Land information surveying and mapping system based on Internet of Things

Abstract

The invention discloses a land information surveying and mapping system based on the Internet of Things, and the system comprises a sensor unit which is composed of various types of high-precision sensors, covers a soil humidity sensor, a soil fertility sensor, a soil acidity and alkalinity sensor, a landform sensor, and a meteorological sensor, and is distributed at key positions and different depth levels of a land to be surveyed and mapped. The invention relates to the technical field of land surveying and mapping, and according to the land information surveying and mapping system based on the Internet of Things, through optimization design of a high-precision sensor, multi-stage data verification and a calibration model based on deep learning, the influence of environmental factors and errors of the sensor on measured data can be effectively eliminated, and the measurement accuracy is improved. The accuracy and reliability of land information data are greatly improved, a high-quality data basis is provided for the fields of precision agriculture, land planning, ecological monitoring and the like, and the scientificity of decision making and the rationality of resource utilization are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of land surveying and mapping, and in particular to a land information surveying and mapping system based on the Internet of Things. Background Art

[0002] At present, although the land information surveying and mapping system based on the Internet of Things can realize the collection and transmission of land data, it has obvious defects in the data verification and calibration mechanism. Environmental factors such as temperature, humidity, electromagnetic interference, etc. will cause deviations in sensor measurements, and the existing simple verification methods cannot effectively identify and correct these errors, thereby affecting the accuracy of land surveying and mapping data, making land planning and agricultural production decisions based on these data lack reliable basis, which is easy to cause waste of resources and decision-making errors. For this reason, the present invention provides a land information surveying and mapping system based on the Internet of Things. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a land information surveying and mapping system based on the Internet of Things, which solves the problem that environmental factors such as temperature, humidity, electromagnetic interference, etc. may cause deviations in sensor measurements, and the existing simple verification methods cannot effectively identify and correct these errors, thereby affecting the accuracy of land surveying and mapping data, making land planning and agricultural production decisions based on these data lack reliable basis, which is easy to cause waste of resources and decision-making errors.

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: A land information surveying and mapping system based on the Internet of Things, comprising:

[0005] The sensor unit is composed of various types of high-precision sensors, including soil moisture sensors, soil fertility sensors, soil pH sensors, topography sensors, and meteorological sensors, which are distributed at key locations and different depth levels of the land to be surveyed. Each sensor is equipped with an independent microprocessor and environmental monitoring module. The microprocessor is responsible for real-time preprocessing and preliminary quality assessment of the collected data. The environmental monitoring module is used to monitor the temperature, humidity, and electromagnetic field strength parameters of the sensor environment and transmit these parameters to the microprocessor. The soil moisture sensor adopts the capacitive measurement principle and is equipped with a temperature compensation circuit. The compensation formula is: M corr =M raw (1+α(T-T0)), where M corr is the soil moisture value after compensation, M raw is the original measurement value, α is the temperature compensation coefficient, T is the actual ambient temperature, and T0 is the sensor calibration temperature; the soil fertility sensor uses ion selective electrode technology combined with multi-electrode array design to simultaneously measure the content of multiple main nutrients such as nitrogen, phosphorus and potassium in the soil, and the measurement error is controlled within ±3%;

[0006] The data transmission unit uses hybrid wireless communication technology and has an intelligent retransmission mechanism. When the receiving end reports data transmission errors or loss, it can automatically retransmit data and adjust transmission parameters according to the error type and number.

[0007] A data processing center, the data processing center comprising:

[0008] The data storage module stores the original data, historical data and standard data after verification and calibration collected by the sensor in categories;

[0009] The data verification module executes a multi-stage data verification process and marks data that exceeds the preset statistical range as suspicious data;

[0010] The calibration model generation module builds neural network models for different types of land information data;

[0011] The calibration execution module performs calibration processing on the suspicious data according to the marking result of the data verification module and the model of the calibration model generation module;

[0012] The user interaction terminal is connected to the data processing center via wired or wireless means to provide users with a visual operation interface.

[0013] Preferably, the sensor unit further includes a self-diagnosis module for detecting the hardware status and measurement performance of the sensor.

[0014] Preferably, the data transmission unit uses photoelectric isolation technology at the interface connected to the sensor to prevent the sensor from being affected by electromagnetic interference on the data transmission line.

[0015] Preferably, when the data verification module performs data correlation verification, for two sets of data X and Y with complex nonlinear correlation, a kernel function-based method is used to map the data to a high-dimensional space, and then calculate the correlation index thereof, using a Gaussian kernel function.

[0016] After mapping, the correlation of the data is evaluated by calculating statistics such as covariance in high-dimensional space, where σ is the kernel function parameter, and x and y are sample points in data X and Y respectively.

[0017] Preferably, when constructing the neural network model, the calibration model generation module adopts transfer learning technology, uses model parameters pre-trained on other similar land environments or data sets as initial values, and on this basis performs fine-tuning for the current land surveying and mapping task, so as to speed up the training speed of the model and improve the generalization ability of the model.

[0018] Preferably, the data processing center also includes a data update module, which obtains the latest land information standard data, environmental data and land use change data from external data sources such as land research institutions and meteorological departments; integrates these external data with historical data within the system through data fusion technology, and uses machine learning algorithms to analyze data differences and change trends, and then automatically updates and optimizes calibration models and data verification rules to adapt to dynamic changes in the land environment.

[0019] Preferably, the system further comprises a solar power supply unit to provide power support for the sensor unit and the data transmission unit.

[0020] Preferably, the user interaction terminal has an early warning function, and when the system detects that the land information data has abnormal changes or exceeds a preset threshold, a warning message is sent to the user in a timely manner.

[0021] Beneficial Effects

[0022] The present invention provides a land information surveying and mapping system based on the Internet of Things. Compared with the prior art, it has the following beneficial effects:

[0023] 1. This land information surveying and mapping system based on the Internet of Things can effectively eliminate the influence of environmental factors and sensor errors on measurement data through the optimized design of high-precision sensors, multi-stage data verification and calibration models based on deep learning, greatly improving the accuracy and reliability of land information data, and providing a high-quality data foundation for precision agriculture, land planning, ecological monitoring and other fields, which helps to improve the scientific nature of decision-making and the rationality of resource utilization.

[0024] 2. This land information surveying and mapping system based on the Internet of Things ensures the reliability and flexibility of data transmission through hybrid wireless communication technology, and adapts to different geographical environments and transmission requirements; the dynamic update mechanism of the data processing center and the self-diagnosis function of the sensor enable the system to respond to land environment changes, sensor performance degradation and other situations in real time, ensuring the long-term stable operation of the system, reducing maintenance costs and data interruption risks, and improving the overall efficiency and service life of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a system architecture diagram of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0027] Example 1, please refer to Figure 1 The present invention provides a land information surveying and mapping system based on the Internet of Things, comprising:

[0028] The sensor unit is composed of various types of high-precision sensors, including soil moisture sensors, soil fertility sensors, soil pH sensors, topography sensors, and meteorological sensors, which are distributed at key locations and different depth levels of the land to be surveyed. Each sensor is equipped with an independent microprocessor and environmental monitoring module. The microprocessor is responsible for real-time preprocessing and preliminary quality assessment of the collected data. The environmental monitoring module is used to monitor the temperature, humidity, and electromagnetic field strength parameters of the sensor environment and transmit these parameters to the microprocessor. The soil moisture sensor adopts the capacitive measurement principle and is equipped with a temperature compensation circuit. The compensation formula is: M corr =M raw (1+α(T-T0)), where M corr is the soil moisture value after compensation, M raw is the original measurement value, α is the temperature compensation coefficient, T is the actual ambient temperature, and T0 is the sensor calibration temperature; the soil fertility sensor uses ion selective electrode technology combined with multi-electrode array design, which can accurately measure the content of multiple main nutrients such as nitrogen, phosphorus, and potassium in the soil at the same time, and the measurement error is controlled within ±3%;

[0029] The data transmission unit adopts hybrid wireless communication technology and integrates 4G, 5G and low-power wide area network (LPWAN) such as LoRa. It can automatically switch communication modes according to the distribution location of sensors, data transmission volume and transmission environment; before data transmission, the data is encrypted and compressed. The encryption adopts the Advanced Encryption Standard (AES) algorithm, and the compression adopts the lossless compression algorithm such as LZ77 algorithm to ensure the security and efficiency of data transmission; at the same time, the unit has an intelligent retransmission mechanism. When the receiving end feedbacks data transmission errors or losses, it can automatically retransmit data and adjust the transmission parameters according to the error type and number, such as increasing the transmission power and changing the frequency band.

[0030] Data Processing Center, the data processing center includes:

[0031] The data storage module uses a storage architecture that combines a distributed file system and a relational database to classify and store the original data, historical data, and standard data collected by the sensor after verification and calibration. The original data and historical data are archived according to time series and geographical areas, and the standard data is stored in a structured form for quick query and call. At the same time, a data backup strategy is set up, and off-site backup and redundant storage technology are used to prevent data loss.

[0032] The data verification module executes a multi-stage data verification process. First, a preliminary verification based on statistics is performed to calculate the mean, standard deviation, median and other statistical quantities of the data, and the data that exceeds the preset statistical range is marked as suspicious data. Then, the data change rate is verified. By comparing the data changes at adjacent time points and combining the natural change law of land information, it is determined whether the data changes are reasonable. For example, a sudden change in soil moisture in a short period of time may be an abnormal situation. Then, a data correlation verification is performed. The correlation between different types of land information data is analyzed using methods such as the Pearson correlation coefficient, and data with abnormal correlation is marked. For example, for soil moisture and precipitation data, if the precipitation continues to increase within a certain period of time but the soil moisture does not change significantly, there may be data anomalies.

[0033] The calibration model generation module builds a calibration model based on a deep learning algorithm. For different types of land information data, neural network models are built separately. For example, a multi-layer perceptron model is built for soil fertility data. The input layer contains the original sensor measurement values ​​and environmental monitoring data. The hidden layer extracts data features through the nonlinear activation function of neurons. The output layer is the accurate value of soil fertility after calibration. During the model training process, an adaptive learning rate adjustment strategy is adopted to dynamically adjust the learning rate according to the changes in the model's loss function to speed up the model convergence. At the same time, regularization techniques such as L1 and L2 regularization are used to prevent model overfitting.

[0034] The calibration execution module calibrates suspicious data according to the marking results of the data verification module and the model of the calibration model generation module. For slightly suspicious data marked in the preliminary verification, a simple calibration model based on linear regression is used to correct it. For abnormal data found in the change rate verification and correlation verification, a deep learning calibration model is used for precise calibration. After calibration, the data is checked for integrity and rationality again to ensure the quality of the calibrated data.

[0035] The user interaction terminal is connected to the data processing center by wired or wireless means to provide users with a visual operation interface. Users can view visual displays of land information data such as charts and maps in real time on the terminal, including information such as land topography, soil fertility distribution, and soil moisture changes. Users can also remotely configure the system through the terminal, such as setting the sensor's acquisition frequency, data transmission parameters, verification and calibration rules, etc. At the same time, the terminal has a data export function, which supports the export of calibrated data in common file formats such as CSV, Excel, Shapefile, etc., so that users can conduct further data analysis and processing.

[0036] In this embodiment, the sensor unit also includes a self-diagnosis module, which regularly detects the hardware status and measurement performance of the sensor, and determines whether the sensor has a fault or performance degradation by sending a standard test signal to the sensor and comparing the measurement results. If a problem is detected, a fault alarm message is sent to the data processing center in a timely manner, and an attempt is made to automatically restart or switch to a backup sensor.

[0037] In this embodiment, the data transmission unit uses photoelectric isolation technology at the interface connected to the sensor to prevent the sensor from being affected by electromagnetic interference on the data transmission line, thereby ensuring the accuracy and stability of data collection.

[0038] In this embodiment, when the data verification module performs data correlation verification, for two sets of data X and Y with complex nonlinear correlation, a kernel function-based method is used to map the data to a high-dimensional space, and then calculate the correlation index thereof, using a Gaussian kernel function.

[0039] After mapping, the correlation of the data is evaluated by calculating statistics such as covariance in high-dimensional space, where σ is the kernel function parameter, and x and y are sample points in data X and Y respectively.

[0040] In this embodiment, the calibration model generation module adopts transfer learning technology when constructing the neural network model, using model parameters pre-trained on other similar land environments or data sets as initial values, and on this basis, fine-tuning is performed for the current land surveying and mapping task to speed up the model training speed and improve the model's generalization ability.

[0041] In this embodiment, the data processing center also includes a data update module, which regularly obtains the latest land information standard data, environmental data, land use change data, etc. from authoritative land research institutions, meteorological departments and other external data sources; integrates these external data with the historical data within the system through data fusion technology, and uses machine learning algorithms to analyze data differences and change trends, and then automatically updates and optimizes the calibration model and data verification rules to adapt to the dynamic changes in the land environment.

[0042] In this embodiment, the system also includes a solar power supply unit to provide power support for the sensor unit and the data transmission unit; the solar power supply unit adopts maximum power point tracking (MPPT) technology to automatically adjust the working point of the solar panel according to the light intensity and ambient temperature to improve the power generation efficiency; at the same time, it is equipped with an intelligent battery management system to manage the charging and discharging of the energy storage battery, including overcharge protection, over-discharge protection, balanced charging and other functions, to extend the battery life and ensure that the system can continue to operate stably in the field environment.

[0043] In this embodiment, the user interaction terminal has an early warning function. When the system detects abnormal changes in land information data or exceeds a preset threshold, such as a sharp drop in soil fertility or excessive soil moisture that may cause floods, the system sends early warning information to the user in a timely manner. The information push methods include but are not limited to text messages, emails, pop-up reminders, etc., so that users can take corresponding countermeasures.

[0044] Embodiment 2, the present invention also provides an implementation case of a land information surveying and mapping system based on the Internet of Things:

[0045] Taking the land information mapping of a certain agricultural production base as an example, the land information mapping system based on the Internet of Things of the present invention is deployed in different farmland areas and soil layers of the base.

[0046] The soil moisture sensor in the sensor unit collects data every 15 minutes. Assume that at a certain moment, the original soil moisture value collected by a sensor is M raw =35%, at this time the ambient temperature T = 30 ° C, the sensor calibration temperature T0 = 25 ° C, the temperature compensation coefficient α = 0.02, according to the temperature compensation formula M corr =M raw (1+α(T-T0)), the soil moisture value after compensation can be calculated as M corr =35%(1+0.02×(30-25))=38.5%.

[0047] The data transmission unit encrypts and compresses the collected data and transmits it to the data processing center. According to the signal strength and data transmission volume of the sensor location, the 4G communication mode is automatically selected for transmission. During the transmission process, if the receiving end finds that there is an error in the data, the data transmission unit will immediately retransmit the data and appropriately increase the transmission power to improve the stability of the transmission.

[0048] After the data processing center receives the data, the data verification module first performs a preliminary verification and calculates that the mean of the historical data of soil moisture in the area is 30%, the standard deviation is 3%, and the preset mean range is 24%-36%. The 38.5% measured this time exceeds the preliminary verification range and is marked as suspicious data; then the data change rate is verified, and it is found that there has been no significant precipitation in the recent period and there are no other reasonable factors for the change in soil moisture, but the data has increased by 8% compared with the last measurement, further confirming that the data may be abnormal; then through data correlation verification, it is found that the correlation with the precipitation data in the same period does not conform to the normal law, and the data is comprehensively judged to be abnormal data.

[0049] The calibration model generation module builds a neural network model for soil moisture data. After training on the historical data of the base, the model parameters have been determined. The calibration execution module inputs the abnormal data into the model. After complex calculations and mapping of the model, the output of the calibrated soil moisture value is 32%. The integrity and rationality of the calibrated data are checked again. After confirmation, it is stored in the data storage module and displayed to the agricultural base managers in the form of visual charts through the user interaction terminal.

[0050] Managers can view the real-time soil moisture data, historical change curves, and correlations with other land information (such as soil fertility and meteorological data) of each farmland through the user interactive terminal in order to formulate accurate irrigation plans. At the same time, the data update module regularly obtains the latest soil moisture standard data and meteorological data from local agricultural research institutions, and updates and optimizes the system's historical data and calibration model to adapt to changes in land information under different seasons and planting conditions.

[0051] During the operation of the entire system, the solar power supply unit continuously provides power to the sensor unit and the data transmission unit, and automatically adjusts the charging and power supply strategies according to the light intensity and battery power to ensure stable operation of the system. When a sensor fails, the self-diagnosis module detects the problem in time and sends an alarm message to the data processing center, while trying to restart automatically. If the fault cannot be repaired, it switches to the backup sensor to ensure the continuity of data collection.

[0052] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0053] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0054] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A land information surveying and mapping system based on the Internet of Things, characterized in that: include: The sensor unit is composed of various types of high-precision sensors, including soil moisture sensors, soil fertility sensors, soil pH sensors, topography sensors, and meteorological sensors, which are distributed at key locations and different depth levels of the land to be surveyed. Each sensor is equipped with an independent microprocessor and environmental monitoring module. The microprocessor is responsible for real-time preprocessing and preliminary quality assessment of the collected data. The environmental monitoring module is used to monitor the temperature, humidity, and electromagnetic field strength parameters of the sensor environment and transmit these parameters to the microprocessor. The soil moisture sensor adopts the capacitive measurement principle and is equipped with a temperature compensation circuit. The compensation formula is: M corr =M raw (1+α(T-T0)), where M corr is the soil moisture value after compensation, M raw is the original measurement value, α is the temperature compensation coefficient, T is the actual ambient temperature, and T0 is the sensor calibration temperature; the soil fertility sensor uses ion selective electrode technology combined with multi-electrode array design to simultaneously measure the content of multiple main nutrients such as nitrogen, phosphorus and potassium in the soil, and the measurement error is controlled within ±3%; The data transmission unit uses hybrid wireless communication technology and has an intelligent retransmission mechanism. When the receiving end reports data transmission errors or loss, it can automatically retransmit data and adjust transmission parameters according to the error type and number. A data processing center, the data processing center comprising: The data storage module stores the original data, historical data and standard data after verification and calibration collected by the sensor in categories; The data verification module executes a multi-stage data verification process and marks data that exceeds the preset statistical range as suspicious data; The calibration model generation module builds neural network models for different types of land information data; The calibration execution module performs calibration processing on the suspicious data according to the marking results of the data verification module and the model of the calibration model generation module; The user interaction terminal is connected to the data processing center via wired or wireless means to provide users with a visual operation interface.

2. The land information surveying and mapping system based on the Internet of Things according to claim 1 is characterized in that: The sensor unit also includes a self-diagnosis module for detecting the hardware status and measurement performance of the sensor.

3. The land information surveying and mapping system based on the Internet of Things according to claim 1 is characterized in that: The data transmission unit adopts photoelectric isolation technology at the interface connected with the sensor to prevent the sensor from being interfered by electromagnetic interference on the data transmission line.

4. The land information surveying and mapping system based on the Internet of Things according to claim 1 is characterized in that: When the data verification module performs data correlation verification, for two sets of data X and Y with complex nonlinear correlation, a kernel function-based method is used to map the data to a high-dimensional space, and then calculate its correlation index, using a Gaussian kernel function. After mapping, the correlation of the data is evaluated by calculating statistics such as covariance in high-dimensional space, where σ is the kernel function parameter, and x and y are sample points in data X and Y respectively.

5. The land information surveying and mapping system based on the Internet of Things according to claim 1 is characterized in that: When constructing the neural network model, the calibration model generation module adopts transfer learning technology, uses model parameters pre-trained on other similar land environments or data sets as initial values, and on this basis, fine-tunes the current land surveying and mapping task to speed up the model training speed and improve the model's generalization ability.

6. The land information surveying and mapping system based on the Internet of Things according to claim 1 is characterized in that: The data processing center also includes a data update module, which obtains the latest land information standard data, environmental data and land use change data from external data sources such as land research institutions and meteorological departments; integrates these external data with historical data within the system through data fusion technology, and uses machine learning algorithms to analyze data differences and change trends, and then automatically updates and optimizes calibration models and data verification rules to adapt to dynamic changes in the land environment.

7. The land information surveying and mapping system based on the Internet of Things according to claim 1 is characterized in that: The system further comprises a solar power supply unit for providing power support for the sensor unit and the data transmission unit.

8. The land information surveying and mapping system based on the Internet of Things according to claim 1 is characterized in that: The user interaction terminal has an early warning function. When the system detects that the land information data has abnormal changes or exceeds a preset threshold, it will send early warning information to the user in a timely manner.

Images