High-standard farmland management platform

Abstract

The invention discloses a high-standard farmland management platform. The high-standard farmland management platform comprises a farmland end and a server end, the farmland end comprises a soil data acquisition module, a meteorological data acquisition module, a crop image acquisition module, a water and fertilizer configuration module and an irrigation control module; and the server side comprises a region division module and a data analysis module. According to the invention, the farmland is divided into a plurality of farmland regions through the region division module, so that the convenience of farmland data acquisition and analysis is improved; the data analysis module obtains the soil prediction data according to the soil data and the meteorological data, obtains the crop type and growth data according to the crop image data, and obtains the water and fertilizer configuration data and the irrigation control data according to the soil prediction data and the crop type and growth data, thereby improving the accuracy of farmland water and fertilizer configuration and irrigation control.

Description

Technical Field

[0001] The present application relates to the field of farmland management technology, and in particular to a high-standard farmland management platform. Background Art

[0002] High-standard farmland has the characteristics of complete facilities, concentrated and continuous areas, fertile soil and good ecology, which are compatible with modern agricultural production methods. Compared with ordinary farmland, high-standard farmland pays more attention to ecological protection, is committed to reducing the impact of agricultural planting on the environment, and puts forward higher requirements for environmental protection, so the requirements for planting irrigation methods are also higher.

[0003] In the prior art, the patent publication number CN116530286A, "Integrated water-fertilizer irrigation management system and method for ecological high-standard farmland", confirms the plants, quickly identifies the plant types, and confirms the plant growth cycle through feature point comparison, thereby achieving rapid and accurate identification of different crop plants in the farmland, and determining the irrigation amount according to the number and growth cycle of the plants, thereby achieving precise irrigation; adjusting the irrigation water volume according to the irrigation task requirements, adjusting the pitch angle to determine the irrigation area, and adjusting the irrigation water volume according to the irrigation task requirements; using one irrigation nozzle to irrigate different plants in different growth cycles in multiple areas without the need for large angle adjustments, thereby improving irrigation efficiency and reducing the loss of nozzles.

[0004] High-standard farmland generally has a large area, and different crops are planted in different regions or different terrains. The nutrient requirements and temperature and humidity requirements of different crops are also different. Therefore, different crops need to be analyzed when managing high-standard farmland. However, the above-mentioned prior art divides the areas where the same adjacent crop plants are located through image recognition units, and image recognition is required each time the areas are divided, which makes farmland data collection and analysis less convenient. In addition, soil temperature, humidity and soil nutrients will be affected by meteorological changes. The above-mentioned prior art only determines the irrigation amount based on the number of plants and the growth cycle, but does not consider the impact of meteorological changes on soil temperature, humidity and soil nutrients. The accuracy of farmland water and fertilizer configuration and irrigation control is poor. Summary of the invention

[0005] The present application provides a high-standard farmland management platform to solve the problems of poor convenience in farmland data collection and analysis, and poor accuracy in farmland water and fertilizer allocation and irrigation control in the prior art.

[0006] On the one hand, the present application provides a high-standard farmland management platform, including: a farmland end and a server end, and the farmland end is communicatively connected to the server end.

[0007] The farmland end includes: a soil data acquisition module, a meteorological data acquisition module, a crop image acquisition module, a water and fertilizer configuration module and an irrigation control module.

[0008] The server side includes: a region division module and a data analysis module.

[0009] The area division module is used to divide the farmland into a plurality of farmland areas.

[0010] The soil data collection module is used to collect soil data of the corresponding farmland area.

[0011] The meteorological data collection module is used to collect meteorological data corresponding to the farmland area.

[0012] The crop image acquisition module is used to acquire crop image data corresponding to the farmland area.

[0013] The data analysis module is used to obtain soil prediction data based on the soil data and the meteorological data, obtain crop type and growth data based on the crop image data, and obtain water and fertilizer configuration data and irrigation control data based on the soil prediction data and the crop type and growth data.

[0014] The water and fertilizer configuration module is used to configure water and fertilizer for the corresponding farmland area according to the water and fertilizer configuration data.

[0015] The irrigation control module is used to perform irrigation control on the corresponding farmland area according to the irrigation control data.

[0016] In a possible implementation, the soil data collection module includes: a soil temperature and humidity collection unit.

[0017] The soil temperature and humidity acquisition unit is used to collect soil temperature and humidity data of the corresponding farmland area.

[0018] The data analysis module includes: a soil temperature and humidity prediction unit, a soil temperature and humidity demand unit and an irrigation control analysis unit.

[0019] The soil temperature and humidity prediction unit is used to obtain soil temperature and humidity prediction data according to the soil temperature and humidity data and the meteorological data.

[0020] The soil temperature and humidity requirement unit is used to obtain soil temperature and humidity requirement data according to the crop type and growth data.

[0021] The irrigation control analysis unit is used to obtain irrigation control data according to the soil temperature and humidity prediction data and the soil temperature and humidity demand data.

[0022] In a possible implementation, the soil temperature and humidity prediction unit uses a time series prediction algorithm to obtain soil temperature and humidity prediction data according to the soil temperature and humidity data and the meteorological data.

[0023] The time series prediction algorithm includes: one of a time series neural network, a linear regression method, an exponential smoothing method, and an ARIMA model.

[0024] In a possible implementation, the soil data collection module includes: a soil nutrient collection unit.

[0025] The soil nutrient collection unit is used to collect soil nutrient data of the corresponding farmland area.

[0026] The data analysis module also includes: a soil nutrient prediction unit, a soil nutrient demand unit and a water and fertilizer configuration analysis unit.

[0027] The soil nutrient prediction unit is used to obtain soil nutrient prediction data according to the soil nutrient data and the meteorological data.

[0028] The soil nutrient requirement unit is used to obtain soil nutrient requirement data according to the crop type and growth data.

[0029] The water-fertilizer configuration analysis unit is used to obtain water-fertilizer configuration data according to the soil nutrient prediction data and the soil nutrient demand data.

[0030] In a possible implementation, the soil nutrient prediction unit obtains soil nutrient prediction data according to the soil nutrient data and the meteorological data using a time series prediction algorithm.

[0031] The time series prediction algorithm includes: one of a time series neural network, a linear regression method, an exponential smoothing method, and an ARIMA model.

[0032] In a possible implementation, the data analysis module includes: a crop image recognition unit.

[0033] The crop image recognition unit is used to obtain crop type and growth data according to the crop image data using an image recognition algorithm.

[0034] In a possible implementation, the farmland end further includes: a first encryption module and a second decryption module; the server end further includes: a first decryption module and a second encryption module.

[0035] The first encryption module is used to encrypt the soil data, the meteorological data and the crop image data to obtain encrypted soil data, encrypted meteorological data and encrypted crop image data.

[0036] The first decryption module is used to decrypt the encrypted soil data, the encrypted meteorological data and the encrypted crop image data.

[0037] The second encryption module is used to encrypt the water-fertilizer configuration data and the irrigation control data to obtain encrypted water-fertilizer configuration data and encrypted irrigation control data.

[0038] The second decryption module is used to decrypt the encrypted water and fertilizer configuration data and the encrypted irrigation control data.

[0039] In a possible implementation manner, the server side also includes: a database module.

[0040] The database module is used to store the soil data, the meteorological data, the crop image data, the water and fertilizer configuration data and the irrigation control data.

[0041] In a possible implementation, the database module includes several sub-databases, each sub-database corresponding to a farmland area.

[0042] The sub-database includes a primary shard and several backup shards.

[0043] The main shard is used to store soil data, meteorological data, crop image data, water and fertilizer configuration data and irrigation control data of the farmland area corresponding to the sub-database.

[0044] The plurality of backup slices are respectively used to store soil data, meteorological data, crop image data, water and fertilizer configuration data and irrigation control data of the farmland areas corresponding to other sub-databases.

[0045] In a possible implementation, the server end is also communicatively connected to a plurality of user ends.

[0046] The client is used to access the database module; different clients have different sub-database access permissions.

[0047] A high-standard farmland management platform in this application has the following advantages:

[0048] The farmland is divided into several farmland areas through the regional division module, which improves the convenience of farmland data collection and analysis; the soil prediction data is obtained according to the soil data and meteorological data through the data analysis module, the crop type and growth data are obtained according to the crop image data, and the water and fertilizer configuration data and irrigation control data are obtained according to the soil prediction data and the crop type and growth data, which improves the accuracy of farmland water and fertilizer configuration and irrigation control.

[0049] The proposed soil temperature and humidity prediction unit adopts a time series prediction algorithm to obtain soil temperature and humidity prediction data based on soil temperature and humidity data and meteorological data, thereby improving the accuracy of soil temperature and humidity prediction.

[0050] The proposed soil nutrient prediction unit uses a time series prediction algorithm to obtain soil nutrient prediction data based on soil nutrient data and meteorological data, which improves the accuracy of soil nutrient prediction.

[0051] The proposed first encryption module, first decryption module, second encryption module and second decryption module improve the transmission security of the farmland data by encrypting and decrypting the farmland data.

[0052] The proposed database module includes several sub-databases, each sub-database corresponds to a farmland area, and the sub-database includes a primary shard and several backup shards, which improves the storage security of farmland data. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 A module schematic diagram of a high-standard farmland management platform provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0056] like Figure 1 As shown, an embodiment of the present application provides a high-standard farmland management platform, including: a farmland end and a server end, and the farmland end is communicatively connected with the server end.

[0057] The farmland end includes: a soil data acquisition module, a meteorological data acquisition module, a crop image acquisition module, a water and fertilizer configuration module and an irrigation control module.

[0058] The server side includes: a region division module and a data analysis module.

[0059] The area division module is used to divide the farmland into a plurality of farmland areas.

[0060] The soil data collection module is used to collect soil data of the corresponding farmland area.

[0061] The meteorological data collection module is used to collect meteorological data corresponding to the farmland area.

[0062] The crop image acquisition module is used to acquire crop image data corresponding to the farmland area.

[0063] The data analysis module is used to obtain soil prediction data based on the soil data and the meteorological data, obtain crop type and growth data based on the crop image data, and obtain water and fertilizer configuration data and irrigation control data based on the soil prediction data and the crop type and growth data.

[0064] The water and fertilizer configuration module is used to configure water and fertilizer for the corresponding farmland area according to the water and fertilizer configuration data.

[0065] The irrigation control module is used to perform irrigation control on the corresponding farmland area according to the irrigation control data.

[0066] Specifically, in this embodiment, the server end is a cloud server, and the area division module and the data analysis module are software programs that can realize their respective functions. The meteorological data acquisition module uses air temperature and humidity sensors, light sensors and rainfall radars, and the meteorological data includes air temperature, air humidity, light intensity and rainfall.

[0067] In this embodiment, the regional division module divides regions based on the same terrain and the same crop types. The difference from the prior art is that after the regional division is performed by the regional division module, the subsequent data collection and data analysis are all performed on the basis of the regional division, and there is no need to repeat the regional division.

[0068] Exemplarily, the soil data collection module includes: a soil temperature and humidity collection unit.

[0069] The soil temperature and humidity acquisition unit is used to collect soil temperature and humidity data of the corresponding farmland area.

[0070] The data analysis module includes: a soil temperature and humidity prediction unit, a soil temperature and humidity demand unit and an irrigation control analysis unit.

[0071] The soil temperature and humidity prediction unit is used to obtain soil temperature and humidity prediction data according to the soil temperature and humidity data and the meteorological data.

[0072] The soil temperature and humidity requirement unit is used to obtain soil temperature and humidity requirement data according to the crop type and growth data.

[0073] The irrigation control analysis unit is used to obtain irrigation control data according to the soil temperature and humidity prediction data and the soil temperature and humidity demand data.

[0074] Specifically, in this embodiment, the soil temperature and humidity acquisition unit uses a soil temperature and humidity sensor, and the soil temperature and humidity prediction unit, the soil temperature and humidity demand unit, and the irrigation control analysis unit are software programs that can realize their respective functions.

[0075] The soil temperature and humidity requirement unit pre-stores a set of soil temperature and humidity requirement data corresponding to different crop types and growth data, which can be set based on experience or after referring to relevant crop encyclopedia content.

[0076] In this embodiment, the relationship between the irrigation control data, the soil temperature and humidity prediction data, and the soil temperature and humidity demand data is set as follows: irrigation control data = (soil temperature and humidity demand data - soil temperature and humidity prediction data) * temperature and humidity irrigation conversion coefficient. The temperature and humidity irrigation conversion coefficient is used to convert the difference between the soil temperature and humidity demand data and the soil temperature and humidity prediction data into the corresponding irrigation water volume, and can be set and adjusted according to actual conditions. In this embodiment, the irrigation control data is set to: irrigate the corresponding irrigation water volume within ten minutes.

[0077] Exemplarily, the soil temperature and humidity prediction unit uses a time series prediction algorithm to obtain soil temperature and humidity prediction data according to the soil temperature and humidity data and the meteorological data.

[0078] The time series prediction algorithm includes: one of a time series neural network, a linear regression method, an exponential smoothing method, and an ARIMA model.

[0079] Specifically, in this embodiment, a long short-term memory network (LSTM) in a time series neural network is used to obtain soil temperature and humidity prediction data based on soil temperature and humidity data and meteorological data.

[0080] First, a temperature and humidity prediction training data set is constructed, including historically collected soil temperature and humidity data and meteorological data. In this embodiment, the soil temperature and humidity data are the historically collected hourly average soil temperature and humidity data, and the meteorological data are the historically collected hourly average meteorological data, with a collection interval of 10 minutes (i.e., each soil temperature and humidity data is the average value of the temperature and humidity collected six times in that hour, and each meteorological data is the respective average value of the air temperature, air humidity, light intensity and rainfall collected six times in that hour).

[0081] Then, the model structure of the long short-term memory network is constructed, including: setting the number of layers of the long short-term memory neural network, the number of neurons in each layer, setting the optimizer, loss function and evaluation index. Finally, the temperature and humidity prediction training data set is used to train the long short-term memory neural network iteratively. After several cycles, the trained long short-term memory neural network is obtained. The trained long short-term memory neural network is used to obtain the soil temperature and humidity prediction data according to the soil temperature and humidity data and meteorological data.

[0082] Specifically, the long short-term memory neural network includes an input layer, several LSTM hidden layers and an output layer. Each LSTM hidden layer has four parts, including: forget gate, input gate, cell state and output gate. The calculation formula of the LSTM hidden layer is as follows:

[0083] f t =σ(W f ·[h t-1 , x t ]+b f )

[0084] i t =σ(W i ·[h t-1 , x t ]+b i )

[0085]

[0086]

[0087] o t =σ(W o [h t-1 , x t ]+b o )

[0088] h t =o t *tanh(C t )

[0089] Among them, f t represents the current forget gate, i t represents the current input gate, Indicates the current candidate state, C t Indicates the current cell state, o t Indicates the current output gate, h t represents the current hidden state, t represents the current time, σ represents the sigmoid activation function, W f Represents the adjustable weight of the forget gate, W i represents the adjustable weight of the input gate, W C represents the adjustable weight of the candidate state, Wo represents the adjustable weight of the output gate, b f represents the adjustable parameter of the forget gate, b i represents the adjustable parameter of the input gate, b C represents the candidate state adjustable parameter, b o represents the adjustable parameter of the output gate, h t-1 represents the hidden state of the previous step, x t Indicates the current input, C t-1 Indicates the cell state at the previous step.

[0090] When t = 1, h t-1 That is h 0 , C t-1 That is C 0 ,h 0 represents the initial hidden state, C 0 represents the initial cell state, h 0 , C 0 Set to 0, 1, or a fixed random value based on actual conditions.

[0091] Exemplarily, the soil data collection module includes: a soil nutrient collection unit.

[0092] The soil nutrient collection unit is used to collect soil nutrient data of the corresponding farmland area.

[0093] The data analysis module also includes: a soil nutrient prediction unit, a soil nutrient demand unit and a water and fertilizer configuration analysis unit.

[0094] The soil nutrient prediction unit is used to obtain soil nutrient prediction data according to the soil nutrient data and the meteorological data.

[0095] The soil nutrient requirement unit is used to obtain soil nutrient requirement data according to the crop type and growth data.

[0096] The water-fertilizer configuration analysis unit is used to obtain water-fertilizer configuration data according to the soil nutrient prediction data and the soil nutrient demand data.

[0097] Specifically, in this embodiment, the soil nutrient collection unit uses a soil nitrogen, phosphorus and potassium sensor, and the soil nutrient prediction unit, the soil nutrient demand unit and the water and fertilizer configuration analysis unit are software programs that can realize their respective functions.

[0098] The soil nutrient requirement unit pre-stores a set of soil nutrient requirement data corresponding to different crop types and growth data, which can be set based on experience or after referring to relevant crop encyclopedia content.

[0099] In this embodiment, the relationship between the water-fertilizer configuration data and the soil nutrient prediction data and the soil nutrient demand data is set as follows: water-fertilizer configuration data = (soil nutrient demand data - soil nutrient prediction data) * nutrient water-fertilizer conversion coefficient. The nutrient water-fertilizer conversion coefficient is used to convert the difference between the soil nutrient demand data and the soil nutrient prediction data into the corresponding water-fertilizer nitrogen, phosphorus and potassium concentrations, and can be set and adjusted according to actual conditions. In this embodiment, the water-fertilizer configuration data is set to: apply a fixed volume of water-fertilizer with a corresponding nitrogen, phosphorus and potassium concentration to the farmland within ten minutes.

[0100] Exemplarily, the soil nutrient prediction unit uses a time series prediction algorithm to obtain soil nutrient prediction data according to the soil nutrient data and the meteorological data.

[0101] The time series prediction algorithm includes: one of a time series neural network, a linear regression method, an exponential smoothing method, and an ARIMA model.

[0102] Specifically, in this embodiment, a long short-term memory network (LSTM) in a time series neural network is used to obtain soil nutrient prediction data based on soil nutrient data and meteorological data.

[0103] First, a nutrient prediction training data set is constructed, including historically collected soil nutrient data and meteorological data. In this embodiment, the soil nutrient data is the historically collected hourly average soil nutrient data, and the meteorological data is the historically collected hourly average meteorological data, and the collection interval is 10 minutes (that is, each soil nutrient data is the average value of the nutrient nitrogen, phosphorus and potassium concentrations collected six times in that hour, and each meteorological data is the respective average value of the air temperature, air humidity, light intensity and rainfall collected six times in that hour).

[0104] Then, the model structure of the long short-term memory network is constructed, including: setting the number of layers of the long short-term memory neural network, the number of neurons in each layer, setting the optimizer, loss function and evaluation index. Finally, the nutrient prediction training data set is used to iterate the long short-term memory neural network. After several cycles, the trained long short-term memory neural network is obtained. The trained long short-term memory neural network is used to obtain soil nutrient prediction data based on soil nutrient data and meteorological data.

[0105] Specifically, the establishment process of the long short-term memory neural network used to obtain soil nutrient prediction data is similar to that of the long short-term memory neural network used to obtain soil temperature and humidity prediction data. The difference lies in that the number of layers of the long short-term memory neural network and the number of neurons in each layer are set differently, the optimizer, loss function and evaluation index are set differently, and the training data sets used are different.

[0106] Exemplarily, the data analysis module includes: a crop image recognition unit.

[0107] The crop image recognition unit is used to obtain crop type and growth data according to the crop image data using an image recognition algorithm.

[0108] Specifically, the crop image recognition unit pre-stores a set of crop species features and a set of crop growth features of different types and different growth stages, which are respectively referred to as a crop species feature set and a crop growth feature set. Each crop species in the crop species feature set corresponds to a crop growth feature set. After acquiring the crop image data, the crop image recognition unit first extracts the current crop species feature and the current crop growth feature in the crop image data, compares the current crop species feature with the crop species feature in the crop species feature set, and after obtaining the current crop species, compares the current crop growth feature with the crop growth feature in the corresponding crop growth feature set to obtain the current crop growth feature. The current crop species and the current crop growth feature constitute the crop species and growth data.

[0109] In this embodiment, the perceptual hash algorithm is used to compare the similarity between the current crop type feature and the crop type feature in the crop type feature set. The specific process is as follows (the current crop type feature and the crop type feature in the crop type feature set in this embodiment are both 32 by 32 grayscale images):

[0110] When the similarity comparison between the current crop species feature and a crop species feature in the crop species feature set is performed, the two images are first subjected to DCT transformation respectively; two 32x32 DCT images are obtained, and the 8x8 DCT image in the upper left corner is retained; the first average grayscale value and the second average grayscale value are calculated for the two 8x8 DCT images respectively, the first 8x8 DCT image is traversed, all pixels greater than or equal to the first average grayscale value are set to 1, and all pixels less than the first average grayscale value are set to 0, the second 8x8 DCT image is traversed, all pixels greater than or equal to the second average grayscale value are set to 1, and all pixels less than the second average grayscale value are set to 0, and two 64-bit hash values ​​are obtained by sorting the pixel positions; the Hamming distance is calculated, and the smaller the Hamming distance, the higher the similarity. Finally, the crop species with the highest average similarity is the current crop species.

[0111] In this embodiment, the perceptual hash algorithm is used to compare the current crop growth characteristics with the crop growth characteristics in the corresponding crop growth characteristic set. The specific process refers to the similarity comparison process of crop species characteristics. Finally, the crop growth stage with the highest average similarity is the current crop growth stage.

[0112] Exemplarily, the farmland end further includes: a first encryption module and a second decryption module; the server end further includes: a first decryption module and a second encryption module.

[0113] The first encryption module is used to encrypt the soil data, the meteorological data and the crop image data to obtain encrypted soil data, encrypted meteorological data and encrypted crop image data.

[0114] The first decryption module is used to decrypt the encrypted soil data, the encrypted meteorological data and the encrypted crop image data.

[0115] The second encryption module is used to encrypt the water-fertilizer configuration data and the irrigation control data to obtain encrypted water-fertilizer configuration data and encrypted irrigation control data.

[0116] The second decryption module is used to decrypt the encrypted water and fertilizer configuration data and the encrypted irrigation control data.

[0117] Specifically, in this embodiment, when encrypting soil data, meteorological data, water and fertilizer configuration data, and irrigation control data, the existing text encryption algorithm is used; when encrypting crop image data, the existing image encryption algorithm is used. The decryption process is the inverse operation of the encryption process.

[0118] Exemplarily, the server side also includes: a database module.

[0119] The database module is used to store the soil data, the meteorological data, the crop image data, the water and fertilizer configuration data and the irrigation control data.

[0120] Exemplarily, the database module includes several sub-databases, each sub-database corresponding to a farmland area.

[0121] The sub-database includes a primary shard and several backup shards.

[0122] The main shard is used to store soil data, meteorological data, crop image data, water and fertilizer configuration data and irrigation control data of the farmland area corresponding to the sub-database.

[0123] The plurality of backup slices are respectively used to store soil data, meteorological data, crop image data, water and fertilizer configuration data and irrigation control data of the farmland areas corresponding to other sub-databases.

[0124] Exemplarily, the server end is also communicatively connected to a plurality of user ends.

[0125] The client is used to access the database module; different clients have different sub-database access permissions.

[0126] Specifically, in this embodiment, different user terminals are different user accounts, and different user accounts have different sub-database access permissions. The user terminal can be installed on a mobile device or a PC device.

[0127] The embodiment of the present application divides the farmland into several farmland areas through the area division module, thereby improving the convenience of farmland data collection and analysis; through the data analysis module, soil prediction data is obtained according to soil data and meteorological data, crop type and growth data are obtained according to crop image data, and water and fertilizer configuration data and irrigation control data are obtained according to soil prediction data and crop type and growth data, thereby improving the accuracy of farmland water and fertilizer configuration and irrigation control.

[0128] The proposed soil temperature and humidity prediction unit adopts a time series prediction algorithm to obtain soil temperature and humidity prediction data based on soil temperature and humidity data and meteorological data, thereby improving the accuracy of soil temperature and humidity prediction.

[0129] The proposed soil nutrient prediction unit uses a time series prediction algorithm to obtain soil nutrient prediction data based on soil nutrient data and meteorological data, which improves the accuracy of soil nutrient prediction.

[0130] The proposed first encryption module, first decryption module, second encryption module and second decryption module improve the transmission security of the farmland data by encrypting and decrypting the farmland data.

[0131] The proposed database module includes several sub-databases, each sub-database corresponds to a farmland area, and the sub-database includes a primary shard and several backup shards, which improves the storage security of farmland data.

[0132] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0133] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A high-standard farmland management platform, characterized in that: include: A farmland end and a server end, wherein the farmland end is communicatively connected with the server end; The farmland end includes: a soil data acquisition module, a meteorological data acquisition module, a crop image acquisition module, a water and fertilizer configuration module and an irrigation control module; The server side includes: a region division module and a data analysis module; The area division module is used to divide the farmland into a plurality of farmland areas; The soil data collection module is used to collect soil data of the corresponding farmland area; The meteorological data collection module is used to collect meteorological data corresponding to the farmland area; The crop image acquisition module is used to acquire crop image data corresponding to the farmland area; The data analysis module is used to obtain soil prediction data according to the soil data and the meteorological data, obtain crop type and growth data according to the crop image data, and obtain water and fertilizer configuration data and irrigation control data according to the soil prediction data and the crop type and growth data; The water and fertilizer configuration module is used to configure water and fertilizer for the corresponding farmland area according to the water and fertilizer configuration data; The irrigation control module is used to perform irrigation control on the corresponding farmland area according to the irrigation control data.

2. A high-standard farmland management platform according to claim 1, characterized in that: The soil data acquisition module includes: a soil temperature and humidity acquisition unit; The soil temperature and humidity collection unit is used to collect soil temperature and humidity data of the corresponding farmland area; The data analysis module includes: a soil temperature and humidity prediction unit, a soil temperature and humidity demand unit and an irrigation control analysis unit; The soil temperature and humidity prediction unit is used to obtain soil temperature and humidity prediction data according to the soil temperature and humidity data and the meteorological data; The soil temperature and humidity requirement unit is used to obtain soil temperature and humidity requirement data according to the crop type and growth data; The irrigation control analysis unit is used to obtain irrigation control data according to the soil temperature and humidity prediction data and the soil temperature and humidity demand data.

3. A high-standard farmland management platform according to claim 2, characterized in that: The soil temperature and humidity prediction unit uses a time series prediction algorithm to obtain soil temperature and humidity prediction data according to the soil temperature and humidity data and the meteorological data; The time series prediction algorithm includes: one of a time series neural network, a linear regression method, an exponential smoothing method, and an ARIMA model.

4. A high-standard farmland management platform according to claim 1, characterized in that: The soil data collection module includes: a soil nutrient collection unit; The soil nutrient collection unit is used to collect soil nutrient data of the corresponding farmland area; The data analysis module also includes: a soil nutrient prediction unit, a soil nutrient demand unit and a water and fertilizer configuration analysis unit; The soil nutrient prediction unit is used to obtain soil nutrient prediction data according to the soil nutrient data and the meteorological data; The soil nutrient requirement unit is used to obtain soil nutrient requirement data according to the crop type and growth data; The water-fertilizer configuration analysis unit is used to obtain water-fertilizer configuration data according to the soil nutrient prediction data and the soil nutrient demand data.

5. A high-standard farmland management platform according to claim 4, characterized in that: The soil nutrient prediction unit uses a time series prediction algorithm to obtain soil nutrient prediction data according to the soil nutrient data and the meteorological data; The time series prediction algorithm includes: one of a time series neural network, a linear regression method, an exponential smoothing method, and an ARIMA model.

6. A high-standard farmland management platform according to claim 1, characterized in that: The data analysis module includes: a crop image recognition unit; The crop image recognition unit is used to obtain crop type and growth data according to the crop image data using an image recognition algorithm.

7. A high-standard farmland management platform according to claim 1, characterized in that: The farm end further includes: a first encryption module and a second decryption module; the server end further includes: a first decryption module and a second encryption module; The first encryption module is used to encrypt the soil data, the meteorological data and the crop image data to obtain encrypted soil data, encrypted meteorological data and encrypted crop image data; The first decryption module is used to decrypt the encrypted soil data, the encrypted meteorological data and the encrypted crop image data; The second encryption module is used to encrypt the water and fertilizer configuration data and the irrigation control data to obtain encrypted water and fertilizer configuration data and encrypted irrigation control data; The second decryption module is used to decrypt the encrypted water and fertilizer configuration data and the encrypted irrigation control data.

8. A high-standard farmland management platform according to claim 1, characterized in that: The server side also includes: a database module; The database module is used to store the soil data, the meteorological data, the crop image data, the water and fertilizer configuration data and the irrigation control data.

9. A high-standard farmland management platform according to claim 8, characterized in that: The database module includes several sub-databases, each sub-database corresponds to a farmland area; The sub-database includes a primary shard and a plurality of backup shards; The main shard is used to store soil data, meteorological data, crop image data, water and fertilizer configuration data and irrigation control data of the farmland area corresponding to the sub-database; The plurality of backup slices are respectively used to store soil data, meteorological data, crop image data, water and fertilizer configuration data and irrigation control data of the farmland areas corresponding to other sub-databases.

10. A high-standard farmland management platform according to claim 9, characterized in that: The server end is also communicatively connected to a plurality of user ends; The client is used to access the database module; different clients have different sub-database access permissions.

Images