CN117934176A - Breeding insurance pricing system based on data analysis - Google Patents
Breeding insurance pricing system based on data analysis Download PDFInfo
- Publication number
- CN117934176A CN117934176A CN202410302731.5A CN202410302731A CN117934176A CN 117934176 A CN117934176 A CN 117934176A CN 202410302731 A CN202410302731 A CN 202410302731A CN 117934176 A CN117934176 A CN 117934176A
- Authority
- CN
- China
- Prior art keywords
- target
- cultivation
- data
- module
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000007405 data analysis Methods 0.000 title claims abstract description 17
- 238000009395 breeding Methods 0.000 title description 10
- 230000001488 breeding effect Effects 0.000 title description 10
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000012502 risk assessment Methods 0.000 claims abstract description 28
- 238000011156 evaluation Methods 0.000 claims abstract description 14
- 238000013210 evaluation model Methods 0.000 claims abstract description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 33
- 238000010606 normalization Methods 0.000 claims description 25
- 238000009313 farming Methods 0.000 claims description 21
- 230000004927 fusion Effects 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 description 28
- 238000003860 storage Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 9
- 230000007613 environmental effect Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 241001465754 Metazoa Species 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 241000287828 Gallus gallus Species 0.000 description 2
- 241000282887 Suidae Species 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 235000013330 chicken meat Nutrition 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 241000283690 Bos taurus Species 0.000 description 1
- 238000006424 Flood reaction Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000012364 cultivation method Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Husbandry (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Marine Sciences & Fisheries (AREA)
- Agronomy & Crop Science (AREA)
- Mining & Mineral Resources (AREA)
- Development Economics (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a culture insurance pricing system based on data analysis. The system comprises: the target data acquisition module is used for acquiring target insurance period and target cultivation data of a target cultivation farm, and target historical weather data and target environment data of a region of the target cultivation farm; the target amount determining module is used for determining target claim amount of the target farm according to the target cultivation data; the target probability evaluation module is used for processing the target cultivation data, the target historical weather data and the target environment data by using a pre-constructed risk evaluation model to obtain target unit claim probability of the target cultivation farm in each unit insurance period; and the target pricing determining module is used for determining target insurance pricing of the target farm according to the target claim amount, the target insurance period and the target unit claim probability. The application can identify and quantify various risk factors and provide a fine and accurate risk assessment result, thereby improving the accuracy of insurance pricing.
Description
Technical Field
The application relates to the technical field of insurance pricing, in particular to a cultivation insurance pricing system based on data analysis.
Background
The cultivation insurance is an important branch of agricultural insurance, and aims to provide economic guarantee for farmers and reduce economic losses caused by natural disasters and other irresistible factors. With the rapid development of the breeding industry, the breeding scale is enlarged and the breeding technology is advanced, and the risks faced by the breeding industry are increased, which comprise animal epidemic diseases, natural disasters (such as floods, drought, storm and the like) and the like. The occurrence of the cultivation insurance can help farmers to reduce risks and stabilize the development of the cultivation industry.
Conventional methods of farm insurance pricing typically rely on a relatively simplified calculation to determine insurance costs, for example, in determining rates, a base rate is first assigned to different farm types (e.g., pigs, cows, chickens, etc.), and then the rates are adjusted at a predetermined ratio based on the region of the farm (e.g., east, west, south, north, etc.).
Although the existing pricing method provides a reference for cultivation insurance to a certain extent, the problem of low accuracy exists.
Disclosure of Invention
In view of the above-mentioned problems, the present application has been made to provide a data analysis-based farming insurance pricing system that overcomes the problems or at least partially solves the problems, including:
a data analysis based farming insurance pricing system, comprising:
The target data acquisition module is used for acquiring target insurance period and target cultivation data of a target cultivation field, and target historical weather data and target environment data of an area of the target cultivation field;
The target amount determining module is used for determining target claim amount of the target farm according to the target cultivation data;
the target probability evaluation module is used for processing the target cultivation data, the target historical weather data and the target environment data by using a pre-constructed risk evaluation model to obtain target unit claim probability of the target cultivation farm in each unit insurance period;
And the target pricing determining module is used for determining target insurance pricing of the target farm according to the target claim amount, the target insurance period and the target unit claim probability.
Preferably, the target cultivation data includes a target cultivation type, a target cultivation scale, a target cultivation density and a target cultivation mode; the target amount determining module includes:
A target quantity determination submodule for determining a target quantity of cultivation of the target farm according to the target cultivation scale and the target cultivation density;
And the target amount determining submodule is used for determining target claim amount of the target farm according to the target cultivation type, the target cultivation mode and the target cultivation amount.
Preferably, the target probability evaluation module includes:
the target data segmentation sub-module is used for dividing the target historical weather data into target unit weather data which are in one-to-one correspondence with the unit insurance period;
And the target probability evaluation sub-module is used for processing the target culture data, the target environment data and the target unit weather data corresponding to the unit insurance period by using a pre-constructed risk evaluation model for each unit insurance period to obtain the target claim probability of the target farm in the unit insurance period.
Preferably, the target cultivation data includes a target cultivation type, a target cultivation scale, a target cultivation density and a target cultivation mode; the target environment data comprise a target mountain distance from the nearest mountain of the target farm and a target water body distance from the nearest water body; the target unit weather data comprise a target unit temperature sequence and a target unit humidity sequence of the region of the target cultivation place; the risk assessment model comprises a multi-mode input layer, a characteristic cross learning layer, an integrated learning layer and an output layer; the target probability evaluation submodule includes:
A first input sub-module, configured to input the target cultivation type, the target cultivation scale, the target cultivation density, the target cultivation mode, the target mountain distance, the target water body distance, the target unit temperature sequence, and the target unit humidity sequence into the multi-mode input layer, to obtain a target type embedded vector corresponding to the target cultivation type, a target mode embedded vector corresponding to the target cultivation mode, a target scale normalized value corresponding to the target cultivation scale, a target density normalized value corresponding to the target cultivation density, a target mountain normalized value corresponding to the target mountain distance, a target water body normalized value corresponding to the target water body distance, and a target weather hidden state corresponding to the target unit temperature sequence and the target unit humidity sequence;
The second input sub-module is used for inputting the target type embedded vector, the target mode embedded vector, the target scale normalization value, the target density normalization value, the target mountain normalization value, the target water body normalization value and the target weather hiding state into the feature cross learning layer to obtain feature cross output;
the third input sub-module is used for inputting the characteristic cross output into the integrated learning layer to obtain integrated learning output;
And the fourth input sub-module is used for inputting the integrated learning output into the output layer to obtain the target claim probability of the target farm in the unit insurance period.
Preferably, the feature cross learning layer comprises a deep cross network and a transducer module; the second input submodule includes:
the depth intersection input sub-module is used for processing and inputting the target type embedded vector, the target mode embedded vector, the target scale normalization value, the target density normalization value, the target mountain normalization value, the target water body normalization value and the target weather hiding state into the depth intersection network to obtain depth intersection output;
the converter input sub-module is used for processing and inputting the target weather hiding state into the converter module to obtain converter output;
And the cross fusion sub-module is used for fusing the depth cross output and the transducer output to obtain a characteristic cross output.
Preferably, the cross fusion submodule includes:
And the serial fusion sub-module is used for carrying out serial connection on the depth cross output and the transducer output to obtain a characteristic cross output.
Preferably, the ensemble learning layer includes a plurality of prediction models; the third input submodule includes:
The model input sub-module is used for inputting the characteristic cross output into each prediction model to obtain model learning output;
And the integrated fusion sub-module is used for fusing all the model learning output to obtain integrated learning output.
Preferably, the integrated fusion submodule includes:
And the weighted fusion sub-module is used for carrying out weighted summation on all the model learning outputs to obtain an integrated learning output.
Preferably, the target pricing determining module includes:
the target probability determination submodule is used for determining target claim probability of the target farm in the target insurance period according to the target insurance period and the target unit claim probability;
And the target pricing determining submodule is used for determining target insurance pricing of the target farm according to the target claim amount and the target claim probability.
Preferably, the method further comprises:
The sample data acquisition module is used for acquiring sample culture data and sample claim conditions of a sample culture farm, and sample historical weather data and sample environment data of a region of the sample culture farm;
And the initial model training module is used for training an initial risk assessment model by using the sample culture data, the sample historical weather data, the sample environment data and the sample claim condition to obtain a risk assessment model.
The application has the following advantages:
in the embodiment of the application, compared with the problem of low accuracy of the existing pricing method, the application provides a solution for determining insurance pricing by calculating the probability of claim in a unit period by using a risk assessment model based on culture data, weather data and environment data, which comprises the following steps: "data analysis-based farming insurance pricing system, comprising: the target data acquisition module is used for acquiring target insurance period and target cultivation data of a target cultivation field, and target historical weather data and target environment data of an area of the target cultivation field; the target amount determining module is used for determining target claim amount of the target farm according to the target cultivation data; the target probability evaluation module is used for processing the target cultivation data, the target historical weather data and the target environment data by using a pre-constructed risk evaluation model to obtain target unit claim probability of the target cultivation farm in each unit insurance period; and the target pricing determining module is used for determining target insurance pricing of the target farm according to the target claim amount, the target insurance period and the target unit claim probability. By comprehensively analyzing the culture data, the weather data and the environmental data by using the risk assessment model, the claim probability in the unit period is obtained, various risk factors can be identified and quantified, and a fine and accurate risk assessment result is provided, so that the accuracy of insurance pricing is improved.
Drawings
In order to more clearly illustrate the technical solutions of the present application, the drawings that are needed in the description of the present application will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of a method for pricing insurance for farming based on data analysis according to an embodiment of the present application;
FIG. 2 is a flow chart of steps of a method for pricing insurance for farming based on data analysis according to another embodiment of the present application;
FIG. 3 is a block diagram of a system for pricing insurance for farming based on data analysis according to one embodiment of the present application;
FIG. 4 is a block diagram of a system for pricing insurance for farming based on data analysis according to another embodiment of the present application;
fig. 5 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Reference numerals in the drawings of the specification are as follows:
12. a computer device; 14. an external device; 16. a processing unit; 18. a bus; 20. a network adapter; 22. an I/O interface; 24. a display; 28. a memory; 30. a random access memory; 32. a cache memory; 34. a storage system; 40. program/utility; 42. program modules.
Detailed Description
In order that the manner in which the above recited objects, features and advantages of the present application are obtained will become more readily apparent, a more particular description of the application briefly described above will be rendered by reference to the appended drawings. It will be apparent that the described embodiments are some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, a method for pricing cultivation insurance based on data analysis according to an embodiment of the present application is shown, including:
S110, acquiring target insurance period and target cultivation data of a target cultivation field, and target historical weather data and target environment data of an area of the target cultivation field;
S120, determining a target claim amount of the target farm according to the target culture data;
S130, processing the target cultivation data, the target historical weather data and the target environment data by using a pre-constructed risk assessment model to obtain target unit claim probability of the target cultivation farm in each unit insurance period;
And S140, determining the target insurance pricing of the target farm according to the target claim amount, the target insurance period and the target unit claim probability.
In the embodiment of the application, compared with the problem of low accuracy of the existing pricing method, the application provides a solution for determining insurance pricing by calculating the probability of claim in a unit period by using a risk assessment model based on culture data, weather data and environment data, which comprises the following steps: "data analysis-based farming insurance pricing system, comprising: the target data acquisition module is used for acquiring target insurance period and target cultivation data of a target cultivation field, and target historical weather data and target environment data of an area of the target cultivation field; the target amount determining module is used for determining target claim amount of the target farm according to the target cultivation data; the target probability evaluation module is used for processing the target cultivation data, the target historical weather data and the target environment data by using a pre-constructed risk evaluation model to obtain target unit claim probability of the target cultivation farm in each unit insurance period; and the target pricing determining module is used for determining target insurance pricing of the target farm according to the target claim amount, the target insurance period and the target unit claim probability. By comprehensively analyzing the culture data, the weather data and the environmental data by using the risk assessment model, the claim probability in the unit period is obtained, various risk factors can be identified and quantified, and a fine and accurate risk assessment result is provided, so that the accuracy of insurance pricing is improved.
Next, a method for pricing cultivation insurance based on data analysis in the present exemplary embodiment will be further described.
The target insurance period and target cultivation data of the target farm, and the target historical weather data and target environmental data of the region to which the target farm belongs are acquired as described in the step S110.
The target insurance period (numerical data) refers to the length of time that the farm insurance covers, and is typically determined based on the growth period of the farmed animals, seasonal risks, and requirements of the farm owners.
The target cultivation data includes a target cultivation type (category data), a target cultivation scale (numerical data), a target cultivation density (numerical data), and a target cultivation pattern (category data); wherein the target breeding species refers to specific animal species bred in a breeding place, such as chickens, fishes, pigs and the like; the target cultivation scale refers to the area or capacity of a farm; the target breeding density refers to the number of breeding animals in a unit area; the target cultivation mode refers to a cultivation method and mode adopted, such as natural cultivation, mixed cultivation, factory cultivation and the like.
The target historical weather data comprises a target historical temperature sequence (time sequence data) and a target historical humidity sequence (time sequence data) of the region of the target farm; wherein the target historical temperature sequence comprises an average, highest or lowest temperature per day over a predetermined period of time in the past; the target historical humidity sequence includes a humidity level per day over a past preset period.
The target environment data comprise a target mountain distance (numerical data) of the target farm from the nearest mountain and a target water body distance (numerical data) of the nearest water body; the distance between the target mountain and the nearest mountain is the linear distance between the position of the farm; the target water distance refers to the linear distance between the position of the farm and the nearest water.
A target claim amount for the target farm is determined based on the target farming data, as described in step S120.
And determining the target cultivation quantity of the target cultivation farm according to the target cultivation scale and the target cultivation density. As one example, the target farming number is calculated according to the following formula:
；（1）
wherein, For the target cultivation quantity,/>For the target cultivation scale,/>Is the target cultivation density.
And determining a target claim amount of the target farm according to the target cultivation type, the target cultivation mode and the target cultivation quantity. As one example, the target claim amount is calculated according to the following formula:
；（2）
wherein, For the target claim amount,/>For the target cultivation quantity,/>For the value coefficient corresponding to the target cultivation category,/>Is a value coefficient corresponding to the target cultivation mode.
And (S130) processing the target cultivation data, the target historical weather data and the target environment data by using a pre-constructed risk assessment model to obtain a target unit claim probability of the target cultivation farm in each unit insurance period.
And dividing the target historical weather data into target unit weather data which are in one-to-one correspondence with the unit insurance periods. The target unit weather data comprises a target unit temperature sequence and a target unit humidity sequence of the region of the target cultivation place.
And for each unit insurance period, processing the target cultivation data, the target environment data and the target unit weather data corresponding to the unit insurance period by using a pre-constructed risk assessment model to obtain target claim probability of the target cultivation farm in the unit insurance period. The risk assessment model may assess claim risk under given conditions based on statistical analysis, machine learning, or other algorithms.
In an embodiment of the present application, the risk assessment model includes a multi-modal input layer, a feature cross learning layer, an ensemble learning layer, and an output layer; the step of processing the target cultivation data, the target environmental data and the target unit weather data corresponding to the unit insurance period by using a pre-constructed risk assessment model to obtain a target claim probability of the target cultivation farm in the unit insurance period includes:
Inputting the target cultivation type, the target cultivation scale, the target cultivation density, the target cultivation mode, the target mountain distance, the target water body distance, the target unit temperature sequence and the target unit humidity sequence into the multi-mode input layer to obtain a target type embedded vector corresponding to the target cultivation type, a target mode embedded vector corresponding to the target cultivation mode, a target scale normalized value corresponding to the target cultivation scale, a target density normalized value corresponding to the target cultivation density, a target mountain normalized value corresponding to the target mountain distance, a target water body normalized value corresponding to the target water body distance and a target weather hiding state corresponding to the target unit temperature sequence and the target unit humidity sequence; specifically, the multi-mode input layer is used for inputting the target cultivation type Coding to obtain a target type embedded vector: /(I); For the target cultivation mode/>Coding to obtain a target mode embedded vector: /(I); Applying normalization to process each successive feature/>(Target cultivation scale, target cultivation density, target mountain distance, target water distance): /(I)Wherein/>And/>Features/>, respectivelyMean and standard deviation of (a); processing target unit temperature sequence and target unit humidity sequence using LSTM network, assuming/>And/>Respectively representing the temperature and humidity at time t, and combining the two as/>And (3) performing treatment: /(I)Wherein/>Is the hidden state at time t.
Inputting the target type embedded vector, the target mode embedded vector, the target scale normalized value, the target density normalized value, the target mountain normalized value, the target water normalized value and the target weather hidden state into the feature cross learning layer to obtain feature cross output; specifically, the feature cross learning layer applies a deep cross network and a transducer module to process embedded category features, normalized continuous features and time sequence features, and fuses the results; the depth intersection network processes a target type embedded vector, a target mode embedded vector, a target scale normalized value, a target density normalized value, a target mountain normalized value, a target water normalized value and a target weather hiding state: Wherein/> Representing a function of the cross-layer,/>Representing the deep network part,/>Is the weight,/>Is an input feature; the Transformer module processes the target weather hiding state: /(I)Wherein/>、/>、/>Respectively query, key and value,/>Is the dimension of the key.
Inputting the characteristic cross output into the integrated learning layer to obtain integrated learning output; specifically, the integrated learning layer predicts by using different models, and fuses the results, and the calculation of model fusion can be expressed as weighted average: Wherein/> Is a prediction of the ith model,/>Is the corresponding weight,/>Is the number of models.
Inputting the integrated learning output into the output layer to obtain target claim probability of the target farm in the unit insurance period; specifically, the final model output may be expressed as: Wherein/> Representing the function processed through the ensemble learning layer.
In the risk assessment model, a multi-mode input layer is used for processing different types of input data, a feature cross learning layer is used for learning and representing interaction among features and complex modes, an integrated learning layer is used for fusing predictions of different models to improve accuracy and robustness, and an output layer is used for outputting a final result. Through the structure composition, the risk assessment model not only can process and analyze complex input data more accurately, but also has high flexibility, expansibility and interpretation, and can provide more accurate claim probability prediction in practical application.
In one embodiment of the application, the feature cross learning layer comprises a deep cross network and a transducer module; the step of inputting the target type embedded vector, the target mode embedded vector, the target scale normalized value, the target density normalized value, the target mountain normalized value, the target water normalized value and the target weather hidden state into the feature cross learning layer to obtain feature cross output includes:
And processing and inputting the target type embedded vector, the target mode embedded vector, the target scale normalized value, the target density normalized value, the target mountain normalized value, the target water normalized value and the target weather hiding state into the depth intersection network to obtain depth intersection output. The embedded vector, the normalized value and the time sequence data are directly input into the DCN to perform characteristic crossing and learning, and deep crossing output is obtained.
And processing and inputting the target weather hiding state into the converter module to obtain a converter output. The time series data are processed by a transducer module and converted into attention codes.
And fusing the depth cross output and the transducer output to obtain a characteristic cross output. The fusion strategy package is connected in series and weighted sum, and as an example, the depth cross output and the transducer output are connected in series to obtain a characteristic cross output.
In the feature cross learning layer, a deep cross network is used for automatically learning feature cross, and a transducer module is used for learning complex dependence among features through a self-attention mechanism. By means of the structure composition, different types of features and data can be fully utilized, and the prediction accuracy and generalization capability of the model are improved by combining the depth feature crossing capability of the depth crossing network and the sequence processing capability of the transducer layer.
In an embodiment of the present application, the ensemble learning layer includes a plurality of prediction models; the step of inputting the characteristic cross output into the integrated learning layer to obtain the integrated learning output comprises the following steps:
And inputting the characteristic cross output into each prediction model to obtain model learning output.
And fusing all the model learning outputs to obtain an integrated learning output. And integrating strategy package stacking, weighted average and voting mechanisms, and as an example, carrying out weighted summation on all the model learning outputs to obtain an integrated learning output.
The ensemble learning layer may include a gradient boosting tree, random forest, neural network, etc. model. By means of the structure composition, prediction results from different models can be combined, and accuracy and robustness of prediction can be improved.
As described in the step S140, a target insurance pricing for the target farm is determined based on the target claim amount, the target insurance period, and the target unit claim probability.
And determining the target claim probability of the target farm in the target insurance period according to the target insurance period and the target unit claim probability. As one example, the target claim probability is calculated as follows:
；（3）
wherein, For target claim probability,/>Target unit claim probability for the ith unit insurance period,/>Is the number of unit insurance periods.
And determining target insurance pricing of the target farm according to the target claim amount and the target claim probability. As one example, target insurance pricing is calculated as follows:
；（4）
wherein, Pricing for target insurance,/>For the target claim amount,/>For target claim probability,/>Is a margin of a preset profit.
Referring to fig. 2, in an embodiment of the present application, the pricing method further comprises:
S010, acquiring sample culture data and sample claim conditions of a sample culture farm, and sample historical weather data and sample environment data of a region of the sample culture farm;
S020, training an initial risk assessment model by using the sample culture data, the sample historical weather data, the sample environment data and the sample claim condition to obtain a risk assessment model.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
Referring to fig. 3, a cultivation insurance pricing system based on data analysis according to an embodiment of the application is shown, including:
a target data obtaining module 310, configured to obtain target insurance period and target cultivation data of a target farm, and target historical weather data and target environment data of an area to which the target farm belongs;
a target amount determining module 320, configured to determine a target claim amount of the target farm according to the target cultivation data;
The target probability evaluation module 330 is configured to process the target cultivation data, the target historical weather data and the target environmental data by using a pre-constructed risk evaluation model, so as to obtain a target unit claim probability of the target cultivation farm in each unit insurance period;
And a target pricing determining module 340 configured to determine target insurance pricing for the target farm according to the target claim amount, the target insurance period, and the target unit claim probability.
In an embodiment of the present application, the target cultivation data includes a target cultivation type, a target cultivation scale, a target cultivation density, and a target cultivation mode; the target amount determining module 320 includes:
A target quantity determination submodule for determining a target quantity of cultivation of the target farm according to the target cultivation scale and the target cultivation density;
And the target amount determining submodule is used for determining target claim amount of the target farm according to the target cultivation type, the target cultivation mode and the target cultivation amount.
In one embodiment of the present application, the objective probability evaluation module 330 includes:
the target data segmentation sub-module is used for dividing the target historical weather data into target unit weather data which are in one-to-one correspondence with the unit insurance period;
And the target probability evaluation sub-module is used for processing the target culture data, the target environment data and the target unit weather data corresponding to the unit insurance period by using a pre-constructed risk evaluation model for each unit insurance period to obtain the target claim probability of the target farm in the unit insurance period.
In an embodiment of the present application, the target cultivation data includes a target cultivation type, a target cultivation scale, a target cultivation density, and a target cultivation mode; the target environment data comprise a target mountain distance from the nearest mountain of the target farm and a target water body distance from the nearest water body; the target unit weather data comprise a target unit temperature sequence and a target unit humidity sequence of the region of the target cultivation place; the risk assessment model comprises a multi-mode input layer, a characteristic cross learning layer, an integrated learning layer and an output layer; the target probability evaluation submodule includes:
A first input sub-module, configured to input the target cultivation type, the target cultivation scale, the target cultivation density, the target cultivation mode, the target mountain distance, the target water body distance, the target unit temperature sequence, and the target unit humidity sequence into the multi-mode input layer, to obtain a target type embedded vector corresponding to the target cultivation type, a target mode embedded vector corresponding to the target cultivation mode, a target scale normalized value corresponding to the target cultivation scale, a target density normalized value corresponding to the target cultivation density, a target mountain normalized value corresponding to the target mountain distance, a target water body normalized value corresponding to the target water body distance, and a target weather hidden state corresponding to the target unit temperature sequence and the target unit humidity sequence;
The second input sub-module is used for inputting the target type embedded vector, the target mode embedded vector, the target scale normalization value, the target density normalization value, the target mountain normalization value, the target water body normalization value and the target weather hiding state into the feature cross learning layer to obtain feature cross output;
the third input sub-module is used for inputting the characteristic cross output into the integrated learning layer to obtain integrated learning output;
And the fourth input sub-module is used for inputting the integrated learning output into the output layer to obtain the target claim probability of the target farm in the unit insurance period.
In one embodiment of the application, the feature cross learning layer comprises a deep cross network and a transducer module; the second input submodule includes:
the depth intersection input sub-module is used for processing and inputting the target type embedded vector, the target mode embedded vector, the target scale normalization value, the target density normalization value, the target mountain normalization value, the target water body normalization value and the target weather hiding state into the depth intersection network to obtain depth intersection output;
the converter input sub-module is used for processing and inputting the target weather hiding state into the converter module to obtain converter output;
And the cross fusion sub-module is used for fusing the depth cross output and the transducer output to obtain a characteristic cross output.
In an embodiment of the present application, the cross-fusion submodule includes:
And the serial fusion sub-module is used for carrying out serial connection on the depth cross output and the transducer output to obtain a characteristic cross output.
In an embodiment of the present application, the ensemble learning layer includes a plurality of prediction models; the third input submodule includes:
The model input sub-module is used for inputting the characteristic cross output into each prediction model to obtain model learning output;
And the integrated fusion sub-module is used for fusing all the model learning output to obtain integrated learning output.
In an embodiment of the present application, the integrated fusion submodule includes:
And the weighted fusion sub-module is used for carrying out weighted summation on all the model learning outputs to obtain an integrated learning output.
In one embodiment of the present application, the target pricing determining module 340 includes:
the target probability determination submodule is used for determining target claim probability of the target farm in the target insurance period according to the target insurance period and the target unit claim probability;
And the target pricing determining submodule is used for determining target insurance pricing of the target farm according to the target claim amount and the target claim probability.
Referring to fig. 4, in an embodiment of the present application, further includes:
A sample data obtaining module 210, configured to obtain sample cultivation data and sample claim conditions of a sample farm, and sample historical weather data and sample environment data of an area to which the sample farm belongs;
The initial model training module 220 is configured to train an initial risk assessment model by using the sample culture data, the sample historical weather data, the sample environmental data and the sample claim condition, so as to obtain a risk assessment model.
Referring to FIG. 5, there is shown a computer device of the present application, the computer device 12 being in the form of a general purpose computing device; the computer device 12 comprises: one or more processors or processing units 16, a memory 28, and a bus 18 that connects the various system components, including the memory 28 and the processing unit 16.
Bus 18 may be one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Computer device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
Memory 28 may include computer system readable media in the form of volatile memory, such as random access memory 30 and/or cache memory 32. The computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (commonly referred to as a "hard disk drive"). Although not shown in fig. 5, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk such as a CD-ROM, DVD-ROM, or other optical media may be provided. In such cases, each drive may be coupled to bus 18 through one or more data medium interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42, the program modules 42 being configured to carry out the functions of embodiments of the application.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in a memory, such program modules 42 including an operating system, one or more application programs, other program modules 42, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.
The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, camera, etc.), one or more devices that enable an operator to interact with the computer device 12, and/or any devices (e.g., network card, modem, etc.) that enable the computer device 12 to communicate with one or more other computing devices. Such communication may occur through the I/O interface 22. Moreover, computer device 12 may also communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet, through network adapter 20. As shown in fig. 5, the network adapter 20 communicates with other modules of the computer device 12 via the bus 18. It should be appreciated that although not shown in fig. 5, other hardware and/or software modules may be used in connection with computer device 12, including, but not limited to: microcode, device drivers, redundant processing units 16, external disk drive arrays, RAID systems, tape drives, data backup storage systems 34, and the like.
The processing unit 16 executes various functional applications and data processing, such as implementing the pricing method provided by any of the embodiments of the present application, by running programs stored in the memory 28.
That is, the processing unit 16 may implement: acquiring target insurance period and target cultivation data of a target cultivation field, and target historical weather data and target environment data of a region of the target cultivation field; determining a target claim amount of the target farm according to the target cultivation data; processing the target cultivation data, the target historical weather data and the target environment data by using a pre-constructed risk assessment model to obtain target unit claim probability of the target cultivation farm in each unit insurance period; and determining the target insurance pricing of the target farm according to the target claim amount, the target insurance period and the target unit claim probability.
In one embodiment of the present application, there is also provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the pricing method provided by any of the embodiments of the present application.
That is, the program, when executed by the processor, may implement: acquiring target insurance period and target cultivation data of a target cultivation field, and target historical weather data and target environment data of a region of the target cultivation field; determining a target claim amount of the target farm according to the target cultivation data; processing the target cultivation data, the target historical weather data and the target environment data by using a pre-constructed risk assessment model to obtain target unit claim probability of the target cultivation farm in each unit insurance period; and determining the target insurance pricing of the target farm according to the target claim amount, the target insurance period and the target unit claim probability.
Any combination of one or more computer readable media may be employed. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including electro-magnetic, optical, or any suitable combination of the preceding. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Computer program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the operator's computer, partly on the operator's computer, as a stand-alone software package, partly on the operator's computer and partly on a remote computer or entirely on the remote computer or server. In the case of remote computers, the remote computer may be connected to the operator computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (e.g., connected through the internet using an internet service provider). In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the application.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or terminal device that comprises the element.
The above detailed description of the method, system, device and storage medium for pricing cultivation insurance based on data analysis provided by the application applies specific examples to illustrate the principle and implementation of the application, and the above examples are only used for helping to understand the method and core idea of the application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (10)
1. A data analysis-based farming insurance pricing system, comprising:
The target data acquisition module is used for acquiring target insurance period and target cultivation data of a target cultivation field, and target historical weather data and target environment data of an area of the target cultivation field;
The target amount determining module is used for determining target claim amount of the target farm according to the target cultivation data;
the target probability evaluation module is used for processing the target cultivation data, the target historical weather data and the target environment data by using a pre-constructed risk evaluation model to obtain target unit claim probability of the target cultivation farm in each unit insurance period;
And the target pricing determining module is used for determining target insurance pricing of the target farm according to the target claim amount, the target insurance period and the target unit claim probability.
2. A pricing system according to claim 1, wherein the target farming data comprises a target farming category, a target farming scale, a target farming density, and a target farming pattern; the target amount determining module includes:
A target quantity determination submodule for determining a target quantity of cultivation of the target farm according to the target cultivation scale and the target cultivation density;
And the target amount determining submodule is used for determining target claim amount of the target farm according to the target cultivation type, the target cultivation mode and the target cultivation amount.
3. A pricing system according to claim 1, wherein the target probability assessment module comprises:
the target data segmentation sub-module is used for dividing the target historical weather data into target unit weather data which are in one-to-one correspondence with the unit insurance period;
And the target probability evaluation sub-module is used for processing the target culture data, the target environment data and the target unit weather data corresponding to the unit insurance period by using a pre-constructed risk evaluation model for each unit insurance period to obtain the target claim probability of the target farm in the unit insurance period.
4. A pricing system according to claim 3, wherein the target farming data comprises a target farming category, a target farming scale, a target farming density, and a target farming pattern; the target environment data comprise a target mountain distance from the nearest mountain of the target farm and a target water body distance from the nearest water body; the target unit weather data comprise a target unit temperature sequence and a target unit humidity sequence of the region of the target cultivation place; the risk assessment model comprises a multi-mode input layer, a characteristic cross learning layer, an integrated learning layer and an output layer; the target probability evaluation submodule includes:
A first input sub-module, configured to input the target cultivation type, the target cultivation scale, the target cultivation density, the target cultivation mode, the target mountain distance, the target water body distance, the target unit temperature sequence, and the target unit humidity sequence into the multi-mode input layer, to obtain a target type embedded vector corresponding to the target cultivation type, a target mode embedded vector corresponding to the target cultivation mode, a target scale normalized value corresponding to the target cultivation scale, a target density normalized value corresponding to the target cultivation density, a target mountain normalized value corresponding to the target mountain distance, a target water body normalized value corresponding to the target water body distance, and a target weather hidden state corresponding to the target unit temperature sequence and the target unit humidity sequence;
The second input sub-module is used for inputting the target type embedded vector, the target mode embedded vector, the target scale normalization value, the target density normalization value, the target mountain normalization value, the target water body normalization value and the target weather hiding state into the feature cross learning layer to obtain feature cross output;
the third input sub-module is used for inputting the characteristic cross output into the integrated learning layer to obtain integrated learning output;
And the fourth input sub-module is used for inputting the integrated learning output into the output layer to obtain the target claim probability of the target farm in the unit insurance period.
5. A pricing system according to claim 4, wherein the feature cross-learning layer comprises a deep cross-network and a transducer module; the second input submodule includes:
the depth intersection input sub-module is used for processing and inputting the target type embedded vector, the target mode embedded vector, the target scale normalization value, the target density normalization value, the target mountain normalization value, the target water body normalization value and the target weather hiding state into the depth intersection network to obtain depth intersection output;
the converter input sub-module is used for processing and inputting the target weather hiding state into the converter module to obtain converter output;
And the cross fusion sub-module is used for fusing the depth cross output and the transducer output to obtain a characteristic cross output.
6. A pricing system according to claim 5, wherein the cross-fusion submodule comprises:
And the serial fusion sub-module is used for carrying out serial connection on the depth cross output and the transducer output to obtain a characteristic cross output.
7. A pricing system according to claim 4, wherein the ensemble learning layer comprises a number of predictive models; the third input submodule includes:
The model input sub-module is used for inputting the characteristic cross output into each prediction model to obtain model learning output;
And the integrated fusion sub-module is used for fusing all the model learning output to obtain integrated learning output.
8. A pricing system according to claim 7, wherein the integrated fusion submodule comprises:
And the weighted fusion sub-module is used for carrying out weighted summation on all the model learning outputs to obtain an integrated learning output.
9. A pricing system according to claim 1, wherein the target pricing determination module comprises:
the target probability determination submodule is used for determining target claim probability of the target farm in the target insurance period according to the target insurance period and the target unit claim probability;
And the target pricing determining submodule is used for determining target insurance pricing of the target farm according to the target claim amount and the target claim probability.
10. A pricing system as recited in claim 1, further comprising:
The sample data acquisition module is used for acquiring sample culture data and sample claim conditions of a sample culture farm, and sample historical weather data and sample environment data of a region of the sample culture farm;
And the initial model training module is used for training an initial risk assessment model by using the sample culture data, the sample historical weather data, the sample environment data and the sample claim condition to obtain a risk assessment model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410302731.5A CN117934176B (en) | 2024-03-18 | 2024-03-18 | Breeding insurance pricing system based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410302731.5A CN117934176B (en) | 2024-03-18 | 2024-03-18 | Breeding insurance pricing system based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117934176A true CN117934176A (en) | 2024-04-26 |
| CN117934176B CN117934176B (en) | 2024-06-11 |
Family
ID=90766937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410302731.5A Active CN117934176B (en) | 2024-03-18 | 2024-03-18 | Breeding insurance pricing system based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117934176B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130332205A1 (en) * | 2012-06-06 | 2013-12-12 | David Friedberg | System and method for establishing an insurance policy based on various farming risks |
| CN110503562A (en) * | 2019-03-27 | 2019-11-26 | 南京国科双创信息技术研究院有限公司 | A kind of artificial intelligence insurance premium rate calculation method based on big data analysis |
| CN111126720A (en) * | 2020-02-28 | 2020-05-08 | 深圳前海微众银行股份有限公司 | Farm risk prediction method, device, equipment and storage medium |
| CN111210227A (en) * | 2018-11-22 | 2020-05-29 | 重庆小雨点小额贷款有限公司 | Data processing method and device, server and computer readable storage medium |
| CN113095889A (en) * | 2021-04-28 | 2021-07-09 | 中国第一汽车股份有限公司 | Insurance pricing method, device, server and storage medium |
| CN116843362A (en) * | 2023-06-29 | 2023-10-03 | 中国平安财产保险股份有限公司 | Premium pricing method, device, equipment and storage medium |
| CN117592662A (en) * | 2024-01-17 | 2024-02-23 | 烟台大学 | Ecological fishery resource evaluation system based on data analysis |
-
2024
- 2024-03-18 CN CN202410302731.5A patent/CN117934176B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130332205A1 (en) * | 2012-06-06 | 2013-12-12 | David Friedberg | System and method for establishing an insurance policy based on various farming risks |
| CN111210227A (en) * | 2018-11-22 | 2020-05-29 | 重庆小雨点小额贷款有限公司 | Data processing method and device, server and computer readable storage medium |
| CN110503562A (en) * | 2019-03-27 | 2019-11-26 | 南京国科双创信息技术研究院有限公司 | A kind of artificial intelligence insurance premium rate calculation method based on big data analysis |
| CN111126720A (en) * | 2020-02-28 | 2020-05-08 | 深圳前海微众银行股份有限公司 | Farm risk prediction method, device, equipment and storage medium |
| CN113095889A (en) * | 2021-04-28 | 2021-07-09 | 中国第一汽车股份有限公司 | Insurance pricing method, device, server and storage medium |
| CN116843362A (en) * | 2023-06-29 | 2023-10-03 | 中国平安财产保险股份有限公司 | Premium pricing method, device, equipment and storage medium |
| CN117592662A (en) * | 2024-01-17 | 2024-02-23 | 烟台大学 | Ecological fishery resource evaluation system based on data analysis |
Non-Patent Citations (2)
| Title |
|---|
| 付万;任学慧;张海静;林霞;: "基于GIS的辽宁省气象灾害与保险风险管理***", 辽宁师范大学学报(自然科学版), no. 03, 15 September 2008 (2008-09-15), pages 361 - 363 * |
| 杨立, 左春, 王裕国: "保险洪灾损失预测模型", 计算机辅助设计与图形学学报, no. 11, 20 November 2005 (2005-11-20), pages 2523 - 2529 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117934176B (en) | 2024-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110458107B (en) | Method and device for image recognition | |
| CN110362823B (en) | Training method and device for descriptive text generation model | |
| CN111784159B (en) | Food risk traceability information grading method and device | |
| CN112699998B (en) | Time series prediction method and device, electronic equipment and readable storage medium | |
| CN112668238B (en) | Rainfall processing method, rainfall processing device, rainfall processing equipment and storage medium | |
| CN111291803B (en) | Image grading granularity migration method, system, equipment and medium | |
| Lin-Ye et al. | Multivariate hybrid modelling of future wave-storms at the northwestern Black Sea | |
| Alexandridis et al. | Real Estate valuation and forecasting in non-homogeneous markets: A case study in Greece during the financial crisis | |
| CN112988840A (en) | Time series prediction method, device, equipment and storage medium | |
| CN115457982A (en) | Pre-training optimization method, device, equipment and medium of emotion prediction model | |
| Chen et al. | Evaluation of GloFAS-Seasonal Forecasts for cascade reservoir impoundment operation in the upper Yangtze River | |
| CN117934176B (en) | Breeding insurance pricing system based on data analysis | |
| CN113239883A (en) | Method and device for training classification model, electronic equipment and storage medium | |
| CN112906398A (en) | Sentence semantic matching method, system, storage medium and electronic equipment | |
| CN116977707A (en) | Image recognition method, device, electronic equipment and storage medium | |
| CN115857314A (en) | Cultivation management method and system based on edge calculation | |
| CN114492657A (en) | Plant disease classification method and device, electronic equipment and storage medium | |
| US20230022253A1 (en) | Fast and accurate prediction methods and systems based on analytical models | |
| CN112529315B (en) | Landslide prediction method, landslide prediction device, landslide prediction equipment and storage medium | |
| CN111062477B (en) | Data processing method, device and storage medium | |
| CN112257908B (en) | Mountain area agricultural multi-source heterogeneous data integration method and device | |
| Liu et al. | Dual‐stage time series analysis on multifeature adaptive frequency domain modeling | |
| CN111178630A (en) | Load prediction method and device | |
| Kumar et al. | A study of iOS machine learning and artificial intelligence frameworks and libraries for cotton plant disease detection | |
| CN115146054A (en) | Multi-label classification method and device and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |