A method and system for realizing protection and rejuvenation of ancient and famous trees

Abstract

This invention relates to the field of ancient and famous tree protection, and discloses a method and system for the protection and rejuvenation of ancient and famous trees. The method includes: extracting core growth data from growth status data; performing data augmentation on the core growth data to obtain enhanced growth data; extracting growth characteristics corresponding to the enhanced growth data; inputting the growth characteristics and preset health characteristics into a pre-configured growth analysis model; sampling the growth characteristics using the characteristic sampling unit in the growth analysis model to obtain growth sampling characteristics; mapping the growth sampling characteristics using the anomaly mapping unit in the growth analysis model to obtain growth anomaly characteristics; determining the anomaly location corresponding to the ancient and famous tree; calculating the soil fertility index and branch and leaf vitality value corresponding to the anomaly location; analyzing the anomaly attributes corresponding to the anomaly location; and determining the corresponding protection and rejuvenation measures for the ancient and famous tree. This invention can improve the effectiveness of protecting and rejuvenating ancient and famous trees.

Description

Technical Field

[0001] This invention relates to a method and system for the protection and rejuvenation of ancient and famous trees, belonging to the field of ancient and famous tree protection. Background Technology

[0002] Ancient and famous trees are precious heritages of nature and human history and culture, possessing significant ecological, scientific, and cultural value. They are living cultural relics, carrying historical memories and regional culture. Due to their long age and drastic changes in their growing environment, ancient and famous trees are prone to problems such as weakened growth, pest and disease infestation, and branch and trunk decay. If effective protection and rejuvenation measures are not taken in a timely manner, their growth status may continue to deteriorate, and they may even die.

[0003] Existing methods for the protection and rejuvenation of ancient and famous trees mostly rely on traditional, experience-based approaches. These methods involve manually observing the tree's external characteristics, such as the shape of its branches and leaves and the condition of its bark, and using experience to diagnose growth problems. Measures such as pruning diseased branches, applying organic fertilizer, and spraying pesticides are then taken. However, this method relies too heavily on manual experience and makes it difficult to fully capture the subtle changes in the tree's internal physiological state and growth environment. It is also difficult to accurately identify hidden problems such as decreased root vitality and soil microenvironment imbalance. Furthermore, the methods lack precise matching for different anomalies, which reduces the effectiveness of the protection and rejuvenation of ancient and famous trees. Summary of the Invention

[0004] This invention provides a method and system for the protection and rejuvenation of ancient and famous trees, the main purpose of which is to improve the effectiveness of the protection and rejuvenation of ancient and famous trees.

[0005] To achieve the above objectives, the present invention provides a method for the protection and rejuvenation of ancient and famous trees, comprising:

[0006] Collect growth status data corresponding to ancient and famous trees, extract core growth data from the growth status data, and perform data augmentation processing on the core growth data to obtain enhanced growth data;

[0007] Extract the growth characterization corresponding to the enhanced growth data, input the growth characterization and the preset health characterization into the pre-configured growth analysis model, use the characterization sampling unit in the growth analysis model to sample the growth characterization to obtain the growth sampling characterization, combine it with the preset health characterization, and use the anomaly mapping unit in the growth analysis model to map the growth sampling characterization to obtain the growth anomaly characterization.

[0008] Based on the aforementioned abnormal growth characteristics, the abnormal locations corresponding to the ancient and famous trees are determined. Environmental data corresponding to the abnormal locations are collected using pre-set environmental monitoring equipment. Based on the environmental data, the soil fertility index and branch and leaf vitality value corresponding to the abnormal locations are calculated.

[0009] By combining the soil fertility index and the branch and leaf vitality value, the abnormal attributes corresponding to the abnormal location are analyzed. By combining the abnormal attributes and the abnormal location, the protection and rejuvenation measures corresponding to the ancient and famous trees are determined.

[0010] Optionally, extracting the core growth data from the growth state data includes:

[0011] Detect the data attribute value corresponding to each data item in the growth status data;

[0012] Based on the data attribute values, the data weight value corresponding to each data item in the growth state data is calculated;

[0013] Based on the data weight values, the growth state data is subjected to weighted filtering to obtain weighted growth data;

[0014] Set the effective data threshold corresponding to the weight growth data, and extract the core weight data from the weight growth data based on the effective data threshold.

[0015] The core weight data is restructured to obtain core growth data.

[0016] Optionally, the step of performing data augmentation processing on the core growth data to obtain augmented growth data includes:

[0017] The core growth data is subjected to numerical equalization processing to obtain balanced growth data;

[0018] Calculate the smoothing value corresponding to each data point in the balanced growth data:

[0019]

[0020] Where S represents the smoothed value corresponding to each data item in the core growth data, M×N represents the data matrix window, M and N represent the number of rows and columns of all data items in the core growth data, i and j represent the row index and column index of the data item in the data matrix, and D(i,j) represents the data value located at position (i,j) in the core growth data.

[0021] Based on the smoothing value, the core growth data is smoothed to obtain smoothed growth data;

[0022] The smoothed growth data is then subjected to detail enhancement processing to obtain enhanced growth data.

[0023] Optionally, extracting the growth characteristics corresponding to the enhanced growth data includes:

[0024] Extract the temporal variation information from the enhanced growth data, and perform segmented aggregation processing on the temporal variation information to obtain the variation trend sequence;

[0025] Based on the change trend sequence, construct the growth state diagram corresponding to the enhanced growth data;

[0026] Based on the growth state diagram, calculate the trend characteristic value of the enhanced growth data;

[0027] The trend feature values ​​are standardized to obtain the target trend feature values;

[0028] Construct a trend feature vector corresponding to the target trend feature value, and generate a growth trend representation of the enhanced growth data based on the trend feature vector;

[0029] The health indicator features of the enhanced growth data are extracted, and the growth trend characterization and the health indicator features are combined to obtain the growth characterization of the enhanced growth data.

[0030] Optionally, the step of sampling the growth characterization using the characterization sampling unit in the growth analysis model to obtain the growth sampling characterization includes:

[0031] The growth characterization is normalized by using the normalization component in the characterization sampling unit to obtain a normalized growth characterization.

[0032] The target growth characterization is obtained by performing feature sampling processing on the standardized growth characterization using the aggregation sampling component in the characterization sampling unit.

[0033] The feature priority corresponding to the target growth representation is calculated using the priority calculation unit in the representation sampling unit;

[0034] Based on the feature priority, the corresponding growth sampling representation is output from the target growth representation using the output component in the representation sampling unit.

[0035] Optionally, calculating the feature priority corresponding to the target growth representation using the priority calculation unit in the representation sampling unit includes:

[0036] The feature labels in the target growth characterization are extracted using the label extractor in the priority calculation unit, and the label frequency corresponding to the feature label is calculated.

[0037] Based on the labeling frequency, the feature dispersion and labeling conditional entropy corresponding to the target growth representation are calculated using the difference function in the priority calculation unit.

[0038] By combining the feature dispersion and the label conditional entropy, the feature saliency ratio corresponding to the target growth representation is calculated;

[0039] Based on the feature saliency ratio, the feature priority corresponding to the target growth characterization is obtained.

[0040] Optionally, the step of combining the preset health characterization and using the anomaly mapping unit in the growth analysis model to map the growth sampling characterization to obtain a growth anomaly characterization includes:

[0041] The growth sampling characterization and the preset health characterization are subjected to structural processing to obtain a first feature structure and a second feature structure;

[0042] The structural similarity value between the first feature structure and the second feature structure is calculated using the mapper in the anomaly mapping unit;

[0043] The feature matching degree between the preset health representation and the growth sampling representation is calculated using the matching function in the anomaly mapping unit;

[0044] By combining the feature matching degree and the structural similarity value, features that differ from the preset healthy characteristics are selected from the growth sampling characteristics to obtain the growth abnormality characteristics.

[0045] Optionally, calculating the feature matching degree between the preset health representation and the growth sampling representation using the matching function in the anomaly mapping unit includes:

[0046] The growth sampling characterization and the preset health characterization are vectorized respectively to obtain a first characterization vector and a second characterization vector.

[0047] Calculate the average values ​​corresponding to the first representation vector and the second representation vector respectively to obtain the first average value and the second average value;

[0048] Calculate the representation contribution value corresponding to each representation in the growth sampling representation;

[0049] Combining the first representation vector, the second representation vector, the first average value, the second average value, and the representation contribution value, the feature matching degree between the preset health representation and the growth sampling representation is calculated using a matching function:

[0050]

[0051] Where A represents the feature matching degree between the preset health characterization and the growth sampling characterization, This represents the contribution value corresponding to the a-th feature in the growth sampling characterization. This represents the vector value corresponding to the a-th feature in the growth sampling representation. Let X represent the vector value corresponding to the a-th feature in the preset health representation, Y represent the average vector value corresponding to the growth sampling representation, a represent the sequence number of the growth sampling representation, and r represent the number of growth sampling representations. This represents the smallest perturbation value.

[0052] Optionally, calculating the soil fertility index and leaf vigor value corresponding to the abnormal location based on the environmental data includes:

[0053] The environmental data is cleaned and calibrated to obtain standard environmental data;

[0054] Analyze the nutrient content and physicochemical properties of the soil in the aforementioned standard environmental data;

[0055] Measure the spectral reflectance characteristics and moisture distribution of the branches and leaves at the abnormal locations;

[0056] Based on the nutrient content and the physicochemical properties, the soil fertility index corresponding to the abnormal location is calculated;

[0057] Based on the spectral reflectance characteristics and the moisture distribution, the leaf and branch vitality value corresponding to the abnormal location is calculated.

[0058] To address the aforementioned problems, the present invention also provides a system for the protection and rejuvenation of ancient and famous trees, the system comprising:

[0059] The growth data processing module is used to collect growth status data corresponding to ancient and famous trees, extract core growth data from the growth status data, and perform data enhancement processing on the core growth data to obtain enhanced growth data.

[0060] The data characterization sampling module is used to extract the growth characterization corresponding to the enhanced growth data, input the growth characterization and the preset health characterization into the pre-configured growth analysis model, use the characterization sampling unit in the growth analysis model to sample the growth characterization to obtain the growth sampling characterization, and combine the preset health characterization with the abnormal mapping unit in the growth analysis model to map the growth sampling characterization to obtain the growth abnormal characterization.

[0061] An abnormal location analysis module is used to determine the abnormal location corresponding to the ancient and famous trees by combining the growth abnormality characteristics, collect environmental data corresponding to the abnormal location using preset environmental monitoring equipment, and calculate the soil fertility index and branch and leaf vitality value corresponding to the abnormal location based on the environmental data.

[0062] The rejuvenation measures determination module is used to analyze the abnormal attributes corresponding to the abnormal location by combining the soil fertility index and the branch and leaf vitality value, and to determine the protection and rejuvenation measures corresponding to the ancient and famous trees by combining the abnormal attributes and the abnormal location.

[0063] Compared to the problems described in the background art, this invention extracts core growth data from the growth status data, removing information irrelevant to the core growth status of ancient and famous trees, focusing on key content in the data, and thus improving the efficiency of subsequent data processing. By extracting growth characteristics corresponding to the enhanced growth data, this invention obtains key information from the enhanced growth data, facilitating subsequent processing of these characteristics by the growth analysis model. Furthermore, by combining the abnormal growth characteristics, this invention locates the abnormal positions corresponding to the ancient and famous trees, thereby improving the accuracy of abnormal position determination. Based on the environmental data, it calculates the soil fertility index and branch and leaf vitality value corresponding to the abnormal position, obtaining the soil nutrient status and plant physiological activity level at the abnormal position, facilitating subsequent comprehensive analysis of the reasons for growth restriction at the abnormal position. Finally, by combining the soil fertility index and branch and leaf vitality value, this invention analyzes the abnormal attributes corresponding to the abnormal position, thereby understanding the growth limiting factors at the abnormal position and improving the targeted nature of the protection and rejuvenation of ancient and famous trees. Therefore, the method and system for protecting and rejuvenating ancient and famous trees provided in this embodiment of the invention can improve the effectiveness of protecting and rejuvenating ancient and famous trees. Attached Figure Description

[0064] Figure 1 This is a flowchart illustrating a method for protecting and rejuvenating ancient and famous trees, provided in an embodiment of the present invention.

[0065] Figure 2 This is a schematic diagram of a module for implementing a protection and rejuvenation system for ancient and famous trees, provided as an embodiment of the present invention.

[0066] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0067] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0068] This application provides a method for the protection and rejuvenation of ancient and famous trees. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for the protection and rejuvenation of ancient and famous trees can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0069] Reference Figure 1 The diagram shown is a flowchart illustrating a method for protecting and rejuvenating ancient and famous trees according to an embodiment of the present invention. In this embodiment, the method for protecting and rejuvenating ancient and famous trees includes:

[0070] S1. Collect growth status data corresponding to ancient and famous trees, extract core growth data from the growth status data, and perform data enhancement processing on the core growth data to obtain enhanced growth data.

[0071] This invention extracts core growth data from the growth status data, thereby removing information irrelevant to the core growth status of ancient and famous trees, focusing on key content in the data, and thus improving the efficiency of subsequent data processing. The core growth data is the key data in the growth status data that directly reflects the growth vitality and size changes of ancient and famous trees.

[0072] As an embodiment of the present invention, the extraction of core growth data from the growth state data includes:

[0073] Detect the data attribute value corresponding to each data item in the growth status data;

[0074] Based on the data attribute values, the data weight value corresponding to each data item in the growth state data is calculated;

[0075] Based on the data weight values, the growth state data is subjected to weighted filtering to obtain weighted growth data;

[0076] Set the effective data threshold corresponding to the weight growth data, and extract the core weight data from the weight growth data based on the effective data threshold.

[0077] The core weight data is restructured to obtain core growth data.

[0078] The data attribute value is the original value corresponding to each data item in the growth state data, including information such as data source, data type, and data collection time. The weighted growth data is a weighted data set formed by assigning weights to the growth state data. The effective data threshold is the boundary value used to divide the weighted growth data into effective data and invalid data.

[0079] Optionally, the data attribute values ​​corresponding to each data item in the growth status data can be directly obtained through data acquisition devices; the calculation method for the data weight value corresponding to each data item in the growth status data is as follows: multiple influencing factors in the data attribute value are weighted and fused, and the data weight value = influence factor 1 × coefficient 1 + influence factor 2 × coefficient 2 + influence factor 3 × coefficient 3; the setting of the effective data threshold corresponding to the weighted growth data can be achieved through data distribution feature analysis methods. By analyzing the numerical distribution of the weighted growth data, the critical value for distinguishing between effective and invalid data is determined; the core growth data can be extracted based on the comparison results between the effective data threshold and the weight value of each data item in the weighted growth data. When the weight value of a data item is higher than the effective data threshold, it is retained as core data, and otherwise it is discarded. By traversing all data items in turn, a preliminary core dataset is obtained. The dataset is then cleaned to remove redundant items, resulting in the core growth data of the weighted growth data; the structured reorganization processing of the weighted core data can be achieved through data table association methods. Core data from different sources and types are integrated and reorganized in a unified format to form a data structure that is easy to analyze.

[0080] This invention improves data quality and strengthens key information by performing data augmentation on the core growth data, making the data more suitable for subsequent analysis and application. The enhanced growth data is the data form obtained after the core growth data has been augmented.

[0081] As an embodiment of the present invention, the step of performing data augmentation processing on the core growth data to obtain enhanced growth data includes:

[0082] The core growth data is subjected to numerical equalization processing to obtain balanced growth data;

[0083] Calculate the smoothing value corresponding to each data point in the balanced growth data;

[0084] Based on the smoothing value, the core growth data is smoothed to obtain smoothed growth data;

[0085] The smoothed growth data is then subjected to detail enhancement processing to obtain enhanced growth data.

[0086] The balanced growth data refers to the set of core growth data whose values ​​are more evenly distributed after being balanced and adjusted. The smoothed values ​​are representative values ​​for smoothing processing obtained after calculation for each data point in the balanced growth data. Detail enhancement processing is an operation that highlights and enhances subtle changes and key features in the data. Furthermore, the numerical balancing processing of the core growth data can be achieved through data standardization methods; the detail enhancement processing of the smoothed growth data can be achieved through high-resolution reconstruction methods.

[0087] Furthermore, as another embodiment of the present invention, the smoothing value corresponding to each data point in the balanced growth data is calculated using the following formula:

[0088]

[0089] Where S represents the smoothed value corresponding to each data item in the core growth data, M×N represents the data matrix window, M and N represent the number of rows and columns of all data items in the core growth data, i and j represent the row index and column index of the data item in the data matrix, and D(i,j) represents the data value located at position (i,j) in the core growth data.

[0090] S2. Extract the growth characteristics corresponding to the enhanced growth data, input the growth characteristics and the preset health characteristics into the pre-configured growth analysis model, use the characteristics sampling unit in the growth analysis model to sample the growth characteristics to obtain the growth sampling characteristics, combine the preset health characteristics, use the anomaly mapping unit in the growth analysis model to map the growth sampling characteristics to obtain the growth anomaly characteristics.

[0091] This invention extracts the growth characteristics corresponding to the enhanced growth data to obtain key information in the enhanced growth data, so that the subsequent growth analysis model can perform relevant processing on the growth characteristics. The growth characteristics are the core information in the enhanced growth data that reflects the growth status and change patterns of ancient and famous trees, such as annual growth range and seasonal fluctuation characteristics.

[0092] As an embodiment of the present invention, the extraction of the growth characterization corresponding to the enhanced growth data includes:

[0093] Extract the temporal variation information from the enhanced growth data, and perform segmented aggregation processing on the temporal variation information to obtain the variation trend sequence;

[0094] Based on the change trend sequence, construct the growth state diagram corresponding to the enhanced growth data;

[0095] Based on the growth state diagram, calculate the trend characteristic value of the enhanced growth data;

[0096] The trend feature values ​​are standardized to obtain the target trend feature values;

[0097] Construct a trend feature vector corresponding to the target trend feature value, and generate a growth trend representation of the enhanced growth data based on the trend feature vector;

[0098] The health indicator features of the enhanced growth data are extracted, and the growth trend characterization and the health indicator features are combined to obtain the growth characterization of the enhanced growth data.

[0099] The time-series change information expresses the attributes of the enhanced growth data over time; the change trend sequence is a sequence reflecting the direction of data change obtained after segmentation and aggregation; the growth status diagram is a graphical representation of the growth status in the enhanced growth data; the trend feature value is a numerical value describing the change attributes of the enhanced growth data, such as average rate of change, fluctuation range, and stability index; the target trend feature value is a feature value obtained after standardization of the trend feature value; and the health indicator feature is a representation of the health status of ancient trees directly reflected in the enhanced growth data.

[0100] Optionally, the temporal variation information in the enhanced growth data can be extracted using time series analysis methods; the segmented aggregation processing of the temporal variation information can be implemented using a sliding window averaging algorithm; the construction of the growth state map corresponding to the enhanced growth data can be achieved using data visualization tools; the calculation of the trend feature values ​​of the enhanced growth data can be achieved using curve fitting methods, gradually fitting the change points in the trend sequence, and calculating the corresponding rate of change or magnitude of change using corresponding formulas; the standardization processing of the trend feature values ​​can be achieved using maximum and minimum value normalization; the construction of the trend feature vector corresponding to the target trend feature value can be achieved using principal component analysis methods; and the health indicator features of the enhanced growth data can be extracted using an indicator weighted fusion method.

[0101] This invention utilizes the characterization sampling unit in the growth analysis model to sample the growth characterization, which allows for the selective extraction and retention of the most critical features. This helps to improve the typicality of the growth characterization and makes it more focused on expressing the core information of the enhanced growth data.

[0102] As an embodiment of the present invention, the step of sampling the growth characterization using the characterization sampling unit in the growth analysis model to obtain the growth sampling characterization includes:

[0103] The growth characterization is normalized by using the normalization component in the characterization sampling unit to obtain a normalized growth characterization.

[0104] The target growth characterization is obtained by performing feature sampling processing on the standardized growth characterization using the aggregation sampling component in the characterization sampling unit.

[0105] The feature priority corresponding to the target growth representation is calculated using the priority calculation unit in the representation sampling unit;

[0106] Based on the feature priority, the corresponding growth sampling representation is output from the target growth representation using the output component in the representation sampling unit.

[0107] The standardization component transforms the growth representation into a form that the growth analysis model can process, and is composed of a data normalization function. The aggregation sampling component is a component that condenses the standardized growth representation and is constructed using a feature selection function, such as a variance selection function. The priority calculation unit is an algorithm used to calculate the priority of the target growth representation, such as a hierarchical ranking method, which determines the priority by comparing the influence of different growth features on the overall growth state of the tree pairwise and ranking them according to their importance. The output component is composed of a result generation function, such as a linear weighted function.

[0108] Furthermore, as an optional embodiment of the present invention, the step of calculating the feature priority corresponding to the target growth representation using the priority calculation unit in the representation sampling unit includes:

[0109] The feature labels in the target growth characterization are extracted using the label extractor in the priority calculation unit, and the label frequency corresponding to the feature label is calculated.

[0110] Based on the labeling frequency, the feature dispersion and labeling conditional entropy corresponding to the target growth representation are calculated using the difference function in the priority calculation unit.

[0111] By combining the feature dispersion and the label conditional entropy, the feature saliency ratio corresponding to the target growth representation is calculated;

[0112] Based on the feature saliency ratio, the feature priority corresponding to the target growth characterization is obtained.

[0113] Wherein, the feature label is the feature category corresponding to the target growth representation, the feature dispersion and the label conditional entropy represent the degree of distribution dispersion and the degree of uncertainty under a specific label corresponding to the target growth representation, respectively, and the feature saliency ratio is a metric used for feature selection.

[0114] Optionally, the label extractor is compiled by a data processing language, such as Python; the label frequency corresponding to the feature label can be obtained by the ratio of the number of times the label appears to the total number of times; the difference function is composed of the standard deviation function and the conditional entropy function; the calculation process of the feature significance ratio corresponding to the target growth representation is as follows: divide the feature dispersion by the corresponding label conditional entropy to obtain the discrimination value corresponding to each feature, calculate the ratio of the discrimination value to the total discrimination, and obtain the feature significance ratio corresponding to each feature.

[0115] This invention improves the accuracy of health status identification of the growth sampling representation by combining the preset health representation with the abnormal mapping unit in the growth analysis model to perform mapping processing on the growth sampling representation. The preset health representation is the ideal health feature corresponding to the ancient and famous tree, and the abnormal growth representation is the feature related to the abnormal condition in the growth sampling representation.

[0116] As an embodiment of the present invention, the step of combining the preset health characterization and using the anomaly mapping unit in the growth analysis model to map the growth sampling characterization to obtain a growth anomaly characterization includes:

[0117] The growth sampling characterization and the preset health characterization are subjected to structural processing to obtain a first feature structure and a second feature structure;

[0118] The structural similarity value between the first feature structure and the second feature structure is calculated using the mapper in the anomaly mapping unit;

[0119] The feature matching degree between the preset health representation and the growth sampling representation is calculated using the matching function in the anomaly mapping unit;

[0120] By combining the feature matching degree and the structural similarity value, features that differ from the preset healthy characteristics are selected from the growth sampling characteristics to obtain the growth abnormality characteristics.

[0121] The mapper is a function that calculates the formal similarity between the first feature structure and the second feature structure, such as a feature overlap rate algorithm. It quantifies the similarity by statistically analyzing the proportion of the same growth indicators in the two feature structures. The structural similarity value represents the similarity value obtained by comparing the first feature structure and the second feature structure. The structural similarity value can be used to understand the formal difference between the first feature structure and the second feature structure. The feature matching degree represents the content consistency between the preset health representation and the growth sampling representation.

[0122] Furthermore, the structured processing of the growth sampling representation and the preset health representation can be achieved through feature tensor quantization; the mapper includes a distance function and a similarity function; features that differ from the preset health representation can be selected from the growth sampling representation by combining the feature matching degree and the structural similarity value with the corresponding set benchmark. When the feature matching degree and the structural similarity value are lower than the corresponding set benchmark, the corresponding features are selected to obtain the growth abnormality representation. The set benchmark is a reference standard value corresponding to the feature matching degree and the structural similarity value, which can be set to 0.7 or adjusted according to actual analysis requirements.

[0123] Furthermore, as another embodiment of the present invention, the step of calculating the feature matching degree between the preset health characterization and the growth sampling characterization using the matching function in the anomaly mapping unit includes:

[0124] The growth sampling characterization and the preset health characterization are vectorized respectively to obtain a first characterization vector and a second characterization vector.

[0125] Calculate the average values ​​corresponding to the first representation vector and the second representation vector respectively to obtain the first average value and the second average value;

[0126] Calculate the representation contribution value corresponding to each representation in the growth sampling representation;

[0127] By combining the first representation vector, the second representation vector, the first average value, the second average value, and the representation contribution value, the feature matching degree between the preset health representation and the growth sampling representation is calculated using a matching function.

[0128] The first representation vector is a numerical vector form that converts various growth characteristics (such as annual increase in diameter at breast height, crown expansion, and number of new shoots) in the growth sampling representation into numerical vector form. The second representation vector is a numerical vector form that converts the corresponding health standard characteristics (such as standard increase in diameter at breast height and standard crown expansion of healthy ancient trees) in the preset health representation into numerical vector form. The first average value is the numerical average of all elements in the first representation vector, and the second average value is the numerical average of all elements in the second representation vector. The representation contribution value is the degree of influence of each feature in the growth sampling representation on the overall growth status assessment of the ancient tree (such as the contribution value of diameter at breast height increase being higher than that of bark appearance characteristics). The matching function is a calculation formula that quantifies the similarity between the two features by integrating vector differences and representation contribution values.

[0129] Furthermore, the vectorization of the growth sampling representation can be achieved through numerical standardization, converting features of different units such as diameter at breast height (DBH) and crown width into values ​​of the same magnitude (e.g., converting DBH increment in millimeters and crown width expansion in centimeters into values ​​in the range of 0-10); the vectorization of the preset health representation can refer to the vector dimension and numerical range of the growth sampling representation to ensure that the vector structures of the two are consistent; the calculation of the first average and the second average can be achieved through the arithmetic mean method, by summing the values ​​of all elements in the corresponding vector and dividing by the number of elements; the calculation of the representation contribution value can be determined by comparing the correlation between the features and the survival of ancient trees, such as referring to the growth records of similar ancient trees, setting the contribution value of core features affecting survival (such as trunk growth) to 0.6-0.8, and the contribution value of secondary features (such as lateral branch sprouting) to 0.2-0.4.

[0130] Furthermore, as another embodiment of the present invention, the feature matching degree between the preset health representation and the growth sampling representation is calculated using the following matching function by combining the first representation vector, the second representation vector, the first average value, the second average value, and the representation contribution value:

[0131]

[0132] Where A represents the feature matching degree between the preset health characterization and the growth sampling characterization, This represents the contribution value corresponding to the a-th feature in the growth sampling characterization. This represents the vector value corresponding to the a-th feature in the growth sampling representation. Let X represent the vector value corresponding to the a-th feature in the preset health representation, Y represent the average vector value corresponding to the growth sampling representation, a represent the sequence number of the growth sampling representation, and r represent the number of growth sampling representations. This represents the smallest perturbation value.

[0133] in, The minimum value (taking values ​​of) ), used to avoid the denominator being zero.

[0134] S3. Based on the abnormal growth characteristics, determine the abnormal location corresponding to the ancient and famous trees, collect environmental data corresponding to the abnormal location using preset environmental monitoring equipment, and calculate the soil fertility index and branch and leaf vitality value corresponding to the abnormal location based on the environmental data.

[0135] This invention, by combining the aforementioned abnormal growth characteristics, locates the abnormal positions corresponding to the ancient and famous trees, thereby improving the accuracy of abnormal position determination. Based on the environmental data, it calculates the soil fertility index and branch and leaf vitality value corresponding to the abnormal position, which can obtain the soil nutrient status and plant physiological activity level corresponding to the abnormal position, facilitating subsequent comprehensive analysis of the reasons for growth restriction corresponding to the abnormal position.

[0136] The abnormal location refers to the specific part of the ancient and famous tree where abnormal growth occurs, such as a canopy area where old leaves are concentratedly yellowing or a branch section with cracked bark. The environmental monitoring equipment is specialized equipment used to collect information on the surrounding growth environment and leaf condition at the abnormal location, such as a soil composition analyzer, leaf moisture sensor, or portable chlorophyll meter. The environmental data includes growth-related information such as soil nutrients, soil moisture, leaf water content, and leaf chlorophyll content at the abnormal location, such as a soil nitrogen content of 1.1 g / kg and a leaf chlorophyll content of 35 SPAD at the abnormal location. The soil fertility index is the comprehensive soil fertility index corresponding to the abnormal location. Nitrogen, phosphorus, and potassium content, along with humidity, quantify the soil's nutrient supply capacity, such as 0.72 (indicating sufficient soil nutrients, suitable humidity, and good fertility). The leaf and branch vitality value is the comprehensive leaf water content and chlorophyll content corresponding to the abnormal location, quantifying the health of leaf and branch growth, such as 0.55 (indicating moderate leaf water and chlorophyll content and average leaf and branch vitality). Optionally, the step of determining the abnormal location corresponding to the ancient and famous tree is as follows: combining the abnormal growth characteristics, identify the abnormal segment in the growth state of the ancient and famous tree, determine the abnormal location corresponding to the ancient and famous tree based on the abnormal segment, and extract key environmental factors from the environmental data.

[0137] As an embodiment of the present invention, the step of calculating the soil fertility index and leaf vigor value corresponding to the abnormal location based on the environmental data includes:

[0138] The environmental data is cleaned and calibrated to obtain standard environmental data;

[0139] Analyze the nutrient content and physicochemical properties of the soil in the aforementioned standard environmental data;

[0140] Measure the spectral reflectance characteristics and moisture distribution of the branches and leaves at the abnormal locations;

[0141] Based on the nutrient content and the physicochemical properties, the soil fertility index corresponding to the abnormal location is calculated;

[0142] Based on the spectral reflectance characteristics and the moisture distribution, the leaf and branch vitality value corresponding to the abnormal location is calculated.

[0143] The standard environmental data refers to a reliable dataset obtained after removing errors and interference from the environmental data. The nutrient content refers to the concentrations of nutrients such as nitrogen, phosphorus, and potassium in the soil. The physicochemical properties include soil pH, organic matter content, and porosity. The spectral reflectance characteristics are the reflectance data of branches and leaves in near-infrared and red-edge bands. The moisture distribution refers to the water content of branches and leaves at different locations. Optionally, the cleaning and calibration of the environmental data can be achieved through a data preprocessing platform; the nutrient content and physicochemical properties of the soil in the standard environmental data can be determined using a soil nutrient rapid analyzer and a physicochemical analyzer; the spectral reflectance characteristics and moisture distribution of branches and leaves at abnormal locations can be obtained using a hyperspectral imager and a branch and leaf moisture meter; and the branch and leaf vitality value corresponding to the abnormal location can be obtained by weighted fusion calculation of the spectral reflectance characteristics and moisture distribution.

[0144] Optionally, as an optional embodiment of the present invention, calculating the soil fertility index corresponding to the abnormal location by combining the nutrient content and the physicochemical properties includes:

[0145] Based on the nutrient content and the physicochemical properties, the supply level of each nutrient factor in the soil at the abnormal location is calculated;

[0146] The ideal nutrient requirement threshold for the growth of the ancient and famous trees was measured.

[0147] The supply compliance rate of the nutrient factors is determined based on the demand threshold and the supply level.

[0148] Based on the aforementioned physicochemical properties, the suitability score of the soil environment at the abnormal location is calculated.

[0149] By combining the supply compliance rate and the suitability score, the soil fertility index corresponding to the abnormal location is calculated.

[0150] Wherein, the supply level is the actual nutrient capacity provided by the soil, the demand threshold is the minimum nutrient requirement to ensure the healthy growth of ancient and famous trees, the supply compliance rate is the ratio of the supply level to the demand threshold, and the suitability score is the degree of support of the soil environment for plant root growth. Optionally, the supply level can be obtained by converting nutrient content to soil bulk density; the compliance rate can be obtained by dividing the supply level by the demand threshold and then multiplying by 100%; the suitability score can be obtained by weighted scoring of indicators such as soil pH, organic matter content, and porosity; and the soil fertility index can be calculated by weighted sum of the compliance rate of each nutrient factor and the suitability score.

[0151] S4. Combining the soil fertility index and the branch and leaf vitality value, analyze the abnormal attributes corresponding to the abnormal location, and combine the abnormal attributes and the abnormal location to determine the protection and rejuvenation measures corresponding to the ancient and famous trees.

[0152] This invention analyzes the abnormal attributes corresponding to abnormal locations by combining the soil fertility index and the branch and leaf vitality value, thereby understanding the growth limiting factors corresponding to the abnormal locations and improving the targeted protection and rejuvenation of ancient and famous trees. The abnormal attributes are the growth obstacle characteristics corresponding to the abnormal locations, such as soil nutrient imbalance or decline in branch and leaf physiological function. Optionally, the analysis of the abnormal attributes corresponding to the abnormal locations can be obtained by combining the numerical levels and interrelationships of the soil fertility index and the branch and leaf vitality value. For example, by comparing the soil fertility index and the branch and leaf vitality value with a preset health benchmark range, the main causes of abnormal growth can be inferred from an existing plant growth obstacle knowledge base based on the degree and correlation between the two. Finally, by combining the abnormal attributes and the abnormal location, the corresponding protection and rejuvenation measures for the ancient and famous trees can be determined.

[0153] Compared to the problems described in the background art, this invention extracts core growth data from the growth status data, removing information irrelevant to the core growth status of ancient and famous trees, focusing on key content in the data, and thus improving the efficiency of subsequent data processing. By extracting growth characteristics corresponding to the enhanced growth data, this invention obtains key information from the enhanced growth data, facilitating subsequent processing of these characteristics by the growth analysis model. Furthermore, by combining the abnormal growth characteristics, this invention locates the abnormal positions corresponding to the ancient and famous trees, thereby improving the accuracy of abnormal position determination. Based on the environmental data, it calculates the soil fertility index and branch and leaf vitality value corresponding to the abnormal position, obtaining the soil nutrient status and plant physiological activity level at the abnormal position, facilitating subsequent comprehensive analysis of the reasons for growth restriction at the abnormal position. Finally, by combining the soil fertility index and branch and leaf vitality value, this invention analyzes the abnormal attributes corresponding to the abnormal position, thereby understanding the growth limiting factors at the abnormal position and improving the targeted nature of the protection and rejuvenation of ancient and famous trees. Therefore, the method and system for protecting and rejuvenating ancient and famous trees provided in this embodiment of the invention can improve the effectiveness of protecting and rejuvenating ancient and famous trees.

[0154] like Figure 2 The diagram shown is a functional module diagram of a system for protecting and rejuvenating ancient and famous trees according to the present invention.

[0155] The present invention discloses a protection and rejuvenation system 200 for ancient and famous trees, which can be installed in an electronic device. Depending on the functions implemented, the system may include a benchmark screening module 201, an operational status analysis module 202, a distribution imbalance analysis module 203, and a trajectory optimization and task allocation module 204. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, and are stored in the memory of the electronic device.

[0156] In this embodiment of the invention, the functions of each module / unit are as follows:

[0157] The growth data processing module 201 is used to collect growth status data corresponding to ancient and famous trees, extract core growth data from the growth status data, and perform data enhancement processing on the core growth data to obtain enhanced growth data.

[0158] The data characterization sampling module 202 is used to extract the growth characterization corresponding to the enhanced growth data, input the growth characterization and the preset health characterization into the pre-configured growth analysis model, use the characterization sampling unit in the growth analysis model to sample the growth characterization to obtain the growth sampling characterization, and combine the preset health characterization with the abnormal mapping unit in the growth analysis model to map the growth sampling characterization to obtain the growth abnormal characterization.

[0159] The abnormal location analysis module 203 is used to determine the abnormal location corresponding to the ancient and famous trees by combining the abnormal growth characteristics, collect environmental data corresponding to the abnormal location using preset environmental monitoring equipment, and calculate the soil fertility index and branch and leaf vitality value corresponding to the abnormal location based on the environmental data.

[0160] The rejuvenation measures determination module 204 is used to analyze the abnormal attributes corresponding to the abnormal location by combining the soil fertility index and the branch and leaf vitality value, and to determine the protection and rejuvenation measures corresponding to the ancient and famous trees by combining the abnormal attributes and the abnormal location.

[0161] In detail, the modules in the protection and rejuvenation system 200 for ancient and famous trees described in this embodiment of the invention employ the same methods as described above during use. Figure 1 The method described herein is the same as the one used for the protection and rejuvenation of ancient and famous trees, and can produce the same technical effect, so it will not be repeated here.

[0162] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0163] Finally, it should be noted that in the above embodiments, each embodiment can be combined with each other or independent. Deleting any one of them will not affect the technical implementation of other embodiments. The above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for the protection and rejuvenation of ancient and famous trees, characterized in that, The method includes: Collect growth status data corresponding to ancient and famous trees, extract core growth data from the growth status data, and perform data augmentation processing on the core growth data to obtain enhanced growth data; Extract the growth characterization corresponding to the enhanced growth data, input the growth characterization and the preset health characterization into the pre-configured growth analysis model, use the characterization sampling unit in the growth analysis model to sample the growth characterization to obtain the growth sampling characterization, combine it with the preset health characterization, and use the anomaly mapping unit in the growth analysis model to map the growth sampling characterization to obtain the growth anomaly characterization. Based on the aforementioned abnormal growth characteristics, the abnormal locations corresponding to the ancient and famous trees are determined. Environmental data corresponding to the abnormal locations are collected using pre-set environmental monitoring equipment. Based on the environmental data, the soil fertility index and branch and leaf vitality value corresponding to the abnormal locations are calculated. By combining the soil fertility index and the branch and leaf vitality value, the abnormal attributes corresponding to the abnormal location are analyzed. By combining the abnormal attributes and the abnormal location, the protection and rejuvenation measures corresponding to the ancient and famous trees are determined.

2. The method for protecting and rejuvenating ancient and famous trees as described in claim 1, characterized in that, The extraction of core growth data from the growth status data includes: Detect the data attribute value corresponding to each data item in the growth status data; Based on the data attribute values, the data weight value corresponding to each data item in the growth state data is calculated; Based on the data weight values, the growth state data is subjected to weighted filtering to obtain weighted growth data; Set the effective data threshold corresponding to the weight growth data, and extract the core weight data from the weight growth data based on the effective data threshold. The core weight data is restructured to obtain core growth data.

3. The method for protecting and rejuvenating ancient and famous trees as described in claim 1, characterized in that, The process of performing data augmentation on the core growth data to obtain augmented growth data includes: The core growth data is subjected to numerical equalization processing to obtain balanced growth data; Calculate the smoothing value corresponding to each data point in the balanced growth data: ； Where S represents the smoothed value corresponding to each data item in the core growth data, M×N represents the data matrix window, M and N represent the number of rows and columns of all data items in the core growth data, i and j represent the row index and column index of the data item in the data matrix, and D(i,j) represents the data value located at position (i,j) in the core growth data. Based on the smoothing value, the core growth data is smoothed to obtain smoothed growth data; The smoothed growth data is then subjected to detail enhancement processing to obtain enhanced growth data.

4. The method for protecting and rejuvenating ancient and famous trees as described in claim 1, characterized in that, The extraction of growth characteristics corresponding to the enhanced growth data includes: Extract the temporal variation information from the enhanced growth data, and perform segmented aggregation processing on the temporal variation information to obtain the variation trend sequence; Based on the change trend sequence, construct the growth state diagram corresponding to the enhanced growth data; Based on the growth state diagram, calculate the trend characteristic value of the enhanced growth data; The trend feature values ​​are standardized to obtain the target trend feature values; Construct a trend feature vector corresponding to the target trend feature value, and generate a growth trend representation of the enhanced growth data based on the trend feature vector; The health indicator features of the enhanced growth data are extracted, and the growth trend characterization and the health indicator features are combined to obtain the growth characterization of the enhanced growth data.

5. A method for the protection and rejuvenation of ancient and famous trees as described in claim 1, characterized in that, The step of sampling the growth characterization using the characterization sampling unit in the growth analysis model to obtain the growth sampling characterization includes: The growth characterization is normalized by using the normalization component in the characterization sampling unit to obtain a normalized growth characterization. The target growth characterization is obtained by performing feature sampling processing on the standardized growth characterization using the aggregation sampling component in the characterization sampling unit. The feature priority corresponding to the target growth representation is calculated using the priority calculation unit in the representation sampling unit; Based on the feature priority, the corresponding growth sampling representation is output from the target growth representation using the output component in the representation sampling unit.

6. A method for the protection and rejuvenation of ancient and famous trees as described in claim 5, characterized in that, The step of calculating the feature priority corresponding to the target growth representation using the priority calculation unit in the representation sampling unit includes: The feature labels in the target growth characterization are extracted using the label extractor in the priority calculation unit, and the label frequency corresponding to the feature label is calculated. Based on the labeling frequency, the feature dispersion and labeling conditional entropy corresponding to the target growth representation are calculated using the difference function in the priority calculation unit. By combining the feature dispersion and the label conditional entropy, the feature saliency ratio corresponding to the target growth representation is calculated; Based on the feature saliency ratio, the feature priority corresponding to the target growth characterization is obtained.

7. A method for the protection and rejuvenation of ancient and famous trees as described in claim 1, characterized in that, The step of combining the preset health characteristics with the abnormality mapping unit in the growth analysis model to map the growth sampling characteristics and obtain growth abnormality characteristics includes: The growth sampling characterization and the preset health characterization are subjected to structural processing to obtain a first feature structure and a second feature structure; The structural similarity value between the first feature structure and the second feature structure is calculated using the mapper in the anomaly mapping unit; The feature matching degree between the preset health representation and the growth sampling representation is calculated using the matching function in the anomaly mapping unit; By combining the feature matching degree and the structural similarity value, features that differ from the preset healthy characteristics are selected from the growth sampling characteristics to obtain the growth abnormality characteristics.

8. A method for the protection and rejuvenation of ancient and famous trees as described in claim 7, characterized in that, The step of calculating the feature matching degree between the preset health representation and the growth sampling representation using the matching function in the anomaly mapping unit includes: The growth sampling characterization and the preset health characterization are vectorized respectively to obtain a first characterization vector and a second characterization vector. Calculate the average values ​​corresponding to the first representation vector and the second representation vector respectively to obtain the first average value and the second average value; Calculate the representation contribution value corresponding to each representation in the growth sampling representation; Combining the first representation vector, the second representation vector, the first average value, the second average value, and the representation contribution value, the feature matching degree between the preset health representation and the growth sampling representation is calculated using a matching function: ； Where A represents the feature matching degree between the preset health characterization and the growth sampling characterization, This represents the contribution value corresponding to the a-th feature in the growth sampling characterization. This represents the vector value corresponding to the a-th feature in the growth sampling representation. Let X represent the vector value corresponding to the a-th feature in the preset health representation, Y represent the average vector value corresponding to the growth sampling representation, a represent the sequence number of the growth sampling representation, and r represent the number of growth sampling representations. This represents the smallest perturbation value.

9. A method for the protection and rejuvenation of ancient and famous trees as described in claim 1, characterized in that, The step of calculating the soil fertility index and leaf vigor value corresponding to the abnormal location based on the environmental data includes: The environmental data is cleaned and calibrated to obtain standard environmental data; Analyze the nutrient content and physicochemical properties of the soil in the aforementioned standard environmental data; Measure the spectral reflectance characteristics and moisture distribution of the branches and leaves at the abnormal locations; Based on the nutrient content and the physicochemical properties, the soil fertility index corresponding to the abnormal location is calculated; Based on the spectral reflectance characteristics and the moisture distribution, the leaf and branch vitality value corresponding to the abnormal location is calculated.

10. A system for the protection and rejuvenation of ancient and famous trees, characterized in that, The system includes: The growth data processing module is used to collect growth status data corresponding to ancient and famous trees, extract core growth data from the growth status data, and perform data enhancement processing on the core growth data to obtain enhanced growth data. The data characterization sampling module is used to extract the growth characterization corresponding to the enhanced growth data, input the growth characterization and the preset health characterization into the pre-configured growth analysis model, use the characterization sampling unit in the growth analysis model to sample the growth characterization to obtain the growth sampling characterization, and combine the preset health characterization with the abnormal mapping unit in the growth analysis model to map the growth sampling characterization to obtain the growth abnormal characterization. An abnormal location analysis module is used to determine the abnormal location corresponding to the ancient and famous trees by combining the growth abnormality characteristics, collect environmental data corresponding to the abnormal location using preset environmental monitoring equipment, and calculate the soil fertility index and branch and leaf vitality value corresponding to the abnormal location based on the environmental data. The rejuvenation measures determination module is used to analyze the abnormal attributes corresponding to the abnormal location by combining the soil fertility index and the branch and leaf vitality value, and to determine the protection and rejuvenation measures corresponding to the ancient and famous trees by combining the abnormal attributes and the abnormal location.

Images