricing method and system for crop meteorological index insurance. Background Art
[0002] With the advancement of technology and the development of the times, the insurance industry has also developed rapidly to provide corresponding protection for people's work and life.
[0003] Among them, in the agricultural field, since the existing grain production is greatly affected by weather and natural disasters, in order to provide corresponding protection for farmers' income, existing technologies have developed corresponding meteorological index insurance and have been applied to a certain extent.
[0004] Furthermore, in the process of pricing meteorological index insurance, most of the existing technologies only select a single meteorological factor. Even if multiple meteorological factors are selected, the relationship between the multiple meteorological factors is not considered, which makes the formulated price prone to errors and correspondingly reduces work efficiency. Summary of the invention
[0005] Based on this, the purpose of the present invention is to provide a pricing method and system for crop meteorological index insurance to solve the problem that most of the existing technologies only select a single meteorological element, and even if multiple meteorological elements are selected, the relationship between the multiple meteorological elements is not considered, which leads to the problem that the formulated prices are prone to errors.
[0006] The first aspect of the embodiment of the present invention proposes: A crop weather index insurance pricing method, wherein the method comprises: Acquire a historical meteorological database, and construct corresponding meteorological disaster risk assessment data sets and prediction model data sets according to the historical meteorological database; Based on GIS, the meteorological disaster risk assessment data set is divided into several disaster risk levels, and target production areas corresponding to each disaster risk level are matched in the preset planning area; Detecting the yield data corresponding to each of the target production areas in real time, and fusing the yield data with the prediction model data set to generate a corresponding target data set in real time; Training and verifying a number of preset initial yield prediction algorithms using the target data set, and selecting a target yield prediction algorithm with the smallest error from among the preset initial yield prediction algorithms; The target yield prediction algorithm is used to calculate the target rate corresponding to each target production area, and the corresponding insurance price is calculated in real time based on the target rate.
[0007] The beneficial effect of the present invention is that the required target production areas and corresponding yield data can be further obtained through the real-time construction of the meteorological disaster risk assessment data set and the prediction model data set. Based on this, the required target data set is integrated to further complete the training and verification of the subsequent initial yield prediction algorithms, and finally obtain the required target yield prediction algorithm, so that the required insurance price can be calculated objectively and accurately, which eliminates the calculation error and improves work efficiency.
[0008] Furthermore, the step of training and verifying a plurality of preset initial yield prediction algorithms using the target data set includes: When the target data set is acquired in real time, the target data set is fully scanned to detect a number of meteorological elements and a number of meteorological disaster risk prevention factors respectively contained in the target data set; The preset algorithm database is called out, and the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are respectively called out in the preset algorithm database, and the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are respectively trained and verified through a number of the meteorological elements and a number of the meteorological disaster risk prevention factors, and the target data set is unique.
[0009] Furthermore, the steps of respectively training and verifying the random forest regression algorithm, the SVR algorithm, and the PSO-LSTM algorithm using the several meteorological elements and the several meteorological disaster risk prevention factors include: Performing fusion processing on the plurality of meteorological elements and the plurality of meteorological disaster risk prevention factors to generate a corresponding first data set in real time; Performing fusion processing on the yield data corresponding to each of the target production areas to generate a corresponding second data set in real time; The random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are trained and verified respectively according to the first data set and the second data set to select the target yield prediction algorithm accordingly.
[0010] Furthermore, the step of training and verifying the random forest regression algorithm, the SVR algorithm, and the PSO-LSTM algorithm respectively according to the first data set and the second data set to select the target yield prediction algorithm accordingly includes: When the first data set and the second data set are respectively obtained, the first data set is correspondingly set as an explanatory variable, and the second data set is correspondingly set as an explained variable; The explanatory variables and the explained variables are respectively input into the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm to complete the corresponding training and verification, and the target yield prediction algorithm is selected accordingly.
[0011] Furthermore, the step of calculating the target rate corresponding to each target production area by the target production prediction algorithm includes: When the yield data corresponding to the target production area is acquired in real time, the meteorological yield, trend yield and random yield corresponding to the target production area are extracted in real time according to the yield data; The actual output corresponding to the target production area is calculated in real time according to the meteorological output, the trend output and the random output, and the target rate is calculated accordingly according to the actual output and the target output prediction algorithm.
[0012] Furthermore, the step of calculating the target rate according to the actual output and the target output prediction algorithm includes: When the target rate is obtained in real time, a meteorological index corresponding to the target production area is matched in real time, and the meteorological index includes a specific value; Performing kernel function density estimation processing on the target production area and the meteorological index in real time through the target production prediction algorithm, so as to calculate the production loss probability between the target production area and the meteorological index in real time; The target rate is calculated according to the production loss probability.
[0013] Furthermore, the step of calculating the target rate according to the production loss probability includes: When the production loss probability is obtained in real time, the corresponding risk additional factor, additional expense rate and pure insurance premium rate are matched in real time according to the size of the production loss probability; The target rate is calculated according to the risk additional factor, the additional expense rate, the pure insurance premium rate and a preset algorithm. The expression of the preset algorithm is:
[0014] Among them, R represents the target rate, R0 represents the pure insurance rate, M represents the risk additional factor, Q represents the expected profit rate, and V represents the additional expense rate.
[0015] The second aspect of the embodiment of the present invention proposes: A crop weather index insurance pricing system, wherein the system comprises: An acquisition module is used to acquire a historical meteorological database, and to construct corresponding meteorological disaster risk assessment data sets and prediction model data sets according to the historical meteorological database; A matching module, for dividing a number of disaster risk levels according to the meteorological disaster risk assessment data set based on GIS, and matching target production areas corresponding to each disaster risk level in a preset planning area; A fusion module is used to detect the yield data corresponding to each of the target production areas in real time, and fuse the yield data with the prediction model data set to generate a corresponding target data set in real time; A processing module, used to train and verify a plurality of preset initial yield prediction algorithms through the target data set, and select a target yield prediction algorithm with the smallest error from among the plurality of preset initial yield prediction algorithms; The calculation module is used to calculate the target rate corresponding to each target production area through the target output prediction algorithm, and calculate the corresponding insurance price in real time according to the target rate.
[0016] Furthermore, the processing module is specifically used for: When the target data set is acquired in real time, the target data set is fully scanned to detect a number of meteorological elements and a number of meteorological disaster risk prevention factors respectively contained in the target data set; The preset algorithm database is called out, and the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are respectively called out in the preset algorithm database, and the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are respectively trained and verified through a number of the meteorological elements and a number of the meteorological disaster risk prevention factors, and the target data set is unique.
[0017] Furthermore, the processing module is specifically used for: Performing fusion processing on the plurality of meteorological elements and the plurality of meteorological disaster risk prevention factors to generate a corresponding first data set in real time; Performing fusion processing on the yield data corresponding to each of the target production areas to generate a corresponding second data set in real time; The random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are trained and verified respectively according to the first data set and the second data set to select the target yield prediction algorithm accordingly.
[0018] Furthermore, the processing module is specifically used for: When the first data set and the second data set are respectively obtained, the first data set is correspondingly set as an explanatory variable, and the second data set is correspondingly set as an explained variable; The explanatory variables and the explained variables are respectively input into the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm to complete the corresponding training and verification, and the target yield prediction algorithm is selected accordingly.
[0019] Furthermore, the calculation module is specifically used for: When the yield data corresponding to the target production area is acquired in real time, the meteorological yield, trend yield and random yield corresponding to the target production area are extracted in real time according to the yield data; The actual output corresponding to the target production area is calculated in real time according to the meteorological output, the trend output and the random output, and the target rate is calculated accordingly according to the actual output and the target output prediction algorithm.
[0020] Furthermore, the calculation module is specifically used for: When the target rate is obtained in real time, a meteorological index corresponding to the target production area is matched in real time, and the meteorological index includes a specific value; Performing kernel function density estimation processing on the target production area and the meteorological index in real time through the target production prediction algorithm, so as to calculate the production loss probability between the target production area and the meteorological index in real time; The target rate is calculated according to the production loss probability.
[0021] Furthermore, the calculation module is specifically used for: When the production loss probability is obtained in real time, the corresponding risk additional factor, additional expense rate and pure insurance premium rate are matched in real time according to the size of the production loss probability; The target rate is calculated according to the risk additional factor, the additional expense rate, the pure insurance premium rate and a preset algorithm. The expression of the preset algorithm is:
[0022] Among them, R represents the target rate, R0 represents the pure insurance rate, M represents the risk additional factor, Q represents the expected profit rate, and V represents the additional expense rate.
[0023] The third aspect of the embodiment of the present invention proposes: A computer comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned crop weather index insurance pricing method when executing the computer program.
[0024] The fourth aspect of the embodiments of the present invention proposes: A readable storage medium stores a computer program, wherein when the program is executed by a processor, the crop weather index insurance pricing method as described above is implemented.
[0025] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] Figure 1 A flowchart of a crop weather index insurance pricing method provided by the first embodiment of the present invention; Figure 2 This is a structural block diagram of a crop weather index insurance pricing system provided in the third embodiment of the present invention.
[0027] The following specific implementation manner will further illustrate the present invention in conjunction with the above-mentioned drawings. DETAILED DESCRIPTION
[0028] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.
[0029] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.
[0030] 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 the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.
[0031] See also Figure 1, shown is the crop meteorological index insurance pricing method provided by the first embodiment of the present invention. The crop meteorological index insurance pricing method provided by this embodiment can objectively and accurately calculate the required insurance price, correspondingly eliminates calculation errors and improves work efficiency.
[0032] Specifically, this embodiment provides: A crop weather index insurance pricing method specifically comprises the following steps: Step S10, obtaining a historical meteorological database, and constructing a corresponding meteorological disaster risk assessment data set and a prediction model data set according to the historical meteorological database; Step S20, based on GIS, divide the meteorological disaster risk assessment data set into a number of disaster risk levels, and respectively match the target production areas corresponding to each disaster risk level in the preset planning area; Step S30, detecting the yield data corresponding to each of the target production areas in real time, and fusing the yield data with the prediction model data set to generate a corresponding target data set in real time; Step S40, training and verifying a plurality of preset initial yield prediction algorithms using the target data set, and selecting a target yield prediction algorithm with the smallest error from the plurality of preset initial yield prediction algorithms; Step S50, the target rate corresponding to each target production area is calculated respectively by the target yield prediction algorithm, and the corresponding insurance price is calculated in real time according to the target rate.
[0033] Specifically, in this embodiment, it should be noted that, in order to be able to objectively and accurately calculate the insurance price adapted to each production area, it is necessary to accurately obtain the production situation of each area, based on which, further determine the corresponding meteorological index, and finally formulate the insurance price corresponding to the meteorological index. Based on this, in order to be able to quickly and effectively complete the corresponding calculation process, it is necessary to construct a model that can automatically complete the calculation, and constructing the required model requires a large amount of data. Based on this, the present invention will connect the server set in the background with the existing historical meteorological database. Based on this, the server can correspondingly obtain various types of original meteorological data from the current historical meteorological database, and can further construct the required meteorological disaster risk assessment data set and prediction model data set according to the current meteorological data, so as to facilitate subsequent processing.
[0034] Furthermore, the present invention will call the existing GIS (geographic information system) to further divide the required disaster risk level according to the above-mentioned meteorological disaster risk assessment data set. At the same time, it can further match the target production area corresponding to the current disaster risk level in the existing preset planning area. It should be pointed out that the above-mentioned preset planning area is the planned production area, and the corresponding target production area is the production area that needs further analysis. Based on this, the present invention can further detect the yield data corresponding to each current target production area in real time through the above-mentioned historical meteorological database. Furthermore, in order to facilitate subsequent training, the current yield data will be further integrated with the above-mentioned prediction model data set, so as to finally generate a target data set for subsequent training. Based on this, before starting the formal calculation, several pre-set initial yield prediction algorithms can be trained and verified one-on-one in real time through the current target data set, and the target yield prediction algorithm with the smallest error can be further selected. On this basis, the target yield prediction algorithm can finally be used to calculate the target rate corresponding to each current target production area one by one, and the target rate is the basis for formulating the insurance price. Based on this, the insurance price corresponding to the meteorological index of each target production area can be further calculated in real time according to the target rate, thereby eliminating the calculation error and improving work efficiency accordingly.
[0035] Second embodiment Furthermore, the step of training and verifying a plurality of preset initial yield prediction algorithms using the target data set includes: When the target data set is acquired in real time, the target data set is fully scanned to detect a number of meteorological elements and a number of meteorological disaster risk prevention factors respectively contained in the target data set; The preset algorithm database is called out, and the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are respectively called out in the preset algorithm database, and the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are respectively trained and verified through a number of the meteorological elements and a number of the meteorological disaster risk prevention factors, and the target data set is unique.
[0036] Furthermore, the steps of respectively training and verifying the random forest regression algorithm, the SVR algorithm, and the PSO-LSTM algorithm using the several meteorological elements and the several meteorological disaster risk prevention factors include: Performing fusion processing on the plurality of meteorological elements and the plurality of meteorological disaster risk prevention factors to generate a corresponding first data set in real time; Performing fusion processing on the yield data corresponding to each of the target production areas to generate a corresponding second data set in real time; The random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are trained and verified respectively according to the first data set and the second data set to select the target yield prediction algorithm accordingly.
[0037] Furthermore, the step of training and verifying the random forest regression algorithm, the SVR algorithm, and the PSO-LSTM algorithm respectively according to the first data set and the second data set to select the target yield prediction algorithm accordingly includes: When the first data set and the second data set are respectively obtained, the first data set is correspondingly set as an explanatory variable, and the second data set is correspondingly set as an explained variable; The explanatory variables and the explained variables are respectively input into the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm to complete the corresponding training and verification, and the target yield prediction algorithm is selected accordingly.
[0038] Furthermore, the step of calculating the target rate corresponding to each target production area by the target production prediction algorithm includes: When the yield data corresponding to the target production area is acquired in real time, the meteorological yield, trend yield and random yield corresponding to the target production area are extracted in real time according to the yield data; The actual output corresponding to the target production area is calculated in real time according to the meteorological output, the trend output and the random output, and the target rate is calculated accordingly according to the actual output and the target output prediction algorithm.
[0039] Furthermore, the step of calculating the target rate according to the actual output and the target output prediction algorithm includes: When the target rate is obtained in real time, a meteorological index corresponding to the target production area is matched in real time, and the meteorological index includes a specific value; Performing kernel function density estimation processing on the target production area and the meteorological index in real time through the target production prediction algorithm, so as to calculate the production loss probability between the target production area and the meteorological index in real time; The target rate is calculated according to the production loss probability.
[0040] Furthermore, the step of calculating the target rate according to the production loss probability includes: When the production loss probability is obtained in real time, the corresponding risk additional factor, additional expense rate and pure insurance premium rate are matched in real time according to the size of the production loss probability; The target rate is calculated according to the risk additional factor, the additional expense rate, the pure insurance premium rate and a preset algorithm. The expression of the preset algorithm is:
[0041] Among them, R represents the target rate, R0 represents the pure insurance rate, M represents the risk additional factor, Q represents the expected profit rate, and V represents the additional expense rate.
[0042] In addition, in the present embodiment, it is also necessary to explain that when the required target data set is obtained in real time through the above steps, in order to quickly and effectively complete the subsequent training and verification, it is necessary to further parse and process the current target data set. Preferably, the present invention will first perform a full scan of the current target data set, so as to be able to scan out a number of meteorological elements and a number of meteorological disaster risk prevention factors corresponding to the current target data set. Based on this, the subsequent training can be started. Furthermore, the present invention will call out a pre-set algorithm database, and can further call out a random forest regression algorithm, an SVR (support vector regression) algorithm, and a PSO-LSTM (particle swarm optimization-long short-term memory neural network) algorithm for subsequent training in the algorithm database. (by) algorithm, further, in the actual training process, it is necessary to determine the corresponding explanatory variables and the explained variables respectively. Based on this, in order to shorten the training time, the present invention will first fuse the current meteorological elements and the current meteorological disaster risk prevention factors, and generate a corresponding first data set. At the same time, the yield data of each target production area is fused to generate a corresponding second data set. Based on this, the current first data set will be immediately set as the required explanatory variable, and correspondingly, the current second data set will be set as the required explained variable. Further, the current two variables are correspondingly input into the above three algorithms to complete the corresponding training and verification, and the required target yield prediction algorithm can be finally selected for subsequent processing.
[0043] Furthermore, after further obtaining the required target yield prediction algorithm through the above steps, the subsequent calculation can be started at this time. Specifically, in the actual calculation process, it is necessary to first obtain the actual yield of each target production area, that is, the real crop yield. Based on this, the present invention can extract the meteorological yield, trend yield and random yield of the corresponding target production area in real time according to the above yield data. It should be pointed out that the above meteorological yield mainly refers to the yield corresponding to the production area under the influence of meteorological conditions, the above trend yield mainly refers to the yield brought by the growth trend of crops in the production area, and the above random yield mainly refers to the yield under the influence of uncertain factors. Based on this, the present invention will further perform corresponding accumulation processing on the current three yields, and further obtain the required actual yield. Further, the present invention can immediately calculate the corresponding target rate in real time through the above target yield prediction algorithm based on the current actual yield. At the same time, the meteorological index corresponding to the current target production area is matched in real time. Based on this, the current target production area and the meteorological index are further processed by the above-mentioned target yield prediction algorithm for the final kernel function density estimation, and the required yield loss probability can be further obtained. Based on this, the size of the current yield loss probability is used as the matching object, and the corresponding risk additional factor, additional expense rate and pure insurance rate are further matched in the preset parameter database. Furthermore, the above parameters are simultaneously input into the pre-set algorithm, and the required target rate can be finally calculated, and the corresponding insurance price can be further calculated, thereby effectively eliminating calculation errors and correspondingly improving work efficiency.
[0044] See also Figure 2 , the third embodiment of the present invention provides: A crop weather index insurance pricing system, wherein the system comprises: An acquisition module is used to acquire a historical meteorological database, and to construct corresponding meteorological disaster risk assessment data sets and prediction model data sets according to the historical meteorological database; A matching module, for dividing a number of disaster risk levels according to the meteorological disaster risk assessment data set based on GIS, and matching target production areas corresponding to each disaster risk level in a preset planning area; A fusion module is used to detect the yield data corresponding to each of the target production areas in real time, and fuse the yield data with the prediction model data set to generate a corresponding target data set in real time; A processing module, used to train and verify a plurality of preset initial yield prediction algorithms through the target data set, and select a target yield prediction algorithm with the smallest error from among the plurality of preset initial yield prediction algorithms; The calculation module is used to calculate the target rate corresponding to each target production area through the target output prediction algorithm, and calculate the corresponding insurance price in real time according to the target rate.
[0045] Furthermore, the processing module is specifically used for: When the target data set is acquired in real time, the target data set is fully scanned to detect a number of meteorological elements and a number of meteorological disaster risk prevention factors respectively contained in the target data set; The preset algorithm database is called out, and the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are respectively called out in the preset algorithm database, and the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are respectively trained and verified through a number of the meteorological elements and a number of the meteorological disaster risk prevention factors, and the target data set is unique.
[0046] Furthermore, the processing module is specifically used for: Performing fusion processing on the plurality of meteorological elements and the plurality of meteorological disaster risk prevention factors to generate a corresponding first data set in real time; Performing fusion processing on the yield data corresponding to each of the target production areas to generate a corresponding second data set in real time; The random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are trained and verified respectively according to the first data set and the second data set to select the target yield prediction algorithm accordingly.
[0047] Furthermore, the processing module is specifically used for: When the first data set and the second data set are respectively obtained, the first data set is correspondingly set as an explanatory variable, and the second data set is correspondingly set as an explained variable; The explanatory variables and the explained variables are respectively input into the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm to complete the corresponding training and verification, and the target yield prediction algorithm is selected accordingly.
[0048] Furthermore, the calculation module is specifically used for: When the yield data corresponding to the target production area is acquired in real time, the meteorological yield, trend yield and random yield corresponding to the target production area are extracted in real time according to the yield data; The actual output corresponding to the target production area is calculated in real time according to the meteorological output, the trend output and the random output, and the target rate is calculated accordingly according to the actual output and the target output prediction algorithm.
[0049] Furthermore, the calculation module is specifically used for: When the target rate is obtained in real time, a meteorological index corresponding to the target production area is matched in real time, and the meteorological index includes a specific value; Performing kernel function density estimation processing on the target production area and the meteorological index in real time through the target production prediction algorithm, so as to calculate the production loss probability between the target production area and the meteorological index in real time; The target rate is calculated according to the production loss probability.
[0050] Furthermore, the calculation module is specifically used for: When the production loss probability is obtained in real time, the corresponding risk additional factor, additional expense rate and pure insurance premium rate are matched in real time according to the size of the production loss probability; The target rate is calculated according to the risk additional factor, the additional expense rate, the pure insurance premium rate and a preset algorithm. The expression of the preset algorithm is:
[0051] Among them, R represents the target rate, R0 represents the pure insurance rate, M represents the risk additional factor, Q represents the expected profit rate, and V represents the additional expense rate.
[0052] A fourth embodiment of the present invention provides a computer, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the crop meteorological index insurance pricing method as described above when executing the computer program.
[0053] A fifth embodiment of the present invention provides a readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the crop meteorological index insurance pricing method as described above is implemented.
[0054] In summary, the crop meteorological index insurance pricing method and system provided by the above embodiments of the present invention can objectively and accurately calculate the required insurance price, thereby eliminating calculation errors and improving work efficiency.
[0055] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.
[0056] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.
[0057] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.
[0058] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0059] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0060] The above-described embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.
Claims
1. A pricing method for crop weather index insurance, characterized in that: The method comprises: Acquire a historical meteorological database, and construct corresponding meteorological disaster risk assessment data sets and prediction model data sets according to the historical meteorological database; Based on GIS, the meteorological disaster risk assessment data set is divided into several disaster risk levels, and target production areas corresponding to each disaster risk level are matched in the preset planning area; Detecting the yield data corresponding to each of the target production areas in real time, and fusing the yield data with the prediction model data set to generate a corresponding target data set in real time; Training and verifying a number of preset initial yield prediction algorithms using the target data set, and selecting a target yield prediction algorithm with the smallest error from among the preset initial yield prediction algorithms; The target yield prediction algorithm is used to calculate the target rate corresponding to each target production area, and the corresponding insurance price is calculated in real time based on the target rate.
2. The crop weather index insurance pricing method according to claim 1, characterized in that: The step of training and verifying a plurality of preset initial yield prediction algorithms using the target data set comprises: When the target data set is acquired in real time, the target data set is fully scanned to detect a number of meteorological elements and a number of meteorological disaster risk prevention factors respectively contained in the target data set; The preset algorithm database is called out, and the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are respectively called out in the preset algorithm database, and the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are respectively trained and verified through a number of the meteorological elements and a number of the meteorological disaster risk prevention factors, and the target data set is unique.
3. The crop weather index insurance pricing method according to claim 2, characterized in that: The step of respectively training and verifying the random forest regression algorithm, the SVR algorithm, and the PSO-LSTM algorithm using the several meteorological elements and the several meteorological disaster risk prevention factors comprises: Performing fusion processing on the plurality of meteorological elements and the plurality of meteorological disaster risk prevention factors to generate a corresponding first data set in real time; Performing fusion processing on the yield data corresponding to each of the target production areas to generate a corresponding second data set in real time; The random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm are trained and verified respectively according to the first data set and the second data set to select the target yield prediction algorithm accordingly.
4. The crop weather index insurance pricing method according to claim 3, characterized in that: The step of training and verifying the random forest regression algorithm, the SVR algorithm, and the PSO-LSTM algorithm respectively according to the first data set and the second data set to select the target yield prediction algorithm accordingly includes: When the first data set and the second data set are respectively obtained, the first data set is correspondingly set as an explanatory variable, and the second data set is correspondingly set as an explained variable; The explanatory variables and the explained variables are respectively input into the random forest regression algorithm, the SVR algorithm and the PSO-LSTM algorithm to complete the corresponding training and verification, and the target yield prediction algorithm is selected accordingly.
5. The crop weather index insurance pricing method according to claim 1, characterized in that: The step of respectively calculating the target rate corresponding to each target production area by the target production prediction algorithm comprises: When the yield data corresponding to the target production area is acquired in real time, the meteorological yield, trend yield and random yield corresponding to the target production area are extracted in real time according to the yield data; The actual output corresponding to the target production area is calculated in real time according to the meteorological output, the trend output and the random output, and the target rate is calculated accordingly according to the actual output and the target output prediction algorithm.
6. The crop weather index insurance pricing method according to claim 5, characterized in that: The step of calculating the target rate according to the actual output and the target output prediction algorithm includes: When the target rate is obtained in real time, a meteorological index corresponding to the target production area is matched in real time, and the meteorological index includes a specific value; Performing kernel function density estimation processing on the target production area and the meteorological index in real time through the target production prediction algorithm, so as to calculate the production loss probability between the target production area and the meteorological index in real time; The target rate is calculated according to the production loss probability.
7. The crop weather index insurance pricing method according to claim 6, characterized in that: The step of calculating the target rate according to the production loss probability comprises: When the production loss probability is obtained in real time, the corresponding risk additional factor, additional expense rate and pure insurance premium rate are matched in real time according to the size of the production loss probability; The target rate is calculated according to the risk additional factor, the additional expense rate, the pure insurance premium rate and a preset algorithm. The expression of the preset algorithm is: Among them, R represents the target rate, R0 represents the pure insurance rate, M represents the risk additional factor, Q represents the expected profit rate, and V represents the additional expense rate.
8. A crop weather index insurance pricing system, characterized in that: The system comprises: An acquisition module is used to acquire a historical meteorological database, and to construct corresponding meteorological disaster risk assessment data sets and prediction model data sets according to the historical meteorological database; A matching module, for dividing a number of disaster risk levels according to the meteorological disaster risk assessment data set based on GIS, and matching target production areas corresponding to each disaster risk level in a preset planning area; A fusion module is used to detect the yield data corresponding to each of the target production areas in real time, and fuse the yield data with the prediction model data set to generate a corresponding target data set in real time; A processing module, used to train and verify a plurality of preset initial yield prediction algorithms through the target data set, and select a target yield prediction algorithm with the smallest error from among the plurality of preset initial yield prediction algorithms; The calculation module is used to calculate the target rate corresponding to each target production area through the target output prediction algorithm, and calculate the corresponding insurance price in real time according to the target rate.
9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the crop weather index insurance pricing method according to any one of claims 1 to 7 is implemented.
10. A readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the crop weather index insurance pricing method as described in any one of claims 1 to 7 is implemented.
