Intelligent agricultural management method and system based on computer analysis

Abstract

The invention discloses an intelligent agricultural management method and system based on computer analysis, and particularly relates to the technical field of agricultural information, and the method comprises the following steps: obtaining farmland resource information, obtaining and processing a farmland resource information set, obtaining an environment data set and a growth data set according to a processing result, and then carrying out the environment analysis and growth analysis, a growth deviation combination and an environment deviation combination are obtained, a crop classification combination set of the target farmland is further obtained, category code numbers are generated, corresponding abnormal type early warning signals and comprehensive abnormal levels are generated according to the category code numbers and a preset early warning strategy and summarized, and an early warning combination set is obtained; by monitoring and analyzing the environment condition and the crop growth state of the farmland in real time, problems in agricultural production can be found and solved in time, various potential problems and risk factors in the farmland can be identified, and basis data of a precise management strategy can be provided for agricultural production.

Description

Technical Field

[0001] The present invention relates to the field of agricultural information technology. More specifically, the present invention relates to an intelligent agricultural management method and system based on computer analysis. Background Art

[0002] With the development of technology and the growth of the population, agricultural production is facing more and more challenges, such as limited land resources, climate change, pests and diseases. Since the sources of farmland information data collection are extensive, and even two adjacent farmlands may have large differences, traditional agricultural management methods often rely on manual experience, with low efficiency and prone to misjudgment, unable to meet the needs of modern agricultural production. Therefore, it is particularly important to conduct intelligent monitoring and management of farmland resources and crop growth. Therefore, an intelligent agricultural management method and system based on computer analysis are proposed herein. Summary of the Invention

[0003] To achieve the above object, the present invention provides the following technical solutions:

[0004] An intelligent agricultural management system based on computer analysis, comprising a farmland resource information collection module, a farmland resource information processing module, an environmental information collection module, a crop growth monitoring module, a cloud analysis module, a neural network module, a farmland division module, and an early warning module;

[0005] The farmland resource information collection module is used to obtain farmland resource information, obtain a farmland resource information set and transmit it to the farmland resource information processing module;

[0006] The farmland resource information processing module is used to process the farmland resource information set, obtain a farmland resource processing set and transmit it to the environmental information collection module and the crop growth monitoring module;

[0007] The environmental information collection module is used to collect the crop growth environment of the target farmland according to the farmland resource processing set, obtain an environmental data set and transmit it to the cloud analysis module;

[0008] The crop growth monitoring module is used to collect the crop growth status of the target farmland according to the farmland resource processing set, obtain a growth data set and transmit it to the cloud analysis module;

[0009] The cloud analysis module is used to perform environmental analysis based on the environmental data set of the target farmland to obtain an environmental deviation combination, perform growth analysis based on the growth data set of the target farmland to obtain a growth deviation combination, and then transmit the environmental deviation combination and the growth deviation combination to the neural network module together;

[0010] The neural network module is used to construct a neural network model based on the environmental deviation combination and the growth deviation combination, obtain the crop classification combination set of the target farmland according to the constructed neural network model, and then send the crop classification combination set of the target farmland to the farmland division module;

[0011] The farmland division module is used to divide the planting categories of the target farmland according to the preset division strategy and the crop classification combination set, generate the corresponding category coding number and send it to the warning module;

[0012] The warning module generates corresponding abnormal type warning signals and comprehensive abnormal levels according to the category coding number and the preset warning strategy, summarizes all the abnormal type warning signals and the comprehensive abnormal levels, and obtains the warning combination set.

[0013] In a preferred embodiment, the farmland resource information set includes the location information, range information, crop type information, and area information to which the target farmland belongs of the target farmland.

[0014] In a preferred embodiment, the farmland resource information processing module is used to process the farmland resource information set, and the obtained farmland resource processing set means: determining the coordinate data of the target farmland and the range graph of the farmland according to the location information and range information of the target farmland in the farmland resource information set, determining the types of crops planted according to the crop type information, and determining the area to which the growth environment belongs according to the area information to which the target farmland belongs.

[0015] In a preferred embodiment, the environmental information collection module is used to collect the crop growth environment of the target farmland according to the farmland resource processing set, and the obtained environmental data set means:

[0016] The environmental information collection module collects the meteorological information of the area to which the target farmland belongs, obtains the actual data corresponding to each preset meteorological index, and obtains the first subset of environmental data; collects the soil information according to the coordinate data of the target farmland and the range graph of the farmland, obtains the actual data corresponding to each preset soil index, and obtains the second subset of environmental data, and summarizes the first subset of environmental data and the second subset of environmental data to obtain the environmental data set.

[0017] In a preferred embodiment, the crop growth monitoring module is used to collect the crop growth status of the target farmland according to the farmland resource processing set, and the obtained growth data set means:

[0018] Obtain images of all farmlands through an optical satellite outside the atmosphere, then import the vector file of the target farmland, crop the image through ArcGIS software to obtain the image corresponding to the range graph of the target farmland, and then use pattern recognition technology to recognize the image corresponding to the range graph of the target farmland, calculate the corresponding data of the pixel point index of the bare land and the pixel point index of the crop leaves respectively, and obtain the corresponding data of the crop height index, the crop leaf color index, and the crop leaf disease spot index. Collect and summarize all the corresponding data of the indexes to obtain a growth data set.

[0019] In a preferred embodiment, the cloud analysis module is used to perform environmental analysis based on the environmental data set of the target farmland, and the environmental deviation combination obtained is:

[0020] Obtain the actual data corresponding to each preset meteorological index in the environmental data subset one, mark the actual data corresponding to each preset meteorological index in the environmental data subset one as QXi respectively, mark the standard data corresponding to each preset meteorological index as QBi respectively, mark the preset deviation ratio threshold corresponding to each preset meteorological index as QCi, and calculate the actual deviation ratio of each preset meteorological index: ; BL1i is the actual deviation ratio of each preset meteorological index. If the actual deviation ratio BL1i of the target preset meteorological index is greater than or equal to the preset deviation ratio threshold QCi, then mark this meteorological index as a deviation item. If the actual deviation ratio BL1i of the target preset meteorological index is less than the preset deviation ratio threshold QCi, then mark this meteorological index as a non-deviation item. The corresponding output value of the non-deviation item is set to the numerical value zero, and the corresponding output value of the deviation item is the actual deviation ratio BL1i;

[0021] Obtain the actual data corresponding to each preset soil index in the environmental data subset two, mark the actual data corresponding to each preset soil index in the environmental data subset two as TXi respectively, mark the standard data corresponding to each preset soil index as TBi respectively, mark the preset deviation ratio threshold corresponding to each preset soil index as TCi, and calculate the actual deviation ratio of each preset soil index: ; BL2i is the actual deviation ratio of each preset soil index. If the actual deviation ratio BL2i of the target preset soil index is greater than or equal to the preset deviation ratio threshold TCi, then mark this soil index as a deviation item. If the actual deviation ratio BL2i of the target preset soil index is less than the preset deviation ratio threshold TCi, then mark this soil index as a non-deviation item. The corresponding output value of the non-deviation item is set to the numerical value zero, and the corresponding output value of the deviation item is the actual deviation ratio BL2i;

[0022] Summarize the output values of the environmental data subset one and the environmental data subset two to obtain an environmental deviation combination;

[0023] The cloud analysis module is used to perform growth analysis based on the growth data set of the target farmland, and the growth deviation combination is:

[0024] The corresponding data of the bare land pixel index and the crop leaf pixel index are marked as LDi and YXi respectively, and the deviation value is calculated as: a1 and a2 are preset proportional coefficients, PC1 is deviation value 1, ZZ1 is the preset land coverage comparison threshold of the target farmland, and the corresponding data of the crop height index, crop leaf color index, and crop leaf disease spot index are marked as GDi, YSi, and BHi respectively, and the deviation value 2 is calculated: ; f1, f2, and f3 are all preset proportional coefficients, PC2 is the deviation value two, and ZZ2 is the preset growth comparison threshold of the target farmland. The deviation value one PC1 and the deviation value two PC2 are summarized to obtain the growth deviation combination.

[0025] In a preferred embodiment, the crop classification combination set of the target farmland obtained by the neural network module according to the constructed neural network model refers to:

[0026] The growth deviation combination and the environmental deviation combination are used as the input data of the constructed neural network model, and the risk value of the preset risk items of crops in each target farmland is obtained as the output data, and it is assigned to 0 or 1 to train the model. 0 indicates that the risk value of the risk item is less than or equal to the set threshold, and 1 indicates that the risk value of the risk item is greater than the set threshold. The assignment results are summarized to obtain the crop classification combination set of the target farmland.

[0027] In a preferred embodiment, the farmland division module is used to divide the target farmland into planting categories according to the preset division strategy and crop classification combination set, and the corresponding category code number is generated:

[0028] The target farmland is divided into farmlands according to the different types of crops, and the crop types are marked as NZi. The risk value of the risk item with an output result of 1 is subjected to the following operations: the risk value of the risk item is obtained and marked as FXi, the set threshold is marked as Wi, the ratio of the risk value FXi of the risk item to the set threshold Wi is calculated and marked as Ri, the crop types NZi and all the ratios Ri are summarized to generate a category code number.

[0029] In a preferred embodiment, the warning module generates corresponding abnormal type warning signals and comprehensive abnormality levels according to the category code number and the preset warning strategy:

[0030] Based on the risk items corresponding to the ratio Ri, an early warning signal of the abnormal type corresponding to the risk item is sent, and the comprehensive abnormal value is calculated through the following formula: ; ZHi is the comprehensive abnormal value, ji is the preset risk coefficient of the risk item in the crop type NZi, and there is a comprehensive abnormal value interval - comprehensive abnormal level form preset in the early warning module. By looking up the comprehensive abnormal value interval into which the comprehensive abnormal value ZHi falls, the comprehensive abnormal level can be obtained.

[0031] In a preferred embodiment, a smart agriculture management method based on computer analysis includes the following steps:

[0032] Step 1: The farmland resource information collection module obtains the farmland resource information, obtains the farmland resource information set and transports it to the farmland resource information processing module;

[0033] Step 2: The farmland resource information processing module processes the farmland resource information set, obtains the farmland resource processing set and transports it to the environmental information collection module and the crop growth monitoring module;

[0034] Step 3: The environmental information collection module collects the crop growth environment of the target farmland according to the farmland resource processing set, obtains the environmental data set and transports it to the cloud analysis module;

[0035] Step 4: The crop growth monitoring module collects the crop growth status of the target farmland according to the farmland resource processing set, obtains the growth data set and transports it to the cloud analysis module;

[0036] Step 5: The cloud analysis module performs environmental analysis and growth analysis, obtains the growth deviation combination and the environmental deviation combination and transports them to the neural network module together. The neural network module obtains the crop classification combination set of the target farmland according to the constructed neural network model;

[0037] Step 6: The farmland division module is used to divide the planting categories of the target farmland according to the preset division strategy and the crop classification combination set, generate the corresponding category coding number and transport it to the early warning module;

[0038] Step 7: The early warning module generates the corresponding abnormal type early warning signal and the comprehensive abnormal level according to the category coding number and the preset early warning strategy, and summarizes all the abnormal type early warning signals and the comprehensive abnormal level to obtain the early warning combination set.

[0039] The technical effects and advantages of the present invention:

[0040] The present invention utilizes GIS technology and intelligent algorithms to achieve intelligent monitoring and management of farmland resource information, environmental data, and crop growth status, improving the intelligent level of farmland management. Based on the analysis of environmental data and growth data, the system can accurately identify various potential problems and risk factors in the farmland, providing data for precise management strategies for agricultural production. By real-time monitoring and analyzing the environmental conditions and crop growth status of the farmland, it is conducive to timely discovering and solving problems in agricultural production, thereby improving the efficiency and yield of agricultural production.

[0041] The present invention can accurately predict possible problems in the farmland, and farmers can take preventive measures before the problems occur, thereby reducing losses and lowering production costs. Through intelligent farmland division and planting category division, it is beneficial for farmers to optimize the utilization of farmland resources, improve land utilization rate and output efficiency. This system can help agricultural production achieve precise, efficient, and sustainable development, promote the coordinated development of agricultural production and the ecological environment, and has positive social and economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the accompanying drawings;

[0043] Figure 1 is the schematic diagram of the intelligent agriculture management system based on computer analysis in the present invention.

[0044] Figure 2 is the schematic diagram of a method for intelligent agriculture management based on computer analysis in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0046] Embodiment 1

[0047] The intelligent agriculture management system based on computer analysis includes a farmland resource information collection module, a farmland resource information processing module, an environmental information collection module, a crop growth monitoring module, a cloud analysis module, a neural network module, a farmland division module, and a warning module.

[0048] The farmland resource information acquisition module is used to obtain farmland resource information, obtain the farmland resource information set and transmit it to the farmland resource information processing module; collect and obtain various information related to farmland resources, and provide data support for subsequent farmland management and monitoring, including the location information, scope information, crop type information, and region information of the target farmland; the location information refers to the geographical location coordinates of the target farmland, usually represented by longitude and latitude or other geographical coordinate systems. The acquisition of location information can help the system accurately locate the position of the target farmland and provide a basis for subsequent geographical information analysis and spatial data processing; the scope information refers to the scope or boundary information of the target farmland, which describes the shape, size and other characteristics of the farmland. The acquisition of scope information can help the system understand the geographical scope of the target farmland and provide basic data for the scope of the target land; the crop type information refers to the type information of the crops planted in the target farmland, including the names and types of crops; the region information refers to the geographical region or administrative region information where the target farmland is located, including the country, province, city, etc. The acquisition of region information can help the system understand the geographical environment and climate conditions where the target farmland is located; for example: Suppose the intelligent agriculture management system is applied to a certain farm, and the farm administrator uses the system for farmland management and crop monitoring. In the system, the farm administrator inputs the relevant information of the target farmland through the farmland resource information acquisition module, including longitude and latitude coordinates (location information), farmland boundary data (scope information), planted crop types (crop type information), and location (region information). These information are transmitted to the farmland resource information processing module for processing. After processing, the farmland resource processing set is obtained, which includes the coordinate data and scope graph of the target farmland (determined according to the location information and scope information), planted crop types (determined according to the crop type information), and region information (determine the region where the growth environment belongs). These processed information will be used for subsequent environmental information collection and crop growth monitoring, providing basic data support for farm management and agricultural production; the farmland resource information processing module is used to process the farmland resource information set, obtain the farmland resource processing set and transmit it to the environmental information collection module and the crop growth monitoring module.

[0049] The environmental information collection module is used to collect the crop growth environment of the target farmland according to the farmland resource processing set, obtain an environmental data set and transmit it to the cloud analysis module; for the area where the target farmland is located, the environmental information collection module obtains the actual data corresponding to various preset meteorological indicators such as temperature, humidity, precipitation, etc. through devices such as meteorological sensors and weather stations. These data reflect the climate conditions of the area where the target farmland is located and have an important impact on the growth of crops; according to the coordinate data and range graph of the target farmland, the environmental information collection module obtains the soil information of the target farmland through soil sensors, soil sampling, etc. These information include the actual data corresponding to preset soil indicators such as the pH value, water content, nutrient content, etc. of the soil, reflecting the soil environmental conditions of the target farmland; the collected meteorological information and soil information are respectively sorted into environmental data subset one and environmental data subset two, and then these two subsets are summarized to obtain a complete environmental data set. This data set contains data related to the meteorological environment and soil environment of the target farmland, providing basic data support for subsequent environmental analysis; for example: assume that the intelligent agricultural management system is applied to a certain farm, and the environmental information collection module in it collects the meteorological information and soil information of the area where the target farmland is located through devices such as weather stations and soil sensors, obtains the meteorological data such as temperature, humidity, precipitation, etc. of the day through the weather station, and obtains the soil data such as the pH value, water content, nutrient content, etc. of the soil through the soil sensor. After these information are sorted and summarized, an environmental data set is formed and transmitted to the cloud analysis module for subsequent environmental analysis.

[0050] The crop growth monitoring module is used to collect the crop growth status of the target farmland according to the farmland resource processing set, obtain the growth data set and transmit it to the cloud analysis module; use equipment such as optical satellites outside the atmosphere to obtain the image data of all farmlands, import the vector file of the target farmland into the ArcGIS software, and obtain the image corresponding to the range graph of the target farmland by cropping the image, etc. Use pattern recognition technology to analyze and identify the image corresponding to the range graph of the target farmland, identify the bare land area and crop area in the image, further analyze the identified crop area, calculate the pixel point index of the bare land, the pixel point index data of the crop leaves, as well as the height, leaf color, and leaf disease spots of the crop, and collect and summarize the obtained index data to form a growth data set; for example: Suppose the intelligent agriculture management system is applied to the wheat planting area of a certain farm. The crop growth monitoring module obtains the image data of the wheat planting area through satellite images, and uses pattern recognition technology to identify the wheat planting area. Then, the module analyzes the image of the wheat area, extracts the pixel point index, height, and leaf color data of the wheat leaves, and detects the covered area of the existing leaf disease spots. Finally, these data are sorted and summarized to form the growth data set of the wheat planting area, providing detailed information about the wheat growth status for the farm management personnel.

[0051] The cloud analysis module is used to perform environmental analysis according to the environmental data set of the target farmland to obtain an environmental deviation combination, perform growth analysis according to the growth data set of the target farmland to obtain a growth deviation combination, and then transmit the environmental deviation combination and the growth deviation combination to the neural network module together; calculation of the environmental deviation combination: obtain the actual data of each preset meteorological index from the environmental data subset one, compare it with the standard data, calculate the actual deviation ratio, if the actual deviation ratio is greater than or equal to the preset deviation ratio threshold, then mark this meteorological index as a deviation item, otherwise mark it as a non-deviation item, obtain the actual data of each preset soil index from the environmental data subset two, and perform similar comparison and processing; summarize the output values of the deviation items in the environmental data subset one and the environmental data subset two to obtain the environmental deviation combination; calculation of the growth deviation combination: calculate the deviation values of the pixel point index of the bare land and the pixel point index of the crop leaves, the deviation values of the crop height index, leaf color index, and leaf disease spot index, obtain deviation value one and deviation value two and summarize them to obtain the growth deviation combination; Suppose in the intelligent agriculture management system, the environmental data subset one of a certain target farmland shows that the temperature deviation exceeds 10%, while the preset deviation ratio threshold is 5%, then the temperature index will be marked as a deviation item. In addition, the environmental data subset two shows that the soil acidity deviation is 3%, which is less than the preset deviation ratio threshold of 5%, so the soil acidity index will be marked as a non-deviation item.

[0052] The neural network module is used to construct a neural network model based on the environmental deviation combination and the growth deviation combination, and obtain the crop classification combination set of the target farmland according to the constructed neural network model. Then, the crop classification combination set of the target farmland is sent to the farmland division module; the environmental deviation combination and the growth deviation combination are used as input data, which have been processed and feature-extracted in the cloud analysis module, used to describe the environment and growth state of the target farmland, prepare the label data related to each target farmland, and mark the risk values of the preset risk items of the crops in this farmland. Usually, these labels can be 0 or 1, indicating whether the risk value of this risk item exceeds the set threshold. Select a suitable neural network structure, such as a convolutional neural network, define the input layer, hidden layer, and output layer of the neural network, and determine the number of neurons and activation functions in each layer. Randomly initialize the parameters of the neural network, such as weights and biases. Divide the prepared dataset into a training set, a validation set, and a test set. Usually, the adopted ratio is 70% of the data for training, 15% for validation, and 15% for testing. Use the training set to train the neural network model, and update the parameters of the model through the backpropagation algorithm and the optimizer to minimize the loss function, usually using the cross-entropy loss function. At the end of each training cycle, use the validation set to evaluate the performance of the model to prevent overfitting, and adjust the hyperparameters of the model according to the performance of the validation set. Use the test set to evaluate the performance of the trained model, including indicators such as accuracy, precision, and recall. When all meet the preset requirements, the construction is completed. Apply the trained neural network model to the new dataset, and conduct risk assessment and management of the farmland according to the risk values of the preset risk items output by the model.

[0053] The farmland division module is used to divide the target farmland into planting categories according to the preset division strategy and the crop classification combination set, generate the corresponding category code number and send it to the early warning module; divide the farmland according to the different crop types of the target farmland, mark the crop type as NZi, and perform the following operations on the risk values of the risk items with an output result of 1: Obtain the risk value of this risk item and mark it as FXi, mark the set threshold as Wi, calculate the ratio of the risk value FXi of this risk item to the set threshold Wi and mark it as Ri, and summarize the crop type NZi and all the ratios Ri to generate a category code number. For example, the category code number is [3, 0, 10, 7, 6], indicating that the crop type is the third type of wheat, 0 indicates that the pest and disease risk item has no risk, that is, the output result of this risk item is 0, 10 indicates that the lodging risk item is at the tenth level, 7 indicates that the non-ear-bearing risk item is at the seventh level, and 6 indicates that the comprehensive risk level of the soil environment and the external natural environment is at the sixth level.

[0054] The warning module generates corresponding abnormal type warning signals and comprehensive abnormal levels according to the category coding number and the preset warning strategy, aggregates all the abnormal type warning signals and the comprehensive abnormal levels to obtain a warning combination set; the warning module issues corresponding abnormal type warning signals according to the ratio Ri of each risk item in the category coding number, and these signals can be in the form of text descriptions, symbols or colors, etc., to indicate the abnormal types represented by each risk item, such as disease warning, comprehensive warning of soil environment and external natural environment, etc. The comprehensive abnormal level is calculated as follows: the warning module calculates the comprehensive abnormal value ZHi according to the ratio Ri of each risk item and the preset risk coefficient ji. This comprehensive abnormal value reflects the overall risk degree of the target farmland, considering the comprehensive influence of various risk factors. The warning module has preset a comprehensive abnormal value interval and the corresponding comprehensive abnormal level. According to the calculated comprehensive abnormal value ZHi, by looking up the comprehensive abnormal value interval to which it belongs, the comprehensive abnormal level of the target farmland can be determined. The warning module generates corresponding warning signals and comprehensive abnormal levels according to the planting situation of the farmland and various risk factors faced. Through this information, the farmer or the agricultural management department can take corresponding measures in a timely manner to reduce losses and ensure the production safety and benefits of the farmland; for example: assume that the category coding number of a certain farmland is [3, 0, 10, 7, 6], and it issues warnings about pest and disease risks, lodging risks, and comprehensive risks of soil environment and external natural environment. After calculation, the comprehensive abnormal value ZHi is 2.8. According to the preset comprehensive abnormal value interval and the comprehensive abnormal level form, it is found that the comprehensive abnormal level to which ZHi belongs is level seven, that is, high risk. Finally, the warning combination set generated by the warning module includes abnormal type warning signals and comprehensive abnormal levels, providing a decision-making reference for the farmer or the agricultural management department to take measures in a timely manner to deal with potential risks and problems. The function of the warning module is of great significance for agricultural production management, and it can help the farmer or the agricultural management department quickly discover and respond to possible abnormal situations, ensuring the production safety and benefits of the farmland.

[0055] The farmland resource information centrally includes the location information, scope information, crop type information, and the information of the region to which the target farmland belongs of the target farmland.

[0056] The farmland resource information processing module is used to process the farmland resource information set to obtain the farmland resource processing set, which means: determining the coordinate data of the target farmland and the scope graph of the farmland according to the location information and scope information of the target farmland in the farmland resource information set, determining the types of crops planted according to the crop type information, and determining the region to which its growth environment belongs according to the information of the region to which the target farmland belongs.

[0057] The environment information collection module is used to collect the crop growth environment of the target farmland according to the farmland resource processing set to obtain the environment data set, which means:

[0058] The environmental information collection module collects the meteorological information of the region where the target farmland is located, obtains the actual data corresponding to each preset meteorological index, and obtains the first subset of environmental data; collects the soil information according to the coordinate data of the target farmland and the range graph of the farmland, obtains the actual data corresponding to each preset soil index, and obtains the second subset of environmental data, and summarizes the first subset of environmental data and the second subset of environmental data to obtain the environmental data set.

[0059] The crop growth monitoring module is used to collect the crop growth status of the target farmland according to the farmland resource processing set. The growth data set obtained refers to:

[0060] Obtain the images of all farmlands through an optical satellite outside the atmosphere, then import the vector file of the target farmland, crop the image through ArcGIS software to obtain the image corresponding to the range graph of the target farmland, and then identify the image corresponding to the range graph of the target farmland through pattern recognition technology, calculate the corresponding data of the pixel point index of the bare land and the pixel point index of the crop leaves respectively, and obtain the corresponding data of the crop height index, the crop leaf color index, and the crop leaf disease spot index. Collect and summarize the corresponding data of all indexes to obtain the growth data set.

[0061] The cloud analysis module is used to perform environmental analysis according to the environmental data set of the target farmland. The environmental deviation combination obtained refers to:

[0062] Obtain the actual data corresponding to each preset meteorological index in the first subset of environmental data, mark the actual data corresponding to each preset meteorological index in the first subset of environmental data as QXi respectively, mark the standard data corresponding to each preset meteorological index as QBi respectively, and mark the preset deviation ratio threshold corresponding to each preset meteorological index as QCi, and calculate the actual deviation ratio of each preset meteorological index: ; BL1i is the actual deviation ratio of each preset meteorological index. If the actual deviation ratio BL1i of the target preset meteorological index is greater than or equal to the preset deviation ratio threshold QCi, then mark this meteorological index as a deviation item. If the actual deviation ratio BL1i of the target preset meteorological index is less than the preset deviation ratio threshold QCi, then mark this meteorological index as a non-deviation item, and set the corresponding output value of the non-deviation item to the numerical value zero, and the corresponding output value of the deviation item is the actual deviation ratio BL1i;

[0063] Obtain the actual data corresponding to each preset soil index in the second subset of environmental data. Mark the actual data corresponding to each preset soil index in the second subset of environmental data as TXi, mark the standard data corresponding to each preset soil index as TBi, and mark the preset deviation ratio threshold corresponding to each preset soil index as TCi. Calculate the actual deviation ratio of each preset soil index: ; BL2i is the actual deviation ratio of each preset soil index. If the actual deviation ratio BL2i of the target preset soil index is greater than or equal to the preset deviation ratio threshold TCi, then mark this soil index as a deviation item. If the actual deviation ratio BL2i of the target preset soil index is less than the preset deviation ratio threshold TCi, then mark this soil index as a non - deviation item. The output value corresponding to the non - deviation item is set to the value zero, and the output value corresponding to the deviation item is the actual deviation ratio BL2i;

[0064] Summarize the output values of the first subset of environmental data and the second subset of environmental data to obtain an environmental deviation combination;

[0065] The cloud analysis module is used to perform growth analysis based on the growth data set of the target farmland. The growth deviation combination refers to:

[0066] Mark the corresponding data of the pixel point index of the bare land and the pixel point index of the crop leaves as LDi and YXi respectively, and calculate the first deviation value: ; a1 and a2 are both preset proportionality coefficients, PC1 is the first deviation value, ZZ1 is the preset land coverage comparison threshold of the target farmland. Mark the corresponding data of the crop height index, the crop leaf color index, and the crop leaf disease spot index as GDi, YSi, and BHi respectively, and calculate the second deviation value: ; f1, f2, and f3 are all preset proportionality coefficients, PC2 is the second deviation value, ZZ2 is the preset growth comparison threshold of the target farmland. Summarize the first deviation value PC1 and the second deviation value PC2 to obtain a growth deviation combination.

[0067] The neural network module obtains the crop classification combination set of the target farmland according to the constructed neural network model, which means:

[0068] Use the growth deviation combination and the environmental deviation combination as the input data of the constructed neural network model. Obtain the risk values of the preset risk items of the crops in each target farmland as the output data, and assign 0 or 1 to train the model. 0 indicates that the risk value of this risk item is less than or equal to the set threshold, and 1 indicates that the risk value of this risk item is greater than the set threshold. Summarize the obtained assignment results to obtain the crop classification combination set of the target farmland.

[0069] The farmland division module is used to divide the target farmland into planting categories according to the preset division strategy and the set of crop classification combinations, and generate the corresponding category coding number, which means:

[0070] The farmland is divided according to the types of crops in the target farmland. The types of crops are marked as NZi. The following operations are performed on the risk values of the risk items with an output result of 1: Obtain the risk value of the risk item and mark it as FXi, mark the set threshold as Wi, calculate the ratio of the risk value FXi of the risk item to the set threshold Wi and mark it as Ri, and summarize the crop type NZi and all the ratios Ri to generate the category coding number.

[0071] The warning module generates corresponding abnormal type warning signals and comprehensive abnormal levels according to the category coding number and the preset warning strategy, which means:

[0072] According to the risk item corresponding to the ratio Ri, issue the abnormal type warning signal corresponding to the risk item. The comprehensive abnormal value is calculated through the following formula: ; ZHi is the comprehensive abnormal value, ji is the preset risk coefficient of the risk item in the crop type NZi, and there is a comprehensive abnormal value interval - comprehensive abnormal level form preset in the warning module. The comprehensive abnormal level can be obtained by finding the comprehensive abnormal value interval into which the comprehensive abnormal value ZHi falls.

[0073] Embodiment 2

[0074] A smart agriculture management method based on computer analysis includes the following steps:

[0075] Step 1: The farmland resource information acquisition module acquires the farmland resource information, obtains the farmland resource information set and transmits it to the farmland resource information processing module;

[0076] Step 2: The farmland resource information processing module processes the farmland resource information set, obtains the farmland resource processing set and transmits it to the environmental information collection module and the crop growth monitoring module;

[0077] Step 3: The environmental information collection module collects the crop growth environment of the target farmland according to the farmland resource processing set, obtains the environmental data set and transmits it to the cloud analysis module;

[0078] Step 4: The crop growth monitoring module collects the crop growth status of the target farmland according to the farmland resource processing set, obtains the growth data set and transmits it to the cloud analysis module;

[0079] Step 5: The cloud analysis module performs environmental analysis and growth analysis, obtains the growth deviation combination and the environmental deviation combination and transmits them to the neural network module together. The neural network module obtains the set of crop classification combinations of the target farmland according to the constructed neural network model;

[0080] Step 6: The farmland division module is used to divide the target farmland into planting categories according to the preset division strategy and the set of crop classification combinations, generate corresponding category coding numbers and transmit them to the warning module;

[0081] Step 7: The warning module generates corresponding abnormal type warning signals and comprehensive abnormal levels according to the category coding numbers and the preset warning strategy, summarizes all the abnormal type warning signals and the comprehensive abnormal levels to obtain a warning combination set.

[0082] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0083] It should be understood that in various embodiments of the present application, the magnitudes of the serial numbers of the above processes do not mean the order of execution is prior or subsequent. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0084] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraint conditions of the technical solution. Professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0085] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0086] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present application, and all of them should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A smart agriculture management system based on computer analysis, characterized in that, It includes a farmland resource information collection module, a farmland resource information processing module, an environmental information collection module, a crop growth monitoring module, a cloud analysis module, a neural network module, a farmland division module, and a warning module; The farmland resource information collection module is used to obtain farmland resource information, obtain a farmland resource information set and transmit it to the farmland resource information processing module; The farmland resource information processing module is used to process the farmland resource information set, obtain a farmland resource processing set and transmit it to the environmental information collection module and the crop growth monitoring module; The environmental information collection module is used to collect the crop growth environment of the target farmland according to the farmland resource processing set, obtain an environmental data set and transmit it to the cloud analysis module; The crop growth monitoring module is used to collect the crop growth status of the target farmland according to the farmland resource processing set, obtain a growth data set and transmit it to the cloud analysis module; The cloud analysis module is used to perform environmental analysis based on the environmental data set of the target farmland to obtain an environmental deviation combination, perform growth analysis based on the growth data set of the target farmland to obtain a growth deviation combination, and then transmit the environmental deviation combination and the growth deviation combination to the neural network module together; The neural network module is used to construct a neural network model based on the environmental deviation combination and the growth deviation combination, and obtain a crop classification combination set of the target farmland according to the constructed neural network model, and then transmit the crop classification combination set of the target farmland to the farmland division module; The farmland division module is used to divide the planting categories of the target farmland according to the preset division strategy and the crop classification combination set, generate corresponding category coding numbers and transmit them to the warning module; The warning module generates corresponding abnormal type warning signals and comprehensive abnormal levels according to the category coding numbers and the preset warning strategy, and summarizes all the abnormal type warning signals and the comprehensive abnormal levels to obtain a warning combination set.

2. The intelligent agriculture management system based on computer analysis according to claim 1, characterized in that, The farmland resource information set includes the location information, range information, crop type information, and region information to which the target farmland belongs.

3. The intelligent agricultural management system based on computer analysis according to claim 2, wherein The farmland resource information processing module is used to process the farmland resource information set, and obtaining a farmland resource processing set means: determining the coordinate data of the target farmland and the range graph of the farmland according to the location information and range information of the target farmland in the farmland resource information set, determining the types of crops planted according to the crop type information, and determining the region to which its growth environment belongs according to the region information to which the target farmland belongs.

4. The computer analysis-based intelligent agriculture management system according to claim 3, characterized in that, The environmental information collection module is used to collect the crop growth environment of the target farmland according to the farmland resource processing set, and obtaining an environmental data set means: The environmental information collection module collects the meteorological information of the region to which the target farmland belongs, obtains the actual data corresponding to each preset meteorological index, and obtains the first subset of environmental data; collects the soil information according to the coordinate data of the target farmland and the range graph of the farmland, obtains the actual data corresponding to each preset soil index, and obtains the second subset of environmental data, and summarizes the first subset of environmental data and the second subset of environmental data to obtain an environmental data set.

5. The computer analysis-based intelligent agriculture management system according to claim 4, wherein The crop growth monitoring module is used to collect the growth status of crops in the target farmland according to the farmland resource processing set, and the growth data set refers to: Obtain images of all farmlands through an optical satellite outside the atmosphere, then import the vector file of the target farmland, crop the image through ArcGIS software to obtain the image corresponding to the range graph of the target farmland, and then use pattern recognition technology to recognize the image corresponding to the range graph of the target farmland, calculate the corresponding data of the pixel point index of the bare land and the pixel point index of the crop leaves respectively, and obtain the corresponding data of the crop height index, the crop leaf color index, and the crop leaf disease spot index. Collect and summarize the corresponding data of all the indexes to obtain the growth data set.

6. The computer analysis-based intelligent agriculture management system according to claim 5, characterized in that The cloud analysis module is used to perform environmental analysis based on the environmental data set of the target farmland, and the environmental deviation combination refers to: Obtain the actual data corresponding to each preset meteorological index in the environmental data subset one, mark the actual data corresponding to each preset meteorological index in the environmental data subset one as QXi respectively, mark the standard data corresponding to each preset meteorological index as QBi respectively, mark the preset deviation ratio threshold corresponding to each preset meteorological index as QCi, and calculate the actual deviation ratio of each preset meteorological index: ; BL1i is the actual deviation ratio of each preset meteorological index. If the actual deviation ratio BL1i of the target preset meteorological index is greater than or equal to the preset deviation ratio threshold QCi, mark this meteorological index as a deviation item. If the actual deviation ratio BL1i of the target preset meteorological index is less than the preset deviation ratio threshold QCi, mark this meteorological index as a non - deviation item. Set the output value corresponding to the non - deviation item to the value zero, and the output value corresponding to the deviation item is the actual deviation ratio BL1i; Obtain the actual data corresponding to each preset soil index in environmental data subset two. Mark the actual data corresponding to each preset soil index in environmental data subset two as TXi respectively, mark the standard data corresponding to each preset soil index as TBi respectively, and mark the preset deviation ratio threshold corresponding to each preset soil index as TCi. Calculate the actual deviation ratio of each preset soil index: ; BL2i is the actual deviation ratio of each preset soil index. If the actual deviation ratio BL2i of the target preset soil index is greater than or equal to the preset deviation ratio threshold TCi, mark this soil index as a deviation item. If the actual deviation ratio BL2i of the target preset soil index is less than the preset deviation ratio threshold TCi, mark this soil index as a non-deviation item. Set the output value corresponding to the non-deviation item to the value zero, and the output value corresponding to the deviation item is the actual deviation ratio BL2i; Summarize the output values of environmental data subset one and environmental data subset two to obtain the environmental deviation combination; The cloud analysis module is used to perform growth analysis based on the growth data set of the target farmland, and the growth deviation combination refers to: The corresponding data of the bare land pixel index and the crop leaf pixel index are marked as LDi and YXi respectively, and the deviation value is calculated as: a1 and a2 are preset proportional coefficients, PC1 is deviation value 1, ZZ1 is the preset land coverage comparison threshold of the target farmland, and the corresponding data of the crop height index, crop leaf color index, and crop leaf disease spot index are marked as GDi, YSi, and BHi respectively, and the deviation value 2 is calculated: ; f1, f2, and f3 are all preset proportional coefficients, PC2 is the deviation value two, and ZZ2 is the preset growth comparison threshold of the target farmland. The deviation value one PC1 and the deviation value two PC2 are summarized to obtain the growth deviation combination.

7. The computer analysis-based intelligent agriculture management system according to claim 6, wherein, The neural network module obtains the crop classification combination set of the target farmland according to the constructed neural network model, which means: Use the growth deviation combination and the environmental deviation combination as the input data of the constructed neural network model, obtain the risk values of the preset risk items of the crops in each target farmland as the output data, and assign 0 or 1 to train the model. 0 means that the risk value of this risk item is less than or equal to the set threshold, and 1 means that the risk value of this risk item is greater than the set threshold. Summarize the obtained assignment results to obtain the crop classification combination set of the target farmland.

8. The computer analysis-based intelligent agriculture management system according to claim 7, characterized in that, The farmland division module is used to divide the target farmland into planting categories according to the preset division strategy and the crop classification combination set, and generate the corresponding category coding number, which means: Divide the farmland according to the different crop types in the target farmland, mark the crop type as NZi, and perform the following operations on the risk value of the risk item with an output result of 1: Obtain the risk value of this risk item and mark it as FXi, mark the set threshold as Wi, calculate the ratio of the risk value FXi of this risk item to the set threshold Wi and mark it as Ri, and summarize the crop type NZi and all the ratios Ri to generate the category coding number.

9. The computer analysis-based intelligent agricultural management system according to claim 8, wherein, The warning module generates the corresponding abnormal type warning signal and the comprehensive abnormal level according to the category coding number and the preset warning strategy, which means: Based on the risk item corresponding to the ratio Ri, an early warning signal of the abnormal type corresponding to the risk item is issued, and the comprehensive abnormal value is calculated through the following formula: ; ZHi is the comprehensive abnormal value, ji is the preset risk coefficient of the risk item in the crop variety NZi, and there is a comprehensive abnormal value range - comprehensive abnormal level form preset in the early warning module. By finding the comprehensive abnormal value range into which the comprehensive abnormal value ZHi falls, the comprehensive abnormal level can be obtained.

10. A computer - based intelligent agriculture management method, implemented based on the computer - based intelligent agriculture management system according to any one of claims 1 - 9, characterized in that, It includes the following steps: Step 1: The farmland resource information collection module obtains the farmland resource information, obtains the farmland resource information set and transports it to the farmland resource information processing module; Step 2: The farmland resource information processing module processes the farmland resource information set, obtains the farmland resource processing set and transports it to the environmental information collection module and the crop growth monitoring module; Step 3: The environmental information collection module collects the crop growth environment of the target farmland according to the farmland resource processing set, obtains the environmental data set and transports it to the cloud analysis module; Step 4: The crop growth monitoring module collects the crop growth status of the target farmland according to the farmland resource processing set, obtains the growth data set and transports it to the cloud analysis module; Step 5: The cloud analysis module conducts environmental analysis and growth analysis, obtains the growth deviation combination and the environmental deviation combination and transports them to the neural network module together. The neural network module obtains the crop classification combination set of the target farmland according to the constructed neural network model; Step 6: The farmland division module is used to divide the target farmland according to the preset division strategy and the crop classification combination set, generate the corresponding category coding number and transport it to the warning module; Step 7: The warning module generates the corresponding abnormal type warning signal and the comprehensive abnormal level according to the category coding number and the preset warning strategy, summarizes all the abnormal type warning signals and the comprehensive abnormal level, and obtains the warning combination set.

Images