A method and system for evaluating and analyzing the grassland-livestock balance in an agro-pastoral composite area

Abstract

The present invention discloses a method and system for evaluating and analyzing the grassland-livestock balance in an agro-pastoral compound area, specifically related to the field of grassland-livestock management; determining and monitoring the target evaluation parameters for grassland resource and livestock demand assessment, verifying and comparing the analysis data in real time, evaluating the timeliness of the data and classifying and managing it, so as to ensure the accuracy and timeliness of the data. By dynamically adjusting the management decision-making, further analyzing the non-real-time data, and continuously optimizing the evaluation of the grassland-livestock supply-demand balance. This method not only prevents overgrazing and degradation of the grassland, but also realizes the sustainable utilization of grassland resources and the harmonious development of livestock production, improving the scientificity and effectiveness of ecological environment management and livestock production.

Description

Technical Field

[0001] The present invention relates to the field of grassland and livestock management, and particularly to a method and system for evaluating and analyzing the grassland-livestock balance in an agro-pastoral composite area. Background Art

[0002] The evaluation and analysis of the grassland-livestock balance in an agro-pastoral composite area refers to the comprehensive analysis of grassland resources (such as grass yield, grass species diversity) and livestock demand (such as food intake, livestock number) within a mixed area of agriculture and animal husbandry to evaluate the supply-demand balance between grassland and livestock. This analysis aims to ensure that grassland resources can sustainably meet the food needs of livestock, prevent overgrazing or degradation of grassland, and thus achieve the harmonious development of the ecological environment and livestock production. However, if the evaluation of grassland and livestock demand relies on outdated data, it may not reflect the current actual situation, resulting in inaccurate data on which the evaluation of grassland and livestock demand depends. At the same time, if inaccurate data overestimates the grassland yield, managers may think that the grassland can support more livestock, thus increasing the grazing intensity. This will lead to overgrazing of the grassland, reduction of grassland vegetation, damage to the soil structure, and ultimately lead to grassland degradation and productivity decline. Summary of the Invention

[0003] The purpose of the present invention is to provide a method and system for evaluating and analyzing the grassland-livestock balance in an agro-pastoral composite area to solve the deficiencies in the background art.

[0004] To achieve the above purpose, the present invention provides the following technical solutions: A method for evaluating and analyzing the grassland-livestock balance in an agro-pastoral composite area, comprising the following steps:

[0005] S1: Determine the target evaluation parameters for judging the evaluation of grassland resources and livestock demand, and monitor and obtain the grassland resource status and livestock activity data within a fixed time period according to the target evaluation parameters;

[0006] S2: Verify the grassland resource status and livestock activity data obtained in real time, compare and analyze them with historical data, and divide the grassland into a data anomaly monitoring area and a data normal monitoring area according to the analysis results;

[0007] S3: In the data anomaly monitoring area, evaluate the real-time nature of the grassland resource status and livestock activity data according to the acquisition frequency deviation and data trend fluctuation amplitude of the grassland resource status and livestock activity data;

[0008] S4; According to the evaluation results, divide the real-time nature of the grassland resource status and livestock activity data into real-time data and non-real-time data, and formulate corresponding management decisions;

[0009] S5: Further analyze the non-real-time data on the grassland resource status and livestock activities, evaluate and provide feedback on the accuracy of the target evaluation parameters for grassland resource and livestock demand assessment, and dynamically adjust management decisions based on the feedback results.

[0010] Preferably, in S2, verify the grassland resource status and livestock activity data obtained in real time, and compare and analyze them with historical data. Specifically:

[0011] Compare and analyze the grassland resource status and livestock activity data obtained in real time with historical data through the Isolation Forest algorithm, and divide the grassland into a data anomaly monitoring area and a data normal monitoring area according to the analysis results;

[0012] Extract the grassland resource and livestock activity data for the past T time periods from the database;

[0013] Merge the real-time data and historical data to form a complete data set containing all key parameters;

[0014] Select the key parameters for analysis: grass yield, grass species diversity, vegetation coverage rate, soil humidity, livestock quantity, food intake, health status;

[0015] Use the historical data as the training data set to train the Isolation Forest model;

[0016] Through the Isolation Forest algorithm, train the model to identify normal data patterns and abnormal data patterns;

[0017] Use the real-time data as the detection data set and detect it through the trained Isolation Forest model.

[0018] Preferably, the model assigns an anomaly score to each data point, compares the obtained anomaly score with the anomaly score threshold. If the anomaly score is less than or equal to the anomaly score threshold, it is classified as normal data; if the anomaly score is greater than the anomaly score threshold, it is classified as abnormal data;

[0019] Mark the abnormal data points according to the prediction results of the model, and divide the grassland into a data anomaly monitoring area according to the geographical locations of the abnormal data points;

[0020] Mark the normal data points according to the prediction results of the model, and divide the grassland into a data normal monitoring area according to the geographical locations of the normal data points.

[0021] Preferably, in S3, evaluate the real-time nature of the grassland resource status and livestock activity data according to the collection frequency deviation and data trend fluctuation amplitude of the grassland resource status and livestock activity data. Specifically:

[0022] Within the data anomaly monitoring area, a collection frequency deviation index is generated based on the grassland resource status and the deviation of the collection frequency of livestock activity data. The method for obtaining the collection frequency deviation index is as follows:

[0023] Obtain the collection frequency FK of the grassland resource status and livestock activity data in real time within the W time period, and obtain the actual collection interval data X according to the collection frequency s and the reference collection interval F, and calculate the actual deviation value D of the actual collection interval at time s relative to the reference collection interval s , and the expression is: Calculate the predicted deviation value EWMA at time s by the exponentially weighted moving average method s , and the expression is: EWMA s =α*X s +(1 - α)EWMA s-1 ; where α is the smoothing parameter, ranging from 0 to 1, and EWMA s is the predicted deviation value at time s. Calculate the collection frequency deviation index, and the expression is: ER = |D s -EWMA s |; where ER is the collection frequency deviation index.

[0024] Preferably, in S3, within the data anomaly monitoring area, a trend fluctuation index is generated based on the data trend fluctuation amplitude of the grassland resource status and livestock activity data. The method for obtaining the trend fluctuation index is as follows:

[0025] Determine the grassland resource status data: grass yield, vegetation coverage rate, soil humidity, grass species diversity, and livestock activity data: livestock quantity, food intake, and health status; construct several time series m(s) from the obtained data in chronological order, where s is time. Select a wavelet basis function to decompose each time data and perform continuous wavelet transform on it. The expression is: where W(a,b) is the wavelet coefficient, representing the transformation result at scale a and displacement b, a is the scale parameter, b is the displacement parameter, and ψ * is the complex conjugate of the wavelet basis function; the wavelet coefficients are respectively the detail coefficient Dj and the approximation coefficient Aj, and the expression is: W(a,b) = Dj + Aj; where Dj = ∑ k m(s)ψ j,k (s), k is the scale label; calculate the standard deviation of the detail coefficients as the fluctuation amplitude of each scale, sum up the fluctuation amplitudes of all scales, and perform a weighted average calculation on each time series of the grassland resource status and livestock activity data to generate a trend fluctuation index.

[0026] Preferably, convert the acquisition frequency deviation index and the trend fluctuation index into a first feature vector, and use the first feature vector as the input of the machine learning model. The machine learning model takes the prediction of the real-time value label of the grassland resource status and livestock activity data for each group of first feature vectors as the prediction target, and takes minimizing the sum of the prediction errors of all real-time value labels of the grassland resource status and livestock activity data as the training target. Train the machine learning model until the sum of the prediction errors converges and then stop the model training. Determine the real-time value of the grassland resource status and livestock activity data according to the model output result, where the machine learning model is a polynomial regression model.

[0027] Preferably, in S4, divide the real-time nature of the grassland resource status and livestock activity data into real-time data and non-real-time data;

[0028] Compare the obtained real-time value of the grassland resource status and livestock activity data with the real-time value reference threshold. If the real-time value of the grassland resource status and livestock activity data is greater than or equal to the real-time value reference threshold, it indicates that the real-time nature of the grassland resource status and livestock activity data is high, and it is divided into real-time data; if the real-time value of the grassland resource status and livestock activity data is less than the real-time value reference threshold, it indicates that the real-time nature of the grassland resource status and livestock activity data is low, and it is divided into non-real-time data.

[0029] Preferably, in S5, further analyze the non-real-time data of the grassland resource status and livestock activity, and evaluate and feedback the accuracy of the target evaluation parameters for the evaluation of grassland resources and livestock needs, specifically:

[0030] When the grassland resource status and livestock activity data are divided into non-real-time data, that is, the real-time value of the grassland resource status and livestock activity data generated within a period of time is less than the real-time value reference threshold, collect the real-time values less than the real-time value reference threshold within a period of time after the management decision is adjusted, and establish a corresponding data set. Calculate the mean and standard deviation of the data set, and after analyzing it, evaluate and feedback the accuracy of the target evaluation parameters for the evaluation of grassland resources and livestock needs.

[0031] Preferably, if the mean of the real-time values in the data set is greater than or equal to the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values is less than the reference threshold of the standard deviation of the real-time values, it indicates that the real-time nature of the data is high and the fluctuation is small. At this time, generate a data accuracy signal and maintain the current management strategy;

[0032] If the mean of the real-time values is greater than or equal to the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values is greater than or equal to the reference threshold of the standard deviation of the real-time values, it indicates that the real-time nature of the data is high but the fluctuation is large. At this time, generate a data inaccuracy signal and further refine the management strategy to reduce data fluctuations;

[0033] If the average value of the real-time performance value is less than the reference threshold of the average value of the real-time performance value, and the standard deviation of the real-time performance value is greater than or equal to the reference threshold of the standard deviation of the real-time performance value, it indicates that the real-time performance of the data is low and the fluctuation is large. At this time, an inaccurate data signal is generated, the management decision is adjusted, and the data collection frequency and stability are improved;

[0034] If the average value of the real-time performance value is less than the reference threshold of the average value of the real-time performance value, and the standard deviation of the real-time performance value is less than the reference threshold of the standard deviation of the real-time performance value, it indicates that the real-time performance of the data is low but the fluctuation is small. At this time, an inaccurate data signal is generated, the management decision is adjusted, and the real-time performance of the data is gradually improved.

[0035] The present invention also provides a grassland-livestock balance evaluation and analysis system in an agro-pastoral compound area, including a data collection module, a comparative analysis module, a real-time performance evaluation module, a decision-making module, and a feedback adjustment module;

[0036] Data collection module: Determine the target evaluation parameters for judging the evaluation of grassland resources and livestock demand, and monitor and obtain the grassland resource status and livestock activity data within a fixed time period according to the target evaluation parameters;

[0037] Comparative analysis module: Verify the grassland resource status and livestock activity data obtained in real time, compare and analyze them with historical data, and divide the grassland into a data anomaly monitoring area and a data normal monitoring area according to the analysis results;

[0038] Real-time performance evaluation module: In the data anomaly monitoring area, evaluate the real-time performance of the grassland resource status and livestock activity data according to the collection frequency deviation and data trend fluctuation amplitude of the grassland resource status and livestock activity data;

[0039] Decision-making module; According to the evaluation results, divide the real-time performance of the grassland resource status and livestock activity data into real-time data and non-real-time data, and formulate corresponding management decisions;

[0040] Feedback adjustment module: Further analyze the non-real-time data of the grassland resource status and livestock activities, evaluate and feedback the accuracy of the target evaluation parameters for the evaluation of grassland resources and livestock demand, and dynamically adjust the management decision according to the feedback results.

[0041] In the above technical solution, the technical effects and advantages provided by the present invention:

[0042] 1. Through steps of determining evaluation parameters, real-time verifying data, evaluating data timeliness, classifying and managing data, and dynamically adjusting management decisions, the present invention effectively solves the problem of inaccurate evaluation caused by relying on outdated data. By applying advanced algorithms such as the Isolation Forest algorithm and wavelet transform, precise analysis is carried out on the grassland resource status and livestock activity data, enabling dynamic and accurate evaluation of the supply-demand balance between grassland and livestock, thereby preventing overgrazing and degradation of grassland and ensuring the sustainable utilization of grassland resources.

[0043] 2. The present invention not only improves the timeliness and accuracy of data, ensures the scientificity and effectiveness of management decisions, but also can continuously optimize the evaluation process of grassland resources and livestock demand by dynamically adjusting management strategies. Ultimately, the harmonious development of the ecological environment and livestock production is achieved, the overall level of grassland resource management and livestock husbandry production is improved, and solid technical support is provided for the sustainable utilization of grassland resources and the efficient management of livestock husbandry. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings.

[0045] Figure 1 It is a flowchart of the method of the present invention.

[0046] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0048] Example 1, please refer to Figure 1 As shown, a method for evaluating and analyzing the grassland-livestock balance in an agro-pastoral composite area in this embodiment includes the following steps:

[0049] S1: Determine the target evaluation parameters for judging the evaluation of grassland resources and livestock demand, and monitor and obtain the grassland resource status and livestock activity data within a fixed time period according to the target evaluation parameters;

[0050] S2: Check the grassland resource status and livestock activity data obtained in real time, compare and analyze them with historical data, and divide the grassland into a data anomaly monitoring area and a data normal monitoring area according to the analysis results;

[0051] S3: In the data anomaly monitoring area, evaluate the real-time nature of the grassland resource status and livestock activity data according to the collection frequency deviation and data trend fluctuation amplitude of the grassland resource status and livestock activity data;

[0052] S4: According to the evaluation results, divide the real-time nature of the grassland resource status and livestock activity data into real-time data and non-real-time data, and formulate corresponding management decisions;

[0053] S5: Further analyze the non-real-time data of the grassland resource status and livestock activities, evaluate and feedback the accuracy of the target evaluation parameters for grassland resource and livestock demand assessment, and dynamically adjust the management decisions according to the feedback results.

[0054] Among them, in S1, determine the target evaluation parameters for judging grassland resource and livestock demand assessment, and monitor and obtain the grassland resource status and livestock activity data within a fixed time period according to the target evaluation parameters.

[0055] Grassland resource evaluation parameters specifically include: Grass yield: The weight of dry grass per unit area. Grass species diversity: The number and distribution evenness of grass species per unit area. Vegetation coverage rate: The percentage of the grassland covered by vegetation and the greenness index (such as NDVI). Soil moisture: The water content in the soil. Climate conditions: Precipitation, temperature, sunshine hours, etc. Soil nutrients: Nitrogen, phosphorus, potassium content and organic matter content.

[0056] Livestock demand evaluation parameters specifically include: Livestock quantity: The quantity and growth rate of different categories of livestock. Food intake: The forage intake per livestock per day. Health status: Body weight, health index (such as body condition score), disease incidence rate. Reproduction rate: The number of newborn livestock and reproduction success rate per year. Production performance: Milk yield, meat yield, etc. Behavior pattern: Foraging time, frequency and location, activity monitoring.

[0057] Grassland resource monitoring includes: Remote sensing technology: Use satellite remote sensing or drone photography to monitor vegetation coverage rate and grass yield. Ground sensors: Install soil moisture sensors and weather stations to monitor soil moisture and climate conditions. Field sampling: Regularly collect grassland samples at different locations to measure grass yield and grass species diversity.

[0058] Livestock demand monitoring includes: GPS collars: Equip livestock with GPS collars to monitor their behavior patterns and activity ranges in real time. Health monitoring devices: Use wireless body temperature sensors, health bracelets, etc. to monitor health indicators such as the body temperature and heart rate of livestock. Intake records: Record the food intake of each livestock through an automatic feeding system. Weight monitoring: Regularly weigh the livestock using an electronic scale and record the growth rate and health status. Reproduction records: Record the reproduction situation of each livestock and count the number of newborns and reproduction success rate.

[0059] Set fixed collection periods (such as daily, weekly, monthly) to collect various parameters of grasslands and livestock. Use automated equipment and sensors to collect data in real time and upload it to the database. Conduct regular field surveys and manual measurements to ensure the accuracy and comprehensiveness of the data.

[0060] Establish a central database to store all the collected data. Classify and store the data according to different parameters of grassland resources and livestock demand for convenient subsequent analysis. Regularly back up the data to prevent data loss.

[0061] S2: Verify the grassland resource status and livestock activity data obtained in real time, compare and analyze them with historical data, and divide the grasslands into data anomaly monitoring areas and data normal monitoring areas according to the analysis results.

[0062] Real-time data verification includes: Checking the integrity of real-time data to ensure there is no missing or incomplete data. Ensuring the consistency of real-time data with historical data in terms of format and units.

[0063] Select key parameters for comparison, such as grass yield, grass species diversity, vegetation coverage, soil moisture, livestock quantity, food intake, health status, etc. Use statistical methods to calculate the mean, standard deviation, and change rate, etc. of real-time data and historical data. Use time series analysis methods to analyze the trend differences between real-time data and historical data. Apply anomaly detection algorithms such as Isolation Forest, DBSCAN, etc. to identify abnormal patterns in the data.

[0064] Compare and analyze the grassland resource status and livestock activity data obtained in real time with historical data through the Isolation Forest algorithm, and divide the grasslands into data anomaly monitoring areas and data normal monitoring areas according to the analysis results. Specifically:

[0065] Extract the grassland resource and livestock activity data in the past T time periods from the database.

[0066] Merge the real-time data and historical data to form a complete data set containing all key parameters.

[0067] Select key parameters for analysis, such as grassland yield, grass species diversity, vegetation coverage, soil moisture, livestock quantity, food intake, and health status.

[0068] Standardize the data to ensure that the value ranges of different parameters are consistent and improve the performance of the algorithm.

[0069] Use historical data as the training dataset to train the Isolation Forest model.

[0070] Through the Isolation Forest algorithm, train the model to identify normal data patterns and abnormal data patterns.

[0071] Use real-time data as the detection dataset and detect it through the trained Isolation Forest model.

[0072] The model will assign an anomaly score to each data point. Compare the obtained anomaly score with the anomaly score threshold. If the anomaly score is less than or equal to the anomaly score threshold, classify it as normal data; if the anomaly score is greater than the anomaly score threshold, classify it as abnormal data.

[0073] Based on the prediction results of the model, mark the abnormal data points. According to the geographical locations of the abnormal data points, divide the grassland into data anomaly monitoring areas.

[0074] Based on the prediction results of the model, mark the normal data points. According to the geographical locations of the normal data points, divide the grassland into data normal monitoring areas.

[0075] Store the data of the divided areas in the database, establish corresponding indexes for easy query and management. Update the area data in real time, adjust the area division and labels according to the new monitoring data. Use a GIS system or visualization tool to display the data anomaly monitoring areas and data normal monitoring areas on the map. Generate a report containing the division results of the abnormal areas and normal areas to provide decision-making support for managers.

[0076] S3: In the data anomaly monitoring area, evaluate the real-time nature of the grassland resource status and livestock activity data according to the collection frequency deviation situation and data trend fluctuation amplitude of the grassland resource status and livestock activity data.

[0077] In the data anomaly monitoring area, generate a collection frequency deviation index according to the collection frequency deviation situation of the grassland resource status and livestock activity data. The method for obtaining the collection frequency deviation index is as follows:

[0078] Real-time obtain the collection frequency FK of the grassland resource status and livestock activity data within the W time period, and obtain the actual collection interval data X according to the collection frequency s And the reference collection interval F, calculate the actual deviation value D of the actual collection interval at time s relative to the reference collection intervals , the expression is: Calculate the predicted deviation value EWMA at time s by the exponentially weighted moving average method s , the expression is: EWMA s =α*X s +(1 - α)EWMA s-1 ; where α is the smoothing parameter, between 0 and 1, and EWMA s is the predicted deviation value at time s. Calculate the acquisition frequency deviation index, and the expression is: ER = |D s -EWMA s |; where ER is the acquisition frequency deviation index.

[0079] The larger the acquisition frequency deviation index, the greater the deviation between the acquisition frequency of grassland resource status and livestock activity data and the expected standard acquisition frequency. This means that the timeliness of the data is worse, that is, the data is not collected frequently or timely enough to accurately reflect the current actual situation, which may lead to inaccuracies in management and decision-making basis. To ensure the timeliness and accuracy of the data, the acquisition frequency deviation index should be kept at a relatively low level.

[0080] Within the data anomaly monitoring area, generate a trend fluctuation index according to the data trend fluctuation amplitude of grassland resource status and livestock activity data. The method for obtaining the trend fluctuation index is as follows:

[0081] Determine the grassland resource status data: grass yield, vegetation coverage rate, soil humidity, grass species diversity, and livestock activity data: livestock quantity, food intake, health status; construct several time series m(s) with the obtained data in chronological order, where s is time, select a wavelet basis function to decompose each time data, and perform continuous wavelet transform on it. The expression is: Among them, W(a,b) is the wavelet coefficient, representing the transformation result at scale a and displacement b. a is the scale parameter, controlling the width of the wavelet function, b is the displacement parameter, controlling the position of the wavelet function, and ψ * is the complex conjugate of the wavelet basis function; the wavelet coefficients are respectively the detail coefficient Dj and the approximation coefficient Aj, and the expression is: W(a,b) = Dj + Aj; where, Dj = ∑ k m(s)ψ j,k (s), k is the scale label; the approximation coefficient is used to capture the main trend of the data, and the detail coefficient is used to capture the local fluctuations of the data. Calculate the standard deviation of the detail coefficient as the fluctuation amplitude of each scale, sum up the fluctuation amplitudes of all scales, and generate a trend fluctuation index after weighted average calculation of each time series of grassland resource status and livestock activity data.

[0082] The larger the trend fluctuation index, the greater the fluctuation range of the grassland resource status and livestock activity data, which means the worse the data stability and the lower the real-time performance. This indicates that there are significant changes between different time points of the data, and it cannot accurately and continuously reflect the actual situation, thus potentially reducing the accuracy of the basis for management and decision-making. To ensure the reliability and real-time performance of the data, the trend fluctuation index should be kept at a relatively low level as much as possible.

[0083] Convert the acquisition frequency deviation index and the trend fluctuation index into the first eigenvector, and use the first eigenvector as the input of the machine learning model. The machine learning model takes predicting the real-time value label of the grassland resource status and livestock activity data for each group of the first eigenvectors as the prediction target, and takes minimizing the sum of the prediction errors of the real-time value labels of all grassland resource status and livestock activity data as the training target to train the machine learning model until the sum of the prediction errors reaches convergence and then stop the model training. Determine the real-time value of the grassland resource status and livestock activity data according to the model output result, where the machine learning model is a polynomial regression model.

[0084] The method for obtaining the real-time value of the grassland resource status and livestock activity data is: obtain the corresponding function expression from the first eigenvector training data of the trained machine learning model: LP = f(ER, EL); where f is the output function of the model, ER is the acquisition frequency deviation index, EL is the trend fluctuation index, and LP is the real-time value of the grassland resource status and livestock activity data.

[0085] S4; According to the evaluation results, classify the real-time performance of the grassland resource status and livestock activity data into real-time data and non-real-time data, and formulate corresponding management decisions.

[0086] Compare the obtained real-time value of the grassland resource status and livestock activity data with the real-time value reference threshold. If the real-time value of the grassland resource status and livestock activity data is greater than or equal to the real-time value reference threshold, it indicates that the real-time performance of the grassland resource status and livestock activity data is high, the fluctuation range is small, the data is stable, and it can accurately reflect the actual situation, and classify it as real-time data; if the real-time value of the grassland resource status and livestock activity data is less than the real-time value reference threshold, it indicates that the real-time performance of the grassland resource status and livestock activity data is low, the fluctuation range is large, the data is unstable, and it cannot continuously and accurately reflect the actual situation, and classify it as non-real-time data.

[0087] The management decisions for real-time data include: Continuing the existing monitoring: Maintaining the current data acquisition frequency and method to ensure the continuity and real-time performance of the data. Data application: Using real-time data for real-time analysis and decision-making, such as regulating the grassland grazing intensity and adjusting the livestock feeding strategy. Feedback mechanism: Establishing a rapid feedback mechanism to promptly handle data anomalies and ensure the effectiveness of management measures.

[0088] Management decisions for non-real-time data include: increasing the collection frequency: increasing the data collection frequency, reducing the data collection interval, and ensuring the real-time and continuity of data. Improving the collection method: adopting more advanced monitoring technologies and equipment, such as remote sensing technology, UAV monitoring, Internet of Things sensors, etc., to improve the accuracy and timeliness of data collection. Data completion: for missing or abnormal data, perform data completion and correction to ensure the integrity and reliability of data. Regular evaluation: regularly evaluate the data collection and processing processes, and continuously improve to ensure data quality.

[0089] S5: Further analyze the non-real-time data on the grassland resource status and livestock activities, evaluate and feedback the accuracy of the target evaluation parameters for grassland resource and livestock demand assessment, and dynamically adjust the management decisions according to the feedback results.

[0090] When the grassland resource status and livestock activity data are classified as non-real-time data, that is, the real-time value of the grassland resource status and livestock activity data generated within a period of time is less than the real-time value reference threshold, collect the real-time values less than the real-time value reference threshold within a period of time after adjusting the management decision, establish the corresponding data set, calculate the mean and standard deviation of the data set, and after analyzing it, evaluate and feedback the accuracy of the target evaluation parameters for grassland resource and livestock demand assessment.

[0091] If the mean of the real-time values in the data set is greater than or equal to the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values is less than the reference threshold of the standard deviation of the real-time values, it indicates that the real-time of the data is high and the fluctuation is small. At this time, generate a data accurate signal, and the management decision adjustment is effective, and the current management strategy can be maintained;

[0092] If the mean of the real-time values is greater than or equal to the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values is greater than or equal to the reference threshold of the standard deviation of the real-time values, it indicates that the real-time of the data is high but the fluctuation is large. At this time, generate a data inaccurate signal, and it is necessary to further refine the management strategy to reduce the data fluctuation;

[0093] If the mean of the real-time values is less than the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values is greater than or equal to the reference threshold of the standard deviation of the real-time values, it indicates that the real-time of the data is low and the fluctuation is large. At this time, generate a data inaccurate signal, and it is necessary to greatly adjust the management decision to improve the data collection frequency and stability;

[0094] If the mean of the real-time values is less than the reference threshold of the mean of the real-time values, and the standard deviation of the real-time values is less than the reference threshold of the standard deviation of the real-time values, it indicates that the real-time of the data is low but the fluctuation is small. At this time, generate a data inaccurate signal, and it is necessary to appropriately adjust the management decision to gradually improve the real-time of the data.

[0095] Dynamically adjust the management decisions of grassland resources and livestock demand according to the results of feedback analysis: Increase the collection frequency: Increase the frequency of data collection and shorten the collection interval. Improve the collection technology: Adopt more advanced technologies and equipment for data collection, such as drones, Internet of Things sensors, etc. Data calibration: Calibrate historical data to ensure the accuracy and consistency of data. Strengthen monitoring: Focus on monitoring non-real-time data areas to promptly discover and solve problems.

[0096] Implement corresponding management decision adjustments according to the feedback results. Continuously monitor the adjusted data, regularly evaluate the real-time nature of the data, and further adjust the management decisions according to the evaluation results.

[0097] In this embodiment, by determining the target evaluation parameters for judging the evaluation of grassland resources and livestock demand, monitoring and obtaining the grassland resource status and livestock activity data within a fixed time period according to the target evaluation parameters; verifying the real-time obtained grassland resource status and livestock activity data, comparing and analyzing them with historical data, and dividing the grassland into a data anomaly monitoring area and a data normal monitoring area according to the analysis results; within the data anomaly monitoring area, evaluating the real-time nature of the grassland resource status and livestock activity data according to the collection frequency deviation and data trend fluctuation range of the grassland resource status and livestock activity data; according to the evaluation results, dividing the real-time nature of the grassland resource status and livestock activity data into real-time data and non-real-time data, and formulating corresponding management decisions; further analyzing the non-real-time data of the grassland resource status and livestock activities, evaluating and providing feedback on the accuracy of the target evaluation parameters for the evaluation of grassland resources and livestock demand, and dynamically adjusting the management decisions according to the feedback results. This not only improves the accuracy and real-time nature of the data, ensures the scientificity and effectiveness of the management decisions, but also can promptly discover and solve data anomaly problems, optimize the evaluation process of grassland resources and livestock demand, and achieve the sustainable utilization of grassland resources and the efficient management of livestock production.

[0098] Example 2, please refer to Figure 2 As shown, a grassland-livestock balance evaluation and analysis system in an agro-pastoral composite area in this embodiment includes a data collection module, a comparison and analysis module, a real-time evaluation module, a decision-making module, and a feedback adjustment module;

[0099] Data collection module: Determine the target evaluation parameters for judging the evaluation of grassland resources and livestock demand, and monitor and obtain the grassland resource status and livestock activity data within a fixed time period according to the target evaluation parameters;

[0100] Comparison and analysis module: Verify the real-time obtained grassland resource status and livestock activity data, compare and analyze them with historical data, and divide the grassland into a data anomaly monitoring area and a data normal monitoring area according to the analysis results;

[0101] Real-time evaluation module: within the data anomaly monitoring area, evaluate the real-time nature of the grassland resource status and livestock activity data based on the deviation of the collection frequency and the amplitude of data trend fluctuations of the grassland resource status and livestock activity data;

[0102] Decision-making module: According to the evaluation results, classify the real-time nature of the grassland resource status and livestock activity data into real-time data and non-real-time data, and formulate corresponding management decisions;

[0103] Feedback adjustment module: Further analyze the non-real-time data of the grassland resource status and livestock activities, evaluate and feedback the accuracy of the target evaluation parameters for the evaluation of grassland resources and livestock needs, and dynamically adjust the management decisions according to the feedback results.

[0104] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula that is closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0105] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0106] It should be understood that the term "and / or" in this text is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this text generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship. The specific meaning can be understood by referring to the context before and after.

[0107] It should be understood that in various embodiments of the present application, the magnitude of the sequence numbers of the above processes does not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0108] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this text can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0109] As mentioned above, the above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, and all should be covered within the protection scope of the present application.

Claims

1. A method for evaluating and analyzing the grassland-livestock balance in an agro-pastoral composite area, characterized in that: Including the following steps; S1: Determine the target evaluation parameters for judging the grassland resources and livestock demand assessment, and monitor and obtain the grassland resources status and livestock activity data within a fixed time period according to the target evaluation parameters; S2: Verify the grassland resources status and livestock activity data obtained in real time, compare and analyze them with historical data, and divide the grassland into data anomaly monitoring areas and data normal monitoring areas according to the analysis results; S3: In the data anomaly monitoring area, evaluate the timeliness of the grassland resources status and livestock activity data according to the collection frequency deviation and data trend fluctuation amplitude of the grassland resources status and livestock activity data. Specifically: In the data anomaly monitoring area, a collection frequency deviation index is generated according to the grassland resource status and the deviation of the collection frequency of livestock activity data. The method for obtaining the collection frequency deviation index is as follows: obtain in real time the collection frequency FK of the grassland resource status and livestock activity data within the W time period, and obtain the actual collection interval data according to the collection frequency and the reference collection interval F, and calculate the actual deviation value of the actual collection interval at time s relative to the reference collection interval , and the expression is: ; calculate the predicted deviation value at time s by the exponentially weighted moving average method , and the expression is: ; in the formula, is the smoothing parameter, which is between 0 and 1, is the predicted deviation value at time s, calculate the collection frequency deviation index, and the expression is: ; in the formula, ER is the collection frequency deviation index; Within the data anomaly monitoring area, a trend fluctuation index is generated based on the amplitude of the data trend fluctuations of the grassland resource status and livestock activity data. The method for obtaining the trend fluctuation index is as follows: Determine the grassland resource status data: grass yield, vegetation coverage rate, soil humidity, grass species diversity, and livestock activity data: livestock quantity, food intake, and health status; construct several time series m(s) with the obtained data in chronological order, where s is time, select a wavelet basis function to decompose each time data, and perform a continuous wavelet transform on it. The expression is: ; where W(a, b) is the wavelet coefficient, representing the transformation result at scale a and displacement b. a is the scale parameter, and b is the displacement parameter. is the complex conjugate of the wavelet basis function; the wavelet coefficients are the detail coefficient Dj and the approximation coefficient Aj respectively, and the expression is: ; where , k is the scale label; calculate the standard deviation of the detail coefficients as the fluctuation amplitude of each scale, sum up the fluctuation amplitudes of all scales, and generate a trend fluctuation index after performing a weighted average calculation on each time series of the grassland resource status and livestock activity data; Convert the collection frequency deviation index and trend fluctuation index into the first feature vector, use the first feature vector as the input of the machine learning model. The machine learning model takes predicting the timeliness value label of the grassland resources status and livestock activity data for each group of the first feature vectors as the prediction target, and takes minimizing the sum of the prediction errors of the timeliness value labels of all grassland resources status and livestock activity data as the training target. Train the machine learning model until the sum of the prediction errors reaches convergence and then stop the model training. Determine the timeliness value of the grassland resources status and livestock activity data according to the model output result. Among them, the machine learning model is a polynomial regression model; S4; According to the evaluation results, divide the timeliness of the grassland resources status and livestock activity data into real-time data and non-real-time data, and formulate corresponding management decisions; S5: Further analyze the non-real-time data of the grassland resources status and livestock activities, evaluate and feedback the accuracy of the target evaluation parameters for grassland resources and livestock demand assessment, and dynamically adjust the management decisions according to the feedback results. Specifically: When the grassland resources status and livestock activity data are divided into non-real-time data, that is, the timeliness value of the grassland resources status and livestock activity data generated within a period of time is less than the timeliness value reference threshold, collect the timeliness values less than the timeliness value reference threshold within a period of time after the management decision is adjusted, and establish a corresponding data set. Calculate the mean and standard deviation of the data set, and after analyzing it, evaluate and feedback the accuracy of the target evaluation parameters for grassland resources and livestock demand assessment.

2. The grassland-livestock balance assessment and analysis method according to claim 1, wherein: In S2, verify the grassland resources status and livestock activity data obtained in real time, and compare and analyze them with historical data. Specifically: Compare and analyze the grassland resources status and livestock activity data obtained in real time with historical data through the Isolation Forest algorithm, and divide the grassland into data anomaly monitoring areas and data normal monitoring areas according to the analysis results; Extract the grassland resources and livestock activity data in the past T time periods from the database; Merge the real-time data and historical data to form a complete data set containing all key parameters; Select the key parameters for analysis: grass yield, grass species diversity, vegetation coverage rate, soil humidity, livestock quantity, food intake, health status; Use historical data as the training data set to train the Isolation Forest model; Through the Isolation Forest algorithm, train a model to identify normal data patterns and abnormal data patterns; Use real-time data as the detection data set and perform detection through the trained Isolation Forest model.

3. The grassland-livestock balance assessment and analysis method according to claim 2, characterized in that: The model assigns an anomaly score to each data point, compares the obtained anomaly score with the anomaly score threshold. If the anomaly score is less than or equal to the anomaly score threshold, it is classified as normal data; if the anomaly score is greater than the anomaly score threshold, it is classified as abnormal data; According to the prediction results of the model, mark the abnormal data points, and divide the grassland into data anomaly monitoring areas according to the geographical locations of the abnormal data points; According to the prediction results of the model, mark the normal data points, and divide the grassland into data normal monitoring areas according to the geographical locations of the normal data points.

4. The grassland-livestock balance assessment and analysis method according to claim 1, characterized in that: In S4, divide the real-time nature of the grassland resource status and livestock activity data into real-time data and non-real-time data; Compare the obtained real-time value of the grassland resource status and livestock activity data with the real-time value reference threshold. If the real-time value of the grassland resource status and livestock activity data is greater than or equal to the real-time value reference threshold, it indicates that the real-time nature of the grassland resource status and livestock activity data is high, and it is classified as real-time data; if the real-time value of the grassland resource status and livestock activity data is less than the real-time value reference threshold, it indicates that the real-time nature of the grassland resource status and livestock activity data is low, and it is classified as non-real-time data.

5. A method for evaluating and analyzing the grassland-livestock balance in an agro-pastoral composite area according to claim 4, characterized in that: If the mean value of the real-time values in the data set is greater than or equal to the reference threshold of the mean value of the real-time values, and the standard deviation of the real-time values is less than the reference threshold of the standard deviation of the real-time values, it indicates that the real-time nature of the data is high and the fluctuation is small. At this time, generate a data accuracy signal and maintain the current management strategy; If the mean value of the real-time values is greater than or equal to the reference threshold of the mean value of the real-time values, and the standard deviation of the real-time values is greater than or equal to the reference threshold of the standard deviation of the real-time values, it indicates that the real-time nature of the data is high but the fluctuation is large. At this time, generate a data inaccuracy signal, further refine the management strategy, and reduce the data fluctuation; If the mean value of the real-time values is less than the reference threshold of the mean value of the real-time values, and the standard deviation of the real-time values is greater than or equal to the reference threshold of the standard deviation of the real-time values, it indicates that the real-time nature of the data is low and the fluctuation is large. At this time, generate a data inaccuracy signal, adjust the management decision, and increase the data collection frequency and stability; If the mean value of the real-time values is less than the reference threshold of the mean value of the real-time values, and the standard deviation of the real-time values is less than the reference threshold of the standard deviation of the real-time values, it indicates that the real-time nature of the data is low but the fluctuation is small. At this time, generate a data inaccuracy signal, adjust the management decision, and gradually improve the real-time nature of the data.

6. A grassland-livestock balance assessment and analysis system in an agro-pastoral composite area, which is used to implement the grassland-livestock balance assessment and analysis method according to any one of claims 1-5, and is characterized in that: It includes a data collection module, a comparison and analysis module, a real-time evaluation module, a decision-making module, and a feedback and adjustment module; Data collection module: Determine the target evaluation parameters for judging the grassland resource and livestock demand assessment, and monitor and obtain the grassland resource status and livestock activity data within a fixed time period according to the target evaluation parameters; Comparison and analysis module: Verify the real-time obtained grassland resource status and livestock activity data, compare and analyze it with the historical data, and divide the grassland into data anomaly monitoring areas and data normal monitoring areas according to the analysis results; Real-time evaluation module: In the data anomaly monitoring area, evaluate the real-time nature of the grassland resource status and livestock activity data according to the deviation of the acquisition frequency of the grassland resource status and livestock activity data and the amplitude of the data trend fluctuation; Decision-making module: According to the evaluation results, classify the real-time nature of the grassland resource status and livestock activity data into real-time data and non-real-time data, and formulate corresponding management decisions; Feedback adjustment module: Further analyze the non-real-time data of the grassland resource status and livestock activities, evaluate and feedback the accuracy of the target evaluation parameters for the evaluation of grassland resources and livestock needs, and dynamically adjust the management decisions according to the feedback results.

Images