An evaluation method for coupling and coordination degree of economic benefit and ecological benefit of smart agriculture

Abstract

The present application belongs to the field of intelligent agriculture technology, and provides an evaluation method for coupling and coordination degree of economic benefit and ecological benefit of intelligent agriculture, comprising: capturing human intervention behavior and collecting crop state, weather cycle and ecological characteristic data before and after intervention; introducing weather forecast similarity correction factor to determine state prediction value before intervention based on historical state time series data, and determining evaluation value after intervention by weighted sum of state characteristics after intervention; determining ecological benefit by S-shaped mapping of ecological evaluation value before and after intervention respectively, determining economic benefit by S-shaped mapping of difference between prediction value and evaluation value, calculating relative deviation of both by inverse tangent function, and quantifying collaborative inclination and direction; determining final benchmark based on semantic analysis mapping policy as basic benchmark, combined with surrounding ecological protection area grade and quantity correction; taking the ratio of recent inclination mean value and benchmark value as evaluation index; the present application realizes real-time quantitative coupling evaluation of agricultural economic benefit and ecological benefit.

Description

Technical Field

[0001] This invention belongs to the field of smart agriculture technology, and in particular relates to a method for evaluating the coupling and coordination degree of economic and ecological benefits of smart agriculture. Background Technology

[0002] The evaluation of the coupling and coordination between the economic and ecological benefits of smart agriculture is a core indicator for measuring the sustainability of agricultural production methods. With the widespread adoption of smart agriculture technologies, how to scientifically evaluate the comprehensive impact of human intervention on economic output and the ecological environment has become a key issue in the field of sustainable agricultural development.

[0003] Existing agricultural benefit evaluation methods often focus on a single dimension. Economic benefit evaluation uses output or income as the core indicator, while ecological benefit evaluation mainly relies on changes in soil or water quality, and the two are conducted independently. Some studies use a comprehensive index method, standardizing economic and ecological indicators separately and then weighting and summing them, but the determination of weights depends on expert experience and lacks dynamic responsiveness. A few schemes introduce coupling coordination degree models, evaluating by calculating the correlation coefficient between the two systems, but they do not include specific human intervention behaviors as the unit of analysis.

[0004] Existing technologies have shortcomings in three aspects: First, the prediction of crop status before intervention does not integrate and correct weather forecast data with historical time-series characteristics, and lacks a dynamic adjustment mechanism based on weather similarity; Second, the benefit assessment of intervention does not map economic and ecological benefits to the same coordinate system for joint quantification of direction and magnitude, making it difficult to determine benefit bias; Third, the determination of evaluation benchmarks does not include the level and number of ecological protection areas surrounding the planting area in the quantification, resulting in benchmark values ​​that cannot reflect regional differences in ecological constraints. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a method for evaluating the coupling and coordination degree of economic and ecological benefits in smart agriculture, thus solving the aforementioned problems.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for evaluating the coupling coordination degree of economic and ecological benefits in smart agriculture, the method comprising:

[0007] The study aims to capture human interventions during crop cultivation and collect data on crop status characteristics, weather cycle characteristics, and ecological characteristics of crop cultivation areas before and after such interventions. Weather cycle characteristics refer to the characteristics of weather within a specific cycle.

[0008] Based on the crop condition characteristics data and weather forecast data before human intervention, determine the predicted values ​​of crop condition before intervention;

[0009] Based on the crop status characteristic data after human intervention, determine the crop status assessment value after intervention;

[0010] Based on the predicted values ​​of crop status before intervention, the assessed values ​​of crop status after intervention, and the ecological characteristic data of crop planting areas, the degree of synergy between economic and ecological benefits is determined.

[0011] Collect information on the surrounding areas and development policies of crop planting areas, and determine the benchmark value of the synergistic tilt between economic and ecological benefits based on the surrounding information and development policies of crop planting areas; among which, the surrounding information of planting areas includes the importance level and number of ecological protection areas around the planting area.

[0012] Based on the degree of synergy between economic and ecological benefits and the benchmark value of the degree of synergy between economic and ecological benefits, an evaluation index for the degree of coupling and coordination between economic and ecological benefits is determined.

[0013] The coupling coordination degree between economic and ecological benefits is evaluated based on the evaluation index of the coupling coordination degree between economic and ecological benefits in smart agriculture.

[0014] Based on the above technical solutions, the present invention also provides the following optional technical solutions:

[0015] Further technical solution: The determination of the predicted crop state before intervention is expressed by the following formula: ;

[0016] In the above formula, This refers to the predicted crop condition before intervention. This refers to the weather similarity correction factor for the i-th state characteristic of crops. This refers to the normalized value of the i-th state feature data of the crop at time t. This refers to the normalized value of the i-th state feature data of the crop at time t-1. This refers to the normalized value of the i-th state feature data of the crop at time tn. , refers to the weight coefficient of the i-th state feature of the crop, and m refers to the total number of state feature data of the crop.

[0017] Further technical solution: the weather similarity correction factor The method for obtaining it is expressed by the formula: ;

[0018] In the above formula, This refers to the superiority value of the j-th actual weather cycle characteristic data before human intervention, relative to the corresponding weather cycle characteristic baseline data. This refers to the superiority value of the weather cycle characteristic forecast data after human intervention relative to the corresponding weather cycle characteristic baseline data. This refers to the reference value for changes in the superiority value. It is the hyperbolic tangent function. This refers to the weighting coefficient of the j-th weather cycle feature, and N refers to the number of weather cycle feature data. To increase or decrease the superiority value using an analytical function, It refers to Compared to Increase or decrease in value; increase or decrease in value The absolute value is and The absolute difference between them;

[0019] The analytic method for increasing or decreasing the superiority value is as follows: If Greater than If the superiority value changes in an increasing trend, then the increase / decrease value will be... If it is a positive value, Less than The superiority value changes in a decreasing trend, while the increase / decrease value is... If it is a negative value; equal Then the increase or decrease value =0;

[0020] The aforementioned weather cycle characteristic benchmark data refers to the reference range of crop planting environment requirements in terms of weather cycle characteristics. The reference range includes the extreme values ​​and the optimal values ​​within the range; (for example, the best daytime cycle average temperature is between 10-15 degrees Celsius, and the optimal temperature is 13 degrees Celsius).

[0021] The superiority value is used to quantify the degree to which weather cycle characteristics meet the environmental requirements for crop cultivation, and the specific value is determined as follows:

[0022] Analyze whether the weather cycle characteristics are within the reference range. If the weather cycle characteristics are within the reference range, the superior value is positive, and the closer the weather cycle characteristics are to the best value within the range, the greater the superior value.

[0023] If the weather cycle characteristic is outside the reference range, the superior value is negative, and the closer the weather cycle characteristic is to the extreme value of the range, the greater the superior value.

[0024] Further technical solution: The determination of the crop status assessment value after intervention is expressed by the formula: ;

[0025] In the above formula, This refers to the crop status assessment value after intervention. This refers to the normalized value of the i-th state characteristic data of crops after human intervention. , refers to the weight coefficient of the i-th state feature of the crop, and m refers to the total number of state feature data of the crop.

[0026] Further technical solutions: The synergistic tilt between economic and ecological benefits specifically includes:

[0027] Based on the ecological characteristic data of crop planting areas before human intervention, the pre-intervention assessment value of the crop planting area ecology is determined; where the pre-intervention assessment value refers to the weighted sum of the normalized values ​​of all crop planting area ecological characteristic data before human intervention.

[0028] Based on the ecological characteristic data of crop planting areas after human intervention, the post-intervention assessment value of the crop planting area ecology is determined; where the post-intervention assessment value refers to the weighted sum of the normalized values ​​of all crop planting area ecological characteristic data after human intervention.

[0029] The ecological benefit assessment value is determined based on the pre-intervention assessment value and the post-intervention assessment value of the ecology of the crop planting area;

[0030] The economic benefit assessment value is determined based on the predicted crop status before intervention and the assessed crop status after intervention.

[0031] The degree of synergy between economic and ecological benefits is determined based on the ecological and economic benefit assessment values.

[0032] Further technical solution: The determination of the ecological benefit assessment value is expressed by the following formula: ;

[0033] In the above formula, This refers to the ecological benefit assessment value of human intervention. This refers to the pre-intervention assessment value. This refers to the post-intervention assessment value. This refers to the deviation reference value. This refers to the slope control parameter.

[0034] Further technical solution: The economic benefit assessment value is expressed by the formula: ;

[0035] In the above formula, This refers to the economic benefit assessment value of human intervention. This refers to the predicted crop condition before intervention. This refers to the crop status assessment value after intervention. This refers to the deviation reference value. This refers to the slope control parameter.

[0036] Further technical solution: The degree of synergy between economic and ecological benefits is determined based on the ecological benefit assessment value and the economic benefit assessment value, expressed by the formula: ;

[0037] In the above formula, This refers to the degree of synergy between economic and ecological benefits. This refers to the economic benefit assessment value of human intervention. This refers to the ecological benefit assessment value of human intervention. It is the arctangent function;

[0038] Among them, the range of values ​​for the synergistic tilt between economic and ecological benefits is positive and negative;

[0039] When the synergy between economic and ecological benefits is positive, it indicates that human intervention is biased towards economic benefits. The larger the absolute value of the synergy between economic and ecological benefits, the more it is biased towards economic benefits.

[0040] When the synergy between economic and ecological benefits is negative, it indicates that human intervention is biased towards ecological benefits. The larger the absolute value of the synergy between economic and ecological benefits, the more it is biased towards ecological benefits.

[0041] Further technical solution: The determination of the benchmark value for the synergistic tilt between economic and ecological benefits specifically includes:

[0042] Based on semantic analysis, development policies are mapped to baseline values ​​for basic synergy inclination.

[0043] Then, using the formula: ;

[0044] Determine the benchmark value for the synergistic tilt between economic and ecological benefits. ;

[0045] In the above formula, This refers to the baseline value of the basic coordination tilt. This refers to the importance level indicator value of the k-th ecological protection area. This refers to the minimum importance level indicator value. This refers to the maximum importance level indicator value, where M refers to the number of ecological protection areas. This refers to adjusting the scaling factor.

[0046] Further technical solution: The evaluation index for determining the coupling coordination degree between economic and ecological benefits is expressed by the following formula: ;

[0047] In the above formula, P refers to the evaluation index of the coupling and coordination degree between economic benefits and ecological benefits. This refers to the average degree of synergy between economic and ecological benefits corresponding to all recent human interventions. This refers to the benchmark value for the synergistic tilt between economic and ecological benefits.

[0048] This invention provides a method for evaluating the coupling and coordination degree of economic and ecological benefits in smart agriculture, which has the following advantages compared with existing technologies:

[0049] This invention captures human intervention behaviors and collects multi-source feature data to construct a prediction and evaluation model of the state before and after intervention. It calculates the synergistic tilt by combining ecological feature data and introduces regional surrounding information to dynamically set benchmark values, thereby realizing real-time quantitative coupling evaluation of economic and ecological benefits. It has the advantage of significantly improving the scientificity and practicality of the evaluation system. Attached Figure Description

[0050] Figure 1 This is a flowchart illustrating the evaluation method for the coupling and coordination of economic and ecological benefits in smart agriculture provided by the present invention.

[0051] Figure 2 This is a schematic diagram of the S40 process provided by the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0053] The specific implementation of the present invention will be described in detail below with reference to specific embodiments.

[0054] Please see Figure 1 The present invention provides a method for evaluating the coupling coordination degree of economic and ecological benefits in smart agriculture, comprising the following steps:

[0055] S10. Capture human intervention behaviors during crop planting, and collect crop status characteristic data, weather cycle characteristic data, and ecological characteristic data of crop planting areas before and after human intervention behaviors; among which, weather cycle characteristic data refers to the characteristics of weather within a specific cycle;

[0056] Weather cycle characteristic data refers to a quantitative description of weather conditions within a specific time period (such as a day, a week, or a growing season). These characteristics can include average temperature, rainfall fluctuations, standard deviation of sunshine hours, wind speed variance, etc., and are used to capture the impact of weather on crop growth.

[0057] Human intervention refers to specific operations performed by humans or automated equipment during the crop cultivation process that are intended to affect crop growth or environmental conditions. These include, but are not limited to, applying pesticides, applying fertilizers, and irrigating.

[0058] Ecological characteristic data of crop planting areas refer to various indicators that describe the ecological environment of crop planting areas. These data may include soil organic matter content, soil microbial diversity, water pollution level, biodiversity index, etc., and are used to assess the impact of agricultural activities on the ecosystem.

[0059] S20. Based on the crop condition characteristics data and weather forecast data before human intervention, determine the predicted values ​​of crop condition before intervention;

[0060] Crop status characteristic data refers to various indicators that describe the current growth status and health level of crops; these data may include leaf color, plant height, biomass, and the occurrence of pests and diseases, and are used to reflect the crop's response to the environment and interventions;

[0061] S30. Determine the crop status assessment value after intervention based on the crop status characteristic data after human intervention.

[0062] S40. Based on the predicted values ​​of crop status before intervention, the assessed values ​​of crop status after intervention, and the ecological characteristic data of crop planting areas, determine the degree of synergy between economic and ecological benefits.

[0063] S50. Collect information on the surrounding areas and development policies of crop planting areas, and determine the benchmark value of the synergistic tilt between economic and ecological benefits based on the surrounding information and development policies of crop planting areas; among which, the surrounding information of planting areas includes the importance level and number of ecological protection areas around the planting area.

[0064] Information surrounding the planting area refers to relevant data on the environment surrounding the crop planting area, including the importance level of the surrounding ecological protection areas (e.g., national level, provincial level) and the number of ecological protection areas, which are used to assess the sensitivity and constraints of the regional ecological environment.

[0065] Development policies refer to guidelines and regulations formulated by governments or relevant agencies to guide agricultural production, environmental protection, and economic development. These policies play a guiding role in evaluating the effectiveness of agricultural activities.

[0066] S60. Based on the synergy between economic and ecological benefits and the benchmark value of the synergy between economic and ecological benefits, determine the evaluation index of the coupling coordination degree between economic and ecological benefits.

[0067] The benchmark value for the synergistic tilt between economic and ecological benefits refers to a reference standard used to measure the ideal or acceptable level of the synergistic tilt between economic and ecological benefits in a specific region or under a specific policy background.

[0068] S70. Evaluate the degree of coordination between economic and ecological benefits in smart agriculture based on the evaluation index of the coupling coordination between economic and ecological benefits.

[0069] Specifically, in S10, human interventions during crop cultivation are captured, and data on crop condition characteristics, weather cycle characteristics, and ecological characteristics of the crop planting area before and after these interventions are collected. The purpose of this step is to provide foundational data for subsequent benefit evaluation. Specifically, human interventions can be captured in various ways. For example, they can be manually recorded by farm managers who input information such as the type, time, location, and dosage of intervention each time they perform operations such as spraying pesticides, fertilizing, or watering. Alternatively, sensor networks deployed in the farmland can be used; for example, the irrigation system can automatically record watering activities when it is activated, and fertilization information can be obtained from the operation logs of fertilizer applicators. Crop condition data can be collected through regular manual inspections, such as observing leaf color, measuring plant height, and recording the occurrence of pests and diseases. Weather cycle data can be obtained from local weather stations, such as obtaining average temperature, total rainfall, and sunshine duration over a past period. Ecological characteristics data of crop planting areas can be obtained through soil sampling and analysis, such as testing soil pH, organic matter content, nitrogen, phosphorus and potassium content, etc.

[0070] In step S20, based on pre-intervention crop condition data and weather forecast data, the predicted crop condition before intervention is determined. The purpose of this step is to establish a benchmark for evaluating the actual benefits of human intervention. Specifically, the predicted crop condition before intervention can be determined in several ways. For example, it can be based on historical crop growth data, using a simple statistical averaging method to predict the crop's growth trend over a future period without intervention. Alternatively, a basic linear regression model can be constructed, using historical crop condition data as input, to predict the future crop condition.

[0071] In step S30, a post-intervention crop status assessment value is determined based on crop status characteristic data following the human intervention. The purpose of this step is to quantify the actual impact of the human intervention on crop growth. Specifically, the post-intervention crop status assessment value can be determined in several ways. For example, a simple average or weighted average can be applied to the crop status characteristic data collected after the intervention to obtain a comprehensive assessment value. Alternatively, expert scoring can be used, where agricultural experts provide a comprehensive score for the crop status based on the performance of various post-intervention crop characteristic data.

[0072] In step S40, the synergistic tilt between economic and ecological benefits is determined based on the predicted crop status before intervention, the assessed crop status after intervention, and the ecological characteristic data of the crop planting area. The purpose of this step is to incorporate economic and ecological benefits into a unified evaluation framework and quantify the balance between them. Specifically, the synergistic tilt between economic and ecological benefits can be determined in several ways. For example, economic benefits (e.g., the difference between the assessed crop status after intervention and the predicted crop status before intervention) and ecological benefits (e.g., changes in the ecological characteristic data of the crop planting area before and after intervention) can be calculated separately, and then the synergistic tilt can be expressed as a simple ratio or difference.

[0073] In S50, information on the surrounding areas and development policies of crop planting regions is collected. Based on this information and these policies, a benchmark value for the synergistic tilt between economic and ecological benefits is determined. The purpose of this step is to provide a regionally and policy-based reference standard for the synergistic tilt. Specifically, the benchmark value for the synergistic tilt between economic and ecological benefits can be determined in several ways. For example, a fixed benchmark value can be set based on general agricultural sustainable development guidelines issued by the local agricultural department. Alternatively, a benchmark value can be set by simply weighting the importance level and number of ecological protection zones surrounding the planting area, combined with a qualitative description of the development policy.

[0074] In S60, an evaluation index for the coupling coordination degree of economic and ecological benefits is determined based on the synergistic tilt degree between economic and ecological benefits and its benchmark value. The purpose of this step is to provide a comprehensive indicator reflecting the sustainability level of agricultural production. Specifically, the evaluation index for the coupling coordination degree of economic and ecological benefits can be determined in several ways. For example, the difference between the actual synergistic tilt degree and the benchmark value can be directly calculated; a smaller difference indicates a higher degree of coupling coordination. Alternatively, a dimensionless evaluation index can be obtained by performing a simple ratio calculation between the actual synergistic tilt degree and the benchmark value.

[0075] In S70, the coupling coordination degree between economic and ecological benefits in smart agriculture is evaluated based on the evaluation index. The purpose of this step is to transform the quantified evaluation index into understandable and actionable evaluation results. Specifically, the evaluation of coupling coordination degree can be achieved in several ways. For example, the evaluation index can be compared with a preset threshold, thereby classifying the evaluation results into levels such as "excellent," "good," "average," or "poor." Alternatively, a visual report can be generated, intuitively displaying the evaluation index and its comparison with benchmark values ​​in chart form.

[0076] This invention captures human intervention behaviors and collects multi-source feature data to construct a prediction and evaluation model of the state before and after intervention. It calculates the synergistic tilt by combining ecological feature data and introduces regional surrounding information to dynamically set benchmark values, thereby realizing real-time quantitative coupling evaluation of economic and ecological benefits. It has the advantage of significantly improving the scientificity and practicality of the evaluation system.

[0077] Preferably, the present invention further proposes the determination of the predicted value of crop status before intervention, expressed by the formula: ;

[0078] In the above formula, This refers to the predicted crop condition before intervention. This refers to the weather similarity correction factor for the i-th state characteristic of crops. This refers to the normalized value of the i-th state feature data of the crop at time t. This refers to the normalized value of the i-th state feature data of the crop at time t-1. This refers to the normalized value of the i-th state feature data of the crop at time tn. This refers to the weight coefficient of the i-th state feature of the crop, and m refers to the total number of crop state feature data.

[0079] Among them, determining the pre-intervention crop status prediction value refers to the quantitative prediction of the crop growth status in the future period before the human intervention occurs. This prediction value serves as the benchmark for evaluating the effect of human intervention, and its accuracy directly affects the reliability of subsequent benefit evaluation.

[0080] ARIMA models are statistical models widely used in time series data analysis and forecasting. By combining autoregressive (AR), differencing (I), and moving average (MA) components, they effectively capture trends, seasonality, and stochastic fluctuations in time series data. In agriculture, ARIMA models can be used to analyze the patterns of various state characteristics (such as leaf area index, biomass, and plant height) during crop growth over time and to predict future states based on historical data. This can be achieved by using standard statistical software packages (such as R or Python's statsmodels library) to identify, estimate, and diagnose model parameters, or by building deep learning models based on ARIMA principles using machine learning frameworks (such as TensorFlow and PyTorch).

[0081] The weather similarity correction factor for the i-th state characteristic of crops is a dynamically adjusted parameter used to quantify the impact of future weather conditions on the predicted value of the i-th state characteristic of crops. This correction factor can adjust the prediction results of the ARIMA model based on historical trends according to the similarity between weather forecast data and historical weather patterns, thereby more accurately reflecting the actual growth potential of crops under specific future weather conditions. This correction factor can be trained based on the correlation between historical weather data and crop state characteristics; for example, by constructing a regression model or neural network to predict the changing trends of crop state characteristics under different weather conditions and converting these trends into a correction factor.

[0082] The weight coefficient of the i-th state feature of a crop is used to represent the relative importance of the i-th state feature in the overall crop state assessment. Different crop state features have different degrees of influence on the final yield, quality, or economic benefits. By assigning different weight coefficients, it can be ensured that key features that have a greater impact on crop yield are given more full consideration during the prediction process. The determination of the weight coefficients can be based on agricultural expert experience, historical data statistical analysis (such as correlation analysis, principal component analysis), or optimized through machine learning algorithms (such as feature selection algorithms).

[0083] The normalized value of the i-th state feature data of a crop refers to the value of the original crop state feature data transformed to a uniform scale range. Since different crop state features may have different dimensions and numerical ranges, directly performing weighted summation or model input may amplify or reduce the influence of some features. Normalization maps all feature data to the same interval (e.g., 0 to 1), thereby eliminating dimensional differences, ensuring the comparability of each feature in the model, and improving the accuracy and stability of predictions. Common normalization methods include min-max normalization and Z-score standardization.

[0084] Specifically, this scheme utilizes the ARIMA model to conduct time-series analysis of crop state characteristic data, effectively capturing the inherent evolutionary patterns during crop growth. Building upon this, by introducing a weather similarity correction factor, the potential impact of weather factors on crop state is quantified and integrated into the prediction model. This ensures that the predicted values ​​are no longer simply extensions of historical data, but rather dynamic assessments incorporating anticipated environmental changes. By assigning weight coefficients to different state characteristics, key characteristics with a significant impact on yield are ensured to dominate the prediction, thereby improving the relevance and reliability of the prediction results.

[0085] This approach, which combines time-series forecasting with environmental correction, provides a scientific benchmark for assessing the actual contribution of human interventions, effectively addressing the insufficient adaptability of single forecasting models in complex and variable agricultural environments. The pre-intervention crop state predictions obtained through this method provide more accurate input for determining the synergistic effect between economic and ecological benefits, thereby improving the overall accuracy and reliability of the evaluation of the coupling and coordination between economic and ecological benefits in smart agriculture.

[0086] Preferably, the present invention further proposes the weather similarity correction factor. The method for obtaining it is expressed by the formula: ;

[0087] In the above formula, This refers to the superiority value of the j-th actual weather cycle characteristic data before human intervention, relative to the corresponding weather cycle characteristic baseline data. This refers to the superiority value of the weather cycle characteristic forecast data after human intervention relative to the corresponding weather cycle characteristic baseline data. This refers to the reference value for changes in the superiority value. It is the hyperbolic tangent function. This refers to the weighting coefficient of the j-th weather cycle feature, and N refers to the number of weather cycle feature data. To increase or decrease the superiority value using an analytical function, It refers to Compared to Increase or decrease in value; increase or decrease in value The absolute value is and The absolute difference between them;

[0088] The analytic method for increasing or decreasing the superiority value is as follows: If Greater than If the superiority value changes in an increasing trend, then the increase / decrease value will be... If it is a positive value, Less than The superiority value changes in a decreasing trend, while the increase / decrease value is... If it is a negative value; equal Then the increase or decrease value =0;

[0089] The aforementioned weather cycle characteristic benchmark data refers to the reference range of crop planting environment requirements in terms of weather cycle characteristics. The reference range includes the extreme values ​​and the optimal values ​​within the range; (for example, the best daytime cycle average temperature is between 10-15 degrees Celsius, and the optimal temperature is 13 degrees Celsius).

[0090] The superiority value is used to quantify the degree to which weather cycle characteristics meet the environmental requirements for crop cultivation, and the specific value is determined as follows:

[0091] Analyze whether the weather cycle characteristics are within the reference range. If the weather cycle characteristics are within the reference range, the superior value is positive, and the closer the weather cycle characteristics are to the best value within the range, the greater the superior value.

[0092] If the weather cycle characteristic is outside the reference range, the superior value is negative, and the closer the weather cycle characteristic is to the extreme value of the range, the greater the superior value.

[0093] Among them, the weather similarity correction factor is a coefficient used to adjust the predicted value of crop status. Its role is to reflect the comprehensive impact of weather changes on crop growth status. It corrects the predicted value by quantifying the similarity between the actual weather and the forecast weather and the degree of influence of this similarity on crop status.

[0094] The superiority value of the j-th actual weather cycle characteristic data before human intervention, relative to the corresponding weather cycle characteristic benchmark data, quantifies the degree to which the observed j-th weather cycle characteristic data conforms to the ideal growth environment requirements of crops (i.e., the weather cycle characteristic benchmark data) before human intervention occurs. Its function is to provide a quantitative benchmark for the impact of historical weather conditions on the crop growth environment. This can be achieved by comparing the actual weather data with the benchmark data using a pre-defined function or lookup table, and calculating the superiority value according to predefined rules (such as distance from the optimal value, whether it is within the suitable range); or by using a fuzzy logic system to map the actual weather data to different superiority levels.

[0095] The superiority value of the forecast data for the j-th weather cycle characteristic after human intervention, relative to the corresponding weather cycle characteristic baseline data, quantifies the degree of conformity between the predicted j-th weather cycle characteristic data and the ideal growth environment requirements of crops (i.e., the weather cycle characteristic baseline data) after the human intervention. Its function is to provide a quantitative prediction of the impact of future weather conditions on the crop growth environment. Implementation method and... Similarly, but the input data source is weather forecast data. For example, short- or medium-term weather forecast data provided by meteorological departments can be used in conjunction with crop growth models to calculate the potential impact of future weather on crop conditions.

[0096] The reference value for the variation of the weather superiority value is used to normalize the variation of the superiority value, so that weather characteristics with different dimensions or ranges of variation can be compared on a unified scale. Its function is to ensure that the hyperbolic tangent function can be mapped within an appropriate range, avoiding insignificant or overly drastic correction effects due to values ​​that are too large or too small. This can be achieved by setting a fixed value that represents the typical amplitude of the variation in the superiority value; or by statistically analyzing historical data to calculate the mean absolute deviation or standard deviation of the variation in the superiority value as a reference value.

[0097] The hyperbolic tangent function is a non-linear activation function used to map the normalized increase or decrease of the superiority value reference value to a finite range (typically between -1 and 1). Its purpose is to smooth the impact of weather changes on the correction factor, ensuring that the correction factor does not respond too sensitively or drastically to extreme weather changes, thereby enhancing the model's robustness. It is implemented by directly calling the hyperbolic tangent function calculation interface in the mathematical library.

[0098] The weighting coefficient of the j-th weather cycle feature reflects the degree of influence of the j-th weather cycle feature on the i-th state feature of the crop. Its function is to differentiate the weighting of the correction factor based on the actual importance of different weather factors to crop growth, ensuring that more important weather factors play a greater role in the correction process. This can be achieved through expert experience, setting the weights based on agronomic knowledge and crop physiological characteristics; or through machine learning methods, such as regression analysis or feature selection algorithms, learning from historical data.

[0099] The superiority value increment / decrement analytic function is used to calculate Compared to The increase or decrease value represents the trend and magnitude of the future weather favorableness value relative to the historical weather favorableness value. Its function is to capture the dynamic changes in weather conditions before and after intervention and to determine whether these changes tend to improve or worsen. This is achieved by making judgments and calculations based on preset logical rules; for example, if... Greater than If the increase or decrease is positive, it indicates improvement; otherwise, it is negative, indicating deterioration.

[0100] Weather cycle characteristic baseline data is a set of weather parameter reference ranges that define the ideal growing environment requirements for crops. Its purpose is to provide an objective standard for assessing the "superiority" of actual and forecast weather. This baseline data can include extreme values ​​and optimal values ​​within the range. For example, by reviewing agricultural literature, consulting experts, or analyzing long-term field trial data, the suitable ranges and optimal values ​​for weather factors such as temperature, humidity, and light at different growth stages of different crops can be determined. Alternatively, it can be statistically summarized based on agricultural production experience and historical high-yield data for a specific region.

[0101] Superiority values ​​are used to quantify the degree to which weather cycle characteristics meet the environmental requirements for crop cultivation. Their function is to transform complex weather data into an intuitive indicator directly related to crop growth needs, facilitating subsequent comparison and correction. The calculation method can be determined based on pre-defined logical judgments and calculation rules. For example, it can be done by analyzing whether the weather cycle characteristics are within a reference range and assigning positive or negative values ​​based on their proximity to the optimal or extreme values ​​within that range; alternatively, a fuzzy membership function-based method can be used to map weather characteristic values ​​to a conformity score between 0 and 1.

[0102] This application achieves refined dynamic adjustment of crop state prediction by constructing a weather similarity correction factor. First, the method introduces the concept of superiority value, transforming complex weather cycle characteristics into a quantitative indicator of the degree of conformity with crop growth environment requirements, thus directly linking weather data to crop growth needs. Based on this, an analytical function for the increase and decrease of superiority value is used to accurately capture the differences in weather change trends before and after human intervention. Furthermore, a hyperbolic tangent function is used to perform a nonlinear mapping of the increase and decrease values, effectively smoothing the impact of extreme weather fluctuations and avoiding drastic oscillations in predicted values. Simultaneously, by combining weighting coefficients for different weather cycle characteristics, differentiated correction of crop state characteristics is achieved, ensuring that the correction process reflects the actual weight of different weather factors on the specific crop state.

[0103] This comprehensive correction mechanism, based on environmental demand compliance and weather change trends, significantly improves the accuracy and robustness of pre-intervention crop status predictions. By applying this correction factor to the method for determining pre-intervention crop status predictions, the predicted crop status not only considers historical time-series data but also dynamically incorporates the impact of weather forecast data on crop growth environment compliance and the changing trends of this impact. This makes the prediction results closer to reality and solves the problem of insufficient or inaccurate consideration of weather factors in traditional prediction methods. This mechanism ensures that crop status predictions can dynamically respond to weather changes, improving prediction accuracy and robustness.

[0104] Preferably, the present invention further proposes the determination of the crop status assessment value after intervention, expressed by the formula: ;

[0105] In the above formula, This refers to the crop status assessment value after intervention. This refers to the normalized value of the i-th state characteristic data of crops after human intervention. This refers to the weight coefficient of the i-th state feature of the crop, and m refers to the total number of crop state feature data.

[0106] This method aims to quantify the actual impact of human intervention on crop status. Its function is to integrate multi-dimensional and heterogeneous crop status characteristic data into a single, comparable value, thereby providing a unified standard for subsequent benefit assessment.

[0107] The purpose of normalizing the i-th state characteristic data of crops after human intervention is to eliminate differences in units, values, and ranges among different crop state characteristic data, making them comparable. For example, crop height may be measured in centimeters, and chlorophyll content may be measured in SPAD values; directly adding the two is meaningless. Through normalization, all characteristic values ​​can be mapped to a unified interval (such as [0,1] or [-1,1]), so that the numerical value can directly reflect the quality of the crop's state. Normalization methods can include min-max normalization, which linearly scales the data to a specified range, or Z-score normalization, which converts the data into a distribution with a mean of 0 and a standard deviation of 1.

[0108] The weight coefficient of the i-th state characteristic of a crop is used to reflect the relative importance of different crop state characteristics to the overall growth status or yield of the crop. For example, for a certain crop, the degree of leaf pests and diseases may have a greater impact on yield than the thickness of the stem, so its weight coefficient should be higher. The weight coefficient can be determined based on expert experience and domain knowledge, such as by agronomic experts scoring the impact of different characteristics on crop health and yield; or by data-driven methods, such as using historical data for regression analysis or training machine learning models to automatically learn and optimize the weights based on the contribution of the characteristics to the target variable (such as final yield or health index).

[0109] This application proposes a weighted summation model to determine the post-intervention crop status assessment value. Upon receiving crop status characteristic data collected after human intervention, the raw data is first normalized, mapping characteristic values ​​of different dimensions and ranges to a comparable numerical interval, ensuring data consistency and comparability. Subsequently, each normalized crop status characteristic data point is weighted according to pre-set weighting coefficients. These weighting coefficients reflect the relative importance of different characteristics to the overall crop status or yield. Finally, all weighted characteristic values ​​are summed to obtain a single, comprehensive post-intervention crop status assessment value. This assessment value comprehensively and objectively reflects the actual growth status of crops after human intervention, providing a standardized quantitative basis for subsequent economic benefit assessments.

[0110] In this way, the solution simplifies the complex multi-dimensional state information of crops into an intuitive numerical value, effectively solving the problem of the lack of unified quantitative standards in traditional assessments, and making the assessment of the effects of human intervention more accurate and scientific.

[0111] For preferred options, please refer to [link / reference]. Figure 2 The present invention further proposes the aforementioned synergistic tilt between economic and ecological benefits, specifically including:

[0112] S41. Based on the ecological characteristic data of crop planting areas before human intervention, determine the pre-intervention assessment value of the crop planting area ecology; wherein, the pre-intervention assessment value refers to the weighted sum of the normalized values ​​of all crop planting area ecological characteristic data before human intervention.

[0113] S42. Based on the ecological characteristic data of crop planting areas after human intervention, determine the post-intervention assessment value of the crop planting area ecology; wherein, the post-intervention assessment value refers to the weighted sum of the normalized values ​​of all crop planting area ecological characteristic data after human intervention.

[0114] S43. Determine the ecological benefit assessment value based on the pre-intervention assessment value and post-intervention assessment value of the ecology of the crop planting area;

[0115] S44. Determine the economic benefit assessment value based on the predicted crop status before intervention and the assessed crop status after intervention.

[0116] S45. Determine the degree of synergy between economic and ecological benefits based on the ecological benefit assessment value and the economic benefit assessment value.

[0117] In the above technical solution, the pre-intervention assessment value of the crop planting area's ecology is determined based on the ecological characteristic data of the crop planting area before human intervention. This pre-intervention assessment value refers to the weighted sum of the normalized values ​​of all ecological characteristic data of the crop planting area before human intervention. Here, "ecological characteristic data of the crop planting area before human intervention" refers to a set of data that quantitatively describes the ecological environment of the crop planting area before agricultural production activities (such as fertilization, pesticide application, and irrigation). This data may include, but is not limited to, soil pH, organic matter content, nitrogen, phosphorus, and potassium content, heavy metal content, microbial diversity index, chemical oxygen demand (COD), ammonia nitrogen content, and dissolved oxygen level of water bodies (such as irrigation water sources), as well as biodiversity indicators within the area (such as insect species and bird activity frequency). This data can be collected in real-time or near real-time using various sensors deployed in farmland (such as soil sensors, water quality sensors, and air quality sensors), or obtained through periodic sampling and laboratory analysis. The "Pre-Intervention Assessment Value of Crop Planting Area Ecology" is a single indicator derived from the comprehensive quantification of these multi-dimensional ecological characteristic data, aiming to fully reflect the ecological health level before intervention. This assessment value can be obtained by normalizing each ecological characteristic data and then assigning different weights to them according to their importance to the ecological environment, followed by weighted summation. For example, normalization can use the Min-Max standardization method to scale the data to the [0,1] interval, or the Z-score standardization method to convert the data into a distribution with a mean of 0 and a standard deviation of 1. The weight coefficients can be determined based on expert experience, historical data analysis, or by training and learning a large amount of ecological data using machine learning models (such as support vector machines and random forests).

[0118] Similarly, based on the ecological characteristic data of crop-growing areas after human intervention, a post-intervention assessment value for the ecology of these areas is determined. This post-intervention assessment value refers to the weighted sum of the normalized values ​​of all ecological characteristic data of crop-growing areas after the human intervention. Here, "ecological characteristic data of crop-growing areas after human intervention" refers to ecological environment data collected again from crop-growing areas some time after the human intervention. The data types and collection methods are similar to those of the pre-intervention ecological characteristic data, aiming to capture the actual impact of the intervention on the ecological environment. The "post-intervention assessment value for the ecology of crop-growing areas" is a comprehensive quantitative indicator of the ecological status after the intervention. Its calculation method is the same as the pre-intervention assessment value, obtained by weighted summation of the normalized ecological characteristic data. By comparing the assessment values ​​before and after the intervention, it is possible to intuitively understand whether the intervention had a positive or negative impact on the ecological environment.

[0119] When determining the ecological benefit assessment value, this step aims to quantify the net impact of human intervention on the ecological environment. In addition to using the Sigmoid function for calculation, the ecological benefit assessment value can also be expressed by directly calculating the difference or ratio between the post-intervention assessment value and the pre-intervention assessment value.

[0120] In determining the economic benefit assessment value, this step aims to quantify the net impact of human intervention on crop growth status (and consequently, economic output). Specifically, besides using the Sigmoid function for calculation, the economic benefit assessment value can also be represented by directly calculating the difference or ratio between the post-intervention crop status assessment value and the pre-intervention crop status prediction value.

[0121] Finally, based on the ecological and economic benefit assessment values, the synergistic tilt between economic and ecological benefits is determined. This step aims to integrate independent economic and ecological benefits into a unified indicator to reflect the bias of intervention behavior between the two. Besides calculation using the arctangent function form given in a subsequent scheme, the synergistic tilt can also be represented by constructing a two-dimensional coordinate system, with the economic and ecological benefit assessment values ​​as coordinate axes. The synergistic tilt can be expressed as the angle between a vector representing the benefit combination and a specific axis (e.g., a 45-degree line representing the equilibrium state). Alternatively, a dynamic weighted average method can be used, dynamically adjusting the weights according to the relative magnitudes of economic and ecological benefits to obtain a comprehensive indicator that reflects the bias.

[0122] This application's solution achieves quantitative analysis of the impact of agricultural human intervention by constructing a multi-dimensional benefit assessment logic. First, by normalizing and weighting the ecological characteristic data of crop planting areas before and after human intervention, pre-intervention and post-intervention ecological assessment values ​​are obtained. This process dynamically captures the direct changes in the ecological environment of the planting area caused by human intervention, providing basic data support for subsequent assessments. Based on this, by comparing the ecological assessment values ​​before and after intervention, an ecological benefit assessment value is determined, transforming complex ecological characteristics into a single benefit indicator, effectively quantifying the degree of improvement or damage to the ecological environment caused by the intervention. Simultaneously, by comparing the predicted crop state before intervention and the assessed crop state after intervention, an economic benefit assessment value is determined. This step directly links changes in crop growth status to economic output, ensuring the objectivity of the economic benefit evaluation. Finally, the ecological benefit assessment value and the economic benefit assessment value are comprehensively calculated to determine the synergistic tilt between economic and ecological benefits.

[0123] The core contribution of this technology lies in unifying the previously independent economic and ecological dimensions within a single evaluation framework. Through the calculation of synergistic tilt, it clearly reveals the trade-off between human intervention and ecological protection. Furthermore, this approach is closely integrated with the steps of capturing human intervention during crop cultivation, collecting relevant data, and determining the predicted and post-intervention crop status. This ensures that the calculation of synergistic tilt is based on comprehensive, dynamic, and predictively corrected data, thereby guaranteeing the accuracy and reliability of the evaluation results. This integrated evaluation system makes the assessment of the coupling and coordination between the economic and ecological benefits of smart agriculture more scientific and comprehensive.

[0124] Preferably, the present invention further proposes the determination of the ecological benefit assessment value, expressed by the formula: ;

[0125] In the above formula, This refers to the ecological benefit assessment value of human intervention. This refers to the pre-intervention assessment value. This refers to the post-intervention assessment value. This refers to the deviation reference value. This refers to the slope control parameter;

[0126] The ecological benefit assessment value of this human intervention is an indicator that quantifies the degree of impact of a specific human intervention on the ecological environment of a crop-growing area. Its value typically ranges from 0 to 1; a higher value indicates a more significant improvement in the ecological environment or a smaller negative impact. This assessment value aims to provide a standardized, quantitative result that can be compared with other benefits (such as economic benefits).

[0127] Pre-intervention assessment values ​​reflect the overall state of the ecological environment in crop-growing areas before human intervention. These values ​​can be obtained by normalizing all ecological characteristic data of crop-growing areas before human intervention and then performing a weighted sum. For example, different weights can be assigned to ecological characteristic data such as soil organic matter content, water pollution index, and biodiversity index, based on their importance to the ecological environment, thereby comprehensively assessing the ecological baseline state before intervention.

[0128] Post-intervention assessment values ​​reflect the overall state of the ecological environment in crop-growing areas after human intervention. These values ​​can be obtained by normalizing all ecological characteristic data from crop-growing areas following human intervention, followed by a weighted sum. For example, after fertilization, data such as soil nutrient content and groundwater nitrate concentration can be collected, normalized, and weighted to assess the immediate or short-term impact of fertilization on the ecological environment.

[0129] The deviation reference value is used to normalize the difference between the pre-intervention and post-intervention assessment values. Its purpose is to eliminate the influence of differences in the dimensions and magnitudes of variation of different ecological characteristic data, making the assessment model applicable to agricultural planting areas of different sizes and types. For example, the deviation reference value can be set based on the average magnitude or standard deviation of historical ecological data changes to ensure that minor changes in ecological status are not over-amplified, while significant changes are effectively reflected. Another approach is to set a threshold based on expert experience or industry standards; when the change in ecological status exceeds this threshold, it is considered a meaningful change, and this threshold is used as the reference for the deviation reference value.

[0130] The slope control parameter is used to adjust the sensitivity of the ecological benefit assessment value to changes in ecological state. By adjusting the magnitude of the slope control parameter, the steepness of the logistic function curve can be controlled, thereby determining the degree of impact of small changes in ecological state on the final assessment value. For example, when a high degree of sensitivity to subtle changes in the ecological environment is required, a larger slope control parameter can be set so that even small improvements or deteriorations in the ecological state will lead to... Significant changes may occur. Conversely, when it is desirable for the assessment values ​​to be less sensitive to small fluctuations and to focus more on significant ecological trends, a smaller slope control parameter can be set. This parameter can be flexibly adjusted according to the specific characteristics of the agro-ecosystem, policy orientation, or risk appetite.

[0131] Specifically, this scheme first acquires ecological characteristic data of crop planting areas before human intervention, and then normalizes and weights the data to obtain the pre-intervention assessment value. Similarly, it acquires ecological characteristic data of crop planting areas after human intervention, and then normalizes and weights the data to obtain the post-intervention assessment value. Subsequently, the difference between the two is calculated, which directly reflects the direction and magnitude of the impact of human intervention on the ecological environment. To transform this raw difference into a standardized ecological benefit assessment value with non-linear response characteristics, this scheme normalizes the difference by dividing it by a deviation reference value to eliminate the influence of differences in the dimensions of different ecological characteristic data. The normalized difference is used as the input to the logistic function, and the steepness of the function is adjusted by the slope control parameter to control... Sensitivity to changes in the ecological state.

[0132] This logistic function-based assessment method transforms complex ecological state changes into standardized assessment values ​​between 0 and 1. When the post-intervention assessment value is significantly better than the pre-intervention assessment value, it indicates that the ecological environment has improved, and the ecological benefit assessment value will approach 1; conversely, the ecological benefit assessment value will approach 0. This nonlinear mapping mechanism can more accurately reflect the true degree of improvement or deterioration of the ecological environment, avoiding the assessment distortion problems that may occur in traditional linear weighted summation methods when dealing with extreme changes or sensitive areas. By quantifying ecological benefits into standardized values... This provides a solid foundation for subsequent comparative analysis with economic benefit assessment values ​​in a unified dimension, thereby enabling a more scientific determination of the synergistic tilt between economic and ecological benefits, and ultimately evaluating the coupling coordination degree of smart agriculture.

[0133] Preferably, the present invention further proposes the aforementioned economic benefit assessment value, expressed by the formula: ;

[0134] In the above formula, This refers to the economic benefit assessment value of human intervention. This refers to the predicted crop condition before intervention. This refers to the crop status assessment value after intervention. This refers to the deviation reference value. This refers to the slope control parameter;

[0135] Among them, the economic benefit assessment value of human intervention is an indicator used to quantify the impact of specific human interventions on the economic output of crops. It aims to transform complex changes in crop conditions into a standardized, comparable value to facilitate subsequent synergistic analysis of economic and ecological benefits. This assessment value, mapped through a nonlinear function, can more accurately reflect the actual contribution of interventions to economic benefits, avoiding the biases that may arise from simple linear comparisons.

[0136] Pre-intervention crop status predictions represent the expected state of crops obtained through comprehensive analysis and forecasting of crop status characteristics and weather forecast data before any human intervention. They serve as a benchmark for evaluating the effectiveness of the intervention, reflecting the state crops might have reached without the intervention or under specific weather conditions. By incorporating historical time-series data and weather similarity corrections, these predictions improve accuracy and dynamic responsiveness.

[0137] The post-intervention crop status assessment value represents the actual state of crops obtained by collecting and evaluating crop status characteristic data after human intervention. It is a direct basis for measuring the actual effect of the intervention and reflects the true growth status of crops after the intervention measures are implemented.

[0138] The deviation reference value is used to normalize the difference between the predicted crop status before intervention and the assessed crop status after intervention. By introducing the deviation reference value, the status changes of different crops, different intervention behaviors, or different dimensions can be unified on a comparable scale, thereby eliminating the impact of dimensional differences on the assessment results and making the economic benefit assessment values ​​universal and comparable. The deviation reference value can be obtained from statistical analysis of historical data; for example, it can be set as the average fluctuation range of crop status characteristic data within a certain time range, or as a threshold determined by expert experience.

[0139] The slope control parameter is used to adjust the slope of the logistic function (Sigmoid function) in the economic benefit assessment model, thereby controlling the model's response curve to changes in crop condition. By adjusting the slope control parameter, the assessment model can be flexibly made to exhibit different sensitivities to small or significant changes in condition under different application scenarios. For example, a larger slope control parameter can be set when high sensitivity to small changes is required; a smaller slope control parameter can be set when smoothing out data fluctuations and focusing more on overall trends is needed. This parameter can be set according to actual application needs, crop characteristics, or expert experience, or it can be optimized by learning from historical data using machine learning methods.

[0140] This application's solution achieves standardized quantification of the economic benefits of human intervention by constructing an economic benefit evaluation model based on logistic functions. The core of this model lies in transforming the difference between the predicted crop state before intervention and the assessed crop state after intervention into a unified economic benefit evaluation value through nonlinear mapping. Specifically, the model first calculates... The difference between the values ​​is directly reflected in the degree of influence of human intervention on crop condition. To eliminate differences in the dimensions of characteristics of different crops or different conditions, this difference is normalized using a deviation reference value to make the processed values ​​comparable. Subsequently, the normalized difference is input into the logistic function, which non-linearly maps the input value to a finite interval (e.g., between 0 and 1), thereby transforming the change in economic benefit into a standardized evaluation value. The slope control parameter plays a crucial role in this process, determining the steepness of the logistic function and thus controlling the sensitivity of the evaluation model to changes in crop condition.

[0141] In this way, even minute changes in crop condition can be effectively captured and reasonably quantified, while avoiding the excessive influence of extreme values ​​on the assessment results. This scheme, closely integrated with the methods for obtaining pre-intervention crop condition predictions and post-intervention crop condition assessments, forms a complete chain for economic benefit assessment. Pre-intervention crop condition predictions comprehensively consider historical crop condition characteristics and weather forecast data, dynamically adjusting the prediction results through weather similarity correction factors to make the baseline prediction more accurate and closer to reality. Post-intervention crop condition assessments directly reflect the actual crop condition after the intervention. Using these two values ​​as inputs to the economic benefit assessment model ensures that the assessment of economic benefits is based on the most accurate capture of changes in crop condition.

[0142] This combination not only solves the problem of the lack of unified quantitative standards for economic benefit assessment in traditional methods, but also enables the assessment results to more realistically reflect the actual contribution of human intervention to economic output through nonlinear mapping, providing accurate and standardized economic dimension input for subsequent calculation of the synergistic tilt between economic and ecological benefits.

[0143] Preferably, the present invention further proposes to determine the synergistic tilt between economic and ecological benefits based on the ecological benefit assessment value and the economic benefit assessment value, expressed by the following formula: ;

[0144] In the above formula, This refers to the degree of synergy between economic and ecological benefits. This refers to the economic benefit assessment value of human intervention. This refers to the ecological benefit assessment value of human intervention. It is the arctangent function;

[0145] Among them, the range of values ​​for the synergistic tilt between economic and ecological benefits is positive and negative;

[0146] When the synergy between economic and ecological benefits is positive, it indicates that human intervention is biased towards economic benefits. The larger the absolute value of the synergy between economic and ecological benefits, the more it is biased towards economic benefits.

[0147] When the synergy between economic and ecological benefits is negative, it indicates that human intervention is biased towards ecological benefits. The larger the absolute value of the synergy between economic and ecological benefits, the more it is biased towards ecological benefits.

[0148] Among them, the synergistic tilt between economic and ecological benefits is a quantitative indicator used to characterize the direction and degree of the comprehensive impact of human intervention on economic and ecological benefits in smart agriculture. Its core lies in integrating two independent benefit assessment values ​​into a unified measurement system, with the positive or negative sign indicating the direction of the tilt and the absolute value indicating the degree of the tilt.

[0149] The arctangent function is a trigonometric function that takes a ratio as input and outputs an angle. In this scheme, it maps the ratio of the economic benefit assessment value to the ecological benefit assessment value to an angle, thereby transforming two independent benefit dimensions into a unified polar coordinate space. This mapping method can effectively capture the relative relationship between the two benefits, providing a foundation for subsequent slope calculations. The formula first calculates... and The arctangent of the ratio of economic benefits to ecological benefits is used to obtain an angle, which intuitively reflects the "intensity" or "dominance" of economic benefits relative to ecological benefits. Next, 45 degrees are subtracted from this angle; 45 degrees represents the case where economic and ecological benefits are equal in a rectangular coordinate system. By subtracting 45 degrees, the tilt is zero when economic and ecological benefits are balanced, thus using the equilibrium point as a reference benchmark. Finally, the result is normalized by dividing by 90 degrees, ensuring that the final synergistic tilt falls within a preset, easily understood numerical range, making the tilt comparable across different scenarios. A positive synergistic tilt indicates that human intervention is biased towards economic benefits; a negative tilt indicates that human intervention is biased towards ecological benefits. The larger the absolute value of the tilt, the greater the degree of bias. This design makes the evaluation results intuitive and quantitatively meaningful.

[0150] Specifically, firstly, the economic and ecological benefit assessment values ​​of the human intervention are obtained through the aforementioned steps. These two assessment values ​​quantify the effects of the intervention from two dimensions: economic output and ecological impact, respectively. Then, these two assessment values ​​are used as input, and their ratio is mapped to an angle space using the arctangent function. This mapping cleverly places the originally independent economic and ecological benefits in a unified two-dimensional coordinate system, where changes in the angle reflect the relative weights between them. To make the assessment results more intuitive and interpretable, the angle value is further normalized by subtracting 45 degrees and then by 90 degrees. Subtracting 45 degrees sets the balance point between economic and ecological benefits as a baseline point with a slope of 0, so that positive values ​​clearly indicate a bias towards economic benefits, and negative values ​​clearly indicate a bias towards ecological benefits. Normalization ensures that the range of slope values ​​is standardized, facilitating comparisons between different intervention behaviors.

[0151] In this way, the scheme simplifies the complex relationship between economic and ecological benefits into a single numerical value with direction and magnitude, thus clearly revealing the benefit bias of human intervention and solving the technical problem that traditional evaluation methods struggle to quantify the direction and magnitude of benefit synergy. This calculation method, closely integrated with the aforementioned steps for obtaining economic and ecological benefit assessment values, constitutes a complete and dynamically responsive smart agriculture benefit evaluation system. This allows the evaluation results to not only reflect the merits of individual benefits but also reveal the synergistic relationship between the two, providing decision-makers with a more comprehensive reference.

[0152] Preferably, the present invention further proposes the benchmark value for determining the synergistic tilt between economic and ecological benefits, specifically including:

[0153] Based on semantic analysis, development policies are mapped to baseline values ​​for basic synergy inclination.

[0154] Then, using the formula: ;

[0155] Determine the benchmark value for the synergistic tilt between economic and ecological benefits. ;

[0156] In the above formula, This refers to the baseline value of the basic coordination tilt. This refers to the importance level indicator value of the k-th ecological protection area. This refers to the minimum importance level indicator value. This refers to the maximum importance level indicator value, where M refers to the number of ecological protection areas. This refers to adjusting the scaling factor;

[0157] One approach involves mapping development policies to a baseline value for synergistic tilt between economic and ecological benefits based on semantic analysis. This aims to transform qualitative development policies into quantitative values, serving as the initial setting for the baseline value for synergistic tilt between economic and ecological benefits. Semantic analysis can employ Natural Language Processing (NLP) techniques, such as keyword extraction, sentiment analysis, or topic modeling, to identify guiding information related to economic development and ecological protection from policy texts. For example, if a policy emphasizes economic priority, the baseline value for synergistic tilt can be set to a positive value; if it emphasizes ecological protection, it can be set to a negative value; and if it emphasizes balanced development, it can be set to a value close to zero. Another approach is to construct a policy guidance database, associating different types of development policies with a preset range of baseline values ​​for synergistic tilt, and obtaining the corresponding baseline value for synergistic tilt by matching the type of the current policy.

[0158] The formula and its components for determining the benchmark value of the synergistic tilt between economic and ecological benefits are used to correct the basic benchmark value of synergistic tilt based on the ecological protection situation around the planting area, so as to obtain the final benchmark value of the synergistic tilt between economic and ecological benefits.

[0159] Among them, the baseline value of basic synergy tilt is an initial baseline obtained through semantic analysis based on development policies, reflecting the basic orientation of macro policies towards the synergy tilt between economic and ecological benefits.

[0160] The importance level indicator value of the k-th ecological protection area quantifies the importance level of the k-th ecological protection area surrounding the planting area. For example, ecological protection areas can be divided into different levels, such as national nature reserves, provincial nature reserves, and municipal wetland parks, and each level can be assigned an indicator value. For example, national nature reserves correspond to higher indicator values, while municipal parks correspond to lower indicator values. Another approach is to comprehensively score the ecological protection area based on indicators such as its ecological function, biodiversity richness, and degree of threat, and use the score result as its importance level indicator value.

[0161] The minimum and maximum importance level indicator values ​​represent the minimum and maximum values ​​among all the importance level indicator values ​​of ecological protection areas, respectively. They are used to normalize the importance level indicator values ​​of each ecological protection area so that they fall within the range of 0 to 1, so as to facilitate unified calculation and comparison in the formula.

[0162] The scaling factor is used to adjust the overall impact of the ecological protection area correction term. For example, when it is necessary to emphasize the impact of the ecological protection area, the scaling factor can be set to a value greater than 1; when it is necessary to reduce its impact, it can be set to a value less than 1. This factor can be calibrated and optimized according to actual application scenarios, expert experience, or historical data analysis to ensure that the baseline value can accurately reflect the actual situation of regional ecological constraints.

[0163] Specifically, this invention first maps development policies to a baseline value for synergistic tilt through semantic analysis. This step transforms qualitative policy guidance into a quantitative numerical basis, ensuring that the evaluation benchmark aligns with the policy direction of agricultural development at the macro level. Building upon this, the scheme cleverly incorporates the ecological sensitivity of the surrounding planting area. By collecting information about the area's periphery, including the importance level indicators and the number of ecological protection areas, a formula is used to correct the baseline value for synergistic tilt. Specifically, the summation term in the formula normalizes and averages the importance level indicators of each ecological protection area, quantifying the overall pressure on regional ecological protection. When the importance level of surrounding ecological protection areas is high or the number is large, this correction term increases, thus adjusting the final baseline value for the synergistic tilt between economic and ecological benefits accordingly towards ecological protection. Finally, a correction scaling factor is used to adjust the above correction results, ultimately determining the baseline value for the synergistic tilt between economic and ecological benefits.

[0164] This approach ensures that the benchmark value is no longer static but can be adaptively adjusted based on the distribution density and importance level of surrounding ecological protection areas. This effectively solves the problem that a single benchmark value cannot reflect regional differences in ecological constraints, providing a more scientific and targeted reference standard for subsequent evaluation of the coupling coordination degree. In this way, when determining the evaluation index for the coupling coordination degree of economic and ecological benefits, this scheme can compare the average synergistic tilt of economic and ecological benefits from human intervention with a benchmark value that fully considers regional policy guidance and ecological constraints, thereby more accurately evaluating the coupling coordination degree of economic and ecological benefits in smart agriculture.

[0165] Preferably, the present invention further proposes the evaluation index for determining the coupling coordination degree of economic benefits and ecological benefits, expressed by the formula: ;

[0166] In the above formula, P refers to the evaluation index of the coupling and coordination degree between economic benefits and ecological benefits. This refers to the average degree of synergy between economic and ecological benefits corresponding to all recent human interventions. This refers to the benchmark value for the synergistic tilt between economic and ecological benefits;

[0167] The Economic and Ecological Benefit Coordination Evaluation Index is a comprehensive indicator used to quantify the degree of coordination between economic output and ecological protection in smart agriculture production activities. This index aims to provide a standardized and comparable evaluation result to overcome the limitations of a single tilt value lacking a unified measurement standard across different scenarios.

[0168] The mean synergistic tilt of economic and ecological benefits corresponding to all recent human interventions refers to the value obtained by averaging the synergistic tilt of economic and ecological benefits calculated for all agricultural human interventions over a period of time. Its purpose is to smooth out random fluctuations or accidental biases that may be caused by a single intervention, thereby more accurately reflecting the overall benefit tendency of agricultural production activities during that period. This mean can be obtained by using methods such as arithmetic average, weighted average, or moving average of the synergistic tilt of historical interventions.

[0169] The purpose of the above formula is to compare the actual overall benefit tendency with regional goals or constraints, thereby generating a relative evaluation index. This ratio relationship makes the evaluation result no longer an isolated value, but has a clear reference meaning, and can intuitively reflect the current performance of smart agricultural production in terms of economic and ecological coordination.

[0170] This application's solution achieves standardized and quantitative evaluation of smart agricultural production methods by constructing an evaluation index for the coupling and coordination of economic and ecological benefits. The core calculation of this index involves comparing the average synergistic tilt of economic and ecological benefits corresponding to all recent human interventions with a benchmark value for the synergistic tilt. Specifically, firstly, the synergistic tilt of economic and ecological benefits is calculated for all recorded human interventions over a period of time (e.g., a planting cycle or a quarter). These synergistic tilts reflect the relative bias and degree of each intervention on economic and ecological benefits. To eliminate the randomness or short-term fluctuations that may be caused by a single intervention, this solution further averages these synergistic tilts to obtain the average synergistic tilt of economic and ecological benefits corresponding to all recent human interventions. This average value can more stably and comprehensively represent the overall benefit tendency of agricultural production activities during this period. Simultaneously, this solution determines a benchmark value for the synergistic tilt of economic and ecological benefits based on information about the surrounding areas and development policies of the crop planting region. This benchmark value is not a fixed number, but is dynamically adjusted based on the importance level of regional ecological protection, the number of ecological protection areas, and national or local development policies, thus fully reflecting the ecological constraints and policy orientations of a specific region. For example, in areas with high ecological protection requirements, the benchmark value may be set as a negative value that is more biased towards ecological benefits, while in areas with more urgent economic development needs, it may be set as a positive value that is more biased towards economic benefits. Finally, by comparing the average synergy tilt between economic and ecological benefits corresponding to all recent human interventions with the benchmark value of the synergy tilt between economic and ecological benefits, an evaluation index of the coupling coordination degree between economic and ecological benefits is obtained. The significance of this index lies in that it provides a relative evaluation scale. When the index is close to 1, it indicates that the actual agricultural production benefits tend to be highly coordinated with the benchmark target set for the region; when the index is greater than 1, it may mean that the actual benefits tend to be more biased towards the economy (if the benchmark is positive) or more biased towards the ecology (if the benchmark is negative, and the actual benefits are more negative); when the index is less than 1, it may indicate that there is a certain gap between the actual benefits tend to be and the benchmark.

[0171] This evaluation mechanism cleverly combines dynamically changing actual production benefits with benchmark targets that have regional and policy characteristics. This allows the evaluation results to not only reflect the current production status but also provide insights into the gap between current production and the targets, thus offering clear guidance for decision-makers in smart agriculture. By introducing a benchmark value as the denominator, agricultural production evaluations under different regions and environmental constraints can be mapped to a unified quantitative dimension, thereby scientifically measuring the degree of coupling and coordination between agricultural production methods and economic output and ecological protection.

[0172] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for evaluating a coupling coordination degree between economic benefits and ecological benefits of smart agriculture, characterized in that, The method specifically includes: The study aims to capture human interventions during crop cultivation and collect data on crop status characteristics, weather cycle characteristics, and ecological characteristics of crop cultivation areas before and after such interventions. Weather cycle characteristics refer to the characteristics of weather within a specific cycle. Based on the crop condition characteristics data and weather forecast data before human intervention, determine the predicted values ​​of crop condition before intervention; Based on the crop status characteristic data after human intervention, determine the crop status assessment value after intervention; Based on the predicted values ​​of crop status before intervention, the assessed values ​​of crop status after intervention, and the ecological characteristic data of crop planting areas, the degree of synergy between economic and ecological benefits is determined. Collect information on the surrounding areas and development policies of crop planting areas, and determine the benchmark value of the synergistic tilt between economic and ecological benefits based on the surrounding information and development policies of crop planting areas; among which, the surrounding information of planting areas includes the importance level and number of ecological protection areas around the planting area. Based on the degree of synergy between economic and ecological benefits and the benchmark value of the degree of synergy between economic and ecological benefits, an evaluation index for the degree of coupling and coordination between economic and ecological benefits is determined. The coupling coordination degree between economic and ecological benefits is evaluated based on the evaluation index of the coupling coordination degree between economic and ecological benefits in smart agriculture.

2. The method according to claim 1, characterized in that, The predicted value of crop status before intervention is expressed by the following formula: ; In the above formula, This refers to the predicted crop condition before intervention. This refers to the weather similarity correction factor for the i-th state characteristic of crops. This refers to the normalized value of the i-th state feature data of the crop at time t. This refers to the normalized value of the i-th state feature data of the crop at time t-1. This refers to the normalized value of the i-th state feature data of the crop at time tn. , refers to the weight coefficient of the i-th state feature of the crop, and m refers to the total number of state feature data of the crop.

3. The method according to claim 2, characterized in that, The weather similarity correction factor The method for obtaining it is expressed by the formula: ; In the above formula, This refers to the superiority value of the j-th actual weather cycle characteristic data before human intervention, relative to the corresponding weather cycle characteristic baseline data. This refers to the superiority value of the weather cycle characteristic forecast data after human intervention relative to the corresponding weather cycle characteristic baseline data. This refers to the reference value for changes in the superiority value. It is the hyperbolic tangent function. This refers to the weighting coefficient of the j-th weather cycle feature, and N refers to the number of weather cycle feature data. To increase or decrease the superiority value using an analytical function, It refers to Compared to Increase or decrease in value; increase or decrease in value The absolute value is and The absolute difference between them; The analytic method for increasing or decreasing the superiority value is as follows: If Greater than If the superiority value changes in an increasing trend, then the increase / decrease value will be... If it is a positive value, Less than The superiority value changes in a decreasing trend, while the increase / decrease value is... If it is a negative value; equal Then the increase or decrease value =0; The aforementioned weather cycle characteristic benchmark data refers to the reference range of crop planting environment requirements in terms of weather cycle characteristics. The reference range includes the extreme values ​​and the optimal values ​​within the range; (for example, the best daytime cycle average temperature is between 10-15 degrees Celsius, and the optimal temperature is 13 degrees Celsius). The superiority value is used to quantify the degree to which weather cycle characteristics meet the environmental requirements for crop cultivation, and the specific value is determined as follows: Analyze whether the weather cycle characteristics are within the reference range. If the weather cycle characteristics are within the reference range, the superior value is positive, and the closer the weather cycle characteristics are to the best value within the range, the greater the superior value. If the weather cycle characteristic is outside the reference range, the superior value is negative, and the closer the weather cycle characteristic is to the extreme value of the range, the greater the superior value.

4. The method according to claim 1, characterized in that, The determination of the crop status assessment value after intervention is expressed by the following formula: ; In the above formula, This refers to the crop status assessment value after intervention. This refers to the normalized value of the i-th state characteristic data of crops after human intervention. , refers to the weight coefficient of the i-th state feature of the crop, and m refers to the total number of state feature data of the crop.

5. The method according to claim 1, characterized in that, The aforementioned synergistic inclination between economic and ecological benefits specifically includes: Based on the ecological characteristic data of crop planting areas before human intervention, the pre-intervention assessment value of the crop planting area ecology is determined; where the pre-intervention assessment value refers to the weighted sum of the normalized values ​​of all crop planting area ecological characteristic data before human intervention. Based on the ecological characteristic data of crop planting areas after human intervention, the post-intervention assessment value of the crop planting area ecology is determined; where the post-intervention assessment value refers to the weighted sum of the normalized values ​​of all crop planting area ecological characteristic data after human intervention. The ecological benefit assessment value is determined based on the pre-intervention assessment value and the post-intervention assessment value of the ecology of the crop planting area; The economic benefit assessment value is determined based on the predicted crop status before intervention and the assessed crop status after intervention. The degree of synergy between economic and ecological benefits is determined based on the ecological and economic benefit assessment values.

6. The method according to claim 5, characterized in that, The determination of the ecological benefit assessment value is expressed by the following formula: ; In the above formula, This refers to the ecological benefit assessment value of human intervention. This refers to the pre-intervention assessment value. This refers to the post-intervention assessment value. This refers to the deviation reference value. This refers to the slope control parameter.

7. The method according to claim 5, characterized in that, The economic benefit assessment value is expressed by the formula: ; In the above formula, This refers to the economic benefit assessment value of human intervention. This refers to the predicted crop condition before intervention. This refers to the crop status assessment value after intervention. This refers to the deviation reference value. This refers to the slope control parameter.

8. The method according to claim 5, characterized in that, The degree of synergy between economic and ecological benefits is determined based on the ecological and economic benefit assessment values, expressed by the following formula: ; In the above formula, This refers to the degree of synergy between economic and ecological benefits. This refers to the economic benefit assessment value of human intervention. This refers to the ecological benefit assessment value of human intervention. It is the arctangent function; Among them, the range of values ​​for the synergistic tilt between economic and ecological benefits is positive and negative; When the synergy between economic and ecological benefits is positive, it indicates that human intervention is biased towards economic benefits. The larger the absolute value of the synergy between economic and ecological benefits, the more it is biased towards economic benefits. When the synergy between economic and ecological benefits is negative, it indicates that human intervention is biased towards ecological benefits. The larger the absolute value of the synergy between economic and ecological benefits, the more it is biased towards ecological benefits.

9. The method according to claim 8, characterized in that, The determination of the benchmark value for the synergistic tilt between economic and ecological benefits specifically includes: Based on semantic analysis, development policies are mapped to baseline values ​​for basic synergy inclination. Then, using the formula: ; Determine the benchmark value for the synergistic tilt between economic and ecological benefits. ; In the above formula, This refers to the baseline value of the basic coordination tilt. This refers to the importance level indicator value of the k-th ecological protection area. This refers to the minimum importance level indicator value. This refers to the maximum importance level indicator value, where M refers to the number of ecological protection areas. This refers to adjusting the scaling factor.

10. The method according to claim 9, characterized in that, The evaluation index for determining the coupling and coordination degree between economic and ecological benefits is expressed by the following formula: ; In the above formula, P refers to the evaluation index of the coupling and coordination degree between economic benefits and ecological benefits. This refers to the average degree of synergy between economic and ecological benefits corresponding to all recent human interventions. This refers to the benchmark value for the synergistic tilt between economic and ecological benefits.

Images