A method and system for measuring soil moisture content during garden maintenance

Abstract

This invention discloses a method and system for measuring soil moisture content during garden maintenance, relating to the field of data processing technology. It addresses the problem of insufficient accuracy in soil moisture content measurement results during garden maintenance. The method includes: acquiring monitoring data from multiple monitoring points in the garden; determining the co-occurring abnormal period for each monitoring point based on the monitoring data from each point; determining the state recovery rate for each monitoring point based on the monitoring data during the co-occurring abnormal period; for each monitoring point, determining the disturbance value of the dielectric constant during the co-occurring abnormal period based on the co-occurring abnormal period, the state recovery rate, the correlation between various monitoring indicators during the co-occurring abnormal period, and the correlation between various monitoring indicators during non-co-occurring abnormal periods; and determining the soil moisture content of the garden based on the disturbance value of the dielectric constant and the spatial relationship between multiple monitoring points.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, specifically to a method and system for measuring soil moisture content during garden maintenance. Background Technology

[0002] In the refined maintenance of gardens, maintaining appropriate soil moisture content is crucial for ensuring healthy plant growth, improving water and fertilizer use efficiency, and maintaining soil ecological balance. Currently, the industry commonly uses sensors based on the principle of capacitance to measure the soil dielectric constant and converts it into volumetric water content through experience or calibration models. This method is widely used due to its ease of implementation.

[0003] However, in actual garden maintenance scenarios, frequent fertilization and irrigation operations can significantly alter the ionic environment and physical state of the soil. These external factors can cause complex interference to the electric field distribution in the soil. In addition, the soil in different areas of the garden itself varies in terms of texture and structure, which limits the accuracy and reliability of traditional methods based on single dielectric constant measurement in dynamically changing environments. Summary of the Invention

[0004] To address the current technical problem of insufficient accuracy in soil moisture content measurement during garden maintenance due to the inability to effectively distinguish and quantify the combined effects of external dynamic disturbances such as fertilization and irrigation, as well as soil spatial heterogeneity on dielectric constant measurements, the present invention aims to provide a method and system for measuring soil moisture content during garden maintenance. The specific technical solution adopted is as follows: In a first aspect, the present invention provides a method for determining soil moisture content during garden maintenance, comprising: acquiring monitoring data from multiple monitoring points in the garden; wherein the monitoring data from each monitoring point includes measured values ​​of multiple monitoring indicators collected over time; determining a co-abnormal period for each monitoring point based on the monitoring data from each monitoring point; wherein the co-abnormal period is a continuous time period in which the measured values ​​of multiple monitoring indicators simultaneously deviate from their respective historical normal fluctuation ranges; determining a state recovery rate for each monitoring point based on the monitoring data from each monitoring point during the co-abnormal period; wherein the state recovery rate characterizes the rate at which the monitoring indicators recover to their historical normal fluctuation range after the co-abnormal period ends; for each monitoring point, determining the disturbance value of the dielectric constant during the co-abnormal period based on the co-abnormal period, the state recovery rate, the correlation between the monitoring indicators during the co-abnormal period, and the correlation between the monitoring indicators during non-co-abnormal periods; and determining the soil moisture content of the garden based on the disturbance value of the dielectric constant and the spatial relationship between the multiple monitoring points.

[0005] In one possible implementation, based on the monitoring data of each monitoring point, the coordinated abnormal period of each monitoring point is determined, specifically including: calculating the coordinated abnormal index of each monitoring point at each time based on the monitoring data of each monitoring point; wherein, the coordinated abnormal index is used to characterize the degree to which the measured values ​​of multiple monitoring indicators deviate from their respective historical normal fluctuation ranges simultaneously; and identifying the time period in which the coordinated abnormal index is continuously higher than a first preset threshold as the coordinated abnormal period.

[0006] In one possible implementation, the collaborative anomaly index of each monitoring point at each time moment is calculated, specifically including: for each monitoring indicator, comparing the measured value at the current time moment with the historical normal fluctuation range to determine the single indicator deviation of the monitoring indicator at the current time moment; obtaining the number of monitoring indicators whose single indicator deviation at the current time moment exceeds a second preset threshold, and combining the average value of the single indicator deviation of all monitoring indicators at the current time moment to determine the collaborative anomaly index.

[0007] In one possible implementation, the state recovery rate of each monitoring point is determined based on the monitoring data of each monitoring point during the period of coordinated anomaly. Specifically, this includes: obtaining the coordinated anomaly index corresponding to the end time of the coordinated anomaly period and the coordinated anomaly index corresponding to the recovery time; wherein, the recovery time is the moment when the measured values ​​of multiple monitoring indicators first recover to their respective historical normal fluctuation ranges after the end time; and determining the state recovery rate based on the duration between the end time and the recovery time, as well as the coordinated anomaly index between the end time and the recovery time.

[0008] In one possible implementation, for each monitoring point, the disturbance value of the dielectric constant during the coordinated anomaly period is determined based on the coordinated anomaly period, the state recovery rate, the correlation between monitoring indicators during the coordinated anomaly period, and the correlation between monitoring indicators during the non-coordinated anomaly period. Specifically, this includes: calculating the first correlation between monitoring indicators during the coordinated anomaly period for each monitoring point; calculating the second correlation between monitoring indicators during historical non-coordinated anomaly periods for each monitoring point; and determining the disturbance value of the dielectric constant based on the first correlation, the second correlation, the coordinated anomaly index, and the state recovery rate.

[0009] In one possible implementation, the soil moisture content of the garden is determined based on the disturbance value of the dielectric constant and the spatial location of multiple monitoring points. Specifically, this includes: calculating the spatial interference correlation degree between every two monitoring points based on the disturbance value of the dielectric constant and the spatial location of multiple monitoring points; classifying two adjacent monitoring points with a spatial interference correlation degree greater than a third preset threshold into the same spatial interference region; determining the parameter correction factor for each monitoring point based on the historical disturbance value of the dielectric constant of each monitoring point within the spatial interference region to which each monitoring point belongs; and determining the soil moisture content of the garden based on the parameter correction factor.

[0010] In one possible implementation, the parameter correction factor for each monitoring point is determined based on the historical dielectric constant disturbance values ​​of each monitoring point within the spatial interference region to which each monitoring point belongs. Specifically, this includes: calculating the average dielectric constant disturbance value of each monitoring point within the spatial interference region to which the monitoring point belongs, and the average dielectric constant disturbance value of all monitoring points, to determine the local anomaly accumulation index; determining the decay trend index of the dielectric constant disturbance value of the monitoring point over historical time; wherein, the decay trend index is used to characterize the degree to which the dielectric constant disturbance value weakens over time; and determining the parameter correction factor based on the current dielectric constant anomaly degree, the local anomaly accumulation index, and the decay trend index.

[0011] In one possible implementation, the soil moisture content of the garden is determined according to a parameter correction factor, specifically including: using the parameter correction factor to correct at least one constant term parameter in the preset soil moisture content calculation model to obtain the corrected calculation parameters; and calculating the soil moisture content of the garden based on the corrected calculation parameters and the dielectric constant monitored in real time at each monitoring point.

[0012] In one possible implementation, multiple monitoring indicators include: dielectric constant, soil electrical conductivity, soil temperature, and soil pH.

[0013] Secondly, this invention provides a soil moisture content measurement system for garden maintenance. The system includes: a data acquisition module, an anomaly analysis module, a recovery assessment module, an interference quantification module, and a moisture content calculation module. The data acquisition module is used to acquire monitoring data from multiple monitoring points in the garden. The monitoring data from each monitoring point includes measured values ​​of multiple monitoring indicators collected over time. The anomaly analysis module is used to determine the co-abnormal period for each monitoring point based on the monitoring data from each monitoring point. The co-abnormal period is a continuous time period in which the measured values ​​of multiple monitoring indicators simultaneously deviate from their respective historical normal fluctuation ranges. The recovery assessment module is used to determine the soil moisture content measurement system based on the monitoring data from each monitoring point. The monitoring data of each monitoring point during the period of coordinated anomaly are used to determine the state recovery rate of each monitoring point. The state recovery rate is used to characterize the rate at which the monitoring indicators recover to the historical normal fluctuation range after the period of coordinated anomaly ends. The interference quantification module is used to determine the interference value of the dielectric constant of each monitoring point during the period of coordinated anomaly, based on the coordinated anomaly index, the state recovery rate, the correlation between each monitoring indicator during the period of coordinated anomaly, and the correlation between each monitoring indicator during the non-coordinated anomaly period. The moisture content calculation module is used to determine the soil moisture content of the garden based on the interference value of the dielectric constant and the spatial relationship between multiple monitoring points.

[0014] Thirdly, the present invention provides an electronic device, comprising: a processor and a memory; wherein the memory is used to store one or more programs, the one or more programs including computer execution instructions, wherein when the electronic device is running, the processor executes the computer execution instructions stored in the memory to cause the electronic device to perform the method for determining soil moisture content in the garden maintenance process as described in the first aspect and any possible implementation thereof.

[0015] Fourthly, the present invention provides a computer-readable storage medium storing one or more programs, the one or more programs including instructions that, when executed by an electronic device of the present invention, cause the electronic device to perform a method for determining soil moisture content in a garden maintenance process as described in the first aspect and any possible implementation thereof.

[0016] Fifthly, the present invention provides a computer program product containing instructions that, when executed on a computer, cause the electronic device of the present invention to perform a method for determining soil moisture content in a garden maintenance process as described in the first aspect and any possible implementation thereof.

[0017] In a sixth aspect, the present invention provides a chip system applied to a soil moisture content measuring device in the process of garden maintenance; the chip system includes one or more interface circuits and one or more processors. The interface circuits and the processors are interconnected via circuitry; the interface circuits are used to receive signals from the memory of the soil moisture content measuring device in the process of garden maintenance and to send the signals to the processors, the signals including computer instructions stored in the memory. When the processor executes the computer instructions, the soil moisture content measuring device in the process of garden maintenance performs the soil moisture content measuring method in the process of garden maintenance as described in the first aspect and any possible design.

[0018] This invention offers the following advantages: First, by detecting synergistic anomalies in multiple indicators, it reliably captures complex disturbance events caused by external factors such as fertilization and irrigation, providing accurate time anchors for subsequent analysis. Second, by assessing the rate of soil recovery from anomalies, it quantifies the resistance and recovery capacity of different soil textures to disturbances, providing a basis for judging the persistent impact of disturbances. Third, by comparing the differences in correlations between multiple indicators under abnormal and normal conditions, and combining anomaly intensity and recovery capacity, it achieves a refined and quantitative assessment of the degree of disturbance to dielectric constant measurements. Finally, by analyzing the spatial aggregation and diffusion patterns of disturbed values, it dynamically modifies the water content calculation model according to local conditions, thereby significantly improving the accuracy and reliability of soil water content detection results based on the capacitance method in complex actual landscape maintenance environments. Attached Figure Description

[0019] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the architecture of a soil moisture content measurement system in the garden maintenance process, provided as an embodiment of the present invention. Figure 2 This is a schematic diagram of the architecture of an anomaly analysis module provided in one embodiment of the present invention; Figure 3 This is a schematic diagram of the architecture of an interference quantization module provided in one embodiment of the present invention; Figure 4 This is one of the flowcharts illustrating a method for determining soil moisture content during garden maintenance, provided in an embodiment of the present invention. Figure 5 This is a second schematic flowchart of a method for determining soil moisture content during garden maintenance, provided as an embodiment of the present invention. Figure 6 This is a third flowchart illustrating a method for determining soil moisture content during garden maintenance, provided as an embodiment of the present invention. Figure 7 This is a fourth flowchart illustrating a method for determining soil moisture content during garden maintenance, provided as an embodiment of the present invention. Figure 8 This is the fifth flowchart illustrating a method for determining soil moisture content during garden maintenance, as provided in one embodiment of the present invention. Detailed Implementation

[0021] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the specific implementation methods, structures, features, and effects of the present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0023] The following description, in conjunction with the accompanying drawings, details the specific scheme of a method and system for measuring soil moisture content during garden maintenance provided by this invention.

[0024] For example, such as Figure 1 The diagram shown is a schematic representation of the architecture of a soil moisture content measurement system (hereinafter referred to as the moisture content measurement system) for garden maintenance, provided by an embodiment of the present invention. The moisture content measurement system 10 includes: a data acquisition module 11, an anomaly analysis module 12, a recovery assessment module 13, an interference quantification module 14, and a moisture content calculation module 15. The modules are described below in sequence: (1) Data acquisition module 11.

[0025] The data acquisition module 11 is responsible for periodically collecting and aggregating multi-source, synchronous soil environmental monitoring data from the sensor network deployed at various monitoring points in the garden, providing a complete and consistent raw data foundation for subsequent moisture content analysis and correction.

[0026] Optionally, the data acquisition module 11 is used to acquire monitoring data from multiple monitoring points in the garden; wherein the monitoring data of each monitoring point includes the measured values ​​of multiple monitoring indicators collected over time.

[0027] Specifically, the data acquisition module 11 can collect dielectric constant, conductivity, soil temperature and pH value through physical devices such as capacitive soil moisture sensors, soil conductivity sensors, temperature sensors and pH sensors deployed at each monitoring point.

[0028] For example, the data acquisition module 11 also includes a wireless communication unit (such as a LoRa or NB-IoT module) and an embedded preprocessing unit, used to collect data from each sensor at fixed intervals (such as every 10 minutes), perform timestamp alignment and filtering to remove noise, and form a structured monitoring data sequence. The processed data is transmitted to the anomaly analysis module 12 in real time to start the analysis process.

[0029] (2) Anomaly analysis module 12.

[0030] The anomaly analysis module 12 is responsible for receiving monitoring data from the data acquisition module 11 and performing core anomaly pattern recognition. It can accurately locate the time period in the time series data where multiple monitoring indicators simultaneously fluctuate abnormally due to external factors such as fertilization and irrigation, i.e., the coordinated anomaly period, and quantify the degree of anomaly in that period.

[0031] Optionally, the anomaly analysis module 12 is used to determine the coordinated anomaly period of each monitoring point based on the monitoring data of each monitoring point. The coordinated anomaly period is a continuous time period in which the measured values ​​of multiple monitoring indicators deviate from their respective historical normal fluctuation ranges.

[0032] For example, such as Figure 2 As shown, to achieve high-precision anomaly identification, the anomaly analysis module 12 can be divided into an index calculation submodule 121 and a time period identification submodule 122, which will be described below: (2.1) Index calculation submodule 121.

[0033] Optionally, the index calculation submodule 121 is used to calculate the collaborative anomaly index of each monitoring point at each time point based on the monitoring data of each monitoring point.

[0034] Specifically, the index calculation submodule 121 first establishes a normal fluctuation range model for each monitored indicator (such as conductivity) based on historical data (such as the past three months); for new data points, it calculates the deviation of each individual indicator; finally, it calculates the coordinated anomaly index by combining the number of indicators with deviations exceeding the threshold with the average deviation of all indicators. This index is transmitted in real time to the time period identification submodule 122.

[0035] (2.2) Time period identification submodule 122.

[0036] Optionally, the time period identification submodule 122 is used to identify the time period in which the coordination anomaly index is continuously higher than the first preset threshold as a coordination anomaly time period.

[0037] Specifically, the time period identification submodule 122 receives the exponential sequence from the exponential calculation submodule 121, and identifies the start and end times of the continuous exponential exceedance through sliding window comparison logic, thereby marking the period of coordinated anomaly. The identified time period information will be simultaneously output to the recovery assessment module 13 and the interference quantification module 14 as the time frame for their analysis.

[0038] The coordinated abnormal time periods and corresponding coordinated abnormal indices of each monitoring point output by the anomaly analysis module 12 are key inputs for subsequent calculations by the recovery assessment module 13 and the interference quantification module 14.

[0039] (3) Recovery assessment module 13.

[0040] The recovery assessment module 13 is responsible for evaluating the ability of the soil at each monitoring point to recover to normal from the disturbance for each coordinated anomaly period identified by the anomaly analysis module 12, i.e., the recovery rate. The strength of the recovery ability directly reflects the duration of the impact of the external disturbance.

[0041] Optionally, the recovery assessment module 13 is used to determine the state recovery rate of each monitoring point based on the monitoring data of each monitoring point during the period of coordinated abnormality; wherein, the state recovery rate is used to characterize the rate at which the monitoring indicators recover to the historical normal fluctuation range after the period of coordinated abnormality ends.

[0042] Specifically, the recovery assessment module 13 first determines the end time of a coordinated anomaly period. Then, after the end time, the recovery assessment module 13 iterates through subsequent monitoring data to find the moment when all indicators at the monitoring points first fully recover to their respective historical normal fluctuation ranges; this moment is recorded as the recovery moment. Next, the recovery assessment module 13 obtains the coordinated anomaly index corresponding to the end time and the recovery moment from the anomaly analysis module 12. Finally, the recovery assessment module 13 calculates a quantified state recovery rate based on the time interval between the end time and the recovery moment, and the ratio of the coordinated anomaly index at these two moments (usually the index is higher at the end time, and the index at the recovery moment is closer to the normal value). The larger this rate value, the faster the soil recovers from this disturbance.

[0043] The state recovery rate calculated by the recovery evaluation module 13 is sent to the interference quantization module 14 as an important correction parameter for evaluating the degree of interference in the dielectric constant measurement.

[0044] (4) Interference quantization module 14.

[0045] The interference quantification module 14 is responsible for comprehensively analyzing the changes in the correlation between time-series anomaly characteristics and indicators, accurately quantifying the degree of external interference on the dielectric constant measurement value of each monitoring point during the coordinated anomaly period, and outputting a dielectric constant interference value.

[0046] Optionally, the interference quantization module 14 is used to determine the interference value of the dielectric constant of each monitoring point during the coordinated abnormal period based on the coordinated abnormal period, the state recovery rate, the correlation between each monitoring indicator during the coordinated abnormal period, and the correlation between each monitoring indicator during the non-coordinated abnormal period.

[0047] For example, such as Figure 3 As shown, the interference quantification module 14 can be divided into a correlation analysis submodule 141 and a comprehensive quantization submodule 142, to handle correlation calculation and final quantization respectively. These will be described in detail below: (4.1) Correlation analysis submodule 141.

[0048] Optionally, the correlation analysis submodule 141 is used to calculate the correlation differences of monitoring indicators at different time periods.

[0049] Specifically, the correlation analysis submodule 141 first extracts the multi-indicator time series sequences of the monitoring point from the historical data of the data acquisition module 11, specifically during historical periods of coordinated anomalies and during other normal (non-coordinated anomalies) periods. Then, the correlation analysis submodule 141 applies a preset correlation analysis algorithm (such as calculating the Pearson correlation coefficient between all pairs of indicators) to these two sets of sequences, thereby obtaining the first comprehensive correlation (during anomaly periods) and the second comprehensive correlation (during normal periods). The correlation analysis submodule 141 calculates the absolute difference between the first and second comprehensive correlations, which reflects the degree to which external interference has altered the correlation pattern between indicators.

[0050] (4.2) Comprehensive Quantification Submodule 142.

[0051] Optionally, the integrated quantization submodule 142 is used to integrate multiple parameters to determine the final disturbed value.

[0052] Specifically, the comprehensive quantization submodule 142 receives correlation difference values ​​from the correlation analysis submodule 141, a co-anomaly index from the anomaly analysis module 12, and a state recovery rate from the recovery evaluation module 13. The comprehensive quantization submodule 142 performs calculations on these input parameters according to preset fusion rules (e.g., a combination of higher correlation difference, higher co-anomaly index, and lower state recovery rate corresponds to a larger output value), ultimately generating a scalar value, namely, the dielectric constant disturbance value. This value intuitively expresses the severity of distortion of the dielectric constant measurement result at the current moment due to external factors.

[0053] The interference-affected dielectric constant values ​​of each monitoring point output by the interference quantification module 14 are the direct basis for the spatial analysis and parameter correction of the water content calculation module 15.

[0054] (5) Moisture content calculation module 15.

[0055] The moisture content calculation module 15 is the final calculation and output unit of the system. It is responsible for introducing spatial dimension analysis, dynamically correcting the moisture content calculation model according to the interference of each point in the region, and finally outputting accurate soil moisture content results.

[0056] Optionally, the moisture content calculation module 15 is used to determine the soil moisture content of the garden based on the interference value of the dielectric constant and the spatial relationship between multiple monitoring points.

[0057] Specifically, the water content calculation module 15 first performs spatial clustering analysis: it calculates the "spatial interference correlation" between every two monitoring points based on spatial distance and the proximity of their dielectric constant disturbance values, and aggregates points with high correlation and adjacent locations into different spatial interference regions. Next, for each monitoring point, the water content calculation module 15 analyzes the cumulative and decay trends of historical dielectric constant disturbance values ​​for all points within its spatial interference region, and, combined with the current dielectric constant anomaly level of that point, calculates a parameter correction factor specific to that point. Then, the water content calculation module 15 uses this parameter correction factor to dynamically adjust the constant parameters in the standard model for calculating water content based on dielectric constant, to compensate for systematic deviations caused by external interference. Finally, the water content calculation module 15 substitutes the real-time dielectric constant measurements collected from each monitoring point into the corrected model to calculate the final, more accurate volumetric water content value.

[0058] The moisture content calculation module 15 not only outputs and stores the moisture content values ​​at each point, but also visualizes the divided spatial interference areas, providing intuitive decision support for garden maintenance personnel.

[0059] The above describes the soil moisture content measurement system 10 and its modules used in garden maintenance.

[0060] For example, such as Figure 4 The diagram shown is a flowchart illustrating a method for determining soil moisture content during garden maintenance according to an embodiment of the present invention, comprising the following steps: S401. Acquire monitoring data from multiple monitoring points in the garden. The monitoring data for each monitoring point includes measured values ​​of multiple monitoring indicators collected over time.

[0061] For example, this step can be performed by the data acquisition module 11 described above, and specifically includes the following steps: (1) Deployment of multi-sensor networks and synchronous data acquisition.

[0062] In this step, the data acquisition module 11 utilizes sensor arrays deployed at various monitoring points within the garden. These sensor arrays include a capacitive soil moisture sensor for measuring dielectric constant, a conductivity sensor for measuring soil conductivity, a temperature sensor, and a pH sensor. Corresponding to the aforementioned sensor types, multiple monitoring indicators include: dielectric constant, soil conductivity, soil temperature, and soil pH. It should be noted that the monitoring points are strategically placed based on the garden's topography, soil texture, and irrigation zones. A gridded or stratified sampling method is employed to ensure uniform spatial coverage and representativeness. The sensor arrays are deployed at a uniform depth (e.g., the active layer of the plant's main root system) at each monitoring point.

[0063] For example, each sensor acquires data synchronously at fixed time intervals (e.g., every 10 minutes) to ensure that all monitored indicators are measured at the same timestamp.

[0064] (2) Data transmission and preliminary processing.

[0065] Optionally, each monitoring point transmits its raw measurements, including location identifiers and timestamps, to the data acquisition module 11 via a wireless communication unit. The preprocessing unit within the data acquisition module 11 aligns, filters, and denoises the raw data, forming a structured, continuous monitoring data sequence, providing a high-quality data foundation for subsequent analysis.

[0066] S402. Based on the monitoring data of each monitoring point, determine the coordinated abnormal period for each monitoring point. The coordinated abnormal period is a continuous time when the measured values ​​of multiple monitoring indicators simultaneously deviate from their respective historical normal fluctuation ranges.

[0067] For example, this step can be performed by the anomaly analysis module 12 described above, specifically including: the anomaly analysis module 12 establishes a historical normal fluctuation range model for each monitoring indicator based on the historical monitoring data (such as the past three months) of each monitoring point. For real-time data, the module first calculates the deviation of the current measured value of each indicator from its historical normal fluctuation range, then comprehensively counts the number of indicators whose deviation exceeds a preset threshold, and calculates the average deviation of all indicators. Finally, a coordinated anomaly index representing the overall anomaly level at the current moment is obtained through weighted fusion. By continuously monitoring this index, continuous time periods with index values ​​consistently higher than the first preset threshold are identified as coordinated anomaly periods. The identified time period information is synchronously provided to the recovery assessment module 13 and the interference quantification module 14. It should be noted that the specific process for determining the coordinated anomaly period of each monitoring point can be found in S501-S502 below, and will not be repeated here.

[0068] In another possible implementation, the anomaly analysis module 12 can also employ a method based on mutation point detection and time window aggregation when determining the collaborative anomaly period for each monitoring point. This method first uses a mutation point detection algorithm to identify mutation points in the time series of a single indicator; then, it statistically analyzes the time points where multiple indicators simultaneously exhibit mutation points within a sliding time window; finally, it marks the continuous intervals where these time points appear densely as collaborative anomaly periods. This method does not rely on statistical modeling of historical fluctuation ranges, makes fewer assumptions about data distribution, and is suitable for scenarios in the early stages of monitoring or with a short data history.

[0069] Alternatively, the anomaly analysis module 12 can also employ a method combining prediction residuals: first, a time-series prediction model is trained for each monitoring indicator to predict the current value based on historical data; then, the residual between the predicted value and the actual measured value is calculated; finally, by analyzing the joint distribution of the residual sequences of multiple indicators, periods in which the joint probability of residuals is consistently below a certain threshold are identified as collaborative anomaly periods. This method can better capture abnormal changes in the correlation between indicators.

[0070] Therefore, by quantifying the degree to which multiple indicators deviate from the normal pattern simultaneously, the anomaly analysis module 12 can accurately locate the time period corresponding to the comprehensive disturbance event caused by external factors such as fertilization and irrigation from the continuous monitoring data stream.

[0071] S403. Based on the monitoring data of each monitoring point during the period of coordinated anomaly, determine the state recovery rate of each monitoring point. The state recovery rate characterizes the rate at which the monitoring indicators recover to their historical normal fluctuation range after the period of coordinated anomaly ends.

[0072] For example, this step can be performed by the recovery assessment module 13 described above, specifically including: For each coordinated abnormal period identified by the anomaly analysis module 12, the recovery assessment module 13 first locates the end time of that period. Then, the module searches for and determines a recovery time in the monitoring data after the end time. This recovery time must satisfy the condition that, from that time onwards, all the measured values ​​of the corresponding monitoring indicators at the monitoring point have for the first time fully recovered to their respective historical normal fluctuation ranges. Next, the recovery assessment module 13 obtains the coordinated abnormality index corresponding to the end time and recovery time of the coordinated abnormal period from the anomaly analysis module 12. Finally, the module calculates a quantified state recovery rate based on the time interval between the end time and the recovery time, and the relative relationship between the coordinated abnormality indices at these two times. The larger the state recovery rate value, the faster the soil recovers from this abnormal disturbance, and the stronger its recovery ability. It should be noted that the specific process for determining the state recovery rate of each monitoring point is described in S601-S602 below, and will not be repeated here.

[0073] In another possible implementation, the recovery assessment module 13 may also use a curve fitting-based approach when determining the state recovery rate: the change process of the cooperative anomaly index after the end of the cooperative anomaly period is fitted into a decay curve model, and the initial decay rate of the decay curve is used as the state recovery rate.

[0074] In another possible implementation, the recovery assessment module 13 can also use a weighted assessment method based on sub-indicators when determining the state recovery rate: considering that different monitoring indicators may have different responses and recovery rates to disturbances, an independent recovery rate is first calculated for each indicator, and then weighted according to the degree of deviation of each indicator during the abnormal period or its importance to the calculation of water content, to obtain the overall state recovery rate. This method takes into account the recovery differences of different soil physicochemical properties in more detail.

[0075] Therefore, the recovery assessment module 13 quantifies the speed at which soil returns to normal from an abnormal state, and can effectively assess the buffering and self-regulating capacity of different soil textures or structures to external disturbances, providing key parameters for judging the persistent impact of disturbances.

[0076] S404. For each monitoring point, the disturbance value of the dielectric constant of each monitoring point during the coordinated abnormal period is determined based on the coordinated abnormal period, the state recovery rate, the correlation between each monitoring indicator during the coordinated abnormal period, and the correlation between each monitoring indicator during the non-coordinated abnormal period.

[0077] For example, this step can be performed by the interference quantification module 14 described above, specifically including: the interference quantification module 14 first extracts the monitoring data sequences of each monitoring indicator within the target coordinated abnormal period, and calculates the first correlation between each pair of these sequences. Simultaneously, the module extracts the monitoring data sequences of the monitoring point in the non-coordinated abnormal period (i.e., normal state) from historical data, and calculates the corresponding second correlation. Next, the module obtains the coordinated abnormality index (or its characteristic value) corresponding to the coordinated abnormal period and the state recovery rate calculated by the recovery assessment module 13. Finally, the interference quantification module 14 calculates, based on the difference between the first and second correlations, the coordinated abnormality index, and the state recovery rate, using a preset data fusion rule, and outputs a quantified value characterizing the degree of interference of the dielectric constant measurement value of the monitoring point with external factors during this period, i.e., the dielectric constant interference value. It should be noted that the specific process for determining the dielectric constant interference value of each monitoring point during the coordinated abnormal period can be found in S701-S703 below, and will not be repeated here.

[0078] In another possible implementation, the interference quantification module 14 can also use a method based on the change in contribution rate of principal component analysis when determining the interference value of the dielectric constant of each monitoring point during the period of coordinated abnormality. This method performs principal component analysis on the multi-indicator data of the abnormal period and the normal period respectively. By comparing the change in the proportion of total variance explained by the first principal component (i.e., contribution rate) in the two periods, the degree of variation of the overall correlation structure between indicators is measured, and this degree of variation is used as one of the key inputs for calculating the interference value.

[0079] Alternatively, the interference quantification module 14 can also introduce a mutual information measurement method. This method uses mutual information to quantify the nonlinear statistical dependence between monitoring indicators during abnormal and normal periods. By comparing the differences in average mutual information, it captures changes in correlation patterns and then participates in the calculation of the interference value.

[0080] Therefore, by comprehensively analyzing the variation of anomaly intensity, recovery dynamics, and correlation patterns among multiple indicators before and after the anomaly, the disturbance quantification module 14 can comprehensively and quantitatively evaluate the complexity of the impact of dielectric constant measurement on a specific disturbance event, and the result is passed to the final water content calculation module as the core input.

[0081] S405. Determine the soil moisture content of the garden based on the interference value of the dielectric constant and the spatial relationship between multiple monitoring points.

[0082] For example, this step can be performed by the moisture content calculation module 15 described above, specifically including: the moisture content calculation module 15 first calculates the spatial interference correlation between every two monitoring points based on the current dielectric constant interference value and their geographical coordinates of all monitoring points. This correlation considers both the proximity of spatial distance and the similarity of interference levels. Subsequently, based on the calculated spatial interference correlation, the module clusters monitoring points with correlation values ​​higher than a preset threshold and spatially adjacent into different spatial interference regions. Next, for each monitoring point, the module analyzes the accumulation and trend of interference in the region based on the historical dielectric constant interference values ​​of each monitoring point within its spatial interference region, and determines a parameter correction factor for that point by combining the current dielectric constant anomaly level of that point. Finally, the module uses this parameter correction factor to personalize the parameters in the preset soil moisture content calculation model, and combines the corrected model with the real-time collected dielectric constant measurement values ​​to calculate and output the accurate soil moisture content of each monitoring point, thereby determining the soil moisture status of the entire garden. It should be noted that the specific process for determining the soil moisture content of the garden can be found in S801-S804 below, and will not be repeated here.

[0083] In another possible implementation, the moisture content calculation module 15 can also use a method based on spatial interpolation to generate a continuous correction field when determining the soil moisture content of the garden. This method first uses the disturbance values ​​of the dielectric constant of all monitoring points to generate a continuous disturbance distribution surface covering the entire garden area through a spatial interpolation algorithm. Then, based on the disturbance value interpolated at each geographical location, the correction amount of the moisture content calculation model parameters corresponding to that location is directly obtained through a predefined lookup table or function mapping, thereby achieving seamless correction in continuous space.

[0084] Alternatively, the moisture content calculation module 15 can also use a regional mean correction method. This method calculates the average parameter correction factor for all monitoring points within each defined spatial disturbance area, and then applies this average correction factor uniformly to all points within the area to correct the moisture content calculation model. This method simplifies the calculation and is suitable for scenarios where the soil properties and disturbance conditions within the area are relatively homogeneous.

[0085] Therefore, the water content calculation module 15 identifies the spatial distribution pattern and aggregation effect of external disturbances in garden soil by introducing spatial clustering analysis, and performs localized and differentiated dynamic parameter correction for water content calculation accordingly. Ultimately, it effectively overcomes the systematic errors caused by local fertilization, irrigation and other operations and soil spatial heterogeneity to capacitance method measurement.

[0086] Based on the above technical solutions, this invention reliably captures complex disturbance events caused by external factors such as fertilization and irrigation by detecting synergistic anomalies in multiple indicators, providing accurate time anchors for subsequent analysis. Secondly, by evaluating the rate of soil recovery from anomalies, the resistance and recovery capabilities of different soil textures to disturbances are quantified, providing a basis for judging the persistent impact of disturbances. Furthermore, by comparing the differences in correlations between multiple indicators under abnormal and normal conditions, and combining anomaly intensity and recovery capability, a refined and quantitative assessment of the degree of disturbance to dielectric constant measurements is achieved. Finally, by analyzing the spatial aggregation and diffusion patterns of disturbed values, dynamic parameter corrections are made to the moisture content calculation model according to local conditions, thereby significantly improving the accuracy and reliability of soil moisture content detection results based on the capacitance method in complex actual landscape maintenance environments.

[0087] For example, in combination Figure 4 ,like Figure 5 The diagram shown is a flowchart illustrating another method for determining soil moisture content during garden maintenance, provided by an embodiment of the present invention. In this method, based on monitoring data from each monitoring point, the coordinated abnormal time period for each monitoring point is determined, specifically including the following steps: S501. Based on the monitoring data of each monitoring point, calculate the coordinated anomaly index of each monitoring point at each time point. The coordinated anomaly index characterizes the degree to which the measured values ​​of multiple monitoring indicators simultaneously deviate from their respective historical normal fluctuation ranges.

[0088] For example, this step can be performed by the index calculation submodule 121 in the anomaly analysis module 12, and specifically includes the following steps: (1) For each monitoring indicator, compare the current measurement value with the historical normal fluctuation range to determine the single indicator deviation of the monitoring indicator at the current time.

[0089] Among them, the historical normal fluctuation range is a statistical measure that defines the normal fluctuation range of a certain indicator when there is no significant external interference. The specific methods for determining it include, but are not limited to, the mean of historical monitoring values. with standard deviation Set a fixed threshold, such as [ , ]; or combine the mean of the first differences of historical monitoring values. A dynamic threshold model is constructed. This embodiment adopts the latter to better adapt to the time-series fluctuation characteristics of the indicator.

[0090] Specifically, the index calculation submodule 121 pre-establishes a historical normal fluctuation range model for each monitoring indicator based on monitoring data within a preset historical time period (e.g., the past three months). The core of this model is to calculate the average monitoring value of the indicator across all historical periods. and the mean of the first difference of its monitored values. .

[0091] Furthermore, for monitoring index k at monitoring point i, at any current calculation time t, the single-index deviation of this index is... Calculated using the following formula: In the above formula, This represents the measured value of monitoring indicator k at time t; This represents the average monitoring value of monitoring indicator k across all historical time points; This represents the first difference value of the monitoring indicator k at time t, i.e. = ; This represents the mean of the first-order differences of the monitoring indicator k over all historical moments; This represents an adjustment factor, which is a very small positive number, such as 10 to the power of negative 5, used to prevent the denominator from being zero and to ensure the numerical stability of the formula.

[0092] It should be noted that the numerator of the above formula combines the instantaneous fluctuation amplitude with the degree of deviation of the current value from the historical average; the denominator serves as the benchmark for the historical average fluctuation. When the instantaneous fluctuation... The larger the value, and the more the current value deviates from the historical average. The larger the value, the higher the calculated deviation of the single index. The larger the value, the higher the probability that the indicator will experience abnormal fluctuations at time t.

[0093] After this, the calculated single-index deviation will be... Normalize to the (0,1) interval.

[0094] (2) Obtain the number of monitoring indicators whose single indicator deviation exceeds the second preset threshold at the current time, and determine the collaborative anomaly index by combining the average value of the single indicator deviation of all monitoring indicators at the current time.

[0095] Specifically, the index calculation submodule 121 calculates the single-index deviation of all monitored indicators at time t. Then, first, statistics. The number of monitoring indicators whose values ​​exceed a second preset threshold is denoted as . For example, the second preset threshold can be set to 0.5. The rule for setting the value is: the closer the normalized deviation is to 1, the greater the probability of an anomaly. Therefore, setting the second preset threshold to 0.5 means that when the normalized deviation of an indicator exceeds 0.5, the indicator is considered to have deviated significantly at the current moment, that is, its probability of an anomaly has exceeded the medium level and can be marked as an anomaly indicator.

[0096] Simultaneously, calculate the single-indicator deviation of all monitoring indicators at time t. The arithmetic mean, denoted as Then, the collaborative anomaly index of each monitoring point at time t is calculated using the following formula. : In the above formula, This represents the number of monitoring indicators whose deviation exceeds the second preset threshold at time t. This represents the total number of monitoring indicators at the monitoring points, and is a positive integer greater than zero. This represents the deviation of all monitored indicators at time t. The arithmetic mean.

[0097] It should be noted that the fractional terms in the above formula... It reflects the proportion of indicators that are significantly abnormal at time t. The higher the proportion, the greater the possibility that multiple indicators are abnormal at the same time. This reflects the overall average level of deviation among all monitored indicators. The synergistic anomaly index is obtained by multiplying the two. It can simultaneously take into account both the number of indicators that show significant anomalies and the overall level of deviation of all indicators, thus comprehensively characterizing the overall degree to which multiple monitoring indicators deviate from their respective historical normal fluctuation ranges at time t. The larger the value, the higher the probability that there is a comprehensive abnormal disturbance caused by external factors affecting multiple indicators at that moment.

[0098] Finally, the index calculation submodule 121 performs the above calculation for each monitoring point at each preset calculation time t (e.g., every minute or every data acquisition cycle), thereby generating a time-ordered sequence of collaborative anomaly indexes for each monitoring point { }

[0099] S502. Identify the time period in which the coordination anomaly index is continuously higher than the first preset threshold as a coordination anomaly period.

[0100] For example, this step can be performed by the time period identification submodule 122 in the anomaly analysis module 12.

[0101] Specifically, the time period identification submodule 122 receives the cooperative anomaly index sequence from the index calculation submodule 121 { } Furthermore, the time period identification submodule 122 sets a first preset threshold. The first preset threshold is used to determine whether the coordination anomaly index is high enough to identify a coordination anomaly. For example, the first preset threshold can be set to the monitoring point's index at all historical points in time (e.g., the past three months). The value is K times the average value, where K is a coefficient greater than 1, for example, 1.5. The rule for its value is: the first preset threshold must be significantly higher than the historical normal level of the collaborative anomaly index of the monitoring point, so as to screen out truly prominent and significant abnormal events and avoid misjudging slight fluctuations as abnormalities.

[0102] Furthermore, the time period recognition submodule 122 executes the following process: when a time period is detected... When the value first exceeds the first preset threshold, that moment is recorded as the starting point of the suspected abnormal period. Subsequently, monitoring continues at subsequent moments. It's worth it, as long as If the value remains consistently above the first preset threshold, the abnormal state is considered to be ongoing. When this is detected... When the value first falls below the first preset threshold, the previous moment is recorded as the end point of the suspected abnormal period. The continuous time period between this start and end point is formally identified as a coordinated abnormal period. If... If the threshold is lower than the first preset threshold and then exceeds the first preset threshold again, the next new period of coordinated anomaly is identified. This process iterates through the entire monitoring period and finally outputs a list of all identified periods of coordinated anomaly for that monitoring point.

[0103] Based on the above technical solution, this invention first quantifies the instantaneous abnormal deviation of each indicator, then calculates a synergistic anomaly index by combining the proportion of abnormal indicators with the average deviation intensity, and finally determines the time period based on the duration of the index threshold. This achieves accurate and automated identification of complex soil disturbance events with multi-indicator responses caused by external factors such as fertilization and irrigation. Therefore, it provides a reliable time anchor and quantitative basis for subsequent assessment of soil recovery capacity and quantification of the degree of disturbance to the dielectric constant.

[0104] For example, in combination Figure 4 ,like Figure 6 The diagram shown is a flowchart illustrating another method for determining soil moisture content during garden maintenance, provided by an embodiment of the present invention. In this method, the recovery rate of each monitoring point is determined based on monitoring data from each monitoring point during a period of coordinated anomaly. Specifically, the method includes the following steps: S601. Obtain the collaborative anomaly index corresponding to the end time of the collaborative anomaly period and the collaborative anomaly index corresponding to the recovery time. The recovery time is the moment after the end time when the measured values ​​of multiple monitoring indicators first all return to their respective historical normal fluctuation ranges.

[0105] In this step, the recovery assessment module 13 directly obtains the end time of the time period from the collaborative anomaly time period information provided by the anomaly analysis module 12, and denotes it as... and simultaneously obtain the Cooperative anomaly index corresponding to time moment This index, calculated using the method described in S501 above, represents the overall degree of abnormality of each indicator at the monitoring point at the moment the abnormal period ends.

[0106] Following this, the recovery assessment module 13 is in After a certain point, subsequent monitoring data for that monitoring point are scanned in chronological order. The goal is to find a recovery point. At this moment, the following condition must be met: From that moment onward, for the first time, the measured values ​​of all monitoring indicators at this monitoring point remained consistently within their respective historical normal fluctuation ranges. This means that, At that time, the multi-indicator synergistic anomaly caused by external disturbances such as fertilization and irrigation had completely subsided, and soil environmental indicators had returned to a stable normal fluctuation range. Recovery assessment module 13, upon determining... Then, the same information is obtained from the anomaly analysis module 12. Cooperative anomaly index corresponding to time moment Ideally, when all indicators return to normal, It should approach zero or a very small value.

[0107] S602. Determine the state recovery rate based on the duration between the end time and the recovery time, and the co-abnormality index between the end time and the recovery time.

[0108] Following S601, the recovery assessment module 13 first calculates the duration T of the abnormal state fading. - .

[0109] Secondly, the recovery assessment module 13 calculates the rate of decrease of the collaborative anomaly index from the end time to the recovery time. To more robustly measure the magnitude of the decrease, an anomaly decrease index g is introduced, whose calculation formula is as follows: In the above formula, Indicates the end time of the collaborative anomaly period. The corresponding collaborative anomaly index; Indicates the recovery time The corresponding collaborative anomaly index; This represents an adjustment factor, which is a very small positive number, such as 10 to the power of negative 5, used to prevent the denominator from being zero and to ensure the numerical stability of the formula.

[0110] Understandably, the g-value represents the decay factor of the co-anomaly index from the end of the anomaly to the point of complete recovery. The larger (the more severe the abnormality at the end) and The smaller the value (the more thorough the recovery), the larger the g value, indicating a greater drop from the abnormal peak to the normal level and a more significant recovery process.

[0111] Furthermore, the recovery assessment module 13 combines the duration T and the abnormal decline index g to calculate the state recovery rate R using the following formula. g / T. It should be noted that the recovery rate R combines the depth of recovery (represented by g) and the "speed" of recovery (represented by 1 / T). A larger R value means that after experiencing this anomalous disturbance, the soil's various indicators not only decreased significantly from a high anomalous level (large g), but also completed this recovery process in a shorter time (small T). This indicates that the soil at the monitoring point has strong resistance to external disturbances and a rapid self-recovery ability. Conversely, a smaller R value means slow or incomplete recovery, and the soil is more susceptible to continuous disturbances.

[0112] Based on the above technical solution, this invention calculates the recovery rate by quantifying the time required for complete recovery from the end of an anomaly and the decay rate of the anomaly index. This rate objectively characterizes the differences in the buffering and self-regulating capabilities of soil at different monitoring points to external disturbances (such as fertilization). Points with strong recovery capabilities show that their dielectric constant measurements quickly return to the true value after a brief disturbance, having a smaller impact on the final moisture content calculation; while points with weak recovery capabilities show that the measured values ​​are affected by the disturbance for a longer duration and with a deeper impact, requiring focused correction in subsequent steps. Therefore, this provides key parameters for assessing the persistent impact of disturbances and achieving accurate moisture content correction.

[0113] For example, in combination Figure 4 ,like Figure 7 The diagram shown is a flowchart illustrating another method for determining soil moisture content during garden maintenance, provided by an embodiment of the present invention. In this method, for each monitoring point, the dielectric constant disturbance value during the period of coordinated anomaly is determined based on the coordinated anomaly period, the state recovery rate, the correlation between monitoring indicators during the coordinated anomaly period, and the correlation between monitoring indicators during the non-coordinated anomaly period. The method specifically includes the following steps: S701. Calculate the first correlation between each monitoring indicator at each monitoring point during the period of coordinated anomaly.

[0114] Optionally, this step can be performed by the correlation analysis submodule 141 in the interference quantification module 14. Specifically, the correlation analysis submodule 141 targets a given period of coordinated anomalies (whose time range is...). , (At the start time), extract the monitoring values ​​of all monitoring indicators (such as dielectric constant, conductivity, temperature, and pH value) within this period from the historical monitoring data sequence of the monitoring point, and arrange them in chronological order to form a multi-indicator time series of a coordinated abnormal period.

[0115] Subsequently, the correlation analysis submodule 141 uses a preset correlation analysis algorithm (e.g., Pearson correlation coefficient method) to calculate the correlation coefficient between the monitoring value sequences of any two different monitoring indicators (e.g., indicator p and indicator q) in the sequence. The subscript "abnormal" indicates a period of coordinated abnormality, and the superscript "abnormal" indicates a period of coordinated abnormality. Specifically, this refers to the p-th and q-th monitoring indicators. The above calculations are performed on all indicators in pairs to obtain a set of correlation coefficients. Finally, the correlation analysis submodule 141 synthesizes these pairwise correlation coefficients and calculates their arithmetic mean to obtain the first comprehensive correlation degree, which characterizes the overall correlation strength among the monitoring indicators at this monitoring point during this period of coordinated anomaly. This is denoted as... This value reflects the synchronicity or correlation pattern of changes in various soil environmental indicators under the influence of external disturbances.

[0116] S702. Calculate the second correlation between each monitoring indicator at each monitoring point during the historical non-coordinated abnormal period.

[0117] Optionally, this step can be performed by the correlation analysis submodule 141 in the interference quantification module 14. Specifically, the correlation analysis submodule 141 filters out all normal time period data that are not marked as coordinated abnormal time periods from the historical monitoring data of the monitoring point. The monitoring values ​​of all monitoring indicators within these normal time periods are arranged in chronological order to form a multi-indicator time series of normal time periods.

[0118] Subsequently, using the same pre-set correlation analysis algorithm as S701, the correlation coefficient between the monitoring value sequences of any two different monitoring indicators in the multi-indicator time series during the normal period was calculated. The subscript "normal" represents the normal time period. After calculating the correlation coefficients for each pair of all indicators, the resulting set of correlation coefficients is combined, and their arithmetic mean is calculated to obtain the second comprehensive correlation, which characterizes the inherent overall correlation strength among the monitoring indicators at the monitoring point under normal conditions. This is denoted as . This value reflects the background correlation level among various soil indicators due to natural physicochemical processes in the absence of significant external disturbances.

[0119] S703. Determine the disturbance value of the dielectric constant based on the first correlation, the second correlation, the cooperative anomaly index, and the state recovery rate.

[0120] Optionally, this step can be performed by the comprehensive quantization submodule 142 in the interference quantization module 14.

[0121] Specifically, the comprehensive quantification submodule 142 receives the first comprehensive correlation from the correlation analysis submodule 141. Second comprehensive correlation The absolute difference between the correlation between normal and abnormal periods is calculated using the state recovery rate R corresponding to the co-abnormal period from the recovery assessment module 13 (the calculation method is shown in S602), as the correlation pattern variability. Simultaneously, the average value of the coordination anomaly index at all times within the coordination anomaly period is obtained and denoted as . .

[0122] The difference value 'c' quantifies the degree to which external disturbances alter the correlation patterns between monitoring indicators compared to the normal background state. A larger 'c' value indicates a more significant distortion of the original relationship between indicators by the disturbance.

[0123] Furthermore, the comprehensive quantization submodule 142 calculates the disturbance value U of the dielectric constant of the monitoring point during this coordinated anomaly period based on the correlation mode variability c and the state recovery rate R, using the following formula: In the above formula, This represents an adjustment factor, which is a very small positive number, such as 10 to the power of negative 5, used to prevent the denominator from being zero and to ensure the numerical stability of the formula.

[0124] It should be noted that the calculation logic of the above formula is as follows: the dielectric constant is affected by the disturbance value U, the correlation mode variability c, and the anomaly intensity. The product of c and c is directly proportional and inversely proportional to the state recovery rate R. This means that when an anomalous disturbance not only causes a significant change in the correlation pattern between indicators (c is large), but also has a high anomalous intensity (c is large), the anomalous disturbance is more likely to occur. When the soil's recovery capacity is low (R is small), the calculated disturbance value U is the largest, indicating that the dielectric constant measurement was most severely distorted in this event.

[0125] Based on the above technical solution, this invention comprehensively assesses the severity of external interference affecting dielectric constant measurements by quantifying the differences in correlation patterns between multiple monitoring indicators during abnormal and normal periods (correlation pattern variability) and combining this with the speed of soil self-recovery from anomalies (state recovery rate). This method not only considers the instantaneous anomaly intensity caused by interference but also captures the complexity of the interference through correlation pattern changes and assesses the persistence of the interference through recovery capability. This achieves a refined and dynamic assessment of the reliability of dielectric constant measurements, providing accurate and quantitative core inputs for subsequent spatial analysis and water content calculation correction.

[0126] For example, in combination Figure 4 ,like Figure 8 The diagram shown is a flowchart illustrating another method for determining soil moisture content during garden maintenance, provided by an embodiment of the present invention. In this method, the soil moisture content of the garden is determined based on the interference value of the dielectric constant and the spatial location of multiple monitoring points. Specifically, the method includes the following steps: S801. Calculate the spatial interference correlation degree between every two monitoring points based on the interference value of the dielectric constant and the spatial location of multiple monitoring points.

[0127] In this step, the water content calculation module 15 obtains the disturbance-affected dielectric constant values ​​of all monitoring points for the current moment. (Where i is the index of the monitoring point) and the spatial coordinates of each monitoring point. For any two monitoring points i and j, their spatial interference correlation degree. Calculated using the following formula: In the above formula, , These represent the disturbance values ​​of the dielectric constants of monitoring points i and j at the current moment, respectively; This represents the dimensionless Euclidean distance between monitoring point i and monitoring point j. This represents the natural exponential function, which maps the product of spatial distance and the difference between the disturbed values ​​to a correlation value between 0 and 1, which monotonically decreases as the independent variable increases.

[0128] It should be noted that spatial interference correlation It also considered the similarity of the degree of interference and the proximity of spatial distance. The closer the interference values ​​of two points (the smaller the difference) and the closer their spatial distance (...), the better. When the value is smaller, the absolute value of the product of negative values ​​within the exponential function is smaller, making... The closer the value is to 1, the stronger the spatial interference correlation between the two points, indicating they are likely affected by interference from the same or related sources. Conversely, if the two points have significantly different interference values ​​or are far apart, then... A value close to 0 indicates a weak correlation.

[0129] S802. Two monitoring points with spatial interference correlation greater than the third preset threshold and adjacent to each other are classified into the same spatial interference area.

[0130] Specifically, the moisture content calculation module 15 sets a third preset threshold, for example, 0.5. The rule for its value is as follows: this threshold is used to determine whether the spatial interference correlation between two monitoring points is strong enough to be considered part of the same interference area. An exemplary value of 0.5 means that when the correlation exceeds 0.5, the two points are considered to be significantly correlated.

[0131] Following this, the water content calculation module 15 iterates through all monitoring point pairs (i, j), and if its calculated spatial interference correlation degree... If two points are greater than a third preset threshold and are spatially adjacent, a connection is established within the module, indicating that the two points belong to the same potential region. Then, the water content calculation module 15 uses a graph connected component algorithm (e.g., using depth-first search or disjoint-set data structure) to merge all monitoring points associated through this connection into the same spatial interference region. Finally, the water content calculation module 15 outputs several spatial interference regions defined at the current time, each region containing one or more monitoring points.

[0132] It should be noted that the criterion for determining whether two monitoring points are spatially adjacent is the distance between them. The distance must be less than a preset proximity threshold. This proximity threshold can be determined based on the average spacing of the monitoring points in the garden, and is typically set to 1.5 to 2 times the average spacing. For example, if the average spacing of the monitoring points is approximately 3 meters, the threshold can be set to 5 meters.

[0133] S803. Based on the historical dielectric constant interference values ​​of each monitoring point within the spatial interference area to which each monitoring point belongs, determine the parameter correction factor for each monitoring point.

[0134] The "historical" data mentioned in this step and subsequent calculations (such as historical dielectric constant disturbance values, historical time series, etc.) refers to the corresponding parameter values ​​continuously calculated and stored by the water content measurement system 10 in previous monitoring cycles. Specifically, the water content measurement system 10 maintains a time series database for each monitoring point, storing the dielectric constant disturbance value U at each calculation moment according to timestamps, as well as parameters such as the local anomaly accumulation index v calculated from real-time data. The length of the historical period can be set according to actual needs, for example, referring to the most recent 24 hours or a predetermined number of monitoring cycles when calculating the decay trend.

[0135] For example, the moisture content calculation module 15 determines the parameter correction factor for each monitoring point based on the historical disturbance values ​​of the dielectric constant of each monitoring point within the spatial disturbance area to which each monitoring point belongs. This specifically includes the following steps: (1) Calculate the average value of the dielectric constant of each monitoring point in the spatial interference area to which the monitoring point belongs, and the average value of the dielectric constant of all monitoring points to determine the local anomaly accumulation index.

[0136] For monitoring point i, let its spatial interference area be denoted as . The module first calculates the region. The average of the disturbance-affected dielectric constant values ​​obtained from all monitoring points up to the current moment is calculated and denoted as . It should be noted that the aforementioned latest calculated value of the dielectric constant affected by interference refers to the U value calculated and updated by the water content calculation module 15 for each monitoring point based on the data from its most recent ended period of coordinated anomaly; if the monitoring point has never triggered a coordinated anomaly since monitoring began, the value is recorded as 0 or a preset background value.

[0137] Simultaneously, calculate the average value of the disturbance-affected dielectric constant obtained from the latest calculation of all monitoring points (global) up to the current moment. Then the local anomaly accumulation index of monitoring point i. Calculated using the following formula: In the above formula, Indicates the spatial interference area to which monitoring point i belongs. The average value of the latest dielectric constant of all monitoring points within the system affected by interference; This represents the global average value of the latest dielectric constant of all monitoring points affected by disturbance. This represents an adjustment factor, which is a very small positive number, such as 10 to the power of negative 5, used to prevent the denominator from being zero and to ensure the numerical stability of the formula.

[0138] Understandably, the ratio This reflects the degree of deviation of the latest disturbance level in the local area where monitoring point i is located from the global average level. If A value greater than 1 indicates that the area is a point where interference is relatively concentrated, and its level of interference is higher than the global average, requiring more correction and attention.

[0139] (2) Determine the decay trend index of the dielectric constant of the monitoring point over historical time. The decay trend index is used to characterize the degree to which the dielectric constant decreases over time due to disturbance.

[0140] For monitoring point i, the water content calculation module 15 extracts its dielectric constant disturbance value sequence over a recent historical period (e.g., the past 24 hours or several recent data acquisition cycles) { The sequence is arranged in reverse chronological order, with the most recent time point at the end. The module calculates the first-order difference sequence of this sequence. All negative values ​​(i.e. decreasing differences) are selected from the difference sequence and recorded as effective decay values.

[0141] Furthermore, let the number of effective attenuation values ​​be... The average effective attenuation value is (Because it is a decreasing decay, therefore) (If it is a negative value), then the decay trend index... Calculated using the following formula: In the above formula, This indicates the number of times the dielectric constant of monitoring point i decreases (i.e., effectively decays) due to disturbance in the historical time series; This represents the average of all effective attenuation values.

[0142] It should be noted that the decay trend index It takes into account the frequency of attenuation. and average amplitude During the observation period, the more decay times and the larger the magnitude of each decay, the better. A larger value indicates that the dielectric constant of the monitoring point is significantly and continuously decreasing due to interference, meaning the interference is dissipating rapidly. Conversely, if... A small value indicates that the interference has not been significantly reduced or continues to exist.

[0143] (3) Determine the parameter correction factor based on the degree of dielectric constant anomaly, local anomaly accumulation index and decay trend index at the current moment.

[0144] In this step, the water content calculation module 15 calculates the degree of dielectric constant anomaly at monitoring point i at the current moment. . It is obtained by comparing the current measured dielectric constant with its historical normal fluctuation range. The specific calculation method can refer to the calculation logic of single-index deviation in S501, but here it only applies to the dielectric constant. This indicates the degree to which the measured dielectric constant deviates from its historical normal range; a larger value indicates a more abnormal current dielectric constant.

[0145] Following this, the water content calculation module 15, combining the local anomaly accumulation index, the decay trend index, and the degree of dielectric constant anomaly, calculates the parameter correction factor using the following formula. : In the above formula, This indicates the degree of abnormality in the dielectric constant of monitoring point i at the current moment; This represents the cumulative index of local anomalies at monitoring point i over a historical period (e.g., the past 24 hours or several recent data collection cycles). The average value reflects the long-term tendency of disturbance accumulation in the area where the point is located; The index representing the decay trend of monitoring point i; This represents an adjustment factor, which is a very small positive number, such as 10 to the power of negative 5, used to prevent the denominator from being zero and to ensure the numerical stability of the formula.

[0146] It should be noted that the parameter correction factor With respect to the degree of anomaly in the current dielectric constant and historical local abnormal accumulation trend All showed a positive correlation with the decay trend index, while the changes were related to the decay trend index. The change shows a negative correlation. This means that when the current dielectric constant measurement value at the monitoring point is abnormally significant ( Large), and its location is historically prone to accumulating disturbances ( (Large), and at the same time, the current interference has not shown a significant weakening trend. When (small), the calculated parameter correction factor The value will increase significantly, indicating that a substantial correction is necessary to the water content calculation model to compensate for severe and persistent disturbances. Conversely, if monitoring data indicates that the disturbance is rapidly dissipating ( (Large), then even if the current dielectric constant still has some anomalies, the parameter correction factor The value of is also suppressed to a relatively low level due to the increase in the denominator, which correspondingly reduces the magnitude of the correction to the calculation model.

[0147] S804. Determine the soil moisture content of the garden based on the parameter correction factor.

[0148] For example, the moisture content calculation module 15 determines the soil moisture content of the garden according to the parameter correction factor, specifically including the following steps: (1) Using parameter correction factors, at least one constant parameter in the preset soil moisture content calculation model is corrected to obtain the corrected calculation parameters.

[0149] In this step, the soil moisture content calculation model preset by the moisture content calculation module 15 is usually a linear formula: ,in Indicates volumetric water content. The dielectric constant is represented by the measured value, and a and b are model parameters obtained through calibration.

[0150] For example, the water content calculation module 15 utilizes a parameter correction factor. The constant term parameter b is corrected using the following formula: In the above formula, This represents the corrected constant term parameters (i.e., the corrected calculation parameters); This represents a sigmoid function, used to convert... Mapping to the (0,1) interval ensures that the correction coefficient is between 0 and 1, avoiding overcorrection.

[0151] Understandably, when A value that is very large indicates severe interference requiring significant correction. Approaching 1, making Approaching 0, that is, significantly reducing the constant term; when Very small (indicating minimal interference) Approaching 0 It is close to the original value b, with almost no correction.

[0152] (2) The soil moisture content of the garden is calculated based on the corrected calculation parameters and the dielectric constant monitored in real time at each monitoring point.

[0153] In this step, for each monitoring point i, the water content calculation module 15 obtains its current real-time dielectric constant. and will With parameter a (parameter a is usually not modified) and Substitute the values ​​into the model and calculate the soil volumetric water content at that point: By performing the above calculations on all monitoring points, the soil moisture content at various locations throughout the garden can be obtained, thus determining the distribution of soil moisture content in the garden.

[0154] Based on the above technical solution, this embodiment of the invention divides the affected region by analyzing the spatial correlation of the dielectric constant under interference. Then, combining the cumulative history and attenuation trend of the interference within the region with the current degree of dielectric constant anomaly, it dynamically generates a personalized parameter correction factor, ultimately adaptively correcting the standard moisture content calculation model. This method effectively overcomes the systematic impact of spatial heterogeneity interference caused by local operations such as fertilization and irrigation on capacitance method measurements, significantly improving the overall accuracy and reliability of soil moisture content detection in complex garden environments.

[0155] In one possible implementation, after calculating and determining the soil moisture content of the garden soil based on the above steps S401 to S405, the present invention further includes a result output and storage process. For example, this process can be jointly executed by the moisture content calculation module 15, the communication unit in the data acquisition module 11, and an independent output device. Specifically, the moisture content calculation module 15 encapsulates the accurate soil moisture content values ​​calculated in S405 for each monitoring point, as well as the spatial interference area information delineated in S802, to form a result data packet. This result data packet is transmitted back to the central data processing server or a nearby edge computing gateway through the communication network of the data acquisition module 11.

[0156] Following this, output devices (such as workstations or monitoring screens) deployed on servers or in monitoring centers receive the result data packet. The output devices perform the following operations: First, they output the actual moisture content values ​​of each monitoring point in the form of a numerical list or chart for maintenance personnel to view in real time. Second, they utilize the built-in visualization engine to overlay the spatial interference area division results onto the garden electronic map using different colors or blocks, visually demonstrating the distribution of interference. Finally, the output devices store all raw data, intermediate analysis results (including periods of coordinated anomalies, interference values ​​of dielectric constant, and parameter correction factors), and the final moisture content data in a related database or cloud storage platform for historical querying, trend analysis, and maintenance report generation.

[0157] Therefore, this invention realizes a fully automated closed loop from data acquisition, intelligent analysis, model correction to result output and storage, providing timely, intuitive and traceable data support for precise irrigation and maintenance decisions in gardens.

[0158] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0159] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for determining soil moisture content during garden maintenance, characterized in that, The method includes: Acquire monitoring data from multiple monitoring points in the garden; the monitoring data for each monitoring point includes the measured values ​​of multiple monitoring indicators collected over time; Based on the monitoring data of each monitoring point, the coordinated abnormal period of each monitoring point is determined; wherein, the coordinated abnormal period is a continuous time period in which the measured values ​​of multiple monitoring indicators deviate from their respective historical normal fluctuation ranges simultaneously; Based on the monitoring data of each monitoring point during the coordinated abnormal period, the state recovery rate of each monitoring point is determined; wherein, the state recovery rate is used to characterize the rate at which the monitoring indicators recover to the historical normal fluctuation range after the coordinated abnormal period ends; For each monitoring point, the dielectric constant disturbance value of each monitoring point during the coordinated abnormal period is determined based on the coordinated abnormal period, the state recovery rate, the correlation between each monitoring indicator during the coordinated abnormal period, and the correlation between each monitoring indicator during the non-coordinated abnormal period. The soil moisture content of the garden is determined based on the disturbance value of the dielectric constant and the spatial relationship between the multiple monitoring points.

2. The method for determining soil moisture content during garden maintenance according to claim 1, characterized in that, Based on the monitoring data from each monitoring point, the coordinated abnormal time period for each monitoring point is determined, specifically including: Based on the monitoring data of each monitoring point, the collaborative anomaly index of each monitoring point at each time point is calculated; wherein, the collaborative anomaly index is used to characterize the degree to which the measured values ​​of multiple monitoring indicators deviate from their respective historical normal fluctuation ranges simultaneously; The time period during which the coordination anomaly index is continuously higher than the first preset threshold is identified as the coordination anomaly period.

3. The method for determining soil moisture content during garden maintenance according to claim 2, characterized in that, The calculation of the collaborative anomaly index of each monitoring point at each time point specifically includes: For each monitoring indicator, the measured value at the current moment is compared with the historical normal fluctuation range to determine the single indicator deviation of the monitoring indicator at the current moment; The number of monitoring indicators whose single-indicator deviation exceeds the second preset threshold at the current moment is obtained, and the collaborative anomaly index is determined by combining the average value of the single-indicator deviation of all monitoring indicators at the current moment.

4. The method for determining soil moisture content during garden maintenance according to claim 1, characterized in that, Based on the monitoring data of each monitoring point during the period of coordinated anomaly, the state recovery rate of each monitoring point is determined, specifically including: Obtain the collaborative anomaly index corresponding to the end time of the collaborative anomaly period and the collaborative anomaly index corresponding to the recovery time; wherein, the recovery time is the moment after the end time when the measured values ​​of the multiple monitoring indicators first recover to their respective historical normal fluctuation ranges. The state recovery rate is determined based on the duration between the end time and the recovery time, and the co-abnormality index between the end time and the recovery time.

5. The method for determining soil moisture content during garden maintenance according to claim 2, characterized in that, For each monitoring point, based on the coordinated anomaly period, the state recovery rate, the correlation between monitoring indicators during the coordinated anomaly period, and the correlation between monitoring indicators during the non-coordinated anomaly period, the disturbance value of the dielectric constant of each monitoring point during the coordinated anomaly period is determined, specifically including: Calculate the first correlation between each monitoring indicator at each monitoring point during the period of coordinated anomaly; Calculate the second correlation between each monitoring indicator for each monitoring point during the historical non-coordinated anomaly period; The disturbance value of the dielectric constant is determined based on the first correlation, the second correlation, the cooperative anomaly index, and the state recovery rate.

6. The method for determining soil moisture content during garden maintenance according to claim 1, characterized in that, Based on the disturbance value of the dielectric constant and the spatial location of the multiple monitoring points, the soil moisture content of the garden is determined, specifically including: Based on the disturbance value of the dielectric constant and the spatial location of the multiple monitoring points, the spatial interference correlation degree between every two monitoring points is calculated; Two adjacent monitoring points with a spatial interference correlation greater than the third preset threshold are classified into the same spatial interference region. Based on the historical dielectric constant interference values ​​of each monitoring point within the spatial interference area to which each monitoring point belongs, determine the parameter correction factor for each monitoring point; The soil moisture content of the garden is determined based on the parameter correction factor.

7. The method for determining soil moisture content during garden maintenance according to claim 6, characterized in that, Based on the historical dielectric constant interference values ​​of each monitoring point within the spatial interference area to which each monitoring point belongs, the parameter correction factor for each monitoring point is determined, specifically including: Calculate the average value of the dielectric constant of each monitoring point within the spatial interference area to which the monitoring point belongs, and the average value of the dielectric constant of all monitoring points to determine the local anomaly accumulation index; Determine the decay trend index of the dielectric constant value of the monitoring point over historical time; wherein the decay trend index is used to characterize the degree to which the dielectric constant value weakens over time. The parameter correction factor is determined based on the degree of dielectric constant anomaly at the current moment, the local anomaly accumulation index, and the decay trend index.

8. The method for determining soil moisture content during garden maintenance according to claim 6, characterized in that, The soil moisture content of the garden is determined based on the parameter correction factor, specifically including: Using the parameter correction factor, at least one constant term parameter in the preset soil moisture content calculation model is corrected to obtain the corrected calculation parameters; Based on the corrected calculation parameters and the dielectric constant monitored in real time at each monitoring point, the soil moisture content of the garden is calculated.

9. The method for determining soil moisture content during garden maintenance according to any one of claims 1-8, characterized in that, The monitoring indicators include: dielectric constant, soil electrical conductivity, soil temperature, and soil pH.

10. A soil moisture content measurement system for garden maintenance, characterized in that, The system includes: a data acquisition module, an anomaly analysis module, a recovery assessment module, an interference quantification module, and a water content calculation module; The data acquisition module is used to acquire monitoring data from multiple monitoring points in the garden; wherein, the monitoring data of each monitoring point includes the measured values ​​of multiple monitoring indicators collected over time; The anomaly analysis module is used to determine the coordinated anomaly period of each monitoring point based on the monitoring data of each monitoring point. The coordinated anomaly period is a continuous time period in which the measured values ​​of multiple monitoring indicators deviate from their respective historical normal fluctuation ranges simultaneously. The recovery assessment module is used to determine the state recovery rate of each monitoring point based on the monitoring data of each monitoring point during the coordinated abnormal period; wherein, the state recovery rate is used to characterize the rate at which the monitoring indicators recover to the historical normal fluctuation range after the coordinated abnormal period ends; The interference quantization module is used to determine the interference value of the dielectric constant of each monitoring point during the coordinated anomaly period based on the coordinated anomaly index, the state recovery rate, the correlation between each monitoring indicator during the coordinated anomaly period, and the correlation between each monitoring indicator during the non-coordinated anomaly period. The moisture content calculation module is used to determine the soil moisture content of the garden based on the disturbance value of the dielectric constant and the spatial relationship between the multiple monitoring points.

Images