Agricultural data visualization and regulation system and method under support of Internet of Things

Abstract

The invention discloses an agricultural data visualization and regulation system and method under the support of Internet of Things, and the method comprises the steps: dividing a crop planting region into a plurality of sampling regions, taking a crop growth cycle T as a sampling cycle, and obtaining the vegetation index of crops in each cycle based on each piece of Internet of Things equipment; constructing a crop growth characteristic evaluation model based on the vegetation index, and calculating a growth characteristic evaluation value of crops in each sampling area; abnormal values in the growth characteristic evaluation value data are detected and screened, and effective data of growth characteristic evaluation values are obtained; data visualization is realized through the time sequence diagram; and based on image data in the time sequence diagram, calculating a growth characteristic evaluation value deviation degree between adjacent data, and optimizing an irrigation strategy and a fertilization plan based on the deviation value. The system has the advantages that by monitoring the crop growth state in real time and performing dynamic data analysis, abnormal values are removed, accurate management is realized, irrigation and fertilization strategies are optimized, and the agricultural production efficiency is improved.

Description

Technical Field

[0001] The present invention relates to Internet of Things technology, and particularly to an agricultural data visualization and regulation system and method supported by the Internet of Things. Background Art

[0002] An agricultural data visualization and regulation system and method supported by the Internet of Things collects various data during the crop growth process in real time by deploying Internet of Things devices in crop planting areas, such as vegetation indices, soil humidity, and climate conditions, etc., and constructs a crop growth characteristic evaluation model with the crop growth cycle as the sampling period. This method can evaluate the growth status of crops in different sampling areas and ensure the validity of data by detecting outliers. Data visualization is achieved through time series graphs, and managers can intuitively monitor the crop growth trend, analyze the deviation between adjacent data, so as to optimize irrigation and fertilization strategies, improve the accuracy and efficiency of agricultural production, and promote the development of smart agriculture.

[0003] Currently, the agricultural data visualization and regulation systems and methods on the market combine advanced technologies such as the Internet of Things, remote sensing technology, big data analysis, and artificial intelligence to achieve the intelligence and precision of agricultural production. Through real-time data collection and analysis, farmers can monitor information such as crop growth, soil conditions, and climate changes, and adjust operations such as irrigation, fertilization, and planting according to the data to optimize resource allocation and improve production efficiency and quality. In addition, the application of decision support systems and blockchain technology has also enhanced the transparency and scientific nature of agricultural management and promoted the sustainable development of agriculture. Summary of the Invention

[0004] In order to improve the existing agricultural data visualization and regulation systems and methods, an agricultural data visualization and regulation system and method supported by the Internet of Things is provided. This method helps monitor and optimize agricultural management by collecting crop growth data in real time, establishing a growth characteristic evaluation model, and performing data visualization. By analyzing data deviation, irrigation and fertilization strategies are accurately adjusted to improve agricultural production efficiency and resource utilization.

[0005] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] An agricultural data visualization and regulation method supported by the Internet of Things, characterized by comprising:

[0007] Dividing the crop planting area into multiple sampling areas, taking the crop growth cycle T as the sampling period, and obtaining the vegetation index of the crop in each period based on each Internet of Things device;

[0008] Constructing a crop growth characteristic evaluation model based on the vegetation index, and calculating the growth characteristic evaluation values of the crops in each sampling area;

[0009] Based on the obtained growth feature evaluation values, detect and screen outliers in the growth feature evaluation value data, and obtain the valid data of the growth feature evaluation values;

[0010] Based on the valid data of the obtained growth feature evaluation values, realize data visualization through a time series graph;

[0011] Based on the image data in the time series graph, calculate the deviation degree of the growth feature evaluation values between adjacent data, and optimize the irrigation strategy and fertilization plan based on the magnitude of the deviation value.

[0012] Preferably, dividing the crop planting area into multiple sampling areas, using the crop growth cycle T as the sampling period, and based on each Internet of Things device to obtain the vegetation index of the crop within each period specifically includes:

[0013] The Internet of Things devices include sensors, remote sensing image devices, and data transmission devices;

[0014] The vegetation index specifically includes coverage rate, growth status, and moisture status;

[0015] The coverage rate includes the normalized difference vegetation index, green normalized difference vegetation index, re-normalized difference vegetation index, and ratio vegetation index;

[0016] The growth status includes the terrestrial chlorophyll index, vegetation extraction color index, over-green vegetation index, green leaf vegetation index, plant pigment ratio, and red-green-blue vegetation index;

[0017] The moisture status includes the moisture index, improved red-edge ratio vegetation index, and vegetation attenuation index.

[0018] Preferably, constructing a crop growth feature evaluation model based on the vegetation index, and calculating the growth feature evaluation values of the crops in each sampling area specifically includes:

[0019] The formula of the growth feature evaluation model is: <I

[0020]

[0021] Among them, S is the growth feature evaluation value, λ i 、α i 、β i are the weight values of each vegetation index, and m, n, and j are the types of vegetation indices reflected by the coverage rate, growth status, and moisture status respectively; <I

[0022] Based on the growth feature evaluation model, substitute the data values obtained from each collection area into the model to obtain the growth feature evaluation model.

[0023] Preferably, detecting and screening outliers in the growth characteristic evaluation value data based on the obtained growth characteristic evaluation value, and obtaining the valid data of the growth characteristic evaluation value specifically includes:

[0024] Based on the growth characteristic evaluation value data of all sampling areas obtained, arrange them in ascending order;

[0025] Calculate the first quartile Q1 of the obtained data, and the formula is: And obtain the first quartile, where ε is the total sample quantity of the growth characteristic evaluation value data;

[0026] Calculate the third quartile Q3 of the obtained data, and the formula is: And obtain the third quartile;

[0027] Based on the first quartile Q1 and the third quartile Q3 calculated and obtained, calculate the interquartile range value, and the formula is:

[0028] IQR = Q3 - Q1

[0029] Set a threshold, and judge the size relationship between the growth characteristic evaluation value data of the obtained sampling area and the threshold. If the collected growth characteristic evaluation value data is less than the lower limit of the threshold or greater than the upper limit of the threshold, it is judged as an outlier;

[0030] Screen out the outliers in the data, and the remaining data are all valid data.

[0031] Preferably, realizing data visualization through a time series graph based on the valid data of the obtained growth characteristic evaluation value specifically includes:

[0032] Form a time series curve based on the horizontal and vertical axis data;

[0033] Based on the moving average technique, eliminate the short-term fluctuations in the time series and highlight the long-term trend, and the formula is:

[0034]

[0035] Where, MA(t) is the average movement to time point t, and N is the size of the string window;

[0036] Calculate the mean difference and standard deviation of the time series curve data, and obtain the central tendency, dispersion degree and fluctuation range of the data.

[0037] Preferably, calculating the deviation degree of the growth characteristic evaluation value between adjacent data based on the image data in the time series graph, and optimizing the irrigation strategy and fertilization plan based on the size of the deviation value specifically includes:

[0038] Based on the obtained growth characteristic evaluation value, calculate the difference Δd between adjacent data and perform standardization processing;

[0039] Based on the obtained standard values, they are processed through a normalization function, and the formula is:

[0040]

[0041] Based on the magnitude of the values after normalization processing, a threshold is set for classification processing, and it is divided into severe deviation, normal deviation, and minor deviation;

[0042] Based on the classification results of the deviation values, adjust the irrigation amount according to the soil humidity;

[0043] Based on the classification results of the deviation values and the nutrient requirements of the crop at different growth stages, combined with the actual situation of the soil nutrients, reasonably adjust the fertilization amount;

[0044] Based on the real-time monitoring data of the sensor, feedback on the adjustment situation to form a closed-loop feedback system.

[0045] Furthermore, an agricultural data visualization and regulation system supported by the Internet of Things is characterized by including:

[0046] Sampling area division module: The sampling area division module is mainly used to divide the agricultural area;

[0047] Vegetation index acquisition module: The vegetation index acquisition module is mainly used to obtain the vegetation index of the crop in each period based on each Internet of Things device;

[0048] Growth characteristic evaluation model construction module: The growth characteristic evaluation model construction module is mainly used to construct an evaluation model based on the vegetation index and calculate the growth characteristic evaluation value of the crop in each sampling area;

[0049] Abnormal detection model, the abnormal detection model is mainly used to detect and screen the abnormal values in the growth characteristic evaluation value data based on the obtained growth characteristic evaluation values, and obtain the valid data of the growth characteristic evaluation values;

[0050] Visualization module: The visualization module is mainly used to obtain a time series graph based on the valid data of the growth characteristic evaluation values;

[0051] Deviation degree classification module: The deviation degree classification module is mainly used to obtain the growth characteristic evaluation value deviation degree between adjacent data based on the image data in the time series graph;

[0052] Feedback module: The feedback module is mainly used to optimize the irrigation strategy and fertilization plan based on the magnitude of the deviation degree;

[0053] Processor: The processor is mainly used for calculating each formula in the growth characteristic evaluation model and calculating the deviation.

[0054] Compared with the prior art, the advantages of the present invention are:

[0055] By dividing the crop planting area into multiple sampling areas and conducting dynamic monitoring in combination with the crop growth cycle, the vegetation index of each area can be obtained in real time and accurately, thereby reflecting the growth status of the crops. Secondly, constructing an evaluation model for crop growth characteristics helps to quantitatively analyze various indicators of crop growth and improve the scientific nature of agricultural production decision-making. By screening effective data and removing outliers, the accuracy and reliability of the data are ensured. Visualization means, such as time series graphs, not only facilitate observing the crop growth trend but also intuitively display the differences in different sampling areas, providing clear information support for managers. By calculating the deviation degree between adjacent data, the dynamic optimization of irrigation and fertilization strategies can be achieved, improving resource utilization efficiency, reducing unnecessary waste, and ultimately enhancing crop yield and quality. Overall, this method realizes precise agricultural management, improves production efficiency, and promotes the development of sustainable agriculture by integrating Internet of Things technology and data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 Schematic diagram of the analysis method of the system and method proposed by the present invention;

[0057] Figure 2 Schematic diagram of the vegetation index of the system and method proposed by the present invention;

[0058] Figure 3 Schematic diagram of obtaining the growth characteristic evaluation value of the system and method proposed by the present invention;

[0059] Figure 4 Schematic diagram of obtaining effective data of the system and method proposed by the present invention;

[0060] Figure 5 Schematic diagram of data visualization of the system and method proposed by the present invention;

[0061] Figure 6 Schematic diagram of adjusting the strategy plan of the system and method proposed by the present invention;

[0062] Figure 7 Architecture diagram of the electronic device in this solution;

[0063] Figure 8 Schematic diagram of the structure of the computer-readable storage medium in this solution. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and those skilled in the art can think of other obvious variations.

[0065] An agricultural data visualization and regulation system supported by the Internet of Things, comprising:

[0066] Sampling area division module: The sampling area division module is mainly used to divide agricultural areas;

[0067] Vegetation index acquisition module: The vegetation index acquisition module is mainly used to obtain the vegetation index of crops in each period based on various Internet of Things devices;

[0068] Growth characteristic evaluation model construction module: The growth characteristic evaluation model construction module is mainly used to construct an evaluation model based on the vegetation index and calculate the growth characteristic evaluation values of crops in each sampling area;

[0069] Anomaly detection model, the anomaly detection model is mainly used to detect and screen out the outliers in the growth characteristic evaluation value data based on the obtained growth characteristic evaluation values, and obtain the valid data of the growth characteristic evaluation values;

[0070] Visualization module: The visualization module is mainly used to obtain a time series graph based on the valid data of the growth characteristic evaluation values;

[0071] Deviation degree classification module: The deviation degree classification module is mainly used to obtain the growth characteristic evaluation value deviation degree between adjacent data based on the image data in the time series graph;

[0072] Feedback module: The feedback module is mainly used to optimize the irrigation strategy and fertilization plan based on the deviation degree size;

[0073] Processor: The processor is mainly used for calculating each formula in the growth characteristic evaluation model and calculating the deviation.

[0074] See Figure 1 As shown, an agricultural data visualization and regulation method supported by the Internet of Things includes:

[0075] Step 1: Divide the crop planting area into multiple sampling areas, use the crop growth cycle T as the sampling cycle, and obtain the vegetation index of crops in each cycle based on various Internet of Things devices;

[0076] Step 2: Construct a crop growth characteristic evaluation model based on the vegetation index and calculate the growth characteristic evaluation values of crops in each sampling area;

[0077] Step 3: Based on the obtained growth characteristic evaluation values, detect and screen out the outliers in the growth characteristic evaluation value data, and obtain the valid data of the growth characteristic evaluation values;

[0078] Step 4: Based on the valid data of the obtained growth characteristic evaluation values, realize data visualization through a time series graph;

[0079] Step 5: Based on the image data in the time series graph, calculate the growth characteristic evaluation value deviation degree between adjacent data, and optimize the irrigation strategy and fertilization plan based on the deviation value size.

[0080] Refer to Figure 2 As shown, the crop planting area is divided into multiple sampling areas, with the crop growth cycle T as the sampling cycle. Based on each Internet of Things device, the vegetation indices of the crops in each cycle are obtained, specifically including:

[0081] The Internet of Things devices include sensors, remote sensing image devices, and data transmission devices;

[0082] The vegetation indices specifically include coverage rate, growth status, and moisture status;

[0083] The coverage rate includes normalized difference vegetation index, green normalized difference vegetation index, re-normalized difference vegetation index, and ratio vegetation index;

[0084] The growth status includes terrestrial chlorophyll index, vegetation extraction color index, over-green vegetation index, green leaf vegetation index, plant pigment ratio, and red-green-blue vegetation index;

[0085] The moisture status includes moisture index, improved red-edge ratio vegetation index, and vegetation attenuation index.

[0086] Specifically, the normalized difference vegetation index (NDVI) is mainly used to evaluate the vegetation coverage and growth. The NDVI value usually ranges from -1 to +1, and a higher value indicates denser vegetation. The green normalized difference vegetation index (GNDVI) is mainly used to evaluate the growth status of green plants and is particularly sensitive to areas with high concentrations of green plants or high-density plant coverage. The modified NDVI (mNDVI) is used to reduce the influence of the atmospheric and soil backgrounds and is especially suitable for areas with high-density vegetation. The ratio vegetation index (RVI) is a simple vegetation index used to estimate the growth status of vegetation. Compared with the NDVI, the RVI is more sensitive to changes in low values. The terrestrial chlorophyll index (TCI) estimates the chlorophyll content in terrestrial vegetation through remote sensing data and is commonly used to monitor the growth status of plants and their photosynthetic capacity. The vegetation extraction color index (VEXI) extracts the color characteristics of vegetation through spectral information in different bands to evaluate the health and growth status of plants. The excess green index (ExG) is mainly used to indicate the greenness of vegetation and thus reflect the health status of plants. This index can help identify areas with excessive greening. The green leaf vegetation index (GLVI) is used to monitor the change in greenness of vegetation and helps to judge the photosynthetic efficiency and health status of plants. The plant pigment ratio (PPR) is used to evaluate the pigment content in vegetation, especially the ratio of chlorophyll to carotenoid, which has certain indicative significance for the growth status and stress resistance of plants. The red green blue vegetation index (RGBVI) is calculated based on the reflectance of the red, green, and blue channels of remote sensing images and is usually used to reflect the vegetation coverage and growth status. The water index (WI) calculates the water content of vegetation and soil and helps to monitor the water stress status of plants. The modified red edge ratio vegetation index (mRERI) can better reflect the water status of plants, especially for evaluating the water and chlorophyll content of plants, by calculating the difference in reflectance of the red edge bands of vegetation. The vegetation attenuation index (VAI) is used to monitor the decline and degradation status of plants and evaluate the vegetation health status.

[0087] See Figure 3 As shown, a crop growth characteristic evaluation model is constructed based on the vegetation index, and the evaluation values of the crop growth characteristics in each sampling area are calculated, specifically including:

[0088] The formula for the growth characteristic evaluation model is:

[0089]

[0090] where S is the evaluation value of the growth characteristics, λ i , α i , β i are the weight values of each vegetation index, and m, n, and j are the numbers of types of vegetation indices reflecting the coverage rate, growth status, and water status, respectively;

[0091] Based on the growth characteristic evaluation model, the data values obtained from each collection area are substituted into the model to obtain the growth characteristic evaluation model.

[0092] See Figure 4As shown, based on the obtained growth feature evaluation values, detecting and screening outliers in the growth feature evaluation value data, and obtaining the valid data of the growth feature evaluation values specifically include:

[0093] Based on the growth feature evaluation value data of all sampling areas obtained, arrange them in ascending order;

[0094] Calculate the first quartile Q1 of the obtained data, and the formula is: And obtain the first quartile, where ε is the total sample size of the growth feature evaluation value data;

[0095] Calculate the third quartile Q3 of the obtained data, and the formula is: And obtain the third quartile;

[0096] Based on the calculated first quartile Q1 and third quartile Q3, calculate the interquartile range value, and the formula is:

[0097] IQR = Q3 - Q1

[0098] Set a threshold, and judge the size relationship between the growth feature evaluation value data of the obtained sampling area and the threshold. If the collected growth feature evaluation value data is less than the lower threshold or greater than the upper threshold, it is judged as an outlier;

[0099] Screen out the outliers in the data, and the remaining data are all valid data.

[0100] It can be understood that according to the quartile method, outliers are usually defined as values less than Q1 - 1.5IQR or greater than Q3 + 1.5IQR. However, the selection of this standard may not be applicable to all datasets, and there may be too many or too few outliers. The threshold for outliers can be adjusted according to the characteristics of the data. For example, the multiple of 1.5 can be adjusted, increasing or decreasing this value to expand or narrow the detection range of outliers. It is also possible to determine the optimal threshold through methods such as cross-validation. For some complex datasets with obvious grouping, try to calculate the quartiles and IQR for different groups separately to avoid the outlier standard of the overall data being inapplicable to some groups.

[0101] Refer to Figure 5 As shown, based on the valid data of the obtained growth feature evaluation values, realizing data visualization through a time series graph specifically includes:

[0102] Form a time series curve based on the horizontal and vertical axis data;

[0103] Based on the moving average technique, eliminate the short-term fluctuations in the time series and highlight the long-term trend, and the formula is:

[0104]

[0105] Among them, MA(t) is the moving average at time point t, and N is the string window size;

[0106] Calculate the mean difference and standard deviation of the time series curve data to obtain the central tendency, dispersion degree, and fluctuation range of the data.

[0107] Refer to Figure 6 , based on the image data in the time series graph, calculate the deviation degree of the growth characteristic evaluation value between adjacent data, and optimize the irrigation strategy and fertilization plan based on the size of the deviation value, specifically including:

[0108] Based on the obtained growth characteristic evaluation value, calculate the difference Δd between adjacent data and perform standardization processing;

[0109] Based on the obtained standard value, perform processing through a normalization function, and the formula is:

[0110]

[0111] Based on the size of the value after normalization processing, set a threshold for classification processing, and classify it into serious deviation, normal deviation, and minor deviation;

[0112] Adjust the irrigation amount based on the deviation value classification result and soil humidity;

[0113] Based on the deviation value classification result and the nutrient requirements of the crop growth stage, combined with the actual situation of soil nutrients, reasonably adjust the fertilization amount;

[0114] Based on the real-time monitoring data of the sensor, feedback on the adjustment situation to form a closed-loop feedback system.

[0115] Furthermore, the method according to the embodiment of the present application can also be implemented with the help of Figure 7 The architecture of the electronic device shown. As Figure 7 shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a read-only memory (ROM) 503, a random access memory (RAM) 504, a communication port 505 connected to the network, an input / output component 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, can store an agricultural data visualization and regulation system and method provided by the present application. The electronic device 500 may also include a terminal interface 508. Of course, Figure 7 The architecture shown is only exemplary. When implementing different devices, one or more components shown in the Figure 7 electronic device may be omitted according to actual needs.

[0116] Figure 8 is a schematic diagram of the structure of a computer-readable storage medium provided by an embodiment of the present application. AsFigure 8 As shown, there is a computer-readable storage medium 600 according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium 600. When the computer-readable instructions are run by a processor, it can execute an agricultural data visualization and regulation system and method according to an embodiment of the present application described with reference to the above drawings. The storage medium 600 includes but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory, etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0117] It should be noted that: the above sequence of embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. And the above specific embodiments of this specification have been described. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0118] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments.

[0119] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An agricultural data visualization and regulation method supported by the Internet of Things, characterized in that, Including: Dividing the crop planting area into multiple sampling areas, using the crop growth cycle T as the sampling cycle, and obtaining the vegetation index of the crops in each cycle based on each Internet of Things device; Constructing a crop growth characteristic evaluation model based on the vegetation index, and calculating the growth characteristic evaluation values of the crops in each sampling area; Based on the obtained growth characteristic evaluation values, detecting and screening outliers in the growth characteristic evaluation value data, and obtaining the valid data of the growth characteristic evaluation values; Based on the obtained valid data of the growth characteristic evaluation values, realizing data visualization through a time series graph; Based on the image data in the time series graph, calculating the deviation degree of the growth characteristic evaluation values between adjacent data, and optimizing the irrigation strategy and fertilization plan based on the size of the deviation value.

2. The agricultural data visualization and regulation method supported by the Internet of Things according to claim 1, wherein, The specific steps of dividing the crop planting area into multiple sampling areas, using the crop growth cycle T as the sampling cycle, and obtaining the vegetation index of the crops in each cycle based on each Internet of Things device include: The Internet of Things devices include sensors, remote sensing image devices, and data transmission devices; The vegetation index specifically includes coverage rate, growth status, and moisture status; The coverage rate includes normalized difference vegetation index, green normalized difference vegetation index, re-normalized difference vegetation index, and ratio vegetation index; The growth status includes terrestrial chlorophyll index, vegetation extraction color index, over-green vegetation index, green leaf vegetation index, plant pigment ratio, and red-green-blue vegetation index; The moisture status includes moisture index, improved red-edge ratio vegetation index, and vegetation attenuation index.

3. The agricultural data visualization and regulation method supported by the Internet of Things according to claim 1, characterized in that The specific steps of constructing a crop growth characteristic evaluation model based on the vegetation index, and calculating the growth characteristic evaluation values of the crops in each sampling area include: The formula of the growth characteristic evaluation model is: Among them, S is the growth characteristic evaluation value, , , are the weight values of each vegetation index, and m, n, and j are the numbers of types of vegetation indices reflecting coverage rate, vegetation indices reflecting growth status, and vegetation indices reflecting moisture status, respectively; Based on the growth characteristic evaluation model, substituting the data values obtained from each collection area into the model to obtain the growth characteristic evaluation model.

4. A method for visualizing and regulating agricultural data supported by the Internet of Things according to claim 1, characterized in that The specific steps of detecting and screening outliers in the growth characteristic evaluation value data based on the obtained growth characteristic evaluation values, and obtaining the valid data of the growth characteristic evaluation values include: Arranging the growth characteristic evaluation value data of all sampling areas obtained in ascending order; Calculate the first quartile of the acquired data , and the formula is: , and obtain the first quartile, where is the total sample size of the growth characteristic evaluation value data; Calculate the third quartile of the obtained data , the formula is: , and obtain the third quartile; Based on the first quartile obtained by calculation and the third quartile , calculate the interquartile range value. The formula is: Setting a threshold, judging the size relationship between the growth characteristic evaluation value data of the obtained sampling area and the threshold. If the collected growth characteristic evaluation value data is less than the lower limit of the threshold or greater than the upper limit of the threshold, it is judged as an outlier; Screening out the outliers in the data, and the remaining data are all valid data.

5. A method for visualizing and regulating agricultural data supported by the Internet of Things according to claim 1, characterized in that The specific steps of realizing data visualization through a time series graph based on the obtained valid data of the growth characteristic evaluation values include: Forming a time series curve based on the horizontal and vertical axis data; Based on the moving average technique, eliminating the short-term fluctuations in the time series and highlighting the long-term trend, the formula is: Among them, is the average movement to at time point t, and N is the string window size; Calculating the mean difference and standard deviation of the time series curve data to obtain the central tendency, dispersion degree, and fluctuation range of the data.

6. The agricultural data visualization and regulation method supported by the Internet of Things according to claim 1, wherein, The specific steps of calculating the deviation degree of the growth characteristic evaluation values between adjacent data based on the image data in the time series graph, and optimizing the irrigation strategy and fertilization plan based on the size of the deviation value include: Calculate the difference between adjacent data based on the obtained growth feature evaluation value , and perform standardization processing; Based on the obtained standard value, performing processing through a normalization function, the formula is: Based on the size of the normalized processed value, setting a threshold for classification processing, and dividing it into severe deviation, normal deviation, and minor deviation; Adjusting the irrigation amount based on the deviation value classification result and soil humidity; Based on the classification results of deviation values and the nutrient requirements of crops at different growth stages, and combined with the actual situation of soil nutrients, the fertilization amount is reasonably adjusted; Based on the real-time monitoring data of sensors, the adjustment situation is fed back to form a closed-loop feedback system.

7. A method for visualizing and regulating agricultural data supported by the Internet of Things, which is used to implement an agricultural data visualization and regulation system supported by the Internet of Things according to any one of claims 1-6, characterized in that, It includes: Sampling area division module: The sampling area division module is mainly used to divide agricultural areas; Vegetation index acquisition module: The vegetation index acquisition module is mainly used to obtain the vegetation indices of crops in each period based on various Internet of Things devices; Growth characteristic evaluation model construction module: The growth characteristic evaluation model construction module is mainly used to construct an evaluation model based on the vegetation index and calculate the growth characteristic evaluation values of crops in each sampling area; Abnormality detection model: The abnormality detection model is mainly used to detect and screen out abnormal values in the growth characteristic evaluation value data based on the obtained growth characteristic evaluation values, and obtain the valid data of the growth characteristic evaluation values; Visualization module: The visualization module is mainly used to obtain a time series graph based on the valid data of the growth characteristic evaluation values; Deviation degree classification module: The deviation degree classification module is mainly used to obtain the deviation degree of the growth characteristic evaluation values between adjacent data based on the image data in the time series graph; Feedback module: The feedback module is mainly used to optimize the irrigation strategy and fertilization plan based on the deviation degree; Processor: The processor is mainly used for calculating each formula in the growth characteristic evaluation model and calculating the deviation.

8. An electronic device, characterized in that, It includes: At least one processor; And a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute an agricultural data visualization and regulation method supported by the Internet of Things as described in any one of claims 1-6.

9. A computer-readable storage medium storing computer-readable instructions, characterized in that, When the computer-readable instructions are executed by the processor, an agricultural data visualization and regulation method supported by the Internet of Things as described in any one of claims 1-6 is implemented.

Images