Control system and method for multi-layer soil temperature and humidity sampling in intelligent agriculture

Abstract

The invention belongs to the technical field of data transmission processing, and discloses a control system and method for intelligent agriculture multilayer soil temperature and humidity sampling. The system comprises a land data acquisition module, an updated data acquisition module, a data set preprocessing module, a soil humidity prediction module, a decision report generation module and a report transmission module, and is characterized in that a land data set is acquired, an updated data set is acquired, the land data set and the updated data set are preprocessed to obtain comprehensive feature data, and the comprehensive feature data are transmitted to the decision report generation module; analyzing the land data set, the update data set and the comprehensive feature data set to obtain a predicted humidity reference value, analyzing the predicted humidity reference value to obtain a soil decision report, processing the soil decision report, and outputting the processed soil decision report to a terminal. The method has the remarkable advantages of high accuracy of sampled soil data, strong auxiliary decision-making capability and good use economic effect.

Description

Technical Field

[0001] The present invention relates to the field of data transmission processing technology, and more specifically, to a control system and method for multi-layer soil temperature and humidity sampling in smart agriculture. Background Art

[0002] Smart agriculture, also known as digital agriculture or information agriculture, involves a variety of agricultural high-tech technologies such as rapid acquisition of agricultural information, farmland planting, land management, pesticide utilization, pollution control, agricultural engineering equipment and its industrialization technology. Information management, as an important branch of computer application, is an important part of smart agriculture and the basis for intelligent decision-making in agricultural production. Smart agriculture uses intelligent machinery to collect data necessary for agricultural production, which can greatly improve agricultural production efficiency, save labor costs and save resources. Thanks to the rapid development of science and technology in my country in recent years, my country, as a major agricultural country, is also gradually promoting smart agricultural technology. Soil is the foundation of agriculture, and the temperature and humidity of the soil are It will directly affect the yield of crops, and the moisture conditions of the soil directly determine whether crops will be drought or waterlogged. Traditional soil temperature and humidity sampling is mostly done by installing temperature and humidity sensors to directly measure the temperature and humidity values ​​of the soil, and then transmit them to the receiving end of the staff. Although this has reduced the time cost and labor cost of field measurements required by the staff to a certain extent, this measurement and sampling method can only simply collect and transmit data. Subsequent decision-making still requires manual operation, and it is difficult to achieve the accuracy, predictability, economy and auxiliaryness of data collection and measurement. How to better use and mine data has become a major problem in the current smart agriculture industry.

[0003] The patent application publication number CN104965059A discloses a temperature, humidity and pH detection and control system for saline-alkali land improvement. By using a high-impedance amplifier for data amplification processing, it can accurately measure soil temperature, humidity and pH values ​​to 3 decimal places. The measurement accuracy is high and the data reference is strong. It can perform seedling detection and control for some precious plants. In addition, the system circuit is equipped with a temperature and humidity detection probe and a pH detection probe. Sampling and testing personnel do not need to carry two devices to sample pH values ​​and temperature and humidity separately. The circuit uses a high-impedance amplifier with high accuracy and strong stability. The power supply uses a 24V power supply that is lower than the safety voltage of the human body. The equipment operates well, has a long standby time, a fast operating speed, and stable operation.

[0004] However, in the above-mentioned temperature, humidity and pH detection and control system used in saline-alkali land improvement, although a high-impedance amplifier is used for data amplification processing to enhance the accuracy of measurement sampling, it is extremely important to generalize the collected data in the multi-layer soil temperature and humidity sampling control system. The traditional sampling system can only collect soil temperature and humidity data and then transmit it, which not only increases the subsequent data processing costs of the staff, but also makes it difficult to effectively use the collected data, resulting in many problems such as high labor costs for staff, poor data predictability and low data measurement accuracy. Therefore, how to better ensure the accuracy of data collection and measurement and conduct in-depth mining of the collected data is particularly important under the premise of the current development of smart agriculture.

[0005] In view of this, the present invention proposes a control system and method for multi-layer soil temperature and humidity sampling in smart agriculture to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and achieve the above-mentioned objectives, the present invention provides the following technical solutions, including: Land data collection module, used to collect land data sets, including soil type data, crop type data and soil depth data; The update data acquisition module is used to acquire an update data set, the update data set including soil temperature data, soil moisture data and rainfall data; The data set preprocessing module is used to preprocess the land data set and the update data set to obtain comprehensive feature data; Furthermore, the land dataset and the update dataset are preprocessed in the following ways: Fill missing values ​​in soil temperature data and soil moisture data. The specific calculation formula for filling is: ,in, is the soil temperature data; Standardize the updated data set. The specific calculation formula for standardization is: ,in, For the Update the basic parameters in the dataset, is the mean, is the standard deviation; Perform feature extraction on the land dataset and the update dataset. The specific calculation formula for the extraction is: ,in, is the soil moisture data, is soil characteristic data; Time series feature extraction is performed on rainfall data. The specific calculation formula for extraction is: ; in, is the size of the time window, is the humidity characteristic data; Package soil characteristic data and moisture characteristic data to obtain a comprehensive characteristic data set; The soil moisture prediction module is used to analyze the land dataset, the update dataset and the comprehensive feature dataset to obtain a predicted moisture reference value; Furthermore, the soil moisture prediction module also includes a historical data calling module, a manual data input module, a model support module and a data transmission module, wherein: The historical data calling module is used to call the historical land data set, historical update data set and historical comprehensive feature data set stored in the database; The manual data output module is used to support personnel to manually input error terms, historical residual coefficients and actual temperature and humidity reference values; The model support module is used to support the system in establishing the required model; The data transmission module is used to support the sending of the predicted humidity reference value; Furthermore, the steps of analyzing the land dataset, the update dataset, and the comprehensive feature dataset include: Step 1: Based on the historical data call module, a set of historical land datasets, historical update datasets, and historical comprehensive feature datasets stored in the database are retrieved and grouped and labeled accordingly from the earliest to the latest timestamps, labeled as Q1, Q2, Q3, ..., Qn, as the sample set; Step 2: Based on the model support module, the sample set is divided into a 70% training set, a 15% test set, and a 15% validation set, and an initial soil prediction model is established based on the sample set; Step 3: Substitute into the calculation formula: ; Get the initial predicted humidity reference value, where and are the lag orders of soil temperature data and soil moisture data, and are the lag term weight coefficients of soil temperature data and soil moisture data, 、 and are the weight factors corresponding to soil type data, crop type data and soil depth data, and are the interaction term weight factors of the land dataset and the update dataset, respectively. and are the regression coefficients of soil characteristic data and moisture characteristic data, is the error term; Step 4: Based on step 3, dynamically update the lag term weight coefficient according to the historical residuals. The specific calculation formula for the update is: ; in, is the learning coefficient, is the historical residual coefficient; Step 5: Based on step 3, calculate the mean absolute error to re-verify the initial predicted humidity reference value obtained in step 3. The specific calculation formula for re-verification is: ; in, is the actual temperature and humidity reference value; when If it is greater than or equal to the preset retest threshold, it returns to step 3 and retrains; Step 6: Repeat steps 3 to 5 until the preset number of iterations is reached to obtain a soil prediction model; Step 7: Input the land dataset, update dataset, and comprehensive feature data into the soil prediction model, output the predicted moisture reference value, and output the predicted moisture reference value to the decision report generation module based on the data transmission module; Furthermore, the real-time residual coefficients are processed, and the specific processing methods include: Define a real-time residual threshold. When the sum of the historical residual mean and the historical residual standard deviation is greater than or equal to the real-time residual threshold, modify the weight factor or add a data interaction term. The soil moisture prediction and detection module is used to check the land dataset, the updated dataset, the comprehensive feature data and the comprehensive feature data against the predicted moisture reference value to obtain a measurement result report; Furthermore, the method of checking the land dataset, the updated dataset, the comprehensive characteristic data, and the predicted humidity reference value of the comprehensive characteristic data includes: The predicted humidity reference value is checked by the rainfall event to see whether the predicted humidity reference value meets the humidity change caused by the rainfall event. If so, the predicted humidity reference value is output. Otherwise, the weight factor in the initial soil prediction model is modified. 、 and , and generate an initial measurement result report. According to the crop humidity requirement interval corresponding to the crop type data, check whether the predicted humidity reference value exceeds the crop humidity requirement interval. If yes, continue to output the predicted humidity reference value. Otherwise, trigger an alarm. The triggering of the alarm is to start the data re-collection process, update the land dataset and the update dataset, and integrate them into the initial measurement result report to obtain a measurement result report; The specific comparison formula for predicting whether the humidity reference value meets the humidity change caused by rainfall events is: ; in, is rainfall data; The decision report generating module is used to analyze the predicted moisture reference value to obtain a soil decision report; Furthermore, the method of analyzing the predicted humidity reference value includes: The crop demand threshold interval (W1, W2) is preset. When the predicted humidity reference value is less than or equal to W1, an irrigation report is generated. When the predicted humidity reference value is greater than W1 and less than W2, a suitable report is generated. When the predicted humidity reference value is greater than or equal to W2, a drainage report is generated. Package irrigation reports, suitability reports, drainage reports and soil depth data to obtain soil decision reports; Furthermore, the soil decision report includes: The irrigation report includes information about the current soil water shortage, reminding staff to arrange irrigation water according to the moisture gap, and drought risk warnings; The suitable report includes a statement that the current soil moisture is suitable, reminding staff that no intervention is required and to maintain the current irrigation frequency; The drainage report includes an explanation of the current soil waterlogging status, a reminder for staff to arrange drainage based on excessive moisture, and a root rot risk warning; The report transmission module is used to process the soil decision report and output it to the terminal; Furthermore, the soil decision report is processed and output to the terminal in the following ways: Detect soil decision report. When the soil decision report is suitable, it will be pushed to the staff receiving end via SMS or APP pop-up window; When the soil decision report is an irrigation report or a drainage report, remind the staff to check the soil decision report by phone; The land dataset, update dataset, comprehensive feature dataset, predicted moisture reference value, prediction result report and soil decision report are stored in the database and grouped by timestamp to support time series query; Furthermore, the humidity gap is the minimum soil moisture content required for crops minus the predicted humidity reference value; The irrigation water volume is calculated by the formula: Get, among them, is the crop demand coefficient, The humidity gap, The area of ​​the designated region; The humidity excess value is the predicted humidity reference value minus the maximum soil moisture content required for crops; The displacement is calculated by the formula: Get, among them, For humidity overvalue, is the volume of the soil layer, is the water density; Furthermore, the control system for multi-layer soil temperature and humidity sampling for smart agriculture also includes a data modification module and a device management module; The data modification module is used to support staff in adding, deleting, modifying and querying land datasets, update datasets, comprehensive feature data, soil prediction models, measurement result reports and soil decision reports; The device management module is used to support staff in adding, deleting, modifying and querying devices; Furthermore, S1: collecting a land dataset, the land dataset includes soil type data, crop type data, and soil depth data; S2: Collect and update data sets, including soil temperature data, soil moisture data, and rainfall data; S3: Preprocess the land dataset and the update dataset to obtain comprehensive feature data; S4: Analyze the land dataset, update dataset, and comprehensive feature dataset to obtain the predicted humidity reference value; S5: Check the land dataset, the updated dataset, the comprehensive characteristic data, and the predicted humidity reference value of the comprehensive characteristic data to obtain a measurement result report; S6: Analyze the predicted moisture reference value to obtain a soil decision report; S7: Process the soil decision report and output it to the terminal.

[0007] The technical effects and advantages of the control system for multi-layer soil temperature and humidity sampling in smart agriculture are as follows: The present invention collects land data sets, collects update data sets, pre-processes the land data sets and update data sets to obtain comprehensive feature data, analyzes the land data sets, update data sets and comprehensive feature data sets to obtain predicted humidity reference values, analyzes the predicted humidity reference values ​​to obtain a soil decision report, processes the soil decision report and outputs it to a terminal, so that the system has the ability to accurately calculate and process data under the influence of dynamic data fluctuations, greatly reducing the high cost, lack of predictability and poor decision-making support capabilities brought about by the single function of traditional sampling systems. In addition, the present invention also optimizes the soil moisture prediction module, and by verifying the soil prediction model, the system can further improve the accuracy of the calculated data, and through the decision report generation module, the system can achieve the effect of deep data mining on the predicted data, thereby greatly reducing the work cost of the staff. Overall, the present invention has the significant advantages of high accuracy of soil data obtained by sampling, strong decision-making support capabilities and good economic effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 This is a schematic diagram of a control system for multi-layer soil temperature and humidity sampling for smart agriculture according to the present invention; Figure 2 This is a schematic diagram of the control method for multi-layer soil temperature and humidity sampling for smart agriculture according to the present invention. DETAILED DESCRIPTION

[0009] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0010] The terms used in the embodiments of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms "a," "an," "the," and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two.

[0011] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0012] In addition, the step sequence in the following method embodiments is only an example and not a strict limitation.

[0013] In practice, the server-side device deployed for the control system for multi-layer soil temperature and humidity sampling in smart agriculture may be composed of one or more devices. The aforementioned control system for multi-layer soil temperature and humidity sampling in smart agriculture can be implemented as a service instance, a virtual machine, and hardware devices. For example, the control system for multi-layer soil temperature and humidity sampling in smart agriculture can be implemented as a service instance deployed on one or more devices in a cloud node. Simply put, the control system for multi-layer soil temperature and humidity sampling in smart agriculture can be understood as software deployed on a cloud node, used to provide a control system for multi-layer soil temperature and humidity sampling in smart agriculture to each client. Alternatively, the control system for multi-layer soil temperature and humidity sampling in smart agriculture can be implemented as a virtual machine deployed on one or more devices in a cloud node. Application software for managing each client is installed in the virtual machine. Alternatively, the control system for multi-layer soil temperature and humidity sampling in smart agriculture can be implemented as a server-side device composed of multiple hardware devices of the same or different types, with one or more hardware devices configured to provide a control system for multi-layer soil temperature and humidity sampling in smart agriculture to each client.

[0014] In terms of implementation, the control system and user end for smart agriculture multi-layer soil temperature and humidity sampling are mutually compatible. That is, if the control system for smart agriculture multi-layer soil temperature and humidity sampling is an application installed on a cloud service platform, the user end is a client that establishes a communication connection with the application; or if the control system for smart agriculture multi-layer soil temperature and humidity sampling is implemented as a website, the user end is implemented as a webpage; or if the control system for smart agriculture multi-layer soil temperature and humidity sampling is implemented as a cloud service platform, the user end is implemented as a mini-program in an instant messaging application.

[0015] like Figure 1 1 is a system architecture diagram of a control system for multi-layer soil temperature and humidity sampling in smart agriculture provided by one embodiment of the present invention.

[0016] The control system for multi-layer soil temperature and humidity sampling for smart agriculture described in the present invention can be set in a cloud server. In terms of implementation, it can be used as one or more service devices, or it can be installed as an application on the cloud (such as a server of a mobile service operator, a server cluster, etc.), or it can be developed as a website. According to the functions implemented, the control system for multi-layer soil temperature and humidity sampling for smart agriculture can include a land data acquisition module, an update data acquisition module, a data set preprocessing module, a soil moisture prediction module, a decision report generation module, and a report transmission module. The module described in the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0017] In an embodiment of the present invention, in a control system for multi-layer soil temperature and humidity sampling for smart agriculture, each of the above modules can be implemented independently and called with other modules. The call here can be understood as a module that can connect to multiple modules of another type and provide corresponding services to the multiple modules connected to it. For example, the sharing evaluation module can call the same information acquisition module to obtain the information collected by the information acquisition module. Based on the above characteristics, in the control system for multi-layer soil temperature and humidity sampling for smart agriculture provided by an embodiment of the present invention, the scope of application of the control system architecture for multi-layer soil temperature and humidity sampling for smart agriculture can be adjusted by adding modules and directly calling them without modifying the program code, thereby realizing cluster-type horizontal expansion, so as to achieve the purpose of quickly and flexibly expanding the control system for multi-layer soil temperature and humidity sampling for smart agriculture. In actual applications, the above modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in cloud servers.

[0018] Example 1 See also Figure 1 As shown, the control system for multi-layer soil temperature and humidity sampling for smart agriculture described in this embodiment includes: The land data collection module is used to collect land data sets, which include soil type data, crop variety data and soil layer depth data; It should be explained that soil type data is obtained by collecting soil samples at the surface and different depths in a specified area through a grid method and combining them with local standard coding: ; Through manual input, collect the types of crops planted in the soil in the specified area, combine the crop codes to obtain the temperature and humidity types required by the crops, and obtain the crop type data: ; Use a soil drill to collect the sampling depth of the soil in the specified area and obtain soil layer depth data: ; The update data acquisition module is used to acquire an update data set, the update data set including soil temperature data, soil moisture data and rainfall data; It should be explained that the real-time temperature value of the soil in the specified area is collected by the thermistor temperature sensor to obtain soil temperature data; the real-time humidity value of the soil in the specified area is collected by the capacitive humidity sensor to obtain soil humidity data; the rainfall value in the specified area is collected by the rain gauge to obtain rainfall data; the total amount of water irrigation in the specified area is collected by the flow meter to obtain soil irrigation data; The data set preprocessing module is used to preprocess the land data set and the update data set to obtain comprehensive feature data; Furthermore, the land dataset and update dataset are preprocessed in the following ways: Fill missing values ​​in soil temperature data and soil moisture data. The specific calculation formula for filling is: ,in, is the soil temperature data; Standardize the updated data set. The specific calculation formula for standardization is: ,in, For the Update the basic parameters in the dataset, is the mean, is the standard deviation; Perform feature extraction on the land dataset and the update dataset. The specific calculation formula for the extraction is: ,in, is the soil moisture data, is soil characteristic data; Time series feature extraction is performed on rainfall data. The specific calculation formula for extraction is: ; in, is the size of the time window, is the humidity characteristic data; Package soil characteristic data and moisture characteristic data to obtain a comprehensive characteristic data set; The soil moisture prediction module is used to analyze the land dataset, the update dataset and the comprehensive feature dataset to obtain a predicted moisture reference value; Furthermore, the soil moisture prediction module also includes a historical data calling module, a manual data input module, a model support module and a data transmission module, wherein: The historical data calling module is used to call the historical land data set, historical update data set and historical comprehensive feature data set stored in the database; The manual data output module is used to support personnel to manually input error terms, historical residual coefficients and actual temperature and humidity reference values; The model support module is used to support the system in establishing the required model; The data transmission module is used to support the sending of the predicted humidity reference value; Furthermore, the steps of analyzing the land dataset, the update dataset, and the comprehensive feature dataset include: Step 1: Based on the historical data call module, a set of historical land datasets, historical update datasets, and historical comprehensive feature datasets stored in the database are retrieved and grouped and labeled accordingly from the earliest to the latest timestamps, labeled as Q1, Q2, Q3, ..., Qn, as the sample set; Step 2: Based on the model support module, the sample set is divided into a 70% training set, a 15% test set, and a 15% validation set, and an initial soil prediction model is established based on the sample set; Step 3: Substitute into the calculation formula: ; Get the initial predicted humidity reference value, where and are the lag orders of soil temperature data and soil moisture data, and are the lag term weight coefficients of soil temperature data and soil moisture data, 、 and are the weight factors corresponding to soil type data, crop type data and soil depth data, and are the interaction term weight factors of the land dataset and the update dataset, respectively. and are the regression coefficients of soil characteristic data and moisture characteristic data, is the error term; It should be explained that the lag order refers to when When , it represents the past three time points; the interaction weight factor reflects the sensitivity of soil type to moisture changes; Step 4: Based on step 3, dynamically update the lag term weight coefficient according to the historical residuals. The specific calculation formula for the update is: ; in, is the learning coefficient, is the historical residual coefficient; It should be explained that the historical residual coefficient is obtained by subtracting the actual temperature and humidity reference value from the predicted humidity reference value; Step 5: Based on step 3, calculate the mean absolute error to re-verify the initial predicted humidity reference value obtained in step 3. The specific calculation formula for re-verification is: ; in, is the actual temperature and humidity reference value; when If it is greater than or equal to the preset retest threshold, it returns to step 3 and retrains; Step 6: Repeat steps 3 to 5 until the preset number of iterations is reached to obtain a soil prediction model; Step 7: Input the land dataset, update dataset, and comprehensive feature data into the soil prediction model, output the predicted moisture reference value, and output the predicted moisture reference value to the decision report generation module based on the data transmission module; Furthermore, the real-time residual coefficients are processed, and the specific processing methods include: Define a real-time residual threshold. When the sum of the historical residual mean and the historical residual standard deviation is greater than or equal to the real-time residual threshold, modify the weight factor or add a data interaction term. The soil moisture prediction and detection module is used to check the land dataset, the updated dataset, the comprehensive feature data and the comprehensive feature data against the predicted moisture reference value to obtain a measurement result report; Furthermore, the method of checking the land dataset, the updated dataset, the comprehensive characteristic data, and the predicted humidity reference value of the comprehensive characteristic data includes: The predicted humidity reference value is checked by the rainfall event to see whether the predicted humidity reference value meets the humidity change caused by the rainfall event. If so, the predicted humidity reference value is output. Otherwise, the weight factor in the initial soil prediction model is modified. 、 and , and generate an initial measurement result report. According to the crop humidity requirement interval corresponding to the crop type data, check whether the predicted humidity reference value exceeds the crop humidity requirement interval. If yes, continue to output the predicted humidity reference value. Otherwise, trigger an alarm. The triggering of the alarm is to start the data re-collection process, update the land dataset and the update dataset, and integrate them into the initial measurement result report to obtain a measurement result report; The specific comparison formula for predicting whether the humidity reference value meets the humidity change caused by rainfall events is: ; in, is rainfall data; The decision report generating module is used to analyze the predicted moisture reference value to obtain a soil decision report; Furthermore, the method of analyzing the predicted humidity reference value includes: The crop demand threshold interval (W1, W2) is preset. When the predicted humidity reference value is less than or equal to W1, an irrigation report is generated. When the predicted humidity reference value is greater than W1 and less than W2, a suitable report is generated. When the predicted humidity reference value is greater than or equal to W2, a drainage report is generated. Package irrigation reports, suitability reports, drainage reports and soil depth data to obtain soil decision reports; Furthermore, the soil decision report includes: The irrigation report includes information about the current soil water shortage, reminding staff to arrange irrigation water according to the moisture gap, and drought risk warnings; The suitable report includes a statement that the current soil moisture is suitable, reminding staff that no intervention is required and to maintain the current irrigation frequency; The drainage report includes an explanation of the current soil waterlogging status, a reminder for staff to arrange drainage based on excessive moisture, and a root rot risk warning; The report transmission module is used to process the soil decision report and output it to the terminal; Furthermore, the soil decision report is processed and output to the terminal in the following ways: Detect soil decision report. When the soil decision report is suitable, it will be pushed to the staff receiving end via SMS or APP pop-up window; When the soil decision report is an irrigation report or a drainage report, remind the staff to check the soil decision report by phone; The land dataset, update dataset, comprehensive feature dataset, predicted moisture reference value, prediction result report and soil decision report are stored in the database and grouped by timestamp to support time series query; Furthermore, the humidity gap is the minimum soil moisture content required for crops minus the predicted humidity reference value; The irrigation water volume is calculated by the formula: Get, among them, is the crop demand coefficient, The humidity gap, The area of ​​the designated region; The humidity excess value is the predicted humidity reference value minus the maximum soil moisture content required for crops; The displacement is calculated by the formula: Get, among them, For humidity overvalue, is the volume of the soil layer, is the water density; It should be explained that the density of water is assumed to be 1000 kilograms per cubic meter; Furthermore, the control system for multi-layer soil temperature and humidity sampling for smart agriculture also includes a data modification module and a device management module; The data modification module is used to support staff in adding, deleting, modifying and querying land datasets, update datasets, comprehensive feature data, soil prediction models, measurement result reports and soil decision reports; The device management module is used to support staff in adding, deleting, modifying and querying devices; This embodiment has the beneficial effect of collecting land data sets, collecting update data sets, pre-processing the land data sets and update data sets to obtain comprehensive feature data, analyzing the land data sets, update data sets and comprehensive feature data sets to obtain predicted humidity reference values, analyzing the predicted humidity reference values ​​to obtain soil decision reports, processing the soil decision reports and outputting them to the terminal, so that the system has the ability to accurately calculate and process data under the influence of dynamic data fluctuations, greatly reducing the high cost, lack of predictability and poor decision-making support capabilities brought about by the single function of traditional sampling systems. In addition, the present invention also optimizes the soil moisture prediction module, and by verifying the soil prediction model, the system can further improve the accuracy of the calculated data, and through the decision report generation module, the system can achieve the effect of deep data mining on the predicted data, thereby greatly reducing the work cost of the staff. Overall, the present invention has the significant advantages of high accuracy of soil data obtained by sampling, strong decision-making support capabilities and good economic effects.

[0019] Example 2 See also Figure 2 As shown, for parts not described in detail in this embodiment, please refer to the description of Example 1. A control method for multi-layer soil temperature and humidity sampling for smart agriculture is provided, the method comprising: S1: collecting a land dataset, the land dataset comprising soil type data, crop type data, and soil layer depth data; S2: Collect and update data sets, including soil temperature data, soil moisture data, and rainfall data; S3: Preprocess the land dataset and the update dataset to obtain comprehensive feature data; S4: Analyze the land dataset, update dataset, and comprehensive feature dataset to obtain the predicted humidity reference value; S5: Check the land dataset, the updated dataset, the comprehensive characteristic data, and the predicted humidity reference value of the comprehensive characteristic data to obtain a measurement result report; S6: Analyze the predicted moisture reference value to obtain a soil decision report; S7: Process the soil decision report and output it to the terminal.

[0020] Example 3 It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0021] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. Any reference to a figure in a claim should not be construed as limiting the claim to which it relates.

[0022] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0023] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in a system claim may also be implemented by a single unit or device through software or hardware. Terms such as "first" and "second" are used to indicate names and do not imply any particular order.

[0024] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A control system and method for multi-layer soil temperature and humidity sampling for smart agriculture, characterized in that: The system includes: a land data acquisition module, an update data acquisition module, a data set preprocessing module, a soil moisture prediction module, a decision report generation module and a report transmission module, wherein: The land data collection module is used to collect land data sets, which include soil type data, crop variety data and soil layer depth data; The update data acquisition module is used to acquire an update data set, the update data set including soil temperature data, soil moisture data and rainfall data; The data set preprocessing module is used to preprocess the land data set and the update data set to obtain comprehensive feature data; The soil moisture prediction module is used to analyze the land dataset, the update dataset and the comprehensive feature dataset to obtain a predicted moisture reference value; The soil moisture prediction and detection module is used to check the land dataset, the updated dataset, the comprehensive feature data and the comprehensive feature data against the predicted moisture reference value to obtain a measurement result report; The decision report generating module is used to analyze the predicted moisture reference value to obtain a soil decision report; The report transmission module is used to process the soil decision report and output it to the terminal.

2. The control system for multi-layer soil temperature and humidity sampling for smart agriculture according to claim 1 is characterized in that: The methods for preprocessing the land dataset and update dataset include: Fill missing values ​​in soil temperature data and soil moisture data. The specific calculation formula for filling is: ,in, is the soil temperature data; Standardize the updated data set. The specific calculation formula for standardization is: ,in, For the Update the basic parameters in the dataset, is the mean, is the standard deviation; Perform feature extraction on the land dataset and the update dataset. The specific calculation formula for the extraction is: ,in, is the soil moisture data, is soil characteristic data; For time series feature extraction, the specific calculation formula is: ； in, is the size of the time window, is the humidity characteristic data; The soil characteristic data and moisture characteristic data are packaged to obtain a comprehensive characteristic data set.

3. The control system for multi-layer soil temperature and humidity sampling for smart agriculture according to claim 1 is characterized in that: The soil moisture prediction module also includes a historical data calling module, a manual data input module, a model support module and a data transmission module, wherein: The historical data calling module is used to call the historical land data set, historical update data set and historical comprehensive feature data set stored in the database; The manual data output module is used to support personnel to manually input error terms, historical residual coefficients and actual temperature and humidity reference values; The model support module is used to support the system in establishing the required model; The data transmission module is used to support sending the predicted humidity reference value.

4. The control system for multi-layer soil temperature and humidity sampling for smart agriculture according to claim 3 is characterized in that: The steps for analyzing the land dataset, update dataset, and comprehensive feature dataset include: Step 1: Based on the historical data call module, a set of historical land datasets, historical update datasets, and historical comprehensive feature datasets stored in the database are retrieved and grouped and labeled accordingly from the earliest to the latest timestamps, labeled as Q1, Q2, Q3, ..., Qn, as the sample set; Step 2: Based on the model support module, the sample set is divided into a 70% training set, a 15% test set, and a 15% validation set, and an initial soil prediction model is established based on the sample set; Step 3: Substitute into the calculation formula: ； Get the initial predicted humidity reference value, where and are the lag orders of soil temperature data and soil moisture data, and are the lag term weight coefficients of soil temperature data and soil moisture data, 、 and are the weight factors corresponding to soil type data, crop type data and soil depth data, and are the interaction term weight factors of the land dataset and the update dataset, respectively. and are the regression coefficients of soil characteristic data and moisture characteristic data, is the error term; Step 4: Based on step 3, dynamically update the lag term weight coefficient according to the historical residuals. The specific calculation formula for the update is: ； in, is the learning coefficient, is the historical residual coefficient; Step 5: Based on step 3, calculate the mean absolute error to re-verify the initial predicted humidity reference value obtained in step 3. The specific calculation formula for re-verification is: ； in, is the actual temperature and humidity reference value; when If it is greater than or equal to the preset retest threshold, it returns to step 3 and retrains; Step 6: Repeat steps 3 to 5 until the preset number of iterations is reached to obtain a soil prediction model; Step 7: Input the land dataset, update dataset and comprehensive feature data into the soil prediction model, output the predicted moisture reference value, and output the predicted moisture reference value to the decision report generation module based on the data transmission module.

5. The control system for multi-layer soil temperature and humidity sampling for smart agriculture according to claim 4 is characterized in that: The real-time residual coefficients are processed. The specific processing methods include: Define a real-time residual threshold. When the sum of the historical residual mean and the historical residual standard deviation is greater than or equal to the real-time residual threshold, modify the weight factor or add a data interaction term.

6. The control system for multi-layer soil temperature and humidity sampling for smart agriculture according to claim 1 is characterized in that: The methods for checking the land dataset, the updated dataset, the comprehensive characteristic data and the predicted humidity reference value of the comprehensive characteristic data include: The predicted humidity reference value is checked by the rainfall event to see whether the predicted humidity reference value meets the humidity change caused by the rainfall event. If so, the predicted humidity reference value is output. Otherwise, the weight factor in the initial soil prediction model is modified. 、 and , and generate an initial measurement result report. According to the crop humidity requirement interval corresponding to the crop type data, check whether the predicted humidity reference value exceeds the crop humidity requirement interval. If yes, continue to output the predicted humidity reference value. Otherwise, trigger an alarm. The triggering of the alarm is to start the data re-collection process, update the land dataset and the update dataset, and integrate them into the initial measurement result report to obtain a measurement result report; The specific comparison formula for predicting whether the humidity reference value meets the humidity change caused by rainfall events is: ； in, For rainfall data.

7. The control system for multi-layer soil temperature and humidity sampling for smart agriculture according to claim 1 is characterized in that: Methods for analyzing the predicted humidity reference value include: The crop demand threshold interval (W1, W2) is preset. When the predicted humidity reference value is less than or equal to W1, an irrigation report is generated. When the predicted humidity reference value is greater than W1 and less than W2, a suitable report is generated. When the predicted humidity reference value is greater than or equal to W2, a drainage report is generated. Package irrigation reports, suitability reports, drainage reports and soil depth data to get a soil decision report.

8. The control system for multi-layer soil temperature and humidity sampling for smart agriculture according to claim 6, characterized in that: The Soil Decision Report includes: The irrigation report includes information about the current soil water shortage, reminding staff to arrange irrigation water according to the moisture gap, and drought risk warnings; The suitable report includes a statement that the current soil moisture is suitable, reminding staff that no intervention is required and to maintain the current irrigation frequency; The drainage report includes an explanation of the current soil being in a water-rich state, a reminder for staff to arrange drainage based on excessive humidity, and a root rot risk warning.

9. The control system for multi-layer soil temperature and humidity sampling for smart agriculture according to claim 7, characterized in that: The humidity gap is the minimum soil moisture content required for crops minus the predicted humidity reference value; The irrigation water volume is calculated by the formula: Get, among them, is the crop demand coefficient, The humidity gap, The area of ​​the designated region; The humidity excess value is the predicted humidity reference value minus the maximum soil moisture content required for crops; The displacement is calculated by the formula: Get, among them, For humidity overvalue, is the volume of the soil layer, is the density of water.

10. A control method for multi-layer soil temperature and humidity sampling for smart agriculture, implemented by the control system for multi-layer soil temperature and humidity sampling for smart agriculture according to any one of claims 1 to 9, characterized in that: The following steps are included: S1: Collect land datasets, including soil type data, crop species data, and soil depth data; S2: Collect and update data sets, including soil temperature data, soil moisture data, and rainfall data; S3: Preprocess the land dataset and the update dataset to obtain comprehensive feature data; S4: Analyze the land dataset, update dataset, and comprehensive feature dataset to obtain the predicted humidity reference value; S5: Check the land dataset, the updated dataset, the comprehensive characteristic data, and the predicted humidity reference value of the comprehensive characteristic data to obtain a measurement result report; S6: Analyze the predicted moisture reference value to obtain a soil decision report; S7: Process the soil decision report and output it to the terminal.

Images