Big Data-Based Total Output Value Prediction Method, System and Medium for Agriculture, Forestry, Animal Husbandry and Fishery

Abstract

The invention of the present application provides a method, system and medium for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data. The method includes: dividing sub-regions according to the regional agricultural production light remote sensing feature portraits generated by regions, matching the production types of each sub-region according to the average data of each production type sample set, calculating the output value correction data of four types of production regions and the total output value data of agriculture, forestry, animal husbandry and fishery based on the unit average output value of similar samples in each type of sub-region, and then evaluating the production effectiveness of agriculture, forestry, animal husbandry and fishery in the region within the cycle through the threshold comparison of the output value comparison results of historical average total data; thus, dividing the production type regions through the light remote sensing information within the region, obtaining the output value data of each type of production region in combination with historical sample data, and obtaining the total output value of agriculture, forestry, animal husbandry and fishery in combination with the interference situation of production factors and judging the production effectiveness of the region, so as to realize the measurement and evaluation of regional agricultural production through big data and night light remote sensing technology.

Description

Technical Field

[0001] The present application relates to the technical field of nighttime light remote sensing images and the production technology fields of agriculture, forestry, animal husbandry and fishery. Specifically, it relates to a method, system and medium for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data. Background Art

[0002] The total output value of agriculture, forestry, animal husbandry and fishery is an important indicator for evaluating the development level of the agricultural economy. Its parameter indicators mainly come from the data reports and research surveys of the statistical department. The traditional evaluation method is time-consuming and laborious, resulting in poor economy and convenience; the nighttime light remote sensing image technology can detect and record the light radiation emitted from regional buildings, streets, factories, and facilities, and can be applied to the research and monitoring of economic and social indicators such as regional population, economy, and productivity. At present, there is still a gap in the research on evaluating and predicting the total output value of agriculture, forestry, animal husbandry and fishery using nighttime light remote sensing image technology, and it has not been realized to effectively evaluate and predict agriculture, forestry, animal husbandry and fishery through the combination of nighttime light remote sensing image technology and big data algorithms.

[0003] In view of the above problems, there is an urgent need for an effective technical solution at present. Summary of the Invention

[0004] The purpose of the present application is to provide a method, system and medium for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data, which can divide the production type areas through the nighttime light remote sensing image information in the area, and obtain the output value data of each type of production area by combining historical sample data, and obtain the total output value of agriculture, forestry, animal husbandry and fishery and judge the production effectiveness of the area by combining the interference situation of production factors, so as to realize the effective calculation and evaluation of the total output value of agriculture, forestry, animal husbandry and fishery in the area through big data and nighttime light remote sensing technology.

[0005] The present application also provides a method for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data, including the following steps:

[0006] Obtain the light remote sensing monitoring information of the preset area within the periodic time period according to the preset area nighttime light remote sensing image information library, and generate a regional agricultural product light remote sensing feature portrait. Divide the preset area into sub-areas according to the light remote sensing distribution characteristics of the feature portrait, obtain multiple light remote sensing monitoring sub-areas and extract light remote sensing feature data;

[0007] Obtain the agricultural light remote sensing area sample sets of multiple sample areas of each production type in the agricultural, forestry, animal husbandry and fishery production types during multiple identical historical cycle time periods, as well as the average data of the sample area light remote sensing characteristics corresponding to the light remote sensing area samples of each production type, and then compare them with the light remote sensing characteristic data of each light remote sensing monitoring sub-area respectively to obtain the sub-area production type light sense similarity coefficients corresponding to the agricultural, forestry, animal husbandry and fishery production types respectively. Then, compare and match the calibrated production types of each light remote sensing monitoring sub-area through the production type light sense similarity threshold, and classify the agricultural, forestry, animal husbandry and fishery production sub-areas of each light remote sensing monitoring sub-area;

[0008] Obtain multiple similar agricultural light remote sensing area similar samples and agricultural area sample light sense record data according to the agricultural area production characteristic data of each agricultural production sub-area, and process to obtain the average output value data of the light sense duration per unit area of agricultural samples. Then, combine with the corresponding light remote sensing characteristic data of each agricultural production sub-area to process and obtain the agricultural production area output value data of the preset area, and correct the agricultural production area output value data according to the agricultural production factor data to obtain the corrected agricultural production area output value data;

[0009] Obtain multiple similar forestry light remote sensing area similar samples and forestry area sample light sense record data according to the forestry area production characteristic data of each forestry production sub-area, and process to obtain the average output value data of the light sense duration per unit area of forestry samples. Then, combine with the corresponding light remote sensing characteristic data of each forestry production sub-area to process and obtain the forestry production area output value data of the preset area, and correct the forestry production area output value data according to the forestry production factor data to obtain the corrected forestry production area output value data;

[0010] Obtain multiple similar animal husbandry light remote sensing area similar samples and animal husbandry area sample light sense record data according to the animal husbandry area production characteristic data of each animal husbandry production sub-area, and process to obtain the average output value data of the light sense duration per unit area of animal husbandry samples. Then, combine with the corresponding light remote sensing characteristic data of each animal husbandry production sub-area to process and obtain the animal husbandry production area output value data of the preset area, and correct the animal husbandry production area output value data according to the animal husbandry production factor data to obtain the corrected animal husbandry production area output value data;

[0011] Obtain multiple similar fishery light remote sensing area similar samples and fishery area sample light sense record data according to the fishery area production characteristic data of each fishery production sub-area, and process to obtain the average output value data of the light sense duration per unit area of fishery samples. Then, combine with the corresponding light remote sensing characteristic data of each fishery production sub-area to process and obtain the fishery production area output value data of the preset area, and correct the fishery production area output value data according to the fishery production factor data to obtain the corrected fishery production area output value data;

[0012] The data of the interference factors of the type industry output value in the agriculture, forestry, animal husbandry and fishery industries in the preset region during the cycle time period is processed through a preset market factor interference model to obtain the interference coefficient of the agriculture, forestry, animal husbandry and fishery industry factors;

[0013] The type production area output value correction data corresponding to the production areas of the agriculture, forestry, animal husbandry and fishery industries in the preset region is processed in combination with the interference coefficient of the agriculture, forestry, animal husbandry and fishery industry factors to obtain the total output value data of the agriculture, forestry, animal husbandry and fishery industries, and the production effectiveness of the agriculture, forestry, animal husbandry and fishery industries in the preset region during the cycle time period is evaluated according to the output value comparison result with the historical average total output value of the agriculture, forestry, animal husbandry and fishery industries.

[0014] Optionally, in the method for predicting the total output value of the agriculture, forestry, animal husbandry and fishery industries based on big data described in this application, the method for obtaining the light remote sensing monitoring information of the preset region during the cycle time period according to the information library of the night light remote sensing images of the preset region, generating the regional agricultural product light remote sensing feature portrait, and dividing the preset region into sub-regions according to the light remote sensing distribution characteristics of the feature portrait to obtain multiple light remote sensing monitoring sub-regions and extracting the light remote sensing feature data includes:

[0015] Obtain the light remote sensing monitoring information of the preset region during the cycle time period according to the information library of the night light remote sensing images of the preset region, including the light distribution intensity information, the light distribution density information, the light distribution time period information and the light frequency duration information;

[0016] Generate the regional agricultural product light remote sensing feature portrait of the preset region during the cycle time period according to the light remote sensing monitoring information;

[0017] Divide the preset region into sub-regions through a preset light remote sensing feature division model according to the light remote sensing distribution characteristics of the regional agricultural product light remote sensing feature portrait to obtain multiple light remote sensing monitoring sub-regions;

[0018] Obtain the light remote sensing feature data of each light remote sensing monitoring sub-region, including the light intensity data, the light density data, the light time period data and the light frequency duration data.

[0019] Optionally, in the method for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data described in this application, obtaining the agricultural product light remote sensing area sample set of multiple sample areas of each production type in the production types of agriculture, forestry, animal husbandry and fishery in multiple identical historical cycle time periods, and the average data of the sample area light remote sensing characteristics corresponding to the light remote sensing area samples of each production type, and then comparing them with the light remote sensing characteristic data of each light remote sensing monitoring sub-area respectively to obtain the sub-area production type light perception similarity coefficients corresponding to the production types of agriculture, forestry, animal husbandry and fishery respectively, and then comparing and matching the calibrated production types of each light remote sensing monitoring sub-area through the production type light perception similarity threshold, and dividing the agricultural, forestry, animal husbandry and fishery production sub-area types of each light remote sensing monitoring sub-area, including:

[0020] Obtaining the agricultural product light remote sensing area sample set of multiple production type sample areas corresponding to each production type in the production types of agriculture, forestry, animal husbandry and fishery according to the preset agricultural, forestry, animal husbandry and fishery production light perception database, including multiple agricultural light remote sensing area samples, forestry light remote sensing area samples, animal husbandry light remote sensing area samples, and fishery light remote sensing area samples;

[0021] Obtaining the sample area light remote sensing characteristic data corresponding to the light remote sensing area samples of each production type in the agricultural product light remote sensing area sample set, including light intensity sample data, light density sample data, light time period sample data, and light frequency duration sample data;

[0022] Obtaining the average data of the sample area light remote sensing characteristics corresponding to the agricultural light remote sensing area samples, forestry light remote sensing area samples, animal husbandry light remote sensing area samples, and fishery light remote sensing area samples in the agricultural product light remote sensing area sample set respectively;

[0023] Comparing the average data of the sample area light remote sensing characteristics corresponding to the light remote sensing area samples of each production type in the agricultural product light remote sensing area sample set with the light remote sensing characteristic data of each light remote sensing monitoring sub-area respectively, and obtaining the sub-area production type light perception similarity coefficients corresponding to the production types of agriculture, forestry, animal husbandry and fishery of each light remote sensing monitoring sub-area respectively;

[0024] Comparing and matching the sub-area production type light perception similarity coefficients with the preset production type light perception similarity thresholds corresponding to the production types of agriculture, forestry, animal husbandry and fishery respectively, and obtaining the threshold matching degrees respectively;

[0025] Taking the production type in the production types of agriculture, forestry, animal husbandry and fishery with the best threshold matching degree as the calibrated production type of each light remote sensing monitoring sub-area;

[0026] Calibrate the production types of each light remote sensing monitoring sub-region within the preset area, and divide each light remote sensing monitoring sub-region into agricultural production sub-regions, forestry production sub-regions, animal husbandry production sub-regions, and fishery production sub-regions.

[0027] Optionally, in the method for predicting the total output value of agriculture, forestry, animal husbandry, and fishery based on big data described in this application, obtaining multiple similar agricultural light remote sensing area similar samples and agricultural area sample light perception record data according to the agricultural area production characteristic data of each agricultural production sub-region, and processing to obtain the average output value data of the light perception duration per unit area of agricultural samples, and then combining the corresponding light remote sensing characteristic data of each agricultural production sub-region to process and obtain the agricultural production area output value data of the preset area, and correcting the agricultural production area output value data according to the agricultural production factor data to obtain the corrected agricultural production area output value data, including:

[0028] Obtain the agricultural area production characteristic data of each agricultural production sub-region, including the data of the type of planted crops, latitude and altitude data, and planted area data;

[0029] According to the preset agricultural, forestry, animal husbandry, and fishery production light perception database, obtain multiple similar agricultural light remote sensing area similar samples similar to the agricultural area production characteristic data of each agricultural production sub-region;

[0030] Obtain the agricultural area sample light perception record data of the multiple agricultural light remote sensing area similar samples in multiple identical historical cycle time periods, including sample cumulative light intensity data, sample cumulative duration data, sample area planted area data, and sample area agricultural output value data;

[0031] Process according to the agricultural area sample light perception record data of each agricultural light remote sensing area similar sample to obtain the average output value data of the light perception duration per unit area of agricultural samples;

[0032] According to the average output value data of the light perception duration per unit area of agricultural samples, combine the corresponding light remote sensing characteristic data and planted area data of each agricultural production sub-region for aggregation processing to obtain the agricultural production area output value data of the preset area;

[0033] Obtain the agricultural production factor data of the preset area in the cycle time period, including irrigation precipitation data, cumulative sunshine amount data, and average temperature volatility data, and correct the agricultural production area output value data to obtain the corrected agricultural production area output value data;

[0034] The calculation formula for the agricultural production area output value data is:

[0035]

[0036] where m zFor the output value data of the agricultural production area, λ W For the average output value data of the light perception duration per unit area of the agricultural sample, x cj , g kj , p mj , b zj , h uj They are respectively the light intensity data, light density data, light period data, light frequency duration data, and planting area data of the j-th agricultural production sub-area. m is the number of agricultural production sub-areas. ε is the preset feature coefficient;

[0037] The correction calculation formula for the corrected data of the agricultural production area output value is:

[0038]

[0039] Among them, m L Is the corrected data of the agricultural production area output value, m z Is the output value data of the agricultural production area, a f , e d , u t They are respectively the irrigation precipitation data, cumulative sunshine data, and average temperature volatility data. ρ 1 , ρ 2 , ρ 3 Are the preset feature coefficients.

[0040] Optionally, in the total output value prediction method of agriculture, forestry, animal husbandry and fishery based on big data of the present application, obtaining a plurality of similar forestry light remote sensing area similar samples and forestry area sample light perception record data according to the forestry area production characteristic data of each forestry production sub-area, and processing to obtain the average output value data of the light perception duration per unit area of the forestry sample, and then combining the corresponding light remote sensing characteristic data of each forestry production sub-area to process to obtain the output value data of the forestry production area of the preset area, and correcting the output value data of the forestry production area according to the forestry production factor data to obtain the corrected data of the forestry production area output value, including:

[0041] Obtaining the forestry area production characteristic data of each forestry production sub-area, including tree species data, latitude and altitude data, and planting area data;

[0042] Obtaining a plurality of forestry light remote sensing area similar samples similar to the forestry area production characteristic data of each forestry production sub-area according to the preset agriculture, forestry, animal husbandry and fishery production light perception database;

[0043] Obtaining the forestry area sample light perception record data of the plurality of forestry light remote sensing area similar samples in a plurality of same historical cycle time periods, including sample cumulative light intensity data, sample cumulative duration data, sample area planting area data, and sample area forestry output value data;

[0044] Process the light perception record data of the forestry area samples of each similar forestry light remote sensing area to obtain the average output value data of the light perception duration per unit area of the forestry samples;

[0045] Perform aggregation processing on the average output value data of the light perception duration per unit area of the forestry samples in combination with the corresponding light remote sensing feature data and planting area data of each forestry production sub-region to obtain the forestry production area output value data of the preset region;

[0046] Obtain the forestry production factor data of the preset region during the cycle time period, including precipitation data, cumulative sunshine amount data, and average temperature volatility data, and correct the forestry production area output value data to obtain the corrected forestry production area output value data;

[0047] The calculation formula for the forestry production area output value data is:

[0048]

[0049] Among them, f g is the forestry production area output value data, is the average output value data of the light perception duration per unit area of the forestry samples, x cj , g kj , p mj , b zj , z vj are respectively the light intensity data, light density data, light time period data, light frequency duration data, and planting area data of the jth forestry production sub-region, m is the number of forestry production sub-regions, ε is the preset characteristic coefficient;

[0050] The correction calculation formula for the corrected forestry production area output value data is:

[0051]

[0052] Among them, f P is the corrected forestry production area output value data, f g is the forestry production area output value data, t s , e d , u t are respectively the precipitation data, cumulative sunshine amount data, and average temperature volatility data, ρ 1 , ρ 2 , ρ 3 are the preset characteristic coefficients.

[0053] Optionally, in the method for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data described in this application, the steps of obtaining multiple similar forestry light remote sensing area similar samples and forestry area sample light perception record data according to the forestry area production characteristic data of each forestry production sub-region, processing to obtain the average output value data of the light perception duration per unit area of the forestry samples, then combining the corresponding light remote sensing characteristic data of each forestry production sub-region to process and obtain the forestry production area output value data of the preset area, and correcting the forestry production area output value data according to the forestry production factor data to obtain the forestry production area output value correction data include:

[0054] Obtain the forestry area production characteristic data of each forestry production sub-region, including tree species category data, latitude and altitude data, and planting area data;

[0055] According to the preset agriculture, forestry, animal husbandry and fishery production light perception database, obtain multiple forestry light remote sensing area similar samples similar to the forestry area production characteristic data of each forestry production sub-region;

[0056] Obtain the forestry area sample light perception record data of the multiple forestry light remote sensing area similar samples in multiple same historical cycle time periods, including sample cumulative light intensity data, sample cumulative duration data, sample area planting area data, and sample area forestry output value data;

[0057] Process according to the forestry area sample light perception record data of each forestry light remote sensing area similar sample to obtain the average output value data of the light perception duration per unit area of the forestry samples;

[0058] According to the average output value data of the light perception duration per unit area of the forestry samples, combine the corresponding light remote sensing characteristic data and planting area data of each forestry production sub-region for aggregation processing to obtain the forestry production area output value data of the preset area;

[0059] Obtain the forestry production factor data of the preset area in the cycle time period, including precipitation data, cumulative sunshine amount data, and average temperature volatility data, and correct the forestry production area output value data to obtain the forestry production area output value correction data;

[0060] The calculation formula for the forestry production area output value data is:

[0061]

[0062] where f g is the forestry production area output value data, is the average output value data of the light perception duration per unit area of the forestry samples, x cj 、g kj 、p mj 、b zj, z vj are respectively the light intensity data, light density data, light period data, light frequency duration data, and planting area data of the j-th forestry production sub-region. m is the number of forestry production sub-regions. ε is a preset feature coefficient;

[0063] The correction calculation formula for the forestry production area output value correction data is:

[0064]

[0065] Among them, f P is the forestry production area output value correction data, f g is the forestry production area output value data, t s , e d , u t are respectively precipitation data, cumulative sunshine duration data, and average temperature volatility data. ρ 1 , ρ 2 , ρ 3 are preset feature coefficients.

[0066] Optionally, in the method for predicting the total output value of agriculture, forestry, animal husbandry, and fishery based on big data described in this application, obtaining multiple similar fishery light remote sensing area similar samples and fishery area sample light perception record data according to the fishery area production characteristic data of each fishery production sub-region, and processing to obtain the average output value data of the fishery sample per unit area of light perception duration, and then combining the corresponding light remote sensing characteristic data of each fishery production sub-region to process and obtain the fishery production area output value data of the preset area, and correcting the fishery production area output value data according to the fishery production factor data to obtain the fishery production area output value correction data, including:

[0067] Obtain the fishery area production characteristic data of each fishery production sub-region, including fishing ground sea area data, operating latitude data, and fishing area data;

[0068] According to the preset agriculture, forestry, animal husbandry, and fishery production light perception database, obtain multiple fishery light remote sensing area similar samples similar to the fishery area production characteristic data of each fishery production sub-region;

[0069] Obtain the fishery area sample light perception record data of the multiple fishery light remote sensing area similar samples in multiple identical historical cycle time periods, including sample cumulative light intensity data, sample cumulative duration data, sample area fishing area data, and sample area fishery output value data;

[0070] Process according to the fishery area sample light perception record data of each fishery light remote sensing area similar sample to obtain the average output value data of the fishery sample per unit area of light perception duration;

[0071] Aggregate the average output value data of the light perception duration per unit area of the fishery samples, combined with the corresponding light remote sensing feature data and fishing area data of each fishery production sub-region, to obtain the fishery production area output value data of the preset region;

[0072] Obtain the fishery production factor data of the preset region during the cycle time period, including meteorological stability data, equipment operation efficiency data, and water temperature volatility data, and correct the fishery production area output value data to obtain the corrected fishery production area output value data;

[0073] The calculation formula for the fishery production area output value data is:

[0074]

[0075] Among them, c m is the fishery production area output value data, γ D is the average output value data of the light perception duration per unit area of the fishery samples, x cj , g kj , p mj , b zj , t cj are respectively the light intensity data, light density data, light period data, light frequency duration data, and fishing area data of the j-th fishery production sub-region, m is the number of fishery production sub-regions, ε is the preset feature coefficient;

[0076] The correction calculation formula for the corrected fishery production area output value data is:

[0077]

[0078] Among them, c V is the corrected fishery production area output value data, c m is the fishery production area output value data, a r , s a , k c are respectively the meteorological stability data, equipment operation efficiency data, and water temperature volatility data, θ 1 , θ 2 are the preset feature coefficients.

[0079] Optionally, in the method for predicting the total output value of agriculture, forestry, animal husbandry, and fishery based on big data described in this application, the type industry output value interference factor data of agriculture, forestry, animal husbandry, and fishery in the preset region is processed through a preset market factor interference model to obtain the agriculture, forestry, animal husbandry, and fishery factor market interference coefficient, including:

[0080] Obtain the data of the interference factors of the output value of the agriculture, forestry, animal husbandry and fishery industries in the preset area during the cycle time period, including the price fluctuation data, quality fluctuation data and policy subsidy fluctuation data corresponding to the agriculture, forestry, animal husbandry and fishery industries respectively;

[0081] Process the price fluctuation data, quality fluctuation data and policy subsidy fluctuation data corresponding to the agriculture, forestry, animal husbandry and fishery industries respectively through a preset market factor interference model to obtain the market factor interference coefficients of the agriculture, forestry, animal husbandry and fishery industries;

[0082] The market factor interference coefficients of the agriculture, forestry, animal husbandry and fishery industries include the market factor interference coefficient of agriculture, the market factor interference coefficient of forestry, the market factor interference coefficient of animal husbandry and the market factor interference coefficient of fishery;

[0083] The calculation formula of the market factor interference coefficients of the agriculture, forestry, animal husbandry and fishery industries is:

[0084]

[0085] Among them, φ fr is the r-th coefficient among the four coefficients of the market factor interference coefficient of agriculture, the market factor interference coefficient of forestry, the market factor interference coefficient of animal husbandry and the market factor interference coefficient of fishery in the market factor interference coefficients of the agriculture, forestry, animal husbandry and fishery industries, and α qr , δ pr , κ er are the price fluctuation data, quality fluctuation data and policy subsidy fluctuation data corresponding to the r-th coefficient among the four coefficients of the market factor interference coefficient of agriculture, the market factor interference coefficient of forestry, the market factor interference coefficient of animal husbandry and the market factor interference coefficient of fishery respectively, and ζ 1 , ζ 2 , ζ 3 are preset characteristic coefficients.

[0086] Optionally, in the method for predicting the total output value of the agriculture, forestry, animal husbandry and fishery industries based on big data in the present application, the processing of combining the type production area output value correction data corresponding to the production areas of the agriculture, forestry, animal husbandry and fishery industries in the preset area with the market factor interference coefficients of the agriculture, forestry, animal husbandry and fishery industries to obtain the total output value data of the agriculture, forestry, animal husbandry and fishery industries, and evaluating the production effectiveness of the agriculture, forestry, animal husbandry and fishery industries in the preset area during the cycle time period according to the output value comparison result with the historical average total output value data of the agriculture, forestry, animal husbandry and fishery industries includes:

[0087] Compensate and aggregate the agricultural production area output value correction data, forestry production area output value correction data, animal husbandry production area output value correction data and fishery production area output value correction data corresponding to the production areas of the agriculture, forestry, animal husbandry and fishery industries in the preset area respectively in combination with the market factor interference coefficients of the agriculture, forestry, animal husbandry and fishery industries to obtain the total output value data of the agriculture, forestry, animal husbandry and fishery industries in the preset area;

[0088] Compare the total data of the output value of agriculture, forestry, animal husbandry and fishery with the historical average total data of the output value of agriculture, forestry, animal husbandry and fishery in the preset area in multiple identical historical cycle time periods to obtain the output value comparison result;

[0089] Compare the output value comparison result with the preset output value comparison threshold, and evaluate the production effectiveness of agriculture, forestry, animal husbandry and fishery in the preset area during the cycle time period according to the threshold comparison result;

[0090] The calculation formula for the total data of the output value of agriculture, forestry, animal husbandry and fishery is:

[0091]

[0092] Wherein, is the total data of the output value of agriculture, forestry, animal husbandry and fishery, m L is the output value correction data of the agricultural production area, f P is the output value correction data of the forestry production area, q H is the output value correction data of the animal husbandry production area, c V is the output value correction data of the fishery production area, φ f1 、φ f2 、φ f3 、φ f4 are the interference coefficients of the agricultural factor market, the interference coefficient of the forestry factor market, the interference coefficient of the animal husbandry factor market, and the interference coefficient of the fishery factor market respectively, χ 1 、χ 2 、χ 3 、χ 4 are preset characteristic coefficients.

[0093] In a second aspect, the present application provides a total output value prediction system of agriculture, forestry, animal husbandry and fishery based on big data. The system includes: a memory and a processor. The memory includes a program of the total output value prediction method of agriculture, forestry, animal husbandry and fishery based on big data. When the program of the total output value prediction method of agriculture, forestry, animal husbandry and fishery based on big data is executed by the processor, the following steps are implemented:

[0094] Obtain the light remote sensing monitoring information of the preset area in the cycle time period according to the preset area night light remote sensing image information library, generate the regional agricultural product light remote sensing feature portrait, divide the preset area into sub-areas according to the light remote sensing distribution characteristics of the feature portrait, obtain multiple light remote sensing monitoring sub-areas and extract the light remote sensing feature data;

[0095] Obtain the agricultural light remote sensing area sample sets of multiple sample areas of each production type in the agricultural, forestry, animal husbandry, and fishery production types during multiple identical historical cycle time periods, as well as the average data of the sample area light remote sensing characteristics corresponding to the light remote sensing area samples of each production type. Then, compare them with the light remote sensing characteristic data of each light remote sensing monitoring sub-area respectively to obtain the sub-area production type light perception similarity coefficients corresponding to the agricultural, forestry, animal husbandry, and fishery production types. Next, compare and match the calibrated production types of each light remote sensing monitoring sub-area through the production type light perception similarity threshold, and classify the agricultural, forestry, animal husbandry, and fishery production sub-areas of each light remote sensing monitoring sub-area;

[0096] Obtain multiple similar agricultural light remote sensing area similar samples and agricultural area sample light perception record data according to the agricultural area production characteristic data of each agricultural production sub-area, and process to obtain the average output value data of the light perception duration per unit area of agricultural samples. Then, combine with the corresponding light remote sensing characteristic data of each agricultural production sub-area to process and obtain the agricultural production area output value data of the preset area, and correct the agricultural production area output value data according to the agricultural production factor data to obtain the corrected agricultural production area output value data;

[0097] Obtain multiple similar forestry light remote sensing area similar samples and forestry area sample light perception record data according to the forestry area production characteristic data of each forestry production sub-area, and process to obtain the average output value data of the light perception duration per unit area of forestry samples. Then, combine with the corresponding light remote sensing characteristic data of each forestry production sub-area to process and obtain the forestry production area output value data of the preset area, and correct the forestry production area output value data according to the forestry production factor data to obtain the corrected forestry production area output value data;

[0098] Obtain multiple similar animal husbandry light remote sensing area similar samples and animal husbandry area sample light perception record data according to the animal husbandry area production characteristic data of each animal husbandry production sub-area, and process to obtain the average output value data of the light perception duration per unit area of animal husbandry samples. Then, combine with the corresponding light remote sensing characteristic data of each animal husbandry production sub-area to process and obtain the animal husbandry production area output value data of the preset area, and correct the animal husbandry production area output value data according to the animal husbandry production factor data to obtain the corrected animal husbandry production area output value data;

[0099] Obtain multiple similar fishery light remote sensing area similar samples and fishery area sample light perception record data according to the fishery area production characteristic data of each fishery production sub-area, and process to obtain the average output value data of the light perception duration per unit area of fishery samples. Then, combine with the corresponding light remote sensing characteristic data of each fishery production sub-area to process and obtain the fishery production area output value data of the preset area, and correct the fishery production area output value data according to the fishery production factor data to obtain the corrected fishery production area output value data;

[0100] The type industry output value interference factor data of the agriculture, forestry, animal husbandry and fishery industries in the preset region during the cycle time period are processed through a preset market factor interference model to obtain the agriculture, forestry, animal husbandry and fishery factor market interference coefficient;

[0101] The type production area output value correction data corresponding to the agriculture, forestry, animal husbandry and fishery production areas in the preset region are processed in combination with the agriculture, forestry, animal husbandry and fishery factor market interference coefficient to obtain the total output value data of the agriculture, forestry, animal husbandry and fishery industries, and the production effectiveness of the agriculture, forestry, animal husbandry and fishery industries in the preset region during the cycle time period is evaluated according to the output value comparison result with the historical average total output value data of the agriculture, forestry, animal husbandry and fishery industries.

[0102] In a third aspect, the present application also provides a computer-readable storage medium, which includes a program for predicting the total output value of the agriculture, forestry, animal husbandry and fishery industries based on big data. When the program for predicting the total output value of the agriculture, forestry, animal husbandry and fishery industries based on big data is executed by a processor, the steps of the method for predicting the total output value of the agriculture, forestry, animal husbandry and fishery industries based on big data as described in any one of the above are implemented.

[0103] As can be seen from the above, the method, system and medium for predicting the total output value of the agriculture, forestry, animal husbandry and fishery industries based on big data provided by the present application generate a regional agricultural product light remote sensing feature portrait and divide sub-regions according to the light remote sensing monitoring information in the preset region during the cycle, extract light remote sensing feature data, obtain a similarity coefficient by comparing the feature average data of the agricultural product light remote sensing area sample sets of each agriculture, forestry, animal husbandry and fishery production type with the light remote sensing feature data to match the production types of each sub-region, then obtain the unit average output value according to the light sense record data of the regional similar samples of each agriculture, forestry, animal husbandry and fishery sub-region, and then process and obtain the output value correction data of four type production areas in combination with the light remote sensing feature data of each type of sub-region, and process in combination with the factor market interference coefficient of the agriculture, forestry, animal husbandry and fishery industries to obtain the total output value data of the agriculture, forestry, animal husbandry and fishery industries, and then evaluate the production effectiveness of the agriculture, forestry, animal husbandry and fishery industries in the region during the cycle according to the output value comparison result of the historical average total data; thereby realizing the division of production type regions through the light remote sensing information in the region, obtaining the output value data of the type production regions in combination with the historical sample data, and obtaining the total output value of the agriculture, forestry, animal husbandry and fishery industries in combination with the production factor interference situation and judging the production effectiveness of the region, so as to realize the measurement and evaluation of the regional agricultural production through big data and light sense technology.

[0104] Other features and advantages of the present application will be described in the subsequent description, and part of them will become obvious from the description, or can be understood by implementing the embodiments of the present application. The objectives and other advantages of the present application can be realized and obtained through the structures specifically pointed out in the written description and the drawings. Description of the Drawings

[0105] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the accompanying drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0106] Figure 1 It is a flowchart of the total output value prediction method for agriculture, forestry, animal husbandry and fishery based on big data provided by the embodiments of the present application;

[0107] Figure 2 It is a flowchart of obtaining light remote sensing feature data of the total output value prediction method for agriculture, forestry, animal husbandry and fishery based on big data provided by the embodiments of the present application;

[0108] Figure 3 It is a flowchart of classifying the types of sub-regions of agricultural, forestry, animal husbandry and fishery production in each light remote sensing monitoring sub-region of the total output value prediction method for agriculture, forestry, animal husbandry and fishery based on big data provided by the embodiments of the present application;

[0109] Figure 4 It is a flowchart of obtaining the corrected data of the output value of the agricultural production area of the total output value prediction method for agriculture, forestry, animal husbandry and fishery based on big data provided by the embodiments of the present application. Detailed implementation manners

[0110] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Usually, the components of the embodiments of the present application described and shown in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0111] It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first" and "second" are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0112] Please refer to Figure 1 , Figure 1It is a flowchart of a total output value prediction method for agriculture, forestry, animal husbandry and fishery based on big data in some embodiments of the present application. The total output value prediction method for agriculture, forestry, animal husbandry and fishery based on big data is used in terminal devices, such as computers, mobile phone terminals, etc. The total output value prediction method for agriculture, forestry, animal husbandry and fishery based on big data includes the following steps:

[0113] S11. Obtain the light remote sensing monitoring information of a preset area within a periodic time period according to a preset area night light remote sensing image information library, and generate a regional agricultural production light remote sensing feature portrait. Divide the preset area into sub-areas according to the light remote sensing distribution characteristics of the feature portrait, obtain a plurality of light remote sensing monitoring sub-areas, and extract light remote sensing feature data;

[0114] S12. Obtain the agricultural production light remote sensing area sample sets of multiple sample areas of each production type in the agriculture, forestry, animal husbandry and fishery production types within a plurality of identical historical periodic time periods, and the average data of the light remote sensing features of the sample areas corresponding to the light remote sensing areas of each production type. Then, compare them with the light remote sensing feature data of each light remote sensing monitoring sub-area respectively to obtain the sub-area production type light sense similarity coefficients corresponding to the agriculture, forestry, animal husbandry and fishery production types. Then, compare and match the calibrated production types of each light remote sensing monitoring sub-area through the production type light sense similarity threshold, and divide the agriculture, forestry, animal husbandry and fishery production sub-area types of each light remote sensing monitoring sub-area;

[0115] S13. Obtain a plurality of similar agricultural light remote sensing area similar samples and agricultural area sample light sense record data according to the agricultural area production feature data of each agricultural production sub-area, and process them to obtain the average output value data of the light sense duration per unit area of agricultural samples. Then, combine with the corresponding light remote sensing feature data of each agricultural production sub-area to process and obtain the agricultural production area output value data of the preset area, and correct the agricultural production area output value data according to the agricultural production factor data to obtain the corrected agricultural production area output value data;

[0116] S14. Obtain a plurality of similar forestry light remote sensing area similar samples and forestry area sample light sense record data according to the forestry area production feature data of each forestry production sub-area, and process them to obtain the average output value data of the light sense duration per unit area of forestry samples. Then, combine with the corresponding light remote sensing feature data of each forestry production sub-area to process and obtain the forestry production area output value data of the preset area, and correct the forestry production area output value data according to the forestry production factor data to obtain the corrected forestry production area output value data;

[0117] S15. Obtain multiple similar livestock husbandry light remote sensing area similar samples and livestock husbandry area sample light perception record data according to the livestock husbandry regional production characteristic data of each livestock husbandry production sub-region, process to obtain the average output value data of the light perception duration per unit area of the livestock husbandry samples, then combine the corresponding light remote sensing characteristic data of each livestock husbandry production sub-region to process and obtain the livestock husbandry production regional output value data of the preset region, and correct the livestock husbandry production regional output value data according to the livestock husbandry production factor data to obtain the corrected livestock husbandry production regional output value data;

[0118] S16. Obtain multiple similar fishery light remote sensing area similar samples and fishery area sample light perception record data according to the fishery regional production characteristic data of each fishery production sub-region, process to obtain the average output value data of the light perception duration per unit area of the fishery samples, then combine the corresponding light remote sensing characteristic data of each fishery production sub-region to process and obtain the fishery production regional output value data of the preset region, and correct the fishery production regional output value data according to the fishery production factor data to obtain the corrected fishery production regional output value data;

[0119] S17. Process the type industry output value interference factor data of the agriculture, forestry, livestock husbandry and fishery in the preset region during the cycle time period through a preset market element interference model to obtain the agriculture, forestry, livestock husbandry and fishery element market interference coefficient;

[0120] S18. Process the type production regional output value corrected data corresponding to the agriculture, forestry, livestock husbandry and fishery production regions of the preset region in combination with the agriculture, forestry, livestock husbandry and fishery element market interference coefficient to obtain the total agriculture, forestry, livestock husbandry and fishery output value data, and evaluate the production effectiveness of the agriculture, forestry, livestock husbandry and fishery in the preset region during the cycle time period according to the output value comparison result with the historical average total agriculture, forestry, livestock husbandry and fishery output value data.

[0121] Among them, to realize the output value prediction and production effectiveness evaluation of the agriculture, forestry, livestock husbandry and fishery in a certain region through the night light remote sensing image information technology, first divide the region into multiple sub-regions according to the light perception distribution situation based on the characteristic portrait obtained from the light perception information, then determine the corresponding types of agriculture, forestry, livestock husbandry and fishery according to the similarity of the sample characteristic average data comparison of each production type for each sub-region, then process the average output value obtained from the light perception record data of historical samples for each production type sub-region and perform aggregation and correction calculations in combination with the light perception characteristic data and factor data of the sub-region to obtain the output value data of the type production region, and then perform compensation aggregation processing in combination with the factor market interference coefficient to obtain the total agriculture, forestry, livestock husbandry and fishery output value data of the region during the cycle, and evaluate the production effectiveness of the region in combination with the output value comparison result of the historical average total data, so as to realize the measurement and evaluation of the regional agricultural production through big data and light remote sensing image information technology.

[0122] Please refer to Figure 2 , Figure 2It is a flowchart for obtaining light remote sensing feature data of the total output value prediction method of agriculture, forestry, animal husbandry and fishery based on big data in some embodiments of the present application. According to the embodiments of the present invention, obtaining the light remote sensing monitoring information of a preset area within a periodic time period according to the preset area night light remote sensing image information library, and generating a regional agricultural product light remote sensing feature portrait, and dividing the preset area into sub-areas according to the light remote sensing distribution characteristics of the feature portrait, obtaining a plurality of light remote sensing monitoring sub-areas and extracting light remote sensing feature data, specifically:

[0123] S21. Obtain the light remote sensing monitoring information of the preset area within the periodic time period according to the preset area night light remote sensing image information library, including light distribution intensity information, light distribution density information, light distribution time period information and light frequency duration information;

[0124] S22. Generate the regional agricultural product light remote sensing feature portrait of the preset area within the periodic time period according to the light remote sensing monitoring information;

[0125] S23. Divide the preset area into sub-areas through a preset light remote sensing feature division model according to the light remote sensing distribution characteristics of the regional agricultural product light remote sensing feature portrait, and obtain a plurality of light remote sensing monitoring sub-areas;

[0126] S24. Obtain the light remote sensing feature data of each light remote sensing monitoring sub-area, including light intensity data, light density data, light time period data and light frequency duration data.

[0127] Among them, to achieve the output value assessment of agriculture, forestry, animal husbandry and fishery within a certain area range over a certain period, it is first necessary to divide the sub-areas of agriculture, forestry, animal husbandry and fishery types within the area, and then conduct type-specific output value assessment on each type of production sub-area through night light remote sensing monitoring (referred to as light sensing) technology. By depicting the distribution of night light remote sensing monitoring within the area, a characteristic portrait of the light sensing distribution of the area is produced. Through the light sensing distribution characteristics of the characteristic portrait, sub-areas are divided. Sub-areas with different light sensing distribution states can be distinguished, so as to realize the type division of the sub-areas of agriculture, forestry, animal husbandry and fishery in the area through light sensing distribution. According to the preset regional night light remote sensing image information database, the night light remote sensing monitoring information of the area within the period is obtained. This information database is a preset third-party database that collects and stores the night light remote sensing image information of each area. Through this information database, the night light remote sensing information of each area can be obtained, including the light sensing intensity distribution, distribution density, distribution time period collected by the night light remote sensing image, and the information of the frequency and duration of the collected night light remote sensing image. Then, according to the night light remote sensing monitoring information, a characteristic portrait of the agricultural product night light remote sensing of the area is generated. This characteristic portrait is used to describe the information portrait of the intensity, density, duration and frequency law of the night light remote sensing image information of the production activities of agriculture, forestry, animal husbandry and fishery within the area. Then, according to the light sensing distribution characteristics of the portrait, sub-areas are divided through the light sensing feature division model, that is, the distribution characteristics of the light sensing information of the characteristic portrait are divided through a preset characteristic classification model for dividing light sensing features, so as to divide different light sensing sub-areas according to the distribution of light sensing features.

[0128] Please refer to Figure 3 , Figure 3 is a flowchart for dividing the types of agricultural, forestry, animal husbandry and fishery production sub-areas of each night light remote sensing monitoring sub-area in the total output value prediction method of agriculture, forestry, animal husbandry and fishery based on big data in some embodiments of the present application. According to an embodiment of the present invention, the method includes obtaining a set of agricultural product night light remote sensing area samples of multiple sample areas of each production type in the agricultural, forestry, animal husbandry and fishery production types within multiple identical historical cycle time periods, and the average data of the night light remote sensing characteristics of the sample areas corresponding to the night light remote sensing area samples of each production type, and then comparing them with the night light remote sensing characteristic data of each night light remote sensing monitoring sub-area respectively to obtain the light sensing similarity coefficients of the sub-area production types corresponding to the agricultural, forestry, animal husbandry and fishery production types, and then comparing and matching the calibrated production types of each night light remote sensing monitoring sub-area through the light sensing similarity threshold of the production type, so as to divide the types of agricultural, forestry, animal husbandry and fishery production sub-areas of each night light remote sensing monitoring sub-area. Specifically:

[0129] S31. Obtain the agricultural production light remote sensing area sample sets corresponding to various production types in the agricultural, forestry, animal husbandry, and fishery production types respectively in multiple identical historical cycle time periods according to the preset agricultural, forestry, animal husbandry, and fishery production light sensing database, including multiple agricultural light remote sensing area samples, forestry light remote sensing area samples, animal husbandry light remote sensing area samples, and fishery light remote sensing area samples;

[0130] S32. Obtain the sample area light remote sensing characteristic data corresponding to the light remote sensing area samples of each production type in the agricultural production light remote sensing area sample set, including light intensity sample data, light density sample data, light period sample data, and light frequency duration sample data;

[0131] S33. Obtain the average sample area light remote sensing characteristic data corresponding to the agricultural light remote sensing area samples, forestry light remote sensing area samples, animal husbandry light remote sensing area samples, and fishery light remote sensing area samples in the agricultural production light remote sensing area sample set respectively;

[0132] S34. Compare the average sample area light remote sensing characteristic data corresponding to the light remote sensing area samples of each production type in the agricultural production light remote sensing area sample set with the light remote sensing characteristic data of each light remote sensing monitoring sub-area respectively, and obtain the sub-area production type light sensing similarity coefficients corresponding to the agricultural, forestry, animal husbandry, and fishery production types of each light remote sensing monitoring sub-area respectively;

[0133] S35. Match and compare the sub-area production type light sensing similarity coefficients with the preset production type light sensing similarity thresholds corresponding to the agricultural, forestry, animal husbandry, and fishery production types respectively, and obtain the threshold matching degrees respectively;

[0134] S36. Take the production type in the agricultural, forestry, animal husbandry, and fishery production types with the best threshold matching degree as the calibrated production type of each light remote sensing monitoring sub-area;

[0135] S37. Calibrate the production types of each light remote sensing monitoring sub-area within the preset area respectively, and divide each light remote sensing monitoring sub-area into agricultural production sub-areas, forestry production sub-areas, animal husbandry production sub-areas, and fishery production sub-areas.

[0136] Among them, for the type of agriculture, forestry, animal husbandry and fishery to which each clearly demarcated sub-region belongs, the light perception characteristics distribution of each sub-region is compared with the characteristics of each type of regional sample. According to the comparison similarity, the type of agriculture, forestry, animal husbandry and fishery to which each sub-region belongs can be judged and identified. Since the light perception characteristics of different types of agriculture, forestry, animal husbandry and fishery regions, such as the distribution of light remote sensing intensity, density distribution, light duration frequency, etc., have characteristic differences, therefore, according to the preset light perception database of agricultural and forestry production, a light perception sample set of multiple sample regions corresponding to each type of agriculture, forestry, animal husbandry and fishery in the same historical period is obtained, and the light remote sensing characteristic data of the corresponding samples is extracted. Then, the average data of the light perception characteristics is obtained by averaging the light perception characteristic data of each type of sample of the four types of agriculture, forestry, animal husbandry and fishery, and then compared with the light perception characteristic data of the sub-region respectively, and the light perception similarity coefficient of the production type corresponding to the four production types of agriculture, forestry, animal husbandry and fishery is obtained for each sub-region. That is, four comparison similarity coefficients of the four production types are obtained for each sub-region by comparison, and then they are respectively matched with the light perception similarity threshold of each production type, and the one with the best matching degree is selected as the calibrated production type of one of the actual agriculture, forestry, animal husbandry and fishery of each sub-region, so as to obtain the identification and division of the production type of each sub-region. Among them, the calculation formula of the light perception similarity coefficient of the sub-region production type is:

[0137]

[0138] Among them, σ Ri is the light perception similarity coefficient of the sub-region production type corresponding to the i-th type among the four types of agriculture, forestry, animal husbandry and fishery production types, are respectively the average data of the light intensity samples, the light density sample data, the average data of the light period samples, and the average data of the light frequency duration samples corresponding to the i-th type of sample among the four types of samples of the agricultural light remote sensing region samples, forestry light remote sensing region samples, animal husbandry light remote sensing region samples, and fishery light remote sensing region samples. x c 、g k 、p m 、b z are respectively the light intensity data, light density data, light period data, and light frequency duration data of the light remote sensing monitoring sub-region. τ 1 、τ 2 、τ 3 、τ 4 、ξ 1 、ξ 2 、ξ 3 、ξ 4 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset light perception database of agricultural and forestry production).

[0139] Please refer to Figure 4 , Figure 4It is a flowchart for obtaining the agricultural production area output value correction data of the big data-based total output value prediction method for agriculture, forestry, animal husbandry and fishery in some embodiments of the present application. According to the embodiments of the present invention, obtaining a plurality of similar agricultural light remote sensing area similar samples and agricultural area sample light perception record data according to the agricultural area production characteristic data of each agricultural production sub-area, and processing to obtain the average output value data of the light perception duration per unit area of the agricultural sample, and then combining the corresponding light remote sensing characteristic data of each agricultural production sub-area to process and obtain the agricultural production area output value data of the preset area, and correcting the agricultural production area output value data according to the agricultural production factor data to obtain the agricultural production area output value correction data, specifically:

[0140] S41. Obtain the agricultural area production characteristic data of each agricultural production sub-area, including the planted crop category data, latitude and altitude data, and planted area data;

[0141] S42. Obtain a plurality of agricultural light remote sensing area similar samples similar to the agricultural area production characteristic data of each agricultural production sub-area according to the preset agriculture, forestry, animal husbandry and fishery production light perception database;

[0142] S43. Obtain the agricultural area sample light perception record data of the plurality of agricultural light remote sensing area similar samples in a plurality of identical historical cycle time periods, including the sample cumulative light intensity data, sample cumulative duration data, sample area planted area data, and sample area agricultural output value data;

[0143] S44. Process according to the agricultural area sample light perception record data of each agricultural light remote sensing area similar sample to obtain the average output value data of the light perception duration per unit area of the agricultural sample;

[0144] S45. Perform aggregation processing according to the average output value data of the light perception duration per unit area of the agricultural sample in combination with the corresponding light remote sensing characteristic data and planted area data of each agricultural production sub-area to obtain the agricultural production area output value data of the preset area;

[0145] S46. Obtain the agricultural production factor data of the preset area in the cycle time period, including the irrigation precipitation data, cumulative sunshine amount data, and average temperature volatility data, and correct the agricultural production area output value data to obtain the agricultural production area output value correction data;

[0146] The calculation formula of the agricultural production area output value data is:

[0147]

[0148] where m z is the agricultural production area output value data, λ W is the average output value data of the light perception duration per unit area of the agricultural sample, xcj , g kj , p mj , b zj , h uj are respectively the light intensity data, light density data, light period data, light frequency duration data, and planting area data of the j-th agricultural production sub-region. m is the number of agricultural production sub-regions. ε is a preset feature coefficient;

[0149] The correction calculation formula for the agricultural production area output value correction data is:

[0150]

[0151] where m L is the agricultural production area output value correction data, m z is the agricultural production area output value data, a f , e d , u t are respectively the irrigation precipitation data, cumulative sunshine duration data, and average temperature volatility data. ρ 1 , ρ 2 , ρ 3 are preset feature coefficients (the feature coefficients are obtained by querying the preset agricultural, forestry, animal husbandry, and fishery production light perception database).

[0152] Among them, is the total regional output value of the agricultural production type sub-region. According to the production characteristic data of each sub-region, multiple regional samples similar to each sub-region are obtained through the preset agricultural, forestry, animal husbandry, and fishery production light perception database, and the light perception record data of multiple similar regional samples in the same historical cycle time period are obtained, including the data of the cumulative light remote sensing intensity, cumulative light perception duration, regional planting area, and regional agricultural output value of the samples. And according to the light perception record data of multiple cycles of multiple similar regional samples, the average output value data of the light perception duration per unit area of the agricultural sample is calculated, that is, the average output value data of the unit area, light perception intensity, and duration of the agricultural regional sample. Then, it is aggregated and calculated with the light remote sensing characteristic data and planting area data of each agricultural production sub-region in the region to obtain the output value data of the agricultural production area in the region. Since agricultural production is also affected by production factors, including irrigation precipitation, cumulative sunshine duration, and average temperature volatility, therefore, the regional output value data is corrected according to the production factor data to obtain the output value correction data of all agricultural production areas in the region. Among them, the calculation formula for the average output value data of the light perception duration per unit area of the agricultural sample is:

[0153]

[0154] where λ W is the average output value data of the light perception duration per unit area of the agricultural sample, m hs, v hs , d ws , h us The agricultural output value data, sample cumulative light intensity data, sample cumulative duration data, and sample area planted data of the sample area in the s-th historical period among k identical historical period time periods of the similar samples of a single agricultural light remote sensing area, respectively. k is the number of identical historical period time periods of the similar samples of a single agricultural light remote sensing area, r is the number of similar samples of the agricultural light remote sensing area, k and r are integers and greater than or equal to 1, and μ, η, and ι are preset feature coefficients (the feature coefficients are obtained by querying the preset agricultural, forestry, animal husbandry, and fishery production light perception database).

[0155] According to the embodiments of the present invention, obtaining a plurality of similar forestry light remote sensing area similar samples and forestry area sample light perception record data according to the forestry area production feature data of each forestry production sub-region, processing to obtain the average output value data of the light perception duration per unit area of the forestry samples, and then combining the corresponding light remote sensing feature data of each forestry production sub-region to process and obtain the forestry production area output value data of the preset area, and correcting the forestry production area output value data according to the forestry production factor data to obtain the corrected forestry production area output value data, specifically:

[0156] Obtaining the forestry area production feature data of each forestry production sub-region, including tree species data, latitude and altitude data, and planted area data;

[0157] Obtaining a plurality of similar forestry light remote sensing area similar samples similar to the forestry area production feature data of each forestry production sub-region according to the preset agricultural, forestry, animal husbandry, and fishery production light perception database;

[0158] Obtaining the forestry area sample light perception record data of the plurality of similar forestry light remote sensing area samples in a plurality of identical historical period time periods, including sample cumulative light intensity data, sample cumulative duration data, sample area planted data, and sample area forestry output value data;

[0159] Processing according to the forestry area sample light perception record data of each forestry light remote sensing area similar sample to obtain the average output value data of the light perception duration per unit area of the forestry samples;

[0160] Performing aggregation processing on the average output value data of the light perception duration per unit area of the forestry samples in combination with the corresponding light remote sensing feature data and planted area data of each forestry production sub-region to obtain the forestry production area output value data of the preset area;

[0161] Obtaining the forestry production factor data of the preset area in the period time period, including precipitation data, cumulative sunshine amount data, and average temperature volatility data, and correcting the forestry production area output value data to obtain the corrected forestry production area output value data;

[0162] The calculation formula for the output value data of the forestry production area is as follows:

[0163]

[0164] Among them, f g is the output value data of the forestry production area, is the average output value data of the light perception duration per unit area of the forestry sample, x cj , g kj , p mj , b zj , z vj are respectively the light intensity data, light density data, light period data, light frequency duration data, and planting area data of the j-th forestry production sub-area, m is the number of forestry production sub-areas, ε is a preset characteristic coefficient;

[0165] The correction calculation formula for the corrected output value data of the forestry production area is as follows:

[0166]

[0167] Among them, f P is the corrected output value data of the forestry production area, f g is the output value data of the forestry production area, t s , e d , u t are respectively the precipitation data, cumulative sunshine duration data, and average temperature volatility data, ρ 1 , ρ 2 , ρ 3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset light perception database for agriculture, forestry, animal husbandry, and fishery production).

[0168] Among them, to evaluate the total regional output value of the forestry production type sub-region, multiple regional samples similar to each sub-region are obtained through a preset agroforestry and fishery production light perception database according to the production characteristic data of each sub-region, and the light perception record data of multiple similar regional samples within the same historical cycle time period is obtained, including the data of the cumulative light intensity of the samples, the cumulative light perception duration, the regional planting area, and the regional forestry output value. And based on the light perception record data of multiple cycles of multiple similar regional samples, the average output value data of the light perception duration per unit area of the forestry samples is calculated, that is, the average output value data under the unit area, light intensity, and duration of the forestry regional samples. Then, it is aggregated and calculated with the light remote sensing characteristic data and the planting area data of each forestry production sub-region within the region to obtain the output value data of the forestry production region within the region. Since forestry production is also affected by production factors, including precipitation, cumulative sunshine hours, and average temperature volatility, therefore, the regional output value data is corrected according to the production factor data to obtain the corrected output value data of all forestry production regions within the region. Among them, the calculation formula for the average output value data of the light perception duration per unit area of forestry samples is:

[0169]

[0170] Among them, is the average output value data of the light perception duration per unit area of forestry samples, f us 、v hs 、d ws 、z vs are respectively the sample regional forestry output value data, the sample cumulative light intensity data, the sample cumulative duration data, and the sample regional planting area data of the s-th historical cycle time period among k identical historical cycle time periods of a single similar sample in the forestry light remote sensing area. k is the number of identical historical cycle time periods of a single similar sample in the forestry light remote sensing area, r is the number of similar samples in the forestry light remote sensing area, k and r are rounded and greater than or equal to 1, and μ, η, and ι are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset agroforestry and fishery production light perception database).

[0171] According to an embodiment of the present invention, obtaining multiple similar samples in the pasture light remote sensing area and the light perception record data of the pasture area samples according to the pasture area production characteristic data of each pasture production sub-region, and processing to obtain the average output value data of the light perception duration per unit area of the pasture samples, and then combining the corresponding light remote sensing characteristic data of each pasture production sub-region to process and obtain the output value data of the pasture production area of the preset area, and correcting the output value data of the pasture production area according to the pasture production factor data to obtain the corrected output value data of the pasture production area, specifically:

[0172] Obtain the pasture area production characteristic data of each pasture production sub-region, including livestock category data, livestock latitude data, and pasture area data;

[0173] Obtain multiple similar samples of the pasture light remote sensing area that are similar to the pasture area production characteristic data of each pasture production sub-region according to the preset light perception database for agriculture, forestry, animal husbandry and fishery production;

[0174] Obtain the light perception record data of the pasture area samples of the multiple similar samples of the pasture light remote sensing area in multiple identical historical cycle time periods, including sample cumulative light intensity data, sample cumulative duration data, sample area pasture area data, and sample area pasture output value data;

[0175] Process according to the light perception record data of the pasture area samples of each similar sample of the pasture light remote sensing area to obtain the average output value data of the light perception duration per unit area of the pasture sample;

[0176] Perform aggregation processing on the average output value data of the light perception duration per unit area of the pasture sample in combination with the corresponding light remote sensing characteristic data and pasture area data of each pasture production sub-region to obtain the pasture production area output value data of the preset area;

[0177] Obtain the pasture production factor data of the preset area in the cycle time period, including soil vegetation quality rate data, livestock morbidity data, and livestock processing efficiency data, and correct the pasture production area output value data to obtain the corrected pasture production area output value data;

[0178] The calculation formula for the pasture production area output value data is:

[0179]

[0180] Among them, q e is the pasture production area output value data, is the average output value data of the light perception duration per unit area of the pasture sample, x cj , g kj , p mj , b zj , a xj are respectively the light intensity data, light density data, light period data, light frequency duration data, and pasture area data of the j-th pasture production sub-region, m is the number of pasture production sub-regions, ε is a preset characteristic coefficient;

[0181] The correction calculation formula for the corrected pasture production area output value data is:

[0182]

[0183] Among them, q H is the corrected pasture production area output value data, q eFor the output value data of the animal husbandry production area, o u 、w n 、y a are respectively the data of the good rate of soil vegetation, the data of livestock morbidity, and the data of livestock processing efficiency. is a preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset light perception database for agriculture, forestry, animal husbandry and fishery production).

[0184] Among them, is the total regional output value for evaluating the sub-regions of animal husbandry production types. According to the production characteristic data of each sub-region, multiple regional samples similar to each sub-region are obtained through the preset light perception database for agriculture, forestry, animal husbandry and fishery production, and the light perception record data of multiple similar regional samples within the same historical cycle time period are obtained, including the data of the cumulative light intensity of the samples, the cumulative light perception duration, the regional animal husbandry area, and the regional animal husbandry output value. And according to the light perception record data of multiple cycles of multiple similar regional samples, the average output value data of the light perception duration per unit area of the animal husbandry samples is calculated, that is, the average output value data under the unit area, light intensity, and duration of the animal husbandry regional samples. Then, it is aggregated and calculated with the light remote sensing characteristic data and the animal husbandry area data of each animal husbandry production sub-region within the region to obtain the output value data of the animal husbandry production area within the region. Since animal husbandry production is affected by production factors, including the data of the good rate of soil and vegetation, livestock morbidity, and the production capacity efficiency of livestock processing, therefore, the output value data of the region is corrected according to the production factor data to obtain the corrected output value data of all animal husbandry production areas within the region. Among them, the calculation formula for the average output value data of the light perception duration per unit area of the animal husbandry samples is:

[0185]

[0186] Among them, is the average output value data of the light perception duration per unit area of the animal husbandry samples, q rs 、v hs 、d ws 、a xs are respectively the sample regional animal husbandry output value data, sample cumulative light intensity data, sample cumulative duration data, and sample regional animal husbandry area data of the s-th historical cycle time period among k identical historical cycle time periods of a single animal husbandry light remote sensing regional similar sample. k is the number of identical historical cycle time periods of a single animal husbandry light remote sensing regional similar sample, r is the number of animal husbandry light remote sensing regional similar samples, k and r are rounded and greater than or equal to 1, and μ, η, and ι are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset light perception database for agriculture, forestry, animal husbandry and fishery production).

[0187] According to an embodiment of the present invention, obtaining a plurality of similar fishery light remote sensing area similar samples and fishery area sample light perception record data according to the fishery area production characteristic data of each fishery production sub-region, processing to obtain the average output value data of the light perception duration per unit area of the fishery sample, and then combining the corresponding light remote sensing characteristic data of each fishery production sub-region to process and obtain the fishery production area output value data of the preset area, and correcting the fishery production area output value data according to the fishery production factor data to obtain the corrected fishery production area output value data, specifically:

[0188] Obtain the fishery area production characteristic data of each fishery production sub-region, including fishing ground sea area data, operating latitude data, and fishing area data;

[0189] According to the preset agricultural, forestry, animal husbandry and fishery production light perception database, obtain a plurality of fishery light remote sensing area similar samples similar to the fishery area production characteristic data of each fishery production sub-region;

[0190] Obtain the fishery area sample light perception record data of the plurality of fishery light remote sensing area similar samples in a plurality of same historical cycle time periods, including sample cumulative light intensity data, sample cumulative duration data, sample area fishing area data, and sample area fishery output value data;

[0191] Process according to the fishery area sample light perception record data of each fishery light remote sensing area similar sample to obtain the average output value data of the light perception duration per unit area of the fishery sample;

[0192] According to the average output value data of the light perception duration per unit area of the fishery sample, combine the corresponding light remote sensing characteristic data and fishing area data of each fishery production sub-region for aggregation processing to obtain the fishery production area output value data of the preset area;

[0193] Obtain the fishery production factor data of the preset area in the cycle time period, including meteorological stability data, equipment operation efficiency data, and water temperature volatility data, and correct the fishery production area output value data to obtain the corrected fishery production area output value data;

[0194] The calculation formula of the fishery production area output value data is:

[0195]

[0196] Among them, c m is the fishery production area output value data, γ D is the average output value data of the light perception duration per unit area of the fishery sample, x cj 、g kj 、p mj 、b zj 、t cjThey are respectively the light intensity data, light density data, light period data, light frequency duration data, and fishing area data of the j-th fishery production sub-region, where m is the number of fishery production sub-regions. ε is a preset feature coefficient;

[0197] The correction calculation formula for the corrected data of the fishery production area output value is:

[0198]

[0199] Among them, c V is the corrected data of the fishery production area output value, c m is the output value data of the fishery production area, a r , s a , k c are respectively the meteorological stability data, equipment operation efficiency data, and water temperature volatility data, and θ 1 , θ 2 are preset feature coefficients (the feature coefficients are obtained by querying the preset agroforestry and fishery production light perception database).

[0200] Among them, is the total regional output value of the sub-region for evaluating the fishery production type. According to the production characteristic data of each sub-region, multiple regional samples similar to each sub-region are obtained through the preset agroforestry and fishery production light perception database, and the light perception record data of multiple similar regional samples within the same historical cycle time period are obtained, including the data of the cumulative light remote sensing intensity, cumulative light perception duration, regional fishing area, and regional fishery output value of the samples. And according to the light perception record data of multiple cycles of multiple similar regional samples, the average output value data of the light perception duration per unit area of the fishery sample is calculated, that is, the average output value data under the unit area, light perception intensity, and duration of the fishery regional sample. Then, it is aggregated and calculated with the light remote sensing characteristic data and fishing area data of each fishery production sub-region within the region to obtain the output value data of the fishery production area within the region. Since fishery production is also affected by production factors, including meteorological stability, equipment operation efficiency, and water temperature volatility, therefore, the regional output value data is corrected according to the production factor data to obtain the corrected data of the output value of all fishery production areas within the region. Among them, the calculation formula for the average output value data of the light perception duration per unit area of the fishery sample is:

[0201]

[0202] Among them, γ D is the average output value data of the light perception duration per unit area of the fishery sample, c ws , v hs , d ws , t csThe sample area fishery output value data, sample cumulative light intensity data, sample cumulative duration data, and sample area fishing area data of a single fishery light remote sensing area similar sample in the s-th historical period among k identical historical period time segments. k is the number of identical historical period time segments of a single fishery light remote sensing area similar sample, r is the number of fishery light remote sensing area similar samples, k and r are integers and greater than or equal to 1, and μ, η, and ι are preset feature coefficients (the feature coefficients are obtained by querying the preset agroforestry and fishery production light perception database).

[0203] According to an embodiment of the present invention, the type industry output value interference factor data of the agroforestry and fishery in the preset area during the period time segment is processed through a preset market element interference model to obtain an agroforestry and fishery element market interference coefficient, specifically:

[0204] Obtain the type industry output value interference factor data of the agroforestry and fishery in the preset area during the period time segment, including the price fluctuation data, quality fluctuation data, and policy subsidy fluctuation data corresponding to the agroforestry and fishery respectively;

[0205] Process the price fluctuation data, quality fluctuation data, and policy subsidy fluctuation data corresponding to the agroforestry and fishery respectively through a preset market element interference model to obtain an agroforestry and fishery element market interference coefficient;

[0206] The agroforestry and fishery element market interference coefficient includes an agricultural element market interference coefficient, a forestry element market interference coefficient, a livestock element market interference coefficient, and a fishery element market interference coefficient;

[0207] The calculation formula of the agroforestry and fishery element market interference coefficient is:

[0208]

[0209] Where φ fr is the r-th coefficient among the four coefficients of the agricultural element market interference coefficient, forestry element market interference coefficient, livestock element market interference coefficient, and fishery element market interference coefficient in the agroforestry and fishery element market interference coefficient, and α qr , δ pr , κ er are the price fluctuation data, quality fluctuation data, and policy subsidy fluctuation data corresponding to the r-th coefficient among the four coefficients of the agricultural element market interference coefficient, forestry element market interference coefficient, livestock element market interference coefficient, and fishery element market interference coefficient respectively, and ζ 1 , ζ 2 , ζ 3 are preset feature coefficients (the feature coefficients are obtained by querying the preset agroforestry and fishery production light perception database).

[0210] Among them, since the overall output value of each production type area in the agriculture, forestry, animal husbandry and fishery industries within the region is interfered by the industry factors of the corresponding agriculture, forestry, animal husbandry and fishery industries, and the output value interference factor data includes the fluctuation data of the prices, quality and policy subsidies corresponding to the agriculture, forestry, animal husbandry and fishery industries respectively. The fluctuation data of prices, quality and policy subsidies can be queried and obtained through a third-party regional agricultural, forestry, animal husbandry and fishery product quality and price data monitoring platform, and then calculated and evaluated according to the fluctuation data of the prices, quality and policy subsidies corresponding to the agriculture, forestry, animal husbandry and fishery industries through the calculation formula of the preset market element interference model to obtain the element market interference coefficients corresponding to the agriculture, forestry, animal husbandry and fishery industries respectively.

[0211] According to an embodiment of the present invention, the type production area output value correction data corresponding to the agricultural, forestry, animal husbandry and fishery production areas in the preset area is combined with the agricultural, forestry, animal husbandry and fishery element market interference coefficients for processing to obtain the total agricultural, forestry, animal husbandry and fishery output value data, and the agricultural, forestry, animal husbandry and fishery production effectiveness in the preset area within the cycle time period is evaluated according to the output value comparison result with the historical average total agricultural, forestry, animal husbandry and fishery output value data, specifically:

[0212] The agricultural production area output value correction data, forestry production area output value correction data, animal husbandry production area output value correction data and fishery production area output value correction data corresponding to the agricultural, forestry, animal husbandry and fishery production areas in the preset area are combined with the agricultural, forestry, animal husbandry and fishery element market interference coefficients for compensation aggregation to obtain the total agricultural, forestry, animal husbandry and fishery output value data of the preset area;

[0213] The total agricultural, forestry, animal husbandry and fishery output value data is compared with the historical average total agricultural, forestry, animal husbandry and fishery output value data in multiple identical historical cycle time periods in the preset area to obtain an output value comparison result;

[0214] The output value comparison result is compared with a preset output value comparison threshold, and the agricultural, forestry, animal husbandry and fishery production effectiveness in the preset area within the cycle time period is evaluated according to the threshold comparison result;

[0215] The calculation formula for the total agricultural, forestry, animal husbandry and fishery output value data is:

[0216]

[0217] Among them, is the total agricultural, forestry, animal husbandry and fishery output value data, m L is the agricultural production area output value correction data, f P is the forestry production area output value correction data, q H is the animal husbandry production area output value correction data, c V is the fishery production area output value correction data, φ f1 、φ f2 、φ f3 、φ f4They are the interference coefficients of agricultural factor market conditions, forestry factor market conditions, animal husbandry factor market conditions, and fishery factor market conditions, χ 1 , χ 2 , χ 3 , χ 4 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset optical sense database of agricultural, forestry, animal husbandry, and fishery production).

[0218] Among them, finally, to obtain an accurate prediction and evaluation of the output value of agriculture, forestry, animal husbandry, and fishery in the region, compensation aggregation calculation is carried out according to the output value correction data of the four production regions of agriculture, forestry, animal husbandry, and fishery combined with the corresponding interference coefficients of the factor market conditions of agriculture, forestry, animal husbandry, and fishery to obtain the total output value data of agriculture, forestry, animal husbandry, and fishery. Then, by comparing with the historical average total output value data of each type, the output value comparison result is obtained. According to the output value comparison result and the preset output value comparison threshold, the production effectiveness of agriculture, forestry, animal husbandry, and fishery in the region within the cycle is evaluated by threshold comparison. If the output value comparison result meets the threshold comparison result of the preset output value comparison threshold, the production effectiveness of agriculture, forestry, animal husbandry, and fishery in the region within the cycle time period is significant, realizing the measurement and effect evaluation of regional agricultural production through optical sense technology.

[0219] The second aspect of the present invention also discloses a total output value prediction system for agriculture, forestry, animal husbandry, and fishery based on big data, including a memory and a processor. The memory includes a total output value prediction method program for agriculture, forestry, animal husbandry, and fishery based on big data. When the total output value prediction method program for agriculture, forestry, animal husbandry, and fishery based on big data is executed by the processor, the following steps are realized:

[0220] Obtain the light remote sensing monitoring information of the preset region within the cycle time period according to the preset regional night light remote sensing image information library, and generate a regional agricultural product light remote sensing feature portrait. According to the light remote sensing distribution characteristics of the feature portrait, the preset region is divided into sub-regions to obtain multiple light remote sensing monitoring sub-regions and extract light remote sensing feature data;

[0221] Obtain the agricultural product light remote sensing area sample sets of multiple sample regions of each production type in the agricultural, forestry, animal husbandry, and fishery production types within multiple same historical cycle time periods, and the average data of the sample region light remote sensing features corresponding to the light remote sensing areas of each production type. Then, compare with the light remote sensing feature data of each light remote sensing monitoring sub-region respectively to obtain the sub-region production type light sense similarity coefficients corresponding to the agricultural, forestry, animal husbandry, and fishery production types. Then, match the calibrated production types of each light remote sensing monitoring sub-region through the production type light sense similarity threshold to divide the agricultural, forestry, animal husbandry, and fishery production sub-region types of each light remote sensing monitoring sub-region;

[0222] Obtain multiple similar agricultural light remote sensing area similar samples and agricultural area sample light perception record data according to the agricultural regional production characteristic data of each agricultural production sub-region, and process to obtain the average output value data of the light perception duration per unit area of agricultural samples. Then, combine with the corresponding light remote sensing characteristic data of each agricultural production sub-region to process and obtain the agricultural production area output value data of the preset region, and correct the agricultural production area output value data according to the agricultural production factor data to obtain the corrected agricultural production area output value data;

[0223] Obtain multiple similar forestry light remote sensing area similar samples and forestry area sample light perception record data according to the forestry regional production characteristic data of each forestry production sub-region, and process to obtain the average output value data of the light perception duration per unit area of forestry samples. Then, combine with the corresponding light remote sensing characteristic data of each forestry production sub-region to process and obtain the forestry production area output value data of the preset region, and correct the forestry production area output value data according to the forestry production factor data to obtain the corrected forestry production area output value data;

[0224] Obtain multiple similar animal husbandry light remote sensing area similar samples and animal husbandry area sample light perception record data according to the animal husbandry regional production characteristic data of each animal husbandry production sub-region, and process to obtain the average output value data of the light perception duration per unit area of animal husbandry samples. Then, combine with the corresponding light remote sensing characteristic data of each animal husbandry production sub-region to process and obtain the animal husbandry production area output value data of the preset region, and correct the animal husbandry production area output value data according to the animal husbandry production factor data to obtain the corrected animal husbandry production area output value data;

[0225] Obtain multiple similar fishery light remote sensing area similar samples and fishery area sample light perception record data according to the fishery regional production characteristic data of each fishery production sub-region, and process to obtain the average output value data of the light perception duration per unit area of fishery samples. Then, combine with the corresponding light remote sensing characteristic data of each fishery production sub-region to process and obtain the fishery production area output value data of the preset region, and correct the fishery production area output value data according to the fishery production factor data to obtain the corrected fishery production area output value data;

[0226] Process the type industry output value interference factor data of agriculture, forestry, animal husbandry and fishery in the preset region during the cycle time period through a preset market element interference model to obtain the agriculture, forestry, animal husbandry and fishery element market interference coefficient;

[0227] Process the corrected type production area output value data corresponding to the agriculture, forestry, animal husbandry and fishery production areas in the preset region in combination with the agriculture, forestry, animal husbandry and fishery element market interference coefficient to obtain the total output value data of agriculture, forestry, animal husbandry and fishery, and evaluate the production effectiveness of agriculture, forestry, animal husbandry and fishery in the preset region during the cycle time period according to the output value comparison result with the historical average total output value data of agriculture, forestry, animal husbandry and fishery.

[0228] Among them, to achieve the prediction of the output value of agriculture, forestry, animal husbandry and fishery in a certain area and the evaluation of production effectiveness through night light remote sensing image information technology, first, according to the characteristic portrait obtained from the light sense information, the area is divided into multiple sub-areas according to the light sense distribution, and then for each sub-area, the corresponding types of agriculture, forestry, animal husbandry and fishery are determined according to the similarity of data comparison of the sample characteristics of each production type. Then, for each production type sub-area, the average output value obtained by processing the light sense record data of historical samples is combined with the light sense characteristic data and element data of the sub-area to perform aggregation and correction calculations to obtain the output value data of the type production area. Finally, combined with the element market interference coefficient for compensation aggregation processing, the total output value data of agriculture, forestry, animal husbandry and fishery in the area within the cycle is obtained, and the production effectiveness of the area is evaluated by combining the comparison results of the historical average total output value, so as to realize the measurement and evaluation of regional agricultural production through big data and night light remote sensing image information technology.

[0229] According to an embodiment of the present invention, obtaining the night light remote sensing monitoring information of a preset area within a cycle time period according to the preset area night light remote sensing image information database, and generating a regional agricultural product night light remote sensing characteristic portrait, and dividing the preset area into sub-areas according to the night light remote sensing distribution characteristics of the characteristic portrait, obtaining a plurality of night light remote sensing monitoring sub-areas and extracting night light remote sensing characteristic data, specifically:

[0230] Obtaining the night light remote sensing monitoring information of a preset area within a cycle time period according to the preset area night light remote sensing image information database, including light distribution intensity information, light distribution density information, light distribution time period information and light frequency duration information;

[0231] Generating the regional agricultural product night light remote sensing characteristic portrait of the preset area within the cycle time period according to the night light remote sensing monitoring information;

[0232] Dividing the preset area into sub-areas through a preset night light remote sensing characteristic division model according to the night light remote sensing distribution characteristics of the regional agricultural product night light remote sensing characteristic portrait, obtaining a plurality of night light remote sensing monitoring sub-areas;

[0233] Obtaining the night light remote sensing characteristic data of each night light remote sensing monitoring sub-area, including light intensity data, light density data, light time period data and light frequency duration data.

[0234] Among them, to achieve the output value assessment of agriculture, forestry, animal husbandry and fishery within a certain area range over a certain period, it is first necessary to divide the sub-areas of agriculture, forestry, animal husbandry and fishery types within the area, and then conduct type-specific output value assessment on each type of production sub-area through the night light remote sensing monitoring (referred to as light sensing) technology. By depicting the characteristics of the light sensing distribution of the area through the distribution of night light remote sensing monitoring within the area, and dividing the sub-areas according to the light sensing distribution characteristics of the characteristic portrait, the sub-areas with different light sensing distribution states can be distinguished, so as to realize the type division of the sub-areas of agriculture, forestry, animal husbandry and fishery in the area through light sensing distribution. According to the preset regional night light remote sensing image information database, obtain the night light remote sensing monitoring information of the area within the cycle. This information database is a preset third-party database for collecting and storing the night light remote sensing image information of each area. Through this information database, the night light remote sensing information of each area can be obtained, including the light sensing intensity distribution, distribution density, distribution time period collected by the night light remote sensing image, and the information of the frequency and duration of the collected night light remote sensing image. Then, generate the characteristic portrait of the regional agricultural product night light remote sensing according to the night light remote sensing monitoring information. This characteristic portrait is used to describe the information portrait of the intensity, density, duration and frequency law of the night light remote sensing image information of the production activities of agriculture, forestry, animal husbandry and fishery within the area. Then, divide the sub-areas according to the light sensing distribution characteristics of the portrait through the light sensing feature division model, that is, divide the distribution characteristics of the light sensing information of the characteristic portrait through the preset characteristic classification model for dividing the light sensing characteristics, so as to divide different light sensing sub-areas according to the distribution of the light sensing characteristics.

[0235] According to the embodiments of the present invention, obtain the agricultural product night light remote sensing area sample set of multiple sample areas of each production type in the production types of agriculture, forestry, animal husbandry and fishery within multiple identical historical cycle time periods, and the average data of the sample area night light remote sensing characteristics corresponding to the night light remote sensing area samples of each production type, and then compare them with the night light remote sensing characteristic data of each night light remote sensing monitoring sub-area respectively to obtain the sub-area production type light sensing similarity coefficients corresponding to the production types of agriculture, forestry, animal husbandry and fishery. Then, compare and match the calibrated production types of each night light remote sensing monitoring sub-area through the production type light sensing similarity threshold to conduct the type division of the production sub-areas of agriculture, forestry, animal husbandry and fishery for each night light remote sensing monitoring sub-area. Specifically:

[0236] Obtain the agricultural product night light remote sensing area sample set of multiple production type sample areas corresponding to each production type in the production types of agriculture, forestry, animal husbandry and fishery within multiple identical historical cycle time periods according to the preset agricultural, forestry, animal husbandry and fishery production light sensing database, including multiple agricultural night light remote sensing area samples, forestry night light remote sensing area samples, animal husbandry night light remote sensing area samples, and fishery night light remote sensing area samples;

[0237] Obtain the sample area light remote sensing feature data corresponding to the light remote sensing area samples of each production type in the agricultural product light remote sensing area sample set, including light intensity sample data, light density sample data, light period sample data, and light frequency duration sample data;

[0238] Obtain the average sample area light remote sensing feature data corresponding to the agricultural light remote sensing area samples, forestry light remote sensing area samples, animal husbandry light remote sensing area samples, and fishery light remote sensing area samples in the agricultural product light remote sensing area sample set respectively;

[0239] Compare the average sample area light remote sensing feature data corresponding to the light remote sensing area samples of each production type in the agricultural product light remote sensing area sample set with the light remote sensing feature data of each light remote sensing monitoring sub-area respectively, and obtain the sub-area production type light sense similarity coefficients corresponding to the agricultural, forestry, animal husbandry, and fishery production types of each light remote sensing monitoring sub-area respectively;

[0240] Match and compare the sub-area production type light sense similarity coefficients with the preset production type light sense similarity thresholds corresponding to the agricultural, forestry, animal husbandry, and fishery production types respectively, and obtain the threshold matching degrees respectively;

[0241] Take the production type in the agricultural, forestry, animal husbandry, and fishery production types with the best threshold matching degree as the calibrated production type of each light remote sensing monitoring sub-area;

[0242] Calibrate the production types of each light remote sensing monitoring sub-area within the preset area respectively, and divide each light remote sensing monitoring sub-area into agricultural production sub-areas, forestry production sub-areas, animal husbandry production sub-areas, and fishery production sub-areas.

[0243] Among them, it belongs to the types of agriculture, forestry, animal husbandry, and fishery in each clearly divided sub-region. By comparing the distribution of light perception characteristics in each sub-region with the characteristics of samples in each type of region, the types of agriculture, forestry, animal husbandry, and fishery to which each sub-region belongs can be identified and judged according to the comparison similarity. Since the light perception characteristics of different types of agriculture, forestry, animal husbandry, and fishery regions, such as the distribution of light remote sensing intensity, density distribution, and light duration frequency, have characteristic differences, therefore, according to the preset light perception database of agricultural, forestry, animal husbandry, and fishery production, a light perception sample set of multiple sample regions corresponding to each type of agriculture, forestry, animal husbandry, and fishery is obtained within the same historical period, and the light remote sensing characteristic data of the corresponding samples is extracted. Then, the average data of the light perception characteristics is obtained by averaging the light perception characteristic data of each type of sample of the four types of agriculture, forestry, animal husbandry, and fishery. Furthermore, the light perception characteristic data of the sub-region is compared respectively to obtain the light perception similarity coefficient of the production type corresponding to the four types of agriculture, forestry, animal husbandry, and fishery for each sub-region. That is, four comparison similarity coefficients of the four production types are obtained for each sub-region by comparison. Then, they are respectively matched with the light perception similarity threshold of each production type, and the one with the best matching degree is selected as the calibrated production type of one of the actual agriculture, forestry, animal husbandry, and fishery for each sub-region, so as to obtain the identification and division of the production type of each sub-region. Among them, the calculation formula of the light perception similarity coefficient of the sub-region production type is as follows:

[0244]

[0245] Among them, σ R i is the light perception similarity coefficient of the sub-region production type corresponding to the i-th type among the four types of agriculture, forestry, animal husbandry, and fishery production types, are respectively the average data of the light intensity samples, the light density sample data, the average data of the light period samples, and the average data of the light frequency duration samples corresponding to the i-th type of sample among the four types of samples of the agricultural light remote sensing area sample, the forestry light remote sensing area sample, the animal husbandry light remote sensing area sample, and the fishery light remote sensing area sample. x c 、g k 、p m 、b z are respectively the light intensity data, the light density data, the light period data, and the light frequency duration data of the light remote sensing monitoring sub-region. τ 1 、τ 2 、τ 3 、τ 4 、ξ 1 、ξ 2 、ξ 3 、ξ 4 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset light perception database of agricultural, forestry, animal husbandry, and fishery production).

[0246] According to an embodiment of the present invention, obtaining multiple similar agricultural light remote sensing area similar samples and agricultural area sample light perception record data based on the agricultural area production characteristic data of each agricultural production sub-region, processing to obtain the average output value data of the light perception duration per unit area of the agricultural samples, and then combining the corresponding light remote sensing characteristic data of each agricultural production sub-region to process and obtain the agricultural production area output value data of the preset area, and correcting the agricultural production area output value data according to the agricultural production factor data to obtain the corrected agricultural production area output value data, specifically:

[0247] Obtain the agricultural area production characteristic data of each agricultural production sub-region, including the planted crop category data, latitude and altitude data, and planted area data;

[0248] According to the preset agroforestry and fishery production light perception database, obtain multiple agricultural light remote sensing area similar samples similar to the agricultural area production characteristic data of each agricultural production sub-region;

[0249] Obtain the agricultural area sample light perception record data of the multiple agricultural light remote sensing area similar samples in multiple same historical cycle time periods, including sample cumulative light intensity data, sample cumulative duration data, sample area planted area data, and sample area agricultural output value data;

[0250] Process according to the agricultural area sample light perception record data of each agricultural light remote sensing area similar sample to obtain the average output value data of the light perception duration per unit area of the agricultural samples;

[0251] According to the average output value data of the light perception duration per unit area of the agricultural samples, combine the corresponding light remote sensing characteristic data and planted area data of each agricultural production sub-region for aggregation processing to obtain the agricultural production area output value data of the preset area;

[0252] Obtain the agricultural production factor data of the preset area in the cycle time period, including irrigation precipitation data, cumulative sunshine amount data, and average temperature volatility data, and correct the agricultural production area output value data to obtain the corrected agricultural production area output value data;

[0253] The calculation formula of the agricultural production area output value data is:

[0254]

[0255] Wherein, m z is the agricultural production area output value data, λ W is the average output value data of the light perception duration per unit area of the agricultural samples, x cj , g kj , p mj , b zj , h ujThey are respectively the light intensity data, light density data, light period data, light frequency duration data, and planting area data of the j-th agricultural production sub-region, where m is the number of agricultural production sub-regions. ε is a preset feature coefficient;

[0256] The correction calculation formula for the agricultural production area output value correction data is:

[0257]

[0258] where m L is the agricultural production area output value correction data, m z is the agricultural production area output value data, a f and e d and u t are respectively the irrigation precipitation data, cumulative sunshine duration data, and average temperature volatility data, and ρ 1 and ρ 2 and ρ 3 are preset feature coefficients (the feature coefficients are obtained by querying the preset agricultural, forestry, animal husbandry, and fishery production light perception database).

[0259] Among them, is the total regional output value of the agricultural production type sub-region. According to the production characteristic data of each sub-region, multiple regional samples similar to each sub-region are obtained through the preset agricultural, forestry, animal husbandry, and fishery production light perception database, and the light perception record data of multiple similar regional samples in the same historical cycle time period are obtained, including the data of the cumulative light remote sensing intensity, cumulative light perception duration, regional planting area, and regional agricultural output value of the samples. And according to the light perception record data of multiple cycles of multiple similar regional samples, the average output value data of the light perception duration per unit area of the agricultural sample is calculated, that is, the average output value data per unit area, light perception intensity, and duration of the agricultural regional sample. Then, it is aggregated and calculated with the light remote sensing characteristic data and planting area data of each agricultural production sub-region within the region to obtain the output value data of the agricultural production area within the region. Since agricultural production is also affected by production factors, including irrigation precipitation, cumulative sunshine duration, and average temperature volatility, therefore, the regional output value data is corrected according to the production factor data to obtain the output value correction data of all agricultural production areas within the region. Among them, the calculation formula for the average output value data of the light perception duration per unit area of the agricultural sample is:

[0260]

[0261] where λ W is the average output value data of the light perception duration per unit area of the agricultural sample, m hs and v hs and d ws and h usThe agricultural output value data, sample cumulative light intensity data, sample cumulative duration data, and sample area planted data of the sample area in the s-th historical cycle period among k identical historical cycle periods of similar samples in individual agricultural light remote sensing regions respectively. Here, k is the number of identical historical cycle periods of similar samples in an individual agricultural light remote sensing region, r is the number of similar samples in the agricultural light remote sensing region, k and r are integers and greater than or equal to 1, and μ, η, and ι are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset agricultural, forestry, animal husbandry, and fishery production light perception database).

[0262] According to an embodiment of the present invention, obtaining a plurality of similar forestry light remote sensing region similar samples and forestry region sample light perception record data based on the forestry region production characteristic data of each forestry production sub-region, processing to obtain the average output value data of the light perception duration per unit area of the forestry samples, and then combining the corresponding light remote sensing characteristic data of each forestry production sub-region to process and obtain the forestry production region output value data of the preset region, and correcting the forestry production region output value data according to the forestry production factor data to obtain the corrected forestry production region output value data, specifically:

[0263] Obtaining the forestry region production characteristic data of each forestry production sub-region, including tree species data, latitude and altitude data, and planted area data;

[0264] Obtaining a plurality of similar forestry light remote sensing region similar samples similar to the forestry region production characteristic data of each forestry production sub-region according to the preset agricultural, forestry, animal husbandry, and fishery production light perception database;

[0265] Obtaining the forestry region sample light perception record data of the plurality of similar forestry light remote sensing region samples in a plurality of identical historical cycle periods, including sample cumulative light intensity data, sample cumulative duration data, sample area planted data in the sample area, and sample area forestry output value data;

[0266] Processing according to the forestry region sample light perception record data of each forestry light remote sensing region similar sample to obtain the average output value data of the light perception duration per unit area of the forestry samples;

[0267] Performing aggregation processing on the average output value data of the light perception duration per unit area of the forestry samples in combination with the corresponding light remote sensing characteristic data and planted area data of each forestry production sub-region to obtain the forestry production region output value data of the preset region;

[0268] Obtaining the forestry production factor data of the preset region in the cycle period, including precipitation data, cumulative sunshine amount data, and average temperature volatility data, and correcting the forestry production region output value data to obtain the corrected forestry production region output value data;

[0269] The calculation formula for the forestry production region output value data is:

[0270]

[0271] Among them, f g is the output value data of the forestry production area, is the average output value data of the light perception duration per unit area of the forestry sample, x cj , g kj , p mj , b zj , z vj are respectively the light intensity data, light density data, light period data, light frequency duration data, and planting area data of the j-th forestry production sub-area, m is the number of forestry production sub-areas, ε is a preset characteristic coefficient;

[0272] The correction calculation formula for the corrected output value data of the forestry production area is:

[0273]

[0274] Among them, f P is the corrected output value data of the forestry production area, f g is the output value data of the forestry production area, t s , e d , u t are respectively the precipitation data, cumulative sunshine duration data, and average temperature volatility data, ρ 1 , ρ 2 , ρ 3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset light perception database of agriculture, forestry, animal husbandry, and fishery production).

[0275] Among them, to evaluate the total regional output value of the forestry production type sub-region, multiple regional samples similar to each sub-region are obtained through a preset agricultural, forestry, animal husbandry and fishery production light perception database according to the production characteristic data of each sub-region, and the light perception record data of multiple similar regional samples within the same historical cycle time period are obtained, including the cumulative light intensity of the samples, the cumulative light perception duration, the regional planting area and the data of the regional forestry output value. And the average output value data of the light perception duration per unit area of the forestry sample is calculated and obtained based on the light perception record data of multiple cycles of multiple similar regional samples, that is, the average output value data under the unit area, light intensity and duration of the forestry regional sample. Then, it is aggregated and calculated with the light remote sensing characteristic data and the planting area data of each forestry production sub-region within the region to obtain the output value data of the forestry production region within the region. Since forestry production is also affected by production factors, including precipitation, cumulative sunshine hours and average temperature volatility, therefore, the output value data of the region is corrected according to the production factor data to obtain the corrected output value data of all forestry production regions within the region. Among them, the calculation formula for the average output value data of the light perception duration per unit area of the forestry sample is:

[0276]

[0277] Among them, is the average output value data of the light perception duration per unit area of the forestry sample, f us 、v hs 、d ws 、z vs are respectively the sample regional forestry output value data, the sample cumulative light intensity data, the sample cumulative duration data, and the sample regional planting area data of the s-th historical cycle time period among k identical historical cycle time periods of a single similar sample of the forestry light remote sensing area. k is the number of identical historical cycle time periods of a single similar sample of the forestry light remote sensing area, r is the number of similar samples of the forestry light remote sensing area, k and r are rounded and greater than or equal to 1, and μ, η, ι are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset agricultural, forestry, animal husbandry and fishery production light perception database).

[0278] According to an embodiment of the present invention, obtaining multiple similar samples of the animal husbandry light remote sensing area and the light perception record data of the animal husbandry area sample according to the animal husbandry area production characteristic data of each animal husbandry production sub-region, and processing to obtain the average output value data of the light perception duration per unit area of the animal husbandry sample, and then combining the corresponding light remote sensing characteristic data of each animal husbandry production sub-region to process and obtain the output value data of the animal husbandry production region of the preset region, and correcting the output value data of the animal husbandry production region according to the animal husbandry production factor data to obtain the corrected output value data of the animal husbandry production region, specifically:

[0279] Obtain the animal husbandry area production characteristic data of each animal husbandry production sub-region, including livestock category data, livestock latitude data and animal husbandry area data;

[0280] Obtain a plurality of similar samples of the pasture light remote sensing regions that are similar to the pasture regional production characteristic data of each pasture production sub-region according to the preset pasture, forestry, agriculture and fishery production light perception database;

[0281] Obtain the pasture regional sample light perception record data of the plurality of similar samples of the pasture light remote sensing regions within a plurality of identical historical cycle time periods, including sample cumulative light intensity data, sample cumulative duration data, sample regional pasture area data, and sample regional pasture output value data;

[0282] Process according to the pasture regional sample light perception record data of each similar sample of the pasture light remote sensing region to obtain the average output value data of the light perception duration per unit area of the pasture sample;

[0283] Perform aggregation processing on the average output value data of the light perception duration per unit area of the pasture sample in combination with the corresponding light remote sensing characteristic data and pasture area data of each pasture production sub-region to obtain the pasture production regional output value data of the preset region;

[0284] Obtain the pasture production factor data of the preset region within the cycle time period, including soil vegetation good rate data, livestock morbidity data, and livestock processing efficiency data, and correct the pasture production regional output value data to obtain the corrected pasture production regional output value data;

[0285] The calculation formula of the pasture production regional output value data is:

[0286]

[0287] Among them, q e is the pasture production regional output value data, is the average output value data of the light perception duration per unit area of the pasture sample, x cj , g kj , p mj , b zj , a xj are respectively the light intensity data, light density data, light period data, light frequency duration data, and pasture area data of the jth pasture production sub-region, m is the number of pasture production sub-regions, ε is a preset characteristic coefficient;

[0288] The correction calculation formula of the corrected pasture production regional output value data is:

[0289]

[0290] Among them, q H is the corrected pasture production regional output value data, q eFor the output value data of the animal husbandry production area, o u and w n and y a are respectively the data of the good rate of soil vegetation, the morbidity rate of livestock, and the processing efficiency data of animal husbandry, is a preset characteristic coefficient (the characteristic coefficient is obtained by querying the preset photosensory database of agriculture, forestry, animal husbandry and fishery production).

[0291] Among them, is the total output value of the sub-region for evaluating the type of animal husbandry production. According to the production characteristic data of each sub-region, multiple regional samples similar to each sub-region are obtained through the preset photosensory database of agriculture, forestry, animal husbandry and fishery production, and the photosensory record data of multiple similar regional samples in the same historical cycle time period are obtained, including the data of the cumulative light intensity of the samples, the cumulative photosensory duration, the area of regional animal husbandry, and the output value of regional animal husbandry. And according to the photosensory record data of multiple cycles of multiple similar regional samples, the average output value data of the photosensory duration per unit area of the animal husbandry sample is calculated, that is, the average output value data of the unit area, photosensory intensity, and duration of the animal husbandry regional sample. Then, it is aggregated and calculated with the data of the light remote sensing characteristics and the area of animal husbandry of each animal husbandry production sub-region in the region to obtain the output value data of the animal husbandry production area in the region. Since animal husbandry production is affected by production factors, including the data of the good rate of soil and vegetation, the morbidity rate of livestock, and the production capacity efficiency of animal husbandry processing, therefore, the output value data of the region is corrected according to the production factor data to obtain the corrected output value data of all animal husbandry production areas in the region. Among them, the calculation formula for the average output value data of the photosensory duration per unit area of the animal husbandry sample is:

[0292]

[0293] Among them, is the average output value data of the photosensory duration per unit area of the animal husbandry sample, q rs and v hs and d ws and a xs are respectively the output value data of the sample regional animal husbandry, the sample cumulative light intensity data, the sample cumulative duration data, and the sample regional animal husbandry area data of the s-th historical cycle time period among k identical historical cycle time periods of a single similar sample of animal husbandry light remote sensing area. k is the number of identical historical cycle time periods of a single similar sample of animal husbandry light remote sensing area, r is the number of similar samples of animal husbandry light remote sensing area, k and r are rounded and greater than or equal to 1, and μ, η, and ι are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset photosensory database of agriculture, forestry, animal husbandry and fishery production).

[0294] According to an embodiment of the present invention, obtaining a plurality of similar fishery light remote sensing area similar samples and fishery area sample light perception record data according to the fishery area production characteristic data of each fishery production sub-region, processing to obtain the average output value data of the light perception duration per unit area of the fishery sample, and then combining the corresponding light remote sensing characteristic data of each fishery production sub-region to process and obtain the fishery production area output value data of a preset area, and correcting the fishery production area output value data according to the fishery production factor data to obtain the corrected fishery production area output value data, specifically:

[0295] Obtain the fishery area production characteristic data of each fishery production sub-region, including fishing ground sea area data, operation latitude data, and fishing area data;

[0296] According to the preset agricultural, forestry, animal husbandry and fishery production light perception database, obtain a plurality of fishery light remote sensing area similar samples similar to the fishery area production characteristic data of each fishery production sub-region;

[0297] Obtain the fishery area sample light perception record data of the plurality of fishery light remote sensing area similar samples in a plurality of same historical cycle time periods, including sample cumulative light intensity data, sample cumulative duration data, sample area fishing area data, and sample area fishery output value data;

[0298] Process according to the fishery area sample light perception record data of each fishery light remote sensing area similar sample to obtain the average output value data of the light perception duration per unit area of the fishery sample;

[0299] According to the average output value data of the light perception duration per unit area of the fishery sample, combine the corresponding light remote sensing characteristic data and fishing area data of each fishery production sub-region for aggregation processing to obtain the fishery production area output value data of a preset area;

[0300] Obtain the fishery production factor data of the preset area in the cycle time period, including meteorological stability data, equipment operation efficiency data, and water temperature volatility data, and correct the fishery production area output value data to obtain the corrected fishery production area output value data;

[0301] The calculation formula of the fishery production area output value data is:

[0302]

[0303] Among them, c m is the fishery production area output value data, γ D is the average output value data of the light perception duration per unit area of the fishery sample, x cj 、g kj 、p mj 、b zj 、t cjThey are respectively the light intensity data, light density data, light period data, light frequency duration data, and fishing area data of the j-th fishery production sub-region, and m is the number of fishery production sub-regions. ε is a preset feature coefficient;

[0304] The correction calculation formula for the output value correction data of the fishery production area is:

[0305]

[0306] Among them, c V is the output value correction data of the fishery production area, c m is the output value data of the fishery production area, a r , s a , k c are respectively the meteorological stability data, equipment operation efficiency data, and water temperature volatility data, and θ 1 , θ 2 are preset feature coefficients (the feature coefficients are obtained by querying the preset agroforestry and fishery production light perception database).

[0307] Among them, is the total regional output value of the sub-region for evaluating the fishery production type. According to the production characteristic data of each sub-region, multiple regional samples similar to each sub-region are obtained through the preset agroforestry and fishery production light perception database, and the light perception record data of multiple similar regional samples in the same historical cycle time period are obtained, including the data of the cumulative light remote sensing intensity, cumulative light perception duration, regional fishing area, and regional fishery output value of the samples. And according to the light perception record data of multiple cycles of multiple similar regional samples, the average output value data of the light perception duration per unit area of the fishery sample is calculated, that is, the average output value data of the unit area, light perception intensity, and duration of the fishery regional sample. Then, it is aggregated and calculated with the light remote sensing characteristic data and fishing area data of each fishery production sub-region in the region to obtain the output value data of the fishery production area in the region. Since fishery production is also affected by production factors, including meteorological stability, equipment operation efficiency, and water temperature volatility, therefore, the output value data of the region is corrected according to the production factor data to obtain the output value correction data of all fishery production areas in the region. Among them, the calculation formula for the average output value data of the light perception duration per unit area of the fishery sample is:

[0308]

[0309] Among them, γ D is the average output value data of the light perception duration per unit area of the fishery sample, c ws , v hs , d ws , t csThe fishery output value data, sample cumulative light intensity data, sample cumulative duration data, and sample area fishing data of the s-th historical period in k identical historical period time segments of each individual fishery light remote sensing area similar sample. Here, k is the number of identical historical period time segments of an individual fishery light remote sensing area similar sample, r is the number of fishery light remote sensing area similar samples, k and r are integers and greater than or equal to 1, and μ, η, and ι are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset agricultural, forestry, animal husbandry, and fishery production light perception database).

[0310] According to an embodiment of the present invention, the type industry output value interference factor data of agriculture, forestry, animal husbandry, and fishery in the preset area during the cycle time period is processed through a preset market factor interference model to obtain the market factor interference coefficient of agriculture, forestry, animal husbandry, and fishery. Specifically:

[0311] Obtain the type industry output value interference factor data of agriculture, forestry, animal husbandry, and fishery in the preset area during the cycle time period, including the price fluctuation data, quality fluctuation data, and policy subsidy fluctuation data corresponding to agriculture, forestry, animal husbandry, and fishery respectively;

[0312] Process the price fluctuation data, quality fluctuation data, and policy subsidy fluctuation data corresponding to agriculture, forestry, animal husbandry, and fishery respectively through a preset market factor interference model to obtain the market factor interference coefficient of agriculture, forestry, animal husbandry, and fishery;

[0313] The market factor interference coefficient of agriculture, forestry, animal husbandry, and fishery includes the market factor interference coefficient of agriculture, the market factor interference coefficient of forestry, the market factor interference coefficient of animal husbandry, and the market factor interference coefficient of fishery;

[0314] The calculation formula of the market factor interference coefficient of agriculture, forestry, animal husbandry, and fishery is:

[0315]

[0316] Among them, φ fr is the r-th coefficient among the four coefficients of the market factor interference coefficient of agriculture, the market factor interference coefficient of forestry, the market factor interference coefficient of animal husbandry, and the market factor interference coefficient of fishery in the market factor interference coefficient of agriculture, forestry, animal husbandry, and fishery, α qr , δ pr , κ er are the price fluctuation data, quality fluctuation data, and policy subsidy fluctuation data corresponding to the r-th coefficient among the four coefficients of the market factor interference coefficient of agriculture, the market factor interference coefficient of forestry, the market factor interference coefficient of animal husbandry, and the market factor interference coefficient of fishery respectively, and ζ 1 , ζ 2 , ζ 3 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset agricultural, forestry, animal husbandry, and fishery production light perception database).

[0317] Among them, since the overall output value of each production type area in the agriculture, forestry, animal husbandry and fishery industries within the region is interfered by the industry elements corresponding to the agriculture, forestry, animal husbandry and fishery industries, and the output value interference element data includes the fluctuation data of the prices, quality and policy subsidies corresponding to the agriculture, forestry, animal husbandry and fishery industries respectively. The fluctuation data of prices, quality and policy subsidies can be queried and obtained through a third-party regional agricultural, forestry, animal husbandry and fishery product quality and price data monitoring platform, and then calculated and evaluated according to the fluctuation data of prices, quality and policy subsidies corresponding to the agriculture, forestry, animal husbandry and fishery industries through the calculation formula of the preset market element interference model to obtain the element market interference coefficients corresponding to the agriculture, forestry, animal husbandry and fishery industries respectively.

[0318] According to an embodiment of the present invention, the type production area output value correction data corresponding to the agricultural, forestry, animal husbandry and fishery production areas in the preset area is combined with the agricultural, forestry, animal husbandry and fishery element market interference coefficients for processing to obtain the total output value data of the agriculture, forestry, animal husbandry and fishery industries, and the agricultural, forestry, animal husbandry and fishery production effectiveness in the preset area within the cycle time period is evaluated according to the output value comparison result with the historical average total output value data of the agriculture, forestry, animal husbandry and fishery industries, specifically as follows:

[0319] The agricultural production area output value correction data, forestry production area output value correction data, animal husbandry production area output value correction data and fishery production area output value correction data corresponding to the agricultural, forestry, animal husbandry and fishery production areas in the preset area are combined with the agricultural, forestry, animal husbandry and fishery element market interference coefficients for compensation aggregation to obtain the total output value data of the agriculture, forestry, animal husbandry and fishery industries in the preset area;

[0320] The total output value data of the agriculture, forestry, animal husbandry and fishery industries is compared with the historical average total output value data of the agriculture, forestry, animal husbandry and fishery industries in the preset area in multiple identical historical cycle time periods to obtain an output value comparison result;

[0321] The output value comparison result is compared with a preset output value comparison threshold, and the agricultural, forestry, animal husbandry and fishery production effectiveness in the preset area within the cycle time period is evaluated according to the threshold comparison result;

[0322] The calculation formula for the total output value data of the agriculture, forestry, animal husbandry and fishery industries is:

[0323]

[0324] Among them, is the total output value data of the agriculture, forestry, animal husbandry and fishery industries, m L is the output value correction data of the agricultural production area, f P is the output value correction data of the forestry production area, q H is the output value correction data of the animal husbandry production area, c V is the output value correction data of the fishery production area, φ f1 、φ f2 、φ f3 、φ f4They are the interference coefficients of agricultural factor market conditions, forestry factor market conditions, animal husbandry factor market conditions, and fishery factor market conditions, χ 1 , χ 2 , χ 3 , χ 4 are preset characteristic coefficients (the characteristic coefficients are obtained by querying the preset light perception database for agricultural, forestry, animal husbandry, and fishery production).

[0325] Among them, finally, to obtain an accurate prediction and evaluation of the output value of agriculture, forestry, animal husbandry, and fishery in the region, compensation aggregation calculation is performed according to the output value correction data of the four production regions of agriculture, forestry, animal husbandry, and fishery combined with the corresponding interference coefficients of the factor market conditions of agriculture, forestry, animal husbandry, and fishery to obtain the total output value data of agriculture, forestry, animal husbandry, and fishery. Then, the output value comparison result is obtained by comparing with the historical average total output value data of each type. According to the comparison result between the output value comparison result and the preset output value comparison threshold, the production effectiveness of agriculture, forestry, animal husbandry, and fishery in the region within the cycle is evaluated. If the output value comparison result meets the threshold comparison result of the preset output value comparison threshold, the production effectiveness of agriculture, forestry, animal husbandry, and fishery in the region within the cycle time period is significant, and the measurement and effect evaluation of regional agricultural production are realized through light perception technology.

[0326] The third aspect of the present invention provides a computer-readable storage medium, which includes a program for predicting the total output value of agriculture, forestry, animal husbandry, and fishery based on big data. When the program for predicting the total output value of agriculture, forestry, animal husbandry, and fishery based on big data is executed by a processor, the steps of the method for predicting the total output value of agriculture, forestry, animal husbandry, and fishery based on big data as described in any one of the above are realized.

[0327] The method, system, and medium for predicting the total output value of agriculture, forestry, animal husbandry, and fishery based on big data disclosed in the present invention generate a regional agricultural product light remote sensing feature portrait and divide sub-regions according to the light remote sensing monitoring information of a preset region within a cycle, extract light remote sensing feature data, obtain a similarity coefficient by comparing the feature average data of the agricultural product light remote sensing regional sample set of each type of agriculture, forestry, animal husbandry, and fishery production with the light remote sensing feature data to match the production types of each sub-region, then obtain the unit average output value according to the light perception record data of the regional similar samples of each sub-region of agriculture, forestry, animal husbandry, and fishery, and then combine the light remote sensing feature data of each type of sub-region to process and obtain the output value correction data of the four type production regions, and combine with the interference coefficients of the factor market conditions of agriculture, forestry, animal husbandry, and fishery to process and obtain the total output value data of agriculture, forestry, animal husbandry, and fishery, and then evaluate the production effectiveness of agriculture, forestry, animal husbandry, and fishery in the region within the cycle through the output value comparison result of the historical average total data; thus, the production type regional division is carried out through the light remote sensing information within the region, and the output value data of each type of production region is obtained by combining historical sample data, and the total output value of agriculture, forestry, animal husbandry, and fishery is obtained by combining the production factor interference situation and the production effectiveness of the region is judged, realizing the measurement and evaluation of the total output value of agriculture, forestry, animal husbandry, and fishery within the region through big data and night light remote sensing technology.

[0328] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the couplings, direct couplings, or communication connections between the components shown or discussed with each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be electrical, mechanical, or other forms.

[0329] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0330] In addition, each functional unit in the embodiments of the present invention can be all integrated in a processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in a unit. The above integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional units.

[0331] Those of ordinary skill in the art can understand that all or part of the steps to implement the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a readable storage medium. When the program is executed, it executes the steps including the above method embodiments. The foregoing storage medium includes various media that can store program codes, such as removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0332] Alternatively, if the above integrated units of the present invention are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. The foregoing storage medium includes various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

Claims

1. A method for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data, characterized in that: The following steps are involved: According to the nighttime light remote sensing image information database of the preset area, light remote sensing monitoring information of the preset area within a periodic time period is obtained, including light distribution intensity information, light distribution density information, light distribution time period information and light frequency duration information; according to the light remote sensing monitoring information, a regional agricultural light remote sensing feature portrait of the preset area within the periodic time period is generated; according to the light remote sensing distribution characteristics of the regional agricultural light remote sensing feature portrait, the preset area is divided into sub-areas by a preset light remote sensing feature division model to obtain a plurality of light remote sensing monitoring sub-areas; and light remote sensing feature data of each light remote sensing monitoring sub-area is obtained, including light intensity data, light density data, light time period data and light frequency duration data; According to the preset agricultural, forestry, animal husbandry and fishery production light sensing database, a plurality of production type sample areas corresponding to each production type in the agricultural, forestry, animal husbandry and fishery production types are obtained in a plurality of same historical period time periods, including a plurality of agricultural light remote sensing area samples, forestry light remote sensing area samples, animal husbandry light remote sensing area samples, and fishery light remote sensing area samples; sample area light remote sensing feature data corresponding to the light remote sensing area samples of each production type in the agricultural light remote sensing area sample set are obtained, including light intensity sample data, light density sample data, light time period sample data, and light frequency duration sample data; and average light remote sensing feature data of the sample areas corresponding to each production type in the agricultural light remote sensing area sample set are obtained. Compare with the light remote sensing feature data of each light remote sensing monitoring sub-area respectively, obtain the sub-area production type light sensitivity similarity coefficient corresponding to the agriculture, forestry, animal husbandry and fishery production type of each light remote sensing monitoring sub-area respectively, match and compare with the preset production type light sensitivity similarity threshold corresponding to the agriculture, forestry, animal husbandry and fishery production type respectively, obtain the threshold matching degree respectively, take the production type of the agriculture, forestry, animal husbandry and fishery production type with the best threshold matching degree as the calibrated production type of each light remote sensing monitoring sub-area, calibrate the production type of each light remote sensing monitoring sub-area in the preset area, and divide each light remote sensing monitoring sub-area into an agricultural production sub-area, a forestry production sub-area, an animal husbandry production sub-area and a fishery production sub-area; The calculation formula of the light sensitivity similarity coefficient of the sub-region production type is: Among them, σ Ri is the light sensitivity similarity coefficient of the sub-region production type corresponding to the ith type among the four types of agricultural, forestry, animal husbandry and fishery production types, The light intensity sample average data, light density sample data, light time sample average data, and light frequency duration sample average data corresponding to the i-th type of sample in the four types of samples, namely, agricultural light remote sensing area samples, forestry light remote sensing area samples, animal husbandry light remote sensing area samples, and fishery light remote sensing area samples, x c , g k 、p m 、b z They are light intensity data, light density data, light time period data, and light frequency duration data of the light remote sensing monitoring sub-area, respectively; τ1, τ2, τ3, τ4, ξ1, ξ2, ξ3, and ξ4 are preset characteristic coefficients; Acquire agricultural regional production characteristic data of each agricultural production sub-region, including planted crop category data, latitude and altitude data, and planted area data; acquire agricultural regional sample light perception record data of multiple agricultural light remote sensing area similar samples similar to the agricultural regional production characteristic data of each agricultural production sub-region in multiple same historical period time periods according to the preset agricultural, forestry, animal husbandry and fishery production light perception database, including sample cumulative light intensity data, sample cumulative duration data, sample area planted area data, and sample area agricultural output value data; process to obtain agricultural sample unit area light perception duration average output value data; perform aggregation processing in combination with the corresponding light remote sensing characteristic data and planted area data of each agricultural production sub-region to obtain agricultural production regional output value data of the preset region; obtain agricultural production factor data of the preset region in the period time period, including irrigation precipitation data, cumulative sunshine data, and average temperature fluctuation rate data; and correct the agricultural production regional output value data to obtain agricultural production regional output value correction data; The calculation formula for the agricultural production area output value data is: Among them, m z is the output value data of agricultural production area, λ W is the average output value of the agricultural sample per unit area of ​​light perception time, x cj , g kj 、p mj 、b zj 、h uj are the light intensity data, light density data, light time data, light frequency duration data, and planting area data of the jth agricultural production sub-area, m is the number of agricultural production sub-areas, ε is the preset characteristic coefficient; The correction calculation formula for the agricultural production area output value correction data is: Among them, m L is the revised data of agricultural production area output value, m z is the regional output value data of agricultural production, a f 、e d 、u t They are irrigation precipitation data, cumulative sunshine data, and average temperature fluctuation rate data, and ρ1, ρ2, and ρ3 are preset characteristic coefficients; The calculation formula for the average output value of the light perception time per unit area of ​​the agricultural sample is: Among them, λ W is the average output value of light perception time per unit area of ​​agricultural samples, m hs 、v hs d ws 、h us The agricultural output value data, sample cumulative light intensity data, sample cumulative duration data, and sample area planting area data of the sample area in the sth historical period in the k same historical period, respectively, of similar samples of a single agricultural light remote sensing area, k is the number of the same historical period of similar samples of a single agricultural light remote sensing area, r is the number of similar samples in the agricultural light remote sensing area, k and r are integers and greater than or equal to 1, μ, η, ι are preset characteristic coefficients; According to the forestry regional production characteristic data of each forestry production sub-region, a plurality of similar forestry light remote sensing regional similar samples and forestry regional sample light perception record data are obtained, and the average output value data of the light perception time per unit area of ​​the forestry samples are obtained by processing, and then the forestry production regional output value data of the preset area is obtained by combining the corresponding light remote sensing characteristic data of each forestry production sub-region, and the forestry production regional output value data is corrected according to the forestry production factor data to obtain the forestry production regional output value correction data; According to the animal husbandry regional production characteristic data of each animal husbandry production sub-region, a plurality of similar animal husbandry light remote sensing regional similar samples and animal husbandry regional sample light sensing record data are obtained, and the animal husbandry sample unit area light sensing duration average output value data is obtained by processing, and then the animal husbandry production regional output value data of the preset area is obtained by combining the corresponding light remote sensing characteristic data of each animal husbandry production sub-region, and the animal husbandry production regional output value data is corrected according to the animal husbandry production factor data to obtain the animal husbandry production regional output value correction data; According to the fishery regional production characteristic data of each fishery production sub-region, a plurality of similar fishery light remote sensing regional similar samples and fishery regional sample light perception record data are obtained, and the average output value data of the light perception time per unit area of ​​the fishery sample is obtained by processing, and then the fishery production regional output value data of the preset area is obtained by combining the corresponding light remote sensing characteristic data of each fishery production sub-region, and the fishery production regional output value data is corrected according to the fishery production factor data to obtain the fishery production regional output value correction data; Obtaining the type industry output value interference factor data of the agriculture, forestry, animal husbandry and fishery in the preset area during the periodic time period, including the price fluctuation data, quality fluctuation data and policy subsidy fluctuation data corresponding to the agriculture, forestry, animal husbandry and fishery respectively, and processing them through a preset market factor interference model to obtain the market interference coefficients of the agriculture, forestry, animal husbandry and fishery factors, including the agricultural factor market interference coefficient, the forestry factor market interference coefficient, the animal husbandry factor market interference coefficient and the fishery factor market interference coefficient; The calculation formula of the market interference coefficient of the agricultural, forestry, animal husbandry and fishery factors is: Among them, φ fr is the rth coefficient among the four coefficients of agricultural factor market interference coefficient, forestry factor market interference coefficient, animal husbandry factor market interference coefficient and fishery factor market interference coefficient, α qr , δ pr , κ er The price fluctuation data, quality fluctuation data, and policy subsidy fluctuation data corresponding to the rth coefficient of the four coefficients of agricultural factor market interference coefficient, forestry factor market interference coefficient, animal husbandry factor market interference coefficient, and fishery factor market interference coefficient, respectively. ζ1, ζ2, and ζ3 are preset characteristic coefficients; The total data of agricultural, forestry, animal husbandry and fishery output values ​​are obtained by processing the output value correction data of the types of production areas corresponding to the agricultural, forestry, animal husbandry and fishery production areas in the preset area in combination with the agricultural, forestry, animal husbandry and fishery factor market interference coefficient, and the agricultural, forestry, animal husbandry and fishery production results of the preset area within the periodic time period are evaluated based on the output value comparison result with the historical average total data of agricultural, forestry, animal husbandry and fishery output values.

2. The method for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data according to claim 1 is characterized in that: The method comprises: obtaining a plurality of similar forestry light remote sensing area similar samples and forestry area sample light sensing record data based on the forestry area production characteristic data of each forestry production sub-area, and processing to obtain the average output value data of the light sensing time per unit area of ​​the forestry samples; and then processing to obtain the forestry production area output value data of the preset area in combination with the corresponding light remote sensing characteristic data of each forestry production sub-area; and correcting the forestry production area output value data based on the forestry production factor data to obtain the forestry production area output value correction data, including: Obtain forestry regional production characteristic data for each forestry production sub-region, including tree category data, latitude and altitude data, and planted area data; Acquire multiple forestry light remote sensing area similar samples similar to the forestry area production characteristic data of each forestry production sub-area according to the preset agriculture, forestry, animal husbandry and fishery production light sensing database; Obtaining forestry area sample light sensing record data of similar samples in the plurality of forestry light remote sensing areas within the same plurality of historical period time periods, including sample cumulative light intensity data, sample cumulative duration data, sample area planting area data, and sample area forestry output value data; Processing the light sensing record data of the forestry area samples of similar samples in each forestry light remote sensing area to obtain the average output value data of the light sensing time per unit area of ​​the forestry samples; The forestry production area output value data of the preset area is obtained by performing aggregation processing based on the average output value data of the light sensing duration per unit area of ​​the forestry samples combined with the corresponding light remote sensing feature data and the planting area data of each forestry production sub-area; Acquire the forestry production factor data of the preset area within the periodic time period, including precipitation data, cumulative sunshine data and average temperature fluctuation rate data, and correct the output value data of the forestry production area to obtain the forestry production area output value correction data; The calculation formula for the output value data of the forestry production area is: Among them, f g It is the regional output value data of forestry production. is the average output value of light perception time per unit area of ​​forestry samples, x cj , g kj 、p mj 、b zj 、z vj are the light intensity data, light density data, light time data, light frequency duration data, and planting area data of the jth forestry production sub-area, m is the number of forestry production sub-areas, ε is the preset characteristic coefficient; The correction calculation formula for the forestry production area output value correction data is: Among them, f P is the revised data of forestry production area output value, f g is the regional output value data of forestry production, t s 、e d 、u t They are precipitation data, cumulative sunshine data, and average temperature fluctuation rate data, and ρ1, ρ2, and ρ3 are preset characteristic coefficients.

3. The method for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data according to claim 2 is characterized in that: The method comprises: obtaining a plurality of similar samples of animal husbandry light remote sensing areas and animal husbandry area sample light sensing record data based on the animal husbandry area production characteristic data of each animal husbandry production sub-area, and processing to obtain the average output value data of the animal husbandry sample per unit area light sensing time, and then combining the corresponding light remote sensing characteristic data of each animal husbandry production sub-area to obtain the animal husbandry production area output value data of the preset area, and correcting the animal husbandry production area output value data based on the animal husbandry production factor data to obtain the animal husbandry production area output value correction data, including: Obtain the livestock regional production characteristic data of each livestock production sub-region, including livestock category data, livestock latitude data and livestock area data; Acquire a plurality of animal husbandry light remote sensing area similar samples similar to the animal husbandry area production characteristic data of each animal husbandry production sub-area according to the preset agricultural, forestry, animal husbandry and fishery production light sensing database; Obtaining the animal husbandry area sample light sensing record data of similar samples in the plurality of animal husbandry light remote sensing areas within the same historical period time periods, including sample cumulative light intensity data, sample cumulative duration data, sample area animal husbandry data, and sample area animal husbandry output value data; Processing the light sensing record data of the animal husbandry area samples of similar samples in each animal husbandry light remote sensing area to obtain the average output value data of the light sensing time per unit area of ​​the animal husbandry samples; According to the average output value data of the light sensing duration per unit area of ​​the animal husbandry samples, combined with the corresponding light remote sensing feature data of each animal husbandry production sub-area and the animal husbandry area data, aggregation processing is performed to obtain the animal husbandry production area output value data of the preset area; Acquire the animal husbandry production factor data of the preset area within the periodic time period, including soil and vegetation yield data, livestock morbidity data and animal husbandry processing efficiency data, and correct the output value data of the animal husbandry production area to obtain the corrected output value data of the animal husbandry production area; The calculation formula for the output value data of the animal husbandry production area is: Among them, q e It is the regional output value data of animal husbandry production. is the average output value of light perception time per unit area of ​​animal husbandry samples, x cj , g kj 、p mj 、b zj 、a xj are the light intensity data, light density data, light time data, light frequency duration data, and animal husbandry area data of the jth animal husbandry production sub-area, m is the number of animal husbandry production sub-areas, ε is the preset characteristic coefficient; The correction calculation formula for the revised data of the output value of animal husbandry production area is: Among them, q H is the revised data of regional output value of animal husbandry production, q e It is the regional output value data of animal husbandry production, u 、w n ,y a They are soil vegetation yield data, livestock morbidity data, and livestock processing efficiency data. is the preset characteristic coefficient.

4. The method for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data according to claim 3 is characterized in that: The method comprises: obtaining a plurality of similar fishery light remote sensing area similar samples and fishery area sample light sensing record data based on the fishery area production characteristic data of each fishery production sub-area, and processing to obtain the average output value data of the light sensing time per unit area of ​​the fishery samples; and then processing to obtain the fishery production area output value data of the preset area in combination with the corresponding light remote sensing characteristic data of each fishery production sub-area; and correcting the fishery production area output value data based on the fishery production factor data to obtain the fishery production area output value correction data, including: Obtain fishery regional production characteristic data for each fishery production sub-region, including fishing ground sea area data, operation latitude data and fishing area data; According to the preset agricultural, forestry, animal husbandry and fishery production light sensing database, a plurality of fishery light remote sensing area similar samples similar to the fishery area production characteristic data of each fishery production sub-area are obtained; Obtaining fishery area sample light perception record data of similar samples in the multiple fishery light remote sensing areas within multiple identical historical period time periods, including sample cumulative light intensity data, sample cumulative duration data, sample area fishing area data, and sample area fishery output value data; Processing the light sensing record data of the fishery area samples of similar samples in each fishery light remote sensing area to obtain the average output value data of the light sensing time per unit area of ​​the fishery samples; The fishery production area output value data of the preset area is obtained by performing aggregation processing based on the average output value data of the light sensing duration per unit area of ​​the fishery samples combined with the corresponding light remote sensing feature data and the fishing area data of each fishery production sub-area; Acquiring the fishery production factor data of the preset area within the periodic time period, including meteorological stability data, equipment operation efficiency data and water temperature fluctuation rate data, and correcting the output value data of the fishery production area to obtain the corrected output value data of the fishery production area; The calculation formula for the output value data of the fishery production area is: Among them, c m is the regional output value data of fishery production, γ D is the average output value of light perception time per unit area of ​​fishery samples, x cj , g kj 、p mj 、b zj ,t cj are the light intensity data, light density data, light time data, light frequency duration data, and fishing area data of the jth fishery production sub-area, m is the number of fishery production sub-areas, ε is the preset characteristic coefficient; The correction calculation formula for the fishery production area output value correction data is: Among them, c V Corrected data for regional output value of fishery production, c m is the regional output value data of fishery production, a r 、s a , k c They are meteorological stability data, equipment operating efficiency data, and water temperature fluctuation data, respectively. θ1 and θ2 are preset characteristic coefficients.

5. The method for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data according to claim 4 is characterized in that: The output value correction data of the types of production areas corresponding to the agricultural, forestry, animal husbandry and fishery production areas in the preset area are processed in combination with the agricultural, forestry, animal husbandry and fishery factor market interference coefficient to obtain the total output value data of agriculture, forestry, animal husbandry and fishery, and the production effect of agriculture, forestry, animal husbandry and fishery in the preset area within the periodic time period is evaluated based on the output value comparison result with the historical average total output value data of agriculture, forestry, animal husbandry and fishery, including: According to the agricultural production area output value correction data, forestry production area output value correction data, animal husbandry production area output value correction data and fishery production area output value correction data corresponding to the agricultural, forestry, animal husbandry and fishery production areas of the preset area, combined with the agricultural, forestry, animal husbandry and fishery factor market interference coefficient, compensation aggregation is performed to obtain the total output value data of agriculture, forestry, animal husbandry and fishery in the preset area; Comparing the total output value data of agriculture, forestry, animal husbandry and fishery with the historical average total output value data of agriculture, forestry, animal husbandry and fishery in the preset area in multiple same historical period time periods to obtain an output value comparison result; Performing a threshold comparison based on the output value comparison result and a preset output value comparison threshold, and evaluating the agricultural, forestry, animal husbandry and fishery production effect of the preset area in the periodic time period according to the threshold comparison result; The calculation formula for the total output value of agriculture, forestry, animal husbandry and fishery is: in, is the total output value of agriculture, forestry, animal husbandry and fishery, m L is the revised data of agricultural production area output value, f P is the revised data of forestry production area output value, q H Corrected data for the regional output value of animal husbandry production, c V is the regional output value correction data of fishery production, φ f1 ,φ f2 ,φ f3 ,φ f4 They are respectively the market interference coefficient of agricultural factors, the market interference coefficient of forestry factors, the market interference coefficient of animal husbandry factors, and the market interference coefficient of fishery factors. χ1, χ2, χ3, and χ4 are preset characteristic coefficients.

6. The total output value prediction system of agriculture, forestry, animal husbandry and fishery based on big data is characterized by: The system includes: a memory and a processor, wherein the memory includes a program of a method for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data, and when the program of the method for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data is executed by the processor, the method for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data as described in any one of claims 1 to 5 is implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a method program for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data. When the method program for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data is executed by a processor, the steps of the method for predicting the total output value of agriculture, forestry, animal husbandry and fishery based on big data as described in any one of claims 1 to 5 are implemented.

Images