Forest community spatial construction method and system optimized by using an ai model

Abstract

The application provides a forest community space construction method and system optimized by using an AI model, first acquires a forest basic environment data set containing terrain features, soil properties and climate condition information, performs community adaptability analysis and processing to obtain adaptability evaluation results of different tree species, calls a pre-trained community space optimization model to perform space configuration calculation, generates a forest community space configuration scheme containing tree species planting location distribution and planting density planning, generates a community planting layout instruction containing geographic coordinate markers and planting quantity allocation rules according to the forest community space configuration scheme, and sends the community planting layout instruction to a forest planting execution system to trigger a planting layout operation, so that the forest community can be constructed scientifically and efficiently, and the forest ecological and economic benefits are improved.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and more specifically, to a method and system for constructing forest community space using AI models. Background Technology

[0002] Forests, as the main body of terrestrial ecosystems, play an irreplaceable role in maintaining ecological balance and providing ecosystem services. Rational forest community spatial design is crucial for improving forest ecological functions, protecting biodiversity, and ensuring the sustainable use of forest resources.

[0003] Traditional methods for constructing forest community spaces primarily rely on human experience and field surveys. Human experience is often limited by individual knowledge and accumulated experience, making it difficult to fully consider the complex environmental factors of forests, such as the impact of topography, soil, and climate on the growth of different tree species. While field surveys can obtain some on-site information, they consume significant human, material, and time resources, and their scope is limited, making it difficult to obtain comprehensive and accurate data. Furthermore, traditional methods lack scientific quantitative analysis when determining tree planting locations and densities, relying heavily on subjective judgment. This leads to irrational spatial configurations of forest communities, easily resulting in poor tree growth, frequent pest and disease outbreaks, and failing to fully realize the ecological and economic benefits of forests. Summary of the Invention

[0004] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, embodiments of the present invention provide a method for constructing forest community space using an AI model, the method comprising:

[0005] Acquire a set of basic forest environmental data, which includes topographic feature information, soil attribute information, and climate condition information;

[0006] Community suitability analysis was performed on the aforementioned forest basic environmental data set to obtain community suitability assessment results for different tree species;

[0007] The pre-trained community spatial optimization model is invoked to perform spatial configuration calculations on the community adaptability assessment results to obtain a forest community spatial configuration scheme, which includes tree species planting location distribution information and planting density planning information.

[0008] A community planting layout instruction is generated based on the forest community spatial configuration scheme. The community planting layout instruction includes geographic coordinate markers corresponding to the planting location distribution information and planting quantity allocation rules corresponding to the planting density planning information.

[0009] The community planting layout instruction is sent to the forest planting execution system to trigger the forest planting execution system to perform the community planting layout operation according to the geographic coordinate markers and planting quantity allocation rules.

[0010] In another aspect, embodiments of the present invention also provide a forest community spatial construction system optimized using an AI model, including a processor and a machine-readable storage medium connected to the processor. The machine-readable storage medium is used to store programs, instructions, or code, and the processor is used to run the programs, instructions, or code in the machine-readable storage medium to implement the above-described method.

[0011] Based on the above, this embodiment of the invention acquires a forest basic environmental data set containing information such as terrain features, soil properties, and climate conditions. It then performs community adaptability analysis on the forest basic environmental data set to obtain community adaptability assessment results for different tree species. A pre-trained community spatial optimization model is then invoked to perform spatial configuration calculations on the adaptability assessment results. Leveraging the powerful computing and learning capabilities of the AI ​​model, a forest community spatial configuration scheme containing tree species planting location distribution and planting density planning is generated. Based on the configuration scheme, a community planting layout instruction containing geographic coordinate markers and planting quantity allocation rules is generated. This community planting layout instruction is sent to the forest planting execution system to trigger the planting layout operation, ensuring the accurate implementation of forest community spatial construction, effectively improving the quality and efficiency of forest community construction, and contributing to the enhancement of forest ecological functions. Attached Figure Description

[0012] Figure 1 This is a schematic diagram of the execution flow of the forest community spatial construction method optimized by AI model provided in an embodiment of the present invention.

[0013] Figure 2 This is a schematic diagram of the hardware architecture of a forest community spatial construction system optimized using an AI model, provided in an embodiment of the present invention. Detailed Implementation

[0014] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 This is a flowchart illustrating a method for constructing forest community space using an AI model, as provided in one embodiment of the present invention. The following is a detailed description of this method for constructing forest community space using an AI model.

[0015] Step S110: Obtain a set of basic forest environmental data, which includes topographic feature information, soil attribute information, and climate condition information.

[0016] In this embodiment, a forest area to be used for community space construction is selected as the target area. For terrain feature information, a drone equipped with a lidar device performs a comprehensive scan of the target area, following a pre-planned flight path to ensure complete coverage and no data overlap or omission. The lidar device emits laser pulses that illuminate the ground and vegetation surfaces. By receiving the reflected pulse signals, distance information at different locations is calculated, generating point cloud data. After preprocessing to remove noise and redundant points, preliminary information such as elevation, slope, and aspect of the terrain can be extracted, forming a raw dataset of terrain feature information.

[0017] Meanwhile, to obtain more accurate terrain details, ground-based surveying methods were also incorporated. Multiple terrain survey points were evenly distributed within the target area, and the three-dimensional coordinates of each point were measured using a total station. The measurement results were then fused and calibrated with point cloud data acquired by lidar to improve the accuracy of terrain feature information.

[0018] For obtaining soil property information, a combination of soil sampling and laboratory analysis is employed. Soil sampling points are set up within the target area using a grid method, with soil samples collected at different depths at each sampling point; common depths are surface, middle, and deep layers. The collected soil samples are placed in sealed containers, and the sampling point location and depth information are marked. After the soil samples are sent to the laboratory, a series of experimental analysis procedures are used to obtain relevant property information. For example, the soil organic matter content is determined using the potassium dichromate oxidation-external heating method; soil pH is determined using a pH meter, during which the soil sample is mixed with distilled water in a specific ratio, stirred, and the supernatant is collected for measurement after settling; the content of nutrient elements in the soil, such as nitrogen, phosphorus, and potassium, is determined using atomic absorption spectrometry or inductively coupled plasma mass spectrometry. These data collectively constitute the soil property information set.

[0019] Acquisition of climate condition information relies on meteorological monitoring stations deployed within the target area. These stations are equipped with temperature sensors, humidity sensors, rain gauges, and sunshine duration recorders. Temperature sensors monitor air temperature changes in real time, recording data hourly. Rain gauges record precipitation at different times, distinguishing between rain and snow. Sunshine duration recorders calculate daily sunshine duration by sensing solar radiation intensity. Simultaneously, historical climate data from long-term meteorological stations surrounding the target area are collected, including temperature variation ranges and precipitation distribution patterns over the past few years. Real-time monitoring data is integrated with historical data to form comprehensive climate condition information.

[0020] Step S120: Perform community suitability analysis on the forest basic environmental data set to obtain community suitability assessment results for different tree species.

[0021] Step S121: Perform terrain type classification processing on the terrain feature information in the forest basic environmental data set, identify the slope distribution, elevation change and aspect distribution in the terrain feature information, and obtain the terrain classification result.

[0022] In this embodiment, topographic-related data is extracted from the forest basic environmental dataset, including elevation data, slope data, and aspect data obtained through lidar and ground surveying. This data is preprocessed to remove outliers and data points with significant measurement errors, ensuring data reliability.

[0023] Next, terrain type classification is performed. A terrain classification algorithm is used to divide the target area into different altitude ranges based on elevation, with each range representing a different altitude type. For example, areas with lower elevations are classified as low-altitude areas, areas with medium elevations as medium-altitude areas, and areas with higher elevations as high-altitude areas. Simultaneously, classification is based on slope: areas with gentle slopes are classified as flat slopes, areas with medium slopes as gentle slopes, and areas with steep slopes as steep slopes. Slope aspect is classified according to azimuth, such as sunny slopes, shady slopes, semi-sunny slopes, and semi-shady slopes.

[0024] When identifying slope distribution, a slope calculation tool is used to process elevation data and generate a slope distribution map. This map clearly shows the distribution of slope magnitude at different locations within the target area, identifying which areas have gentler slopes and which have steeper slopes. Elevation changes are obtained through statistical analysis of the elevation data, calculating the maximum and minimum elevation values ​​and the range of elevation changes for the entire target area. Simultaneously, an elevation contour map is generated to visually display the spatial distribution of elevation. The aspect distribution is processed using an aspect calculation tool to generate an aspect distribution map, clearly defining the distribution range and area proportion of different slope aspects within the target area.

[0025] The classification results based on elevation, slope, and aspect are integrated to form a terrain classification result. The terrain classification result is presented in the form of a vector map or raster map, and each region unit is labeled with the corresponding elevation type, slope type, and aspect type.

[0026] Step S122: Calculate the growth suitability parameters of different tree species in various terrain regions based on the terrain classification results.

[0027] In this embodiment, after obtaining the terrain classification results, the growth suitability parameters for different tree species are calculated based on these results. First, biological characteristic data of various tree species that may be planted in the target area are collected. This data includes the suitable range requirements of each tree species for altitude, slope, and aspect. For example, some tree species are suitable for growth at low altitudes, on gentle slopes, and on sunny slopes, while others are more suitable for growth at medium to high altitudes, on gentle slopes, and on shady slopes.

[0028] For each tree species, the suitability of the species in different terrain regions was evaluated by combining the altitude type, slope type, and aspect type in the terrain classification results. For the altitude factor, the suitable altitude range of the tree species was compared with the altitude range in the terrain classification results. If the altitude range of a certain terrain region is completely within the suitable altitude range of the tree species, the tree species has a high suitability score for that altitude factor; if there is partial overlap, the score is medium; if there is no overlap at all, the score is low.

[0029] The assessment of slope factors is similar. Based on the tree species' tolerance to slope, the slope type in the terrain classification results is matched with the suitable slope range for the tree species. For example, tree species that prefer gentle terrain score highly on gentle slopes and lowly on steep slopes. The aspect factor is assessed based on the tree species' light requirements; light-loving species score highly on sunny slopes, while shade-loving species score highly on shady slopes.

[0030] After obtaining the suitability scores for altitude, slope, and aspect, a weighted calculation method is used to synthesize the growth suitability parameters of the tree species in a specific terrain region. The weights are determined based on the importance of each terrain factor to the tree species' growth. For example, for some tree species, altitude has a greater impact and therefore a higher weight; while for others, aspect has a more significant impact and therefore a higher weight. Through this method, the growth suitability parameters of each tree species in different terrain classifications within the target area are calculated, forming a multi-dimensional parameter matrix. Each parameter corresponds to the growth suitability of a tree species in a specific terrain region.

[0031] Step S123: Perform component analysis on the soil attribute information in the forest basic environmental data set, extract the organic matter content, pH and nutrient element content from the soil attribute information, and obtain the soil component analysis results.

[0032] In this embodiment, the component analysis of soil property information is a crucial step in community suitability analysis. Various test data from soil samples are extracted from the forest basic environmental dataset, including organic matter content, pH value, and the content of various nutrient elements.

[0033] First, the organic matter content was analyzed. The organic matter content data from each soil sampling point measured in the laboratory were compiled, and outliers caused by experimental errors were removed. Then, spatial interpolation algorithms, such as Kriging interpolation, were used to calculate the spatial distribution of organic matter content throughout the target area based on the data from each sampling point. An organic matter content distribution map was generated, using different colors or numerical ranges to represent the high and low distribution of organic matter content, thus obtaining the analysis results of the organic matter content.

[0034] For pH levels, pH data from each sampling point were also compiled. Soil pH was categorized based on its range, such as strongly acidic, acidic, neutral, alkaline, and strongly alkaline. Spatial interpolation methods were used to generate a soil pH distribution map, showing the distribution of pH types in different areas, clarifying the spatial variation patterns of soil pH within the target area, and forming the analysis results for pH conditions.

[0035] The analysis of nutrient element content focused on major nutrients such as nitrogen, phosphorus, and potassium, as well as other minor nutrients. For each nutrient element, the content detection data from each sampling point were compiled, outlier handling was performed, and a spatial interpolation algorithm was used to generate the corresponding nutrient element content distribution map. The distribution map clearly shows the enriched and deficient areas of various nutrients within the target region. The analysis results of organic matter content, pH, and nutrient element content were integrated to form the soil composition analysis results, comprehensively reflecting the soil properties of the target area.

[0036] Step S124: Determine the soil condition matching parameters for different tree species based on the soil composition analysis results.

[0037] In this embodiment, after obtaining the soil composition analysis results, the matching parameters of soil conditions for different tree species are determined. First, soil requirement characteristics data of various tree species to be evaluated are collected. These data record in detail the suitable organic matter content range, suitable pH range, and the required amount of various nutrients for the growth of each tree species.

[0038] For each tree species, the results were compared with those of soil composition analysis. For organic matter content, the suitable organic matter content range for each tree species was matched with the spatial distribution of organic matter content in the soil composition analysis results. In a specific soil area within the target region, if the organic matter content of that area falls within the suitable range for the tree species, the organic matter requirement matching score for that tree species in that area is higher; if it is lower or higher than the suitable range, the score is correspondingly lower.

[0039] Regarding pH levels, the suitable pH range for tree species is compared with the pH distribution in the soil composition analysis results. If the pH of the soil area is within the suitable range for the tree species, the pH requirement matching score is high; otherwise, the score is low.

[0040] Regarding nutrient elements, for each nutrient element, the required amount by the tree species was matched with the content distribution of that nutrient element in the soil composition analysis results. For nutrient elements with high requirements, a high matching score was obtained if the content of that element in the soil was sufficient, and a low score was obtained if the content was insufficient. For some tree species that do not require excessive amounts of nutrient elements, an excessively high content of that element in the soil may also lead to a lower matching score.

[0041] After obtaining the demand matching scores for organic matter, pH, and various nutrient elements, weights are assigned based on the importance of each soil factor to tree species growth. A weighted calculation is then performed to obtain the demand matching degree parameter for that tree species in a specific soil region. Different tree species have varying sensitivities to soil factors, and the weighting will differ accordingly. For example, some tree species are highly sensitive to soil pH, so pH will have a higher weight; while other tree species are more dependent on organic matter content, so organic matter will have a correspondingly higher weight. Through the above calculation process, the demand matching degree parameters for each tree species in different soil regions of the target area are obtained, forming a multi-dimensional parameter matrix.

[0042] Step S125: Perform time-period statistical processing on the climate condition information in the forest basic environmental data set to obtain the temperature variation range, precipitation distribution and sunshine duration distribution in the climate condition information, and obtain the climate statistical results.

[0043] In this embodiment, the time-period statistical processing of climate condition information aims to extract key climate characteristics of the target area. Temperature data, precipitation data, and sunshine duration data recorded by meteorological monitoring stations, as well as historical climate data from surrounding long-term meteorological stations, are extracted from the forest basic environmental data set.

[0044] First, the temperature variation range is statistically analyzed. Temperature data is divided into time periods, such as annually, quarterly, or monthly. The highest, lowest, and average temperatures within each time period are calculated to determine the temperature variation range for different time periods. Simultaneously, seasonal temperature patterns are analyzed, such as the high-temperature periods in summer, the low-temperature periods in winter, and temperature fluctuations in spring and autumn. Through these statistical analyses, information on the temperature variation range of the target area is obtained.

[0045] The statistics on precipitation distribution include both temporal and spatial distribution. Temporally, precipitation is statistically analyzed for different time periods (e.g., monthly, quarterly, annually), calculating the changes in total precipitation, precipitation frequency, and precipitation intensity, and analyzing the distribution characteristics of the rainy and dry seasons. Spatially, precipitation distribution maps are generated using spatial interpolation methods, combining precipitation data from multiple meteorological monitoring stations to demonstrate the differences in precipitation at different locations within the target area.

[0046] The statistical analysis of sunshine duration distribution involves organizing and analyzing data recorded by sunshine duration loggers. Sunshine duration is statistically analyzed daily, monthly, and yearly, calculating the average sunshine duration, longest sunshine duration, and shortest sunshine duration, and analyzing seasonal variations and spatial distribution differences in sunshine duration. For example, some areas may have shorter sunshine durations due to terrain obstruction, while open areas may have longer sunshine durations.

[0047] By integrating the statistical results of temperature variation range, precipitation distribution, and sunshine duration distribution, a climate statistical result is formed, which comprehensively reflects the climate characteristics of the target area.

[0048] Step S126: Calculate the adaptability parameters of different tree species to climate conditions based on the climate statistics results.

[0049] In this embodiment, the adaptability parameters of different tree species are calculated by combining climate statistics results. First, climate adaptability data of each tree species are collected to clarify the suitable temperature range, precipitation range, and sunshine duration range for the growth of each tree species.

[0050] Regarding temperature conditions, the temperature variation range in the climate statistics is compared with the suitable temperature range of the tree species. For a certain climate zone within the target area, if the temperature variation range of the zone is entirely within the suitable temperature range of the tree species, the tree species will have a higher temperature adaptability score in that zone; if it partially exceeds the suitable range, the score will decrease accordingly based on the degree of exceedance; if it completely exceeds the suitable range, the score will be lower.

[0051] The assessment of adaptability to precipitation conditions is similar, matching the precipitation distribution data in climate statistics with the suitable precipitation range for tree species. If the precipitation in a certain climate region is within the suitable precipitation range for a tree species, and the precipitation distribution pattern matches the growth requirements of the tree species, the precipitation adaptability score is high; if the precipitation is too much or too little, or the precipitation distribution is uneven, the score is low.

[0052] The assessment of light duration adaptability compares the distribution of light duration in climate statistics with the suitable light duration range for tree species. If the light duration in a certain climate region is within the suitable range for a tree species, the light adaptation score is high; if the light duration is insufficient or excessive, exceeding the tolerance range of the tree species, the score is low.

[0053] After obtaining adaptation scores for temperature, precipitation, and sunshine duration, a weighted calculation is performed based on the influence weights of each climatic factor on tree species growth to obtain the adaptability parameters of that tree species in a specific climatic region. Different tree species have different degrees of dependence on climatic factors, and the weighting settings also differ. For example, tropical tree species have higher temperature requirements, so temperature has a larger weight; while drought-resistant tree species have a relatively lower weight for precipitation. Through the above calculations, the adaptability parameters of each tree species in different climatic regions of the target area are obtained, forming a multi-dimensional parameter matrix.

[0054] Step S127: After standardizing and transforming the growth suitability parameters, demand matching parameters and adaptability parameters, the community adaptability assessment results of different tree species are generated by weighted splicing calculation. The weights of the weighted splicing calculation are set based on the priority of key influencing factors of tree species growth.

[0055] In this embodiment, after obtaining the growth suitability parameter, demand matching parameter, and adaptability parameter, these parameters need to be standardized to eliminate the differences in dimensions between different parameters and ensure the rationality of subsequent calculations. The standardization transformation uses the Min-Max standardization method, mapping the value range of each parameter to the [0,1] interval. Specifically, for each parameter type, the maximum and minimum values ​​of that parameter across all regions and tree species are found, and then the standardized parameter value is calculated using the formula (parameter value - minimum value) / (maximum value - minimum value). This transformation makes different types of parameters comparable.

[0056] After standardization, a weighted concatenation calculation is performed to generate the community suitability assessment results. First, the weights of growth suitability parameters, demand matching parameters, and adaptability parameters in the community suitability assessment are determined. These weights are set based on the priority of key factors influencing tree species growth, determined through expert experience or data analysis. For example, for some tree species, soil conditions are crucial to their growth, so the demand matching parameter will have a higher weight; while for other tree species, climate conditions have a greater impact, so the adaptability parameter will have a correspondingly higher weight.

[0057] In the weighted splicing process, for each tree species in each region, the standardized growth suitability parameter, demand matching parameter, and adaptability parameter are multiplied by their respective weights. These three weighted parameters are then spliced ​​together in sequence to form the community suitability assessment result for that tree species in that region. For example, if the weight of the growth suitability parameter is W1, the weight of the demand matching parameter is W2, and the weight of the adaptability parameter is W3, and the standardized parameter values ​​are P1, P2, and P3 respectively, then the spliced ​​community suitability assessment result is [P1×W1, P2×W2, P3×W3]. Through this method, three different aspects of suitability parameters are integrated into a holistic assessment result, comprehensively reflecting the community suitability of the tree species in a specific region.

[0058] Step S130: Call the pre-trained community spatial optimization model to perform spatial configuration calculation on the community adaptability assessment results to obtain a forest community spatial configuration scheme, which includes tree species planting location distribution information and planting density planning information.

[0059] Step S131: Input the community adaptability assessment result into the feature input layer of the community spatial optimization model. The feature input layer performs dimension normalization on the community adaptability assessment result so that the feature dimension of the community adaptability assessment result is consistent with the preset input dimension of the community spatial optimization model, thereby obtaining the normalized adaptability feature.

[0060] In this embodiment, after the community fitness assessment results are input into the community spatial optimization model, they first enter the feature input layer. The primary task of the feature input layer is to perform dimensionality checks on the input community fitness assessment results to determine the feature dimensions of the current input data. Since community fitness assessment results from different batches or different sources may have dimensionality differences, which can affect the subsequent processing accuracy of the model, dimensionality normalization is required.

[0061] During dimensionality normalization, if the feature dimension of the community fit assessment result is lower than the model's preset input dimension, the missing dimension is supplemented through feature expansion. Feature expansion generates supplementary features that match the preset dimension based on the distribution patterns and correlations of existing features. These supplementary features can reflect the potential information of the original features to a certain extent. If the feature dimension of the community fit assessment result is higher than the model's preset input dimension, a feature selection algorithm is used to select core features that have a greater impact on spatial configuration calculations, while redundant or secondary features are eliminated to reduce the data dimensionality to the preset input dimension.

[0062] After dimensionality adjustment, the feature input layer further standardizes the data, unifying the numerical range of the regularized adaptive features to the standard range used during model training, thus avoiding interference with the model's processing results due to differences in data scale. After these processes, the regularized adaptive features are obtained, which meet the dimensionality requirements of subsequent layers in the community space optimization model for the input data.

[0063] Step S132: Input the regularized adaptability features into the spatial association layer of the community spatial optimization model. The spatial association layer analyzes the mutual influence relationship between the regularized adaptability features of different tree species, identifies tree species combinations with symbiotic promotion and tree species combinations with competitive inhibition, and obtains the tree species association analysis results.

[0064] Step S1321: In the spatial association layer of the community spatial optimization model, extract the key influencing factors in the regularized adaptability characteristics of different tree species. The key influencing factors include terrain adaptability factors, soil demand factors, and climate adaptability factors.

[0065] In this embodiment, before analyzing the inter-species relationships, the spatial association layer needs to extract key influencing factors from the regularized adaptability features. The extraction of key influencing factors is based on a feature importance assessment algorithm, which can screen out factors that play a decisive role according to the degree of influence of features on tree species growth and interactions.

[0066] Topographic adaptability factors primarily reflect a tree species' ability to adapt to topographic conditions, including its growth adaptation characteristics in areas with different altitudes, slopes, and aspects. Soil requirement factors reflect a tree species' needs for soil properties, covering adaptation characteristics such as organic matter content, pH, and nutrient element content. Climate adaptability factors reflect a tree species' ability to adapt to climatic conditions, including adaptation characteristics such as temperature variation range, precipitation distribution, and sunshine duration distribution.

[0067] During the extraction process, the contribution and correlation of each feature in historical data were calculated to determine the specific composition and weight of topographic adaptation factors, soil requirement factors, and climate adaptation factors. These key influencing factors can comprehensively reflect the growth characteristics and environmental requirements of tree species, laying the foundation for subsequent analysis of the interactions between tree species.

[0068] Step S1322: Calculate the similarity coefficient between the key influencing factors of any two tree species.

[0069] In this embodiment, after extracting the key influencing factors, the spatial association layer begins to calculate the similarity coefficient between any two tree species. During the calculation process, the similarity is calculated separately for terrain adaptation factors, soil requirement factors, and climate adaptation factors, and then the overall similarity coefficient is obtained through weighted summation.

[0070] For topographic adaptability factors, the similarity component of the topographic adaptability factor is calculated by comparing the adaptability range and degree of two tree species in terms of altitude, slope, and aspect, and calculating their overlap in topographic adaptation. The similarity component of the soil requirement factor is obtained by comparing the overlap in the range and intensity of the two tree species' requirements for soil properties such as organic matter content, pH, and nutrient content. The similarity component of the climate adaptability factor is calculated based on the degree of overlap in the adaptability ranges of two tree species to climatic conditions such as temperature, precipitation, and light.

[0071] The similarity components of these three factors are combined according to certain weights, which are determined based on the importance of each factor in the relationship between tree species. This yields the similarity coefficient between the key influencing factors of any two tree species. A higher similarity coefficient indicates that the two tree species are more similar in their characteristics regarding the key influencing factors.

[0072] Step S1323: Divide the similarity level according to the similarity coefficient. When the similarity coefficient is in the preset high similarity interval, determine that the two tree species are potential competitors. When the similarity coefficient is in the preset low similarity interval, determine that the two tree species are potential symbiotics.

[0073] In this embodiment, after obtaining the similarity coefficient, the spatial association layer classifies it according to a preset similarity level classification standard. The similarity level classification standard is determined based on statistical analysis of a large amount of tree species interaction data, and presets three level ranges: high similarity interval, medium similarity interval, and low similarity interval.

[0074] When the similarity coefficient of two tree species falls within the preset high similarity range, it indicates a high degree of similarity in key influencing factors such as terrain adaptation, soil requirements, and climate adaptation. This implies a significant overlap in their needs for the growing environment and their dependence on resources, thus classifying them as potential competitors. When the similarity coefficient falls within the preset low similarity range, it indicates significant differences in key influencing factors and strong complementarity in environmental needs and resource utilization, thus classifying them as potential symbiotic relationships. For tree species combinations falling within the medium similarity range, further analysis and verification are needed to determine their relationship type.

[0075] By using the above classification, we can initially screen out potential competitive tree species combinations and potential symbiotic tree species combinations.

[0076] Step S1324: For tree species combinations with potential symbiotic relationships, further analyze the resource complementarity during their growth process, including water utilization complementarity, nutrient absorption complementarity, and light utilization complementarity, and calculate the symbiotic promotion coefficient.

[0077] In this embodiment, for tree species combinations identified as having a potential symbiotic relationship, the spatial association layer will conduct a more in-depth analysis of resource complementarity. The water use complementarity analysis mainly examines the differences in root depth and water absorption capacity between the two tree species. If one tree species has shallow roots and mainly absorbs shallow surface water, while the other tree species has deep roots and mainly absorbs deep soil water, then they can complement each other in water use, reducing water competition.

[0078] Nutrient absorption complementarity analysis focuses on the preferred absorption characteristics of tree species for different types of nutrients. For example, if one tree species has a high demand for nitrogen and another has a high demand for phosphorus, and their fallen leaves release the nutrients needed by the other, then they are complementary in nutrient absorption. Light utilization complementarity analysis is based on the shade tolerance of tree species. If one species is a light-loving species suitable for growing in areas with ample sunlight, and another is a shade-loving species suitable for growing in areas with less sunlight, planting them together can fully utilize spaces with different light intensities and improve light utilization efficiency.

[0079] Based on the analysis of these resource complementarities, a corresponding score is assigned to each complementarity dimension, and then a symbiotic promotion coefficient is obtained through weighted calculation. The higher the symbiotic promotion coefficient, the stronger the symbiotic promotion effect of the tree species combination.

[0080] Step S1325: For tree species combinations with potential competitive relationships, analyze the resource competition during their growth process, including competition for soil nutrients, light resources, and growth space, and calculate the competition inhibition coefficient.

[0081] In this embodiment, for tree species combinations with potential competition, the spatial correlation layer focuses on analyzing their resource competition. The analysis of soil nutrient competition compares the demand intensity and absorption efficiency of the two tree species for major nutrients in the soil. If both tree species have high demands for major nutrients such as nitrogen, phosphorus, and potassium, and their absorption methods are similar, then their competition for soil nutrients is highly intense.

[0082] The analysis of competition for light resources is based on the tree species' height, crown width, and growth rate. Tall and rapidly growing tree species will block the light from shorter tree species. If the two tree species have similar height and crown width and both require sufficient light, the competition for light resources will be more pronounced. The analysis of competition for growth space mainly considers the root system expansion range and the space requirements for branch and leaf growth. If the root system expansion ranges of the two tree species overlap significantly, and their branch and leaf growth space encroaches on each other, the competition for growth space will be intense.

[0083] Based on the analysis of these resource competition situations, a corresponding score is assigned to each competition dimension, and then a competition inhibition coefficient is obtained through weighted calculation. The higher the value of the competition inhibition coefficient, the stronger the competition inhibition effect of the tree species combination.

[0084] Step S1326: Based on the symbiotic promotion coefficient and the competition inhibition coefficient, classify and label all tree species combinations, and generate tree species association analysis results containing a list of symbiotic promotion tree species combinations and a list of competition inhibition tree species combinations.

[0085] In this embodiment, the spatial association layer performs final classification and labeling of all tree species combinations based on the magnitude of the symbiosis promotion coefficient and the competition inhibition coefficient. Thresholds are set for the symbiosis promotion coefficient and the competition inhibition coefficient. When the symbiosis promotion coefficient of a tree species combination is higher than a preset symbiosis threshold and the competition inhibition coefficient is lower than a preset competition threshold, it is marked as a symbiosis-promoting tree species combination and included in the symbiosis-promoting tree species combination list.

[0086] When a tree species combination has a competition inhibition coefficient higher than a preset competition threshold and a symbiotic promotion coefficient lower than a preset symbiotic threshold, it is marked as a competition inhibition tree species combination and included in the competition inhibition tree species combination list. For tree species combinations where both the symbiotic promotion coefficient and the competition inhibition coefficient are in the middle range, a comprehensive judgment is made based on the actual situation before classification and labeling. Through the above classification and labeling, tree species association analysis results are generated, which present the types of relationships between different tree species combinations within the target area.

[0087] Step S133: Based on the tree species association analysis results, the configuration generation layer of the community spatial optimization model constructs an initial spatial configuration matrix, where each matrix element corresponds to a tree species allocation identifier for a geographical region.

[0088] In this embodiment, after receiving the tree species association analysis results, the configuration generation layer begins to construct the initial spatial configuration matrix. First, the target area is divided into multiple geographical regions according to a preset grid size, with each geographical region corresponding to a matrix element in the initial spatial configuration matrix. The grid size is determined based on the area and terrain complexity of the target region to ensure the accuracy and rationality of the spatial configuration.

[0089] Then, based on the community adaptability assessment results, tree species with high adaptability were initially selected for each geographic region. During the selection process, priority was given to tree species that ranked high in the community adaptability assessment within that geographic region. Next, the tree species allocation in adjacent geographic regions was coordinated based on the results of tree species association analysis. For adjacent geographic regions, tree species combinations with symbiotic and promoting relationships were selected as much as possible, avoiding the allocation of tree species with competitive and inhibitory relationships in adjacent regions.

[0090] Each tree species assigned to a geographic region is assigned a unique tree species assignment identifier, which contains key information such as tree species type and growth characteristics. These tree species assignment identifiers are then filled into an initial spatial configuration matrix according to the geographical region's location order, with each matrix element corresponding to a tree species assignment identifier for a geographic region, thus completing the construction of the initial spatial configuration matrix.

[0091] Step S134: Call the optimization adjustment layer of the community spatial optimization model to perform iterative optimization processing on the initial spatial configuration matrix. In each iteration, adjust the tree species allocation identifier of the matrix elements according to the differences in tree species adaptability between adjacent geographical regions until the iteration result meets the preset spatial configuration uniformity index.

[0092] Step S1341: In the first iteration, calculate the difference between the community fitness assessment result of the tree species corresponding to each matrix element in the initial spatial configuration matrix and the community fitness assessment result of the tree species corresponding to the adjacent matrix elements to obtain a set of fitness difference values.

[0093] In this embodiment, at the start of the first iteration, the optimization adjustment layer extracts the community suitability evaluation results of the tree species corresponding to each matrix element in the initial spatial configuration matrix. For each matrix element, its neighboring matrix elements are determined, and the adjacency relationship includes horizontal and vertical adjacency.

[0094] Then, the difference between the community suitability assessment result of the tree species corresponding to each matrix element and the community suitability assessment result of the tree species corresponding to each adjacent matrix element is calculated. These differences reflect the degree of difference in tree species suitability between adjacent geographic regions. All calculated differences are summarized to form a suitability difference value set, which contains tree species suitability difference information between all adjacent geographic regions in the initial spatial configuration matrix.

[0095] Step S1342: Determine the region exceeding the difference limit based on the set of adaptation difference values. The region exceeding the difference limit is the geographical region corresponding to the adjacent matrix element whose adaptation difference value exceeds a preset difference threshold.

[0096] In this embodiment, the optimization adjustment layer sets a preset difference threshold, which is determined based on a large amount of spatial configuration case data and the actual situation of the target area. It is used to determine whether the differences in tree species adaptability between adjacent geographical areas are within an acceptable range.

[0097] Each difference in the set of adaptability difference values ​​is compared with a preset difference threshold. When a difference exceeds the preset threshold, it indicates that the tree species adaptability difference between the geographical areas represented by the corresponding adjacent matrix elements is too large, which is not conducive to the stable growth of the forest community. The geographical areas corresponding to these adjacent matrix elements are marked as areas with excessive differences. In this way, the areas in the initial spatial configuration matrix that need to be adjusted are accurately identified.

[0098] Step S1343: For the matrix elements in the difference-exceeding region, reallocate tree species allocation identifiers. During the reallocation process, prioritize tree species that have a symbiotic relationship with the tree species corresponding to the adjacent matrix elements, and ensure that the community adaptability assessment results of the reallocated tree species meet the preset adaptability requirements.

[0099] In this embodiment, for matrix elements in areas where differences exceed limits, the optimization and adjustment layer begins to reallocate tree species allocation identifiers. First, tree species whose community suitability assessment results in this geographical area meet preset suitability requirements are selected from the tree species library. The preset suitability requirements mean that the community suitability assessment results of the tree species are not lower than a certain threshold, so as to ensure that the reallocated tree species can grow normally in this area.

[0100] Then, based on the results of the tree species association analysis, tree species that have a symbiotic relationship with the tree species corresponding to adjacent matrix elements are preferentially selected from those that meet the preset suitability requirements. If multiple tree species meet the conditions, their community suitability assessment results are further compared, and the tree species with higher suitability is selected as the tree species for reassignment.

[0101] Assign new tree species allocation identifiers to the reassigned tree species and update the corresponding matrix element positions in the spatial configuration matrix to complete the initial adjustment of the difference-exceeding regions.

[0102] Step S1344: After the redistribution is completed, a new spatial configuration matrix is ​​generated, and the spatial configuration uniformity index of the new spatial configuration matrix is ​​calculated. The spatial configuration uniformity index is obtained by calculating the average of the fitness difference values ​​of all adjacent matrix elements.

[0103] In this embodiment, after the reallocation is completed, the optimization adjustment layer generates a new spatial configuration matrix. To evaluate the optimization effect of the new spatial configuration matrix, its spatial configuration uniformity index needs to be calculated. During the calculation process, firstly, the community fitness evaluation results of the tree species corresponding to each matrix element in the new spatial configuration matrix are extracted, and then the fitness difference value between all adjacent matrix elements is calculated.

[0104] These fitness differences are aggregated, and their average value is calculated. This average value is the spatial uniformity index of the new spatial configuration matrix. The smaller the value of the spatial uniformity index, the smaller the differences in tree species fitness between adjacent geographical areas, and the better the spatial uniformity.

[0105] Step S1345: Determine whether the spatial configuration uniformity index has reached the preset uniformity standard. If it has not reached the standard, use the new spatial configuration matrix as the initial matrix of the current iteration and repeat the steps of calculating the fitness difference value set, determining the difference exceeding the limit region, reallocating the tree species allocation identifier and calculating the spatial configuration uniformity index.

[0106] In this embodiment, the optimization and adjustment layer compares the calculated spatial configuration uniformity index with a preset uniformity standard. The preset uniformity standard is set based on the ecological needs and forest management objectives of the target area and is an important basis for measuring whether the spatial configuration is reasonable.

[0107] If the spatial configuration uniformity index does not reach the preset uniformity standard, it indicates that there is still significant room for optimization in the current spatial configuration, requiring further iterative optimization. In this case, the newly generated spatial configuration matrix is ​​used as the initial matrix for the current iteration, and the next iteration begins. In this new iteration, the difference between the community suitability assessment result of the tree species corresponding to each element in the initial matrix and the community suitability assessment result of the tree species corresponding to the adjacent matrix elements is recalculated, generating a new set of suitability difference values. This process is consistent with the calculation method used in the first iteration, ensuring the accuracy and consistency of the difference calculation. By comparing the suitability assessment results of each element with its adjacent elements, the differences in spatial configuration are comprehensively captured.

[0108] Next, regions exceeding the difference limit are determined based on the newly generated set of adaptation difference values. Again, using a preset difference threshold as the criterion, the geographical regions corresponding to adjacent matrix elements whose adaptation difference values ​​exceed the threshold are marked as new regions exceeding the difference limit. During this determination process, the relationship between each difference value and the threshold needs to be carefully checked to avoid overlooking any regions exceeding the limit and to ensure that all regions with significant adaptation differences are included in the optimization scope.

[0109] Then, tree species assignment labels are reassigned to the matrix elements in the new regions exceeding the difference limit. During reassignment, tree species with symbiotic and promoting relationships with the tree species corresponding to adjacent matrix elements are still given priority. This is to utilize the positive interactions between tree species to improve the overall community stability and growth status. At the same time, it is essential to ensure that the community adaptability assessment results of the reassigned tree species meet the preset adaptability requirements. That is, the adaptability assessment results of the tree species in this region cannot be lower than the set minimum standard to ensure that the tree species can grow normally in this region.

[0110] After the reallocation is completed, a new spatial configuration matrix is ​​generated, and the spatial configuration uniformity index of this matrix is ​​calculated. The calculation method is still to calculate the average of the fitness differences of all adjacent matrix elements. This average value can intuitively reflect the uniformity of the current spatial configuration.

[0111] Next, it is determined whether the newly calculated spatial configuration uniformity index meets the preset uniformity standard. If it still does not, the steps of calculating the set of adaptability difference values, identifying areas with excessive differences, reallocating tree species allocation identifiers, and calculating the spatial configuration uniformity index are repeated, and so on. Each iteration aims to gradually reduce the adaptability differences in spatial configuration, making the spatial configuration more uniform and reasonable.

[0112] During the iteration process, key information for each iteration needs to be recorded, including the iteration number, the generated spatial configuration matrix, the set of fitness difference values, the region where differences exceed limits, and the spatial configuration uniformity index. These records help track the progress of the iteration process and analyze the optimization effect. Through multiple iterations, the spatial configuration matrix is ​​continuously optimized, and the uniformity of the spatial configuration is gradually improved until the spatial configuration uniformity index reaches the preset uniformity standard.

[0113] Step S1346: If the preset uniformity standard is reached, stop the iteration process and use the current spatial configuration matrix as the optimized spatial configuration matrix.

[0114] In this embodiment, when the spatial configuration uniformity index obtained from a certain iteration reaches the preset uniformity standard, it indicates that the current spatial configuration is within an acceptable range in terms of adaptability differences, and the spatial distribution is relatively uniform and reasonable. At this point, the optimization and adjustment layer stops its iterative operation and no longer performs new adaptability difference calculations, determines regions exceeding the difference limit, or redistributes tree species.

[0115] The current spatial configuration matrix is ​​determined as the optimized spatial configuration matrix. This matrix has undergone multiple iterations of optimization, fully considering factors such as tree species adaptability, inter-species relationships, and spatial uniformity, and can better meet the needs of forest community spatial construction. After determining the optimized matrix, its completeness and accuracy need to be checked to ensure that each element in the matrix has a clear tree species assignment identifier, and that the identifier information is accurate and consistent with the adjustment results during the iterative optimization process. Simultaneously, the matrix's dimensions and coverage are checked to ensure they match the geographical scope of the target area, avoiding problems such as incorrect matrix dimensions or incomplete coverage.

[0116] Step S135: After the iterative optimization process is completed, the output layer of the community spatial optimization model performs analytical processing on the optimized spatial configuration matrix, extracts the tree species planting location distribution information and planting density planning information corresponding to each geographical region, and obtains the forest community spatial configuration scheme.

[0117] In this embodiment, after the iterative optimization process is completed and the optimized spatial configuration matrix is ​​determined, the output layer of the community spatial optimization model begins to parse the matrix. First, the output layer reads all the data information in the optimized spatial configuration matrix, including the geographical region identifier and tree species allocation identifier corresponding to each matrix element.

[0118] When extracting tree species planting location distribution information, the output layer establishes a mapping relationship between the position information of matrix elements and the geographic coordinate system of the target area. The row and column position of each matrix element corresponds to a specific geographic region within the target area. Through this mapping relationship, the position of the matrix elements is converted into actual geographic coordinate ranges, clarifying the specific geographic location where each tree species is assigned for planting. Simultaneously, the set of geographic regions corresponding to each tree species is recorded, forming a correspondence between tree species and planting locations, thereby generating tree species planting location distribution information.

[0119] For extracting planting density planning information, the output layer analyzes the biological characteristics of tree species and the environmental conditions of the target area. Different tree species have different suitable planting densities due to variations in growth habits, growth rates, and spatial requirements. Based on the tree species allocation identifier for each geographical region in the optimized spatial configuration matrix, the output layer calls a pre-defined tree species density parameter library, which stores recommended planting density ranges for different tree species under various environmental conditions.

[0120] The output layer determines the specific planting density of corresponding tree species within a geographical area, based on environmental factors such as area size, soil fertility, and climate conditions, within a recommended planting density range. For example, in areas with fertile soil and suitable climate, the planting density of a certain tree species can be appropriately increased; while in areas with poor soil or unfavorable climate conditions, the planting density of that tree species needs to be reduced. Through the above analysis and calculation, the planting density of different tree species in each geographical area is determined, generating planting density planning information.

[0121] Finally, the output layer integrates the extracted tree species planting location distribution information and planting density planning information, and generates a forest community spatial configuration scheme according to the preset format specifications, presenting the planting location and planting density requirements of each tree species in the target area.

[0122] Step S140: Generate a community planting layout instruction according to the forest community spatial configuration scheme. The community planting layout instruction includes geographic coordinate markers corresponding to the planting location distribution information and planting quantity allocation rules corresponding to the planting density planning information.

[0123] Step S141: Analyze the planting location distribution information in the forest community spatial configuration scheme, and extract the relative coordinate information corresponding to each planting location. The relative coordinate information is determined based on a preset forest area benchmark.

[0124] In this embodiment, the planting location distribution information in the forest community spatial configuration scheme is first analyzed. The planting location distribution information is presented in the form of text descriptions, charts, or data tables, detailing the planting area range for each tree species. During the analysis process, it is necessary to identify the boundaries and range of each specific planting location and determine its relative position within the target area.

[0125] The preset forest area benchmark is a fixed reference point selected within the target area. The location of this benchmark is precisely measured and recorded. Relative coordinate information is the coordinate value in a Cartesian coordinate system established with this benchmark as the origin. Relative coordinates accurately represent the orientation and distance of each planting location relative to the benchmark. When extracting relative coordinate information, the X and Y coordinate values ​​of each planting location in the relative coordinate system are calculated based on the relative positional relationship between the planting location and the benchmark in the planting location distribution information. These coordinate values ​​together constitute the relative coordinate information corresponding to each planting location.

[0126] Step S142: Convert the relative coordinate information into absolute geographic coordinate information. During the conversion process, combine the geographic coordinate system parameters of the forest area to ensure that the absolute geographic coordinate information corresponds one-to-one with the actual geographic spatial location.

[0127] In this embodiment, converting relative coordinate information into absolute geographic coordinate information is a crucial step in ensuring the accuracy of planting location. This conversion process requires the use of geographic coordinate system parameters of the forest area to achieve a mapping from relative location to actual geographic spatial location.

[0128] Step S1421: Obtain the geographic coordinate system parameters of the forest area, which include coordinate system type, reference surface parameters and projection parameters.

[0129] In this embodiment, the geographic coordinate system parameters of the target forest area are first obtained through a geographic information system or relevant surveying and mapping data. The coordinate system type refers to the type of geographic coordinate system used, such as the geodetic coordinate system and the Gauss-Kruger coordinate system. Different coordinate system types have different coordinate definitions and calculation methods.

[0130] Reference surface parameters are an important component of a geographic coordinate system, including ellipsoidal parameters and geoid differential. Ellipsoidal parameters define the geometrical parameters of the ellipsoid used to simulate the shape of the Earth, such as its semi-major and semi-minor axes; geoid differential reflects the height difference between the geoid and the ellipsoid. Projection parameters involve the projection method and projection zone used to project the three-dimensional coordinates of the Earth's surface onto a two-dimensional plane. Different projection methods are suitable for different regional ranges and accuracy requirements.

[0131] Step S1422: Determine the coordinate transformation algorithm according to the coordinate system type. Different coordinate system types correspond to different coordinate transformation algorithms. The coordinate transformation algorithm is used to realize the mathematical transformation from relative coordinates to absolute geographic coordinates.

[0132] In this embodiment, after obtaining the coordinate system type, a corresponding coordinate transformation algorithm is selected based on that type. Each coordinate system type has its specific mathematical model and transformation rules, thus requiring a matching transformation algorithm. For example, if the coordinate system type is a Gaussian-Kruger coordinate system, a transformation algorithm suitable for that coordinate system is selected, involving mathematical processes such as forward or inverse calculations of Gaussian projection.

[0133] The core of coordinate transformation algorithms is establishing the mathematical relationship between relative coordinates and absolute geographic coordinates. Through a series of mathematical operations, the X and Y values ​​of relative coordinates are converted into longitude, latitude, or other coordinate forms of absolute geographic coordinates. After determining the coordinate transformation algorithm, the parameters and calculation steps need to be verified to ensure that it can correctly achieve the conversion between the two coordinate systems.

[0134] Step S1423: Input the relative coordinate information and the geographic coordinate system parameters of the forest area into the coordinate transformation algorithm to calculate the initial absolute geographic coordinate information.

[0135] In this embodiment, the extracted relative coordinate information (including X and Y coordinate values) of each planting location, along with the obtained geographic coordinate system parameters of the forest area, are organized and formatted according to the input requirements of the coordinate transformation algorithm. Then, this data is input into the coordinate transformation algorithm, which performs calculations based on preset mathematical formulas and steps.

[0136] During the calculation process, the algorithm uses ellipsoidal parameters and projection parameters in the coordinate system to transform the relative coordinates, converting them from coordinate values ​​in the relative coordinate system to coordinate values ​​in the absolute geographic coordinate system, generating initial absolute geographic coordinate information. This initial absolute geographic coordinate information is usually expressed in the form of longitude and latitude, which can initially reflect the approximate location of the planting site on the Earth's surface. After the calculation is completed, the initial absolute geographic coordinate information needs to be preliminarily checked to see if there are any obvious calculation errors or unreasonable coordinate values.

[0137] Step S1424: Perform error correction processing on the initial absolute geographic coordinate information. During the correction process, the coordinates of known geographic control points within the forest area are introduced, and the deviation between the initial absolute geographic coordinate information and the geographic control point coordinates is calculated.

[0138] In this embodiment, to improve the accuracy of absolute geographic coordinate information, error correction processing is required on the initial absolute geographic coordinate information. Geographic control points are points with precisely known coordinates selected within the target forest area. The coordinates of these points are obtained through professional surveying and mapping, and have high accuracy and reliability.

[0139] During the calibration process, multiple evenly distributed geographic control points are first selected, and their known absolute geographic coordinates are obtained. Then, the relative coordinates of these geographic control points in a relative coordinate system are input into a coordinate transformation algorithm to obtain the corresponding initial absolute geographic coordinates. The initial absolute geographic coordinates of the geographic control points calculated by the algorithm are compared with their known absolute geographic coordinates, and the difference between the two, i.e., the deviation value, is calculated. The deviation value includes longitude deviation and latitude deviation. By calculating the deviation values ​​of multiple geographic control points, systematic and random errors existing in the coordinate transformation process can be analyzed.

[0140] Step S1425: Adjust the parameters in the coordinate transformation algorithm according to the deviation value, and recalculate the corrected absolute geographic coordinate information.

[0141] In this embodiment, the relevant parameters in the coordinate transformation algorithm are adjusted based on the calculated deviation values. The distribution pattern and magnitude of the deviation values ​​are analyzed to determine the source of the error. If the deviation values ​​exhibit a certain regularity, it indicates the existence of a systematic error, and the corresponding algorithm parameters can be corrected. For example, if the longitude deviation of all geographic control points exhibits a fixed difference, the parameters related to longitude calculation in the algorithm can be adjusted to eliminate this fixed deviation.

[0142] When adjusting parameters, appropriate adjustment methods should be adopted based on the magnitude and nature of the deviation to ensure the rationality of the parameter adjustments. After the parameter adjustments are completed, the relative coordinate information of all planting locations and the adjusted coordinate system parameters are re-entered into the coordinate transformation algorithm for recalculation to obtain the corrected absolute geographic coordinate information. The corrected absolute geographic coordinate information should effectively reduce errors and more closely approximate the actual geographic spatial location.

[0143] Step S1426: Verify the accuracy of the corrected absolute geographic coordinate information. The verification method is to randomly select a portion of the corrected absolute geographic coordinate information, compare it with the geographic coordinate information measured on the ground, and calculate the comparison error.

[0144] In this embodiment, a verification operation is required to ensure the accuracy of the corrected absolute geographic coordinate information. A certain number of samples are randomly selected from all the corrected absolute geographic coordinate information. The selected samples should cover different locations in the target area and be representative.

[0145] For each selected sample, its accurate geographic coordinates are obtained through field measurements. High-precision measuring tools such as GPS devices are used for field measurements to ensure the reliability of the results. The geographic coordinates obtained from the field measurements are compared with the corrected absolute geographic coordinates, and the difference between the two is calculated; this difference is the comparison error. The comparison error also includes longitude and latitude errors. By calculating these error values, the accuracy of the corrected absolute geographic coordinates can be evaluated.

[0146] Step S1427: If the comparison error is less than the preset error threshold, the corrected absolute geographic coordinate information is determined to be valid; if the comparison error is greater than or equal to the preset error threshold, the error correction process is re-executed until the comparison error is less than the preset error threshold, so that the absolute geographic coordinate information corresponds one-to-one with the actual geographic spatial location.

[0147] In this embodiment, the calculated comparison error is compared with a preset error threshold. The preset error threshold is the maximum allowable error range set according to the planting accuracy requirements. If the comparison error is less than this threshold, it indicates that the accuracy of the corrected absolute geographic coordinate information can meet the planting requirements, and its validity is determined.

[0148] If the comparison error is greater than or equal to the preset error threshold, it indicates that the corrected coordinate information still has a large error, and the error correction process needs to be repeated. Returning to step S1424, the geographic control point coordinates are used again to calculate the deviation value. Then, the coordinate transformation algorithm parameters are adjusted based on the new deviation value, the corrected absolute geographic coordinate information is recalculated, and verification is performed again. This process is repeated until the comparison error of the randomly selected sample is less than the preset error threshold, ensuring that the final absolute geographic coordinate information accurately corresponds to the actual geographic spatial location.

[0149] Step S143: Mark the absolute geographic coordinate information, assign a unique coordinate identifier to each absolute geographic coordinate information, and generate geographic coordinate markers corresponding to the planting location distribution information.

[0150] In this embodiment, after obtaining valid absolute geographic coordinate information, it is marked. Each absolute geographic coordinate represents a specific planting location. To facilitate identification and management, a unique coordinate identifier needs to be assigned to each coordinate. The coordinate identifier can be a combination of letters and numbers, or generated according to certain coding rules to ensure that each identifier is unique within the entire target area and will not be duplicated.

[0151] When assigning coordinate markers, a correspondence table is established between absolute geographic coordinate information and coordinate markers, recording the longitude and latitude coordinate values ​​corresponding to each marker. Simultaneously, the coordinate markers are associated with the corresponding tree species information, clarifying the type of tree species planned to be planted at that coordinate location. Through the above marking process, geographic coordinate markers corresponding to the planting location distribution information are generated, thereby identifying the specific geographic coordinates and related planting information for each planting location.

[0152] Step S144: Analyze the planting density planning information in the spatial configuration scheme of the forest community, and extract the planting density parameters of different tree species in each geographical region.

[0153] In this embodiment, the planting density planning information in the spatial configuration scheme of forest communities is analyzed. The planting density planning information specifies in detail the planting density requirements for different tree species in various geographical areas, and may be presented in the form of text descriptions, tables, or charts.

[0154] During the analysis process, it is necessary to identify the scope of each geographical region and its corresponding tree species, and then extract the planting density parameter for that tree species within that geographical region. The planting density parameter is typically expressed as the number of trees planted per unit area, such as the number of trees planted per square meter. During extraction, it is crucial to ensure accurate correspondence between the tree species, geographical region, and planting density parameter to avoid confusion or incorrect extraction. After extraction, the planting density parameters are organized and stored to form structured data.

[0155] Step S145: Based on the planting density parameters and the area information of each geographical region, calculate the planting quantity of different tree species in each geographical region to obtain the planting quantity calculation result.

[0156] In this embodiment, after extracting the planting density parameter, the planting quantity is calculated by combining it with the area information of each geographical region. First, the area data of each geographical region is obtained. This area information can be obtained by dividing and measuring the target area through a geographic information system to ensure the accuracy of the area data.

[0157] For each tree species within each geographical region, the planting quantity is calculated using a multiplication operation based on its planting density parameter and the area of ​​the region. That is, the planting quantity equals the planting density parameter multiplied by the geographical region area. During the calculation, it is crucial to ensure unit consistency; the units of the planting density parameter and the area unit must match to guarantee the accuracy of the result. For example, if the planting density parameter is the number of trees per square meter and the geographical region area is in square meters, then multiplying the two will give the planting quantity of that tree species within that region. This calculation is performed for all geographical regions and their corresponding tree species to obtain the planting quantity of different tree species within each geographical region, thus forming the planting quantity calculation result.

[0158] Step S146: Based on the calculation results of the planting quantity, formulate the planting quantity allocation rules, which include the correspondence between tree species type and planting quantity and the correspondence between geographical region and planting quantity.

[0159] In this embodiment, planting quantity allocation rules are formulated based on the planting quantity calculation results. First, the planting quantity calculation results are systematically reviewed to clarify the detailed planting quantity of each tree species in different geographical regions. This step requires classifying the scattered calculation results according to a certain logic to facilitate the subsequent rule formulation.

[0160] Step S1461: Classify and statistically analyze the planting quantity calculation results, group the planting quantity according to tree species type, obtain the total planting quantity corresponding to each tree species type, and generate a first correspondence table between tree species type and total planting quantity.

[0161] In this embodiment, the planting quantity calculation results are categorized and statistically analyzed according to tree species. The planting quantity data for all geographical regions are traversed, and the planting quantities belonging to the same tree species are summed. For example, if the planting quantity of tree species A in geographical region 1 is A1, in geographical region 2 is A2, and in geographical region 3 is A3, then the total planting quantity of tree species A is A1 + A2 + A3. This summation calculation is performed for all tree species to obtain the total planting quantity corresponding to each tree species type. Then, the tree species types and their corresponding total planting quantities are presented in tabular form, generating a first correspondence table. The first correspondence table clearly shows the total planting scale of each tree species throughout the entire target area.

[0162] Step S1462: Group the planting quantity calculation results according to geographical regions to obtain the planting quantity of different tree species in each geographical region, and generate a second correspondence table between geographical regions and tree species planting quantities.

[0163] In this embodiment, the calculation results of the planting quantity are grouped according to geographical regions. Taking geographical regions as units, the planting quantities of all tree species within the region are summarized. For example, in geographical region A, there are tree species A, tree species B, and tree species C, and their planting quantities are A_A, B_A, and C_A respectively. Then, in the second corresponding relationship table, under the entry corresponding to geographical region A, it will record tree species A: A_A, tree species B: B_A, and tree species C: C_A. The above summarization process is carried out for all geographical regions, presenting the planting quantities of each geographical region and the different tree species it contains in tabular form, and generating the second corresponding relationship table. The second corresponding relationship table reflects in detail the tree species planting distribution within each geographical region and is an important basis for formulating the planting plan for geographical regions.

[0164] Step S1463: Analyze the proportion of the total planting quantity of each tree species type in the first corresponding relationship table, and determine the tree species priority order according to the proportion of the total planting quantity. The higher the proportion of the total planting quantity of a tree species type, the higher the tree species priority order.

[0165] In this embodiment, analyze the proportion of the total planting quantity of each tree species in the first corresponding relationship table. First, calculate the sum of the total planting quantities of all tree species, and then divide the total planting quantity of each tree species by the sum of the total planting quantities to obtain the proportion of the total planting quantity of this tree species. For example, if the sum of the total planting quantities of all tree species is S and the total planting quantity of tree species A is A_total, then the proportion of the total planting quantity of tree species A is A_total / S. The above calculations are carried out for all tree species to obtain their respective proportions. Sort the tree species according to the size of the proportion of the total planting quantity. The higher the proportion of a tree species, the higher its priority order in the planting plan. The above priority setting helps to ensure the planting needs of tree species with larger planting quantities first under the condition of limited planting resources, and ensure the smooth progress of the overall planting plan.

[0166] Step S1464: Analyze the planting quantity distribution of each geographical region in the second corresponding relationship table, identify the regions with intensive planting quantities and the regions with sparse planting quantities, and allocate preferential planting resources to the regions with intensive planting quantities.

[0167] In this embodiment, analyze the planting quantity distribution of each geographical region in the second corresponding relationship table. Calculate the sum of the planting quantities of all tree species within each geographical region to obtain the total planting quantity of each geographical region. By comparing the total planting quantities of different geographical regions, identify the regions with intensive planting quantities and the regions with sparse planting quantities. Regions with intensive planting quantities refer to geographical regions with larger total planting quantities, and more planting resources and efforts are required in these regions; regions with sparse planting quantities are regions with smaller total planting quantities. Allocate preferential planting resources to regions with intensive planting quantities, including preferentially deploying planting equipment, planting personnel, and tree species seedlings, etc., to improve planting efficiency and ensure that the planting tasks in these regions can be completed on time.

[0168] Step S1465: Based on the priority order of the tree species and the distribution of planting quantity in geographical areas, formulate planting order rules, which specify the order of planting different tree species in different geographical areas.

[0169] In this embodiment, a planting sequence rule is established by combining the priority order of tree species and the distribution of planting quantity in geographical areas. For densely planted areas, tree species with higher priority are planted first; within the same geographical area, planting is arranged sequentially according to the priority order of tree species. For example, if geographical area B is a densely planted area, and tree species A has a higher priority than tree species B, and tree species B has a higher priority than tree species C, then in geographical area B, tree species A is planted first, then tree species B, and finally tree species C. For sparsely planted areas, planting is also arranged according to the priority order of tree species, but the planting rhythm can be adjusted appropriately according to the actual situation. The establishment of a planting sequence rule can rationally plan the planting process, avoid chaos and disorder in planting work, and improve the efficiency of planting operations.

[0170] Step S1466: Integrate the first correspondence table, the second correspondence table, and the planting order rules to form a planting quantity allocation rule that includes the correspondence between tree species type and planting quantity, the correspondence between geographical region and planting quantity, and the planting order requirements.

[0171] In this embodiment, the first correspondence table, the second correspondence table, and the planting sequence rules are integrated. The correspondence between tree species and total planting quantity, the correspondence between geographical region and tree species planting quantity, and the planting sequence requirements for different tree species in different regions are organically combined to form a complete planting quantity allocation rule. This planting quantity allocation rule comprehensively covers the allocation of planting quantity and the arrangement of planting sequence.

[0172] Step S1467: Perform a logical verification on the planting quantity allocation rule to check if there is a mismatch between the tree species type and the planting quantity in the geographical area. If so, adjust the planting quantity or tree species type allocation in the corresponding geographical area until the logical verification passes.

[0173] In this embodiment, the planting quantity allocation rules are logically validated. The data in the first and second correspondence tables are checked one by one to see if there are any discrepancies between the planting quantity of a tree species in a certain geographical area and the total planting quantity of that tree species. For example, if the total planting quantity of a tree species is less than its planting quantity in a certain geographical area, this is obviously unreasonable. Simultaneously, the planting order rules are checked to ensure they match the planting quantity allocation, and to identify any inconsistencies between the planting order and the planting quantity of tree species. If a mismatch is found between the tree species type and the planting quantity in a geographical area, or if there is a logical contradiction in the planting order rules, the planting quantity in the corresponding geographical area is adjusted, or the tree species type is reassigned. This adjustment process is repeated until all logical validation points are passed, ensuring the rationality and accuracy of the planting quantity allocation rules.

[0174] Step S147: Integrate the geographic coordinate markers and planting quantity allocation rules, and generate community planting layout instructions according to the preset instruction format specifications.

[0175] In this embodiment, geographic coordinate markers and planting quantity allocation rules are integrated. Geographic coordinate markers clearly define the specific geographic coordinates and corresponding tree species for each planting location, while the planting quantity allocation rules specify the planting quantity and order of each tree species in different geographic regions. By linking and integrating these two pieces of information, each geographic coordinate marker can correspond to specific tree species planting quantity and order requirements. Following a preset instruction format specification, the integrated information is organized into structured instruction content. The instruction format specification includes requirements for the information arrangement order, expression method, and data format to ensure that the forest planting execution system can correctly parse and execute the instructions. The generated community planting layout instructions contain all the necessary planting information and serve as a crucial bridge connecting the forest community spatial configuration scheme and actual planting operations.

[0176] Step S150: Send the community planting layout instruction to the forest planting execution system to trigger the forest planting execution system to perform the community planting layout operation according to the geographic coordinate markers and planting quantity allocation rules.

[0177] In this embodiment, after generating the community planting layout instruction, it needs to be sent to the forest planting execution system. The sending process is carried out through a stable communication channel to ensure that the instruction can be transmitted to the execution system completely and accurately. After receiving the instruction, the forest planting execution system will determine the planting location according to the geographical coordinates in the instruction and execute the corresponding planting operations according to the planting quantity allocation rules, thereby realizing the spatial layout of the forest community.

[0178] For example, step S151: establish a communication connection with the forest planting execution system, send the community planting layout instruction to the forest planting execution system, so that after the forest planting execution system receives the community planting layout instruction, it obtains the original community planting layout instruction and parses the geographic coordinate markers and planting quantity allocation rules in the community planting layout instruction.

[0179] In this embodiment, a communication connection is first established with the forest planting execution system. Establishing this connection requires ensuring that both parties use the same communication protocol, typically employing wired or wireless communication methods such as Ethernet or wireless networks. After the connection is established and communication is confirmed to be normal, the community planting layout instruction is sent to the forest planting execution system through this communication connection. Upon receiving the instruction, the forest planting execution system receives and stores it, obtaining the original community planting layout instruction. Then, the parsing module within the execution system parses the original instruction, extracting the geographic coordinate marker information and planting quantity allocation rule information.

[0180] Step S152: Control the forest planting execution system to plan the planting path according to the parsed geographic coordinates, and avoid obstacle areas in the forest area during the planting path planning process.

[0181] In this embodiment, after parsing the geographic coordinates, the forest planting execution system begins planning the planting path. The planning of the planting path needs to comprehensively consider the distribution of all planting locations to achieve efficient planting operations.

[0182] Step S1521: Control the forest planting execution system to extract the geographic coordinate markers in the community planting layout instructions, import all geographic coordinate markers into the path planning module, and form a set of planting location coordinates.

[0183] In this embodiment, the forest planting execution system extracts all geographic coordinate markers from the parsed community planting layout instructions. Each geographic coordinate marker contains specific longitude and latitude information, as well as corresponding tree species information. The coordinate information from these geographic coordinate markers is extracted and imported into the path planning module of the execution system. The path planning module integrates this coordinate information to form a coordinate set containing all planting locations, i.e., the planting location coordinate set.

[0184] Step S1522: Use the path planning module to obtain obstacle distribution information in the forest area. The obstacle distribution information includes the location coordinates of the obstacles, the size of the obstacles, and the type of obstacles.

[0185] In this embodiment, the path planning module acquires obstacle distribution information in the forest area through a pre-set database or real-time detection. Obstacles include objects such as rocks, water bodies, existing buildings, and large trees that may affect the passage of planting equipment and planting operations. The obstacle distribution information records the location coordinates of each obstacle in detail, which determines its specific location within the forest area. The obstacle's size and coverage area are described, such as length, width, and height. The obstacle type information indicates the nature of the obstacle, such as rocks or water bodies. This information is crucial for planning planting paths that avoid obstacles, and the path planning module needs to design reasonable paths based on this information.

[0186] Step S1523: For each geographic coordinate marker in the set of planting location coordinates, calculate the distance between it and each obstacle, determine the safe zone range around each geographic coordinate marker, and there are no obstacles distributed within the safe zone range.

[0187] In this embodiment, the path planning module processes each geographic coordinate marker in the planting location coordinate set. It calculates the straight-line distance between each geographic coordinate marker and all obstacles within the forest area, setting different safety distance thresholds based on the type and size of the obstacles. For example, the safety distance threshold may be larger for large rock obstacles and smaller for small shrub obstacles. The area surrounding each geographic coordinate marker with a distance greater than the safety distance threshold is defined as a safe zone, ensuring that no obstacles are distributed within this safe zone, providing a safe operating space for the planting equipment to reach the planting location.

[0188] Step S1524: Based on the set of planting location coordinates and the obstacle distribution information of the forest area, construct the constraints for path planning. The constraints include the movement range constraint, movement speed constraint, and turning angle constraint of the planting equipment.

[0189] In this embodiment, path planning constraints are constructed based on the set of planting location coordinates and obstacle distribution information. The movement range constraint stipulates that the planting equipment can only move within the passable area of ​​the forest region, cannot exceed the boundary of the target forest region, and must avoid areas containing obstacles. The movement speed constraint is set according to the terrain conditions of the forest region and the performance of the planting equipment. In areas with complex terrain or many obstacles, the movement speed constraint value is lower; in flat, open areas, the movement speed constraint value can be appropriately increased. The turning angle constraint considers the mechanical performance of the planting equipment, setting the maximum turning angle that the equipment can achieve, avoiding the planning of turning paths that the equipment cannot complete. These constraints work together to ensure that the planned planting path is within the actual operational capabilities of the equipment.

[0190] Step S1525: Call the path planning algorithm to perform preliminary planning of the planting path. The path planning algorithm is based on the shortest path principle, connects all planting location coordinate markers, and generates a preliminary planting path.

[0191] In this embodiment, the path planning module calls a path planning algorithm to perform preliminary planting path planning. The path planning algorithm adopts the principle of shortest path, such as Dijkstra's algorithm or A* algorithm. These algorithms can find the shortest path connecting all nodes given a set of nodes (i.e., the set of planting location coordinates) and constraints. The algorithm first treats each planting location coordinate as a node, then calculates the distance between nodes, and connects each node sequentially according to the shortest path principle to form a preliminary planting path that covers all planting locations. The generation of the preliminary planting path aims to complete the traversal of all planting locations with the shortest distance, improving planting efficiency.

[0192] Step S1526: Check whether the preliminary planting path meets the constraints. If the preliminary planting path passes through an obstacle area or exceeds the movement range of the planting equipment, the preliminary planting path is adjusted by replanning the path segment to bypass the obstacle area.

[0193] In this embodiment, the initial planting path undergoes a constraint check. Each segment of the initial planting path is examined to determine whether it passes through obstacle areas, exceeds the movement range of the planting equipment, and whether the turning angles meet the constraint requirements. If the initial planting path is found to pass through obstacle areas, exceed the movement range, or have incorrect turning angles, the path needs to be adjusted. During adjustment, for path segments that do not meet the constraints, new path segments that bypass obstacle areas or remain within the movement range are replanned to ensure that the adjusted path segments meet all constraints.

[0194] Step S1527: Smooth the adjusted planting path, calculate the total length and estimated travel time of the smoothed planting path, and compare them with the preset path length threshold and time threshold. If the total length exceeds the path length threshold or the estimated travel time exceeds the time threshold, the path planning step is re-executed to optimize the path node sequence. Otherwise, the planting path is determined as the final planting path so that the forest planting execution system can control the movement of the planting equipment according to the final planting path.

[0195] In this embodiment, the adjusted planting path is smoothed. The purpose of smoothing is to eliminate sharp bends and abrupt changes in the path, enabling the planting equipment to move more smoothly and reducing equipment wear and operational difficulty. Smoothing can be achieved through methods such as curve fitting, converting a polygonal path into a smooth curved path. After processing, the total length of the smoothed planting path is calculated, and the estimated travel time is calculated based on the moving speed constraint of the planting equipment. The total length is compared with a preset path length threshold, and the estimated travel time is compared with a preset time threshold. If the total length exceeds the path length threshold, or the estimated travel time exceeds the time threshold, it indicates that the current path still has room for optimization. The path planning steps need to be re-executed, the connection order of the planting position coordinates needs to be adjusted, the path node order needs to be optimized, and a preliminary planting path needs to be generated again for subsequent checks and adjustments. If the total length and the estimated travel time are both within the corresponding threshold range, the planting path is determined as the final planting path, and the forest planting execution system will control the movement of the planting equipment according to the final planting path.

[0196] Step S153: Control the forest planting execution system to allocate corresponding tree seedlings to each planting location according to the parsed planting quantity allocation rules.

[0197] In this embodiment, the forest planting execution system allocates corresponding tree seedlings to each planting location according to the parsed planting quantity allocation rules. The system first identifies the tree species type corresponding to each geographic coordinate marker, and then ensures that each planting location receives the correct seedlings based on the planting quantity allocation rules for that tree species in the corresponding geographic area. During the allocation process, the system verifies that the number of seedlings matches the planting quantity requirements to avoid shortages or surpluses. Simultaneously, according to the planting sequence rules, the corresponding batches of seedlings are prepared in advance to ensure that the planting equipment can promptly acquire the required seedlings for planting when it arrives at the planting location.

[0198] Step S154: Control the forest planting execution system to control the planting equipment to move to each planting location according to the planned planting path, execute the planting operation according to the planting quantity allocation rule, record the actual planting situation of each planting location during the planting operation, and generate a planting operation record.

[0199] In this embodiment, the forest planting execution system controls the planting equipment to start and move according to the final planned planting path. During movement, the planting equipment obtains its own location information in real time through a positioning system, ensuring accurate arrival at the coordinates of each planting location. Upon arrival at the planting location, the planting equipment performs planting operations according to the allocated tree species and planting quantity rules, such as digging holes, placing seedlings, and filling soil. During the planting operation, the execution system records the actual planting situation at each planting location in real time, including the type of tree species planted, the actual number planted, the planting time, and the status of the planting equipment, and then generates a planting operation record.

[0200] Step S155: After the planting operation is completed, obtain the planting operation record uploaded by the forest planting execution system and store the planting operation record.

[0201] Figure 2 The diagram illustrates the hardware structure of an AI-model-optimized forest community spatial construction system 100 for implementing the above-described AI-model-optimized forest community spatial construction method, as provided in an embodiment of the present invention. Figure 2 As shown, the forest community spatial construction system 100 optimized using an AI model may include a processor 110, a machine-readable storage medium 120, a bus 130, and a communication unit 140.

[0202] In the specific implementation process, one or more processors 110 execute computer-executable instructions stored in machine-readable storage medium 120, so that processor 110 can execute the forest community spatial construction method optimized by AI model as described in the above method embodiment. Processor 110, machine-readable storage medium 120 and communication unit 140 are connected through bus 130. Processor 110 can be used to control the sending and receiving actions of communication unit 140.

[0203] The specific implementation process of processor 110 can be found in the various method embodiments executed by the forest community spatial construction system 100 optimized by the AI ​​model described above. The implementation principle and technical effect are similar, and will not be repeated here.

[0204] It should be noted that, in order to simplify the description of this invention and thus aid in the understanding of one or more embodiments, the foregoing description of the embodiments of this invention sometimes combines multiple features into a single embodiment, drawing, or description thereof. Similarly, it should be noted that, in order to simplify the description of this invention and thus aid in the understanding of one or more embodiments, the foregoing description of the embodiments of this invention sometimes combines multiple features into a single embodiment, drawing, or description thereof.

Claims

1. A forest community space construction method optimized using an AI model, characterized by, The method comprises: acquiring a forest basic environment data set containing topographic feature information, soil property information, and climate condition information; performing community adaptability analysis processing on the forest basic environment data set to obtain community adaptability evaluation results of different tree species; calling a pre-trained community space optimization model to perform spatial configuration calculation processing on the community adaptability evaluation results to obtain a forest community space configuration scheme, the forest community space configuration scheme containing tree species planting location distribution information and planting density planning information; generating community planting layout instructions according to the forest community space configuration scheme, the community planting layout instructions containing geographical coordinate markers corresponding to the planting location distribution information and planting quantity allocation rules corresponding to the planting density planning information; sending the community planting layout instructions to a forest planting execution system to trigger the forest planting execution system to perform community planting layout operations according to the geographical coordinate markers and the planting quantity allocation rules; The forest community space configuration scheme comprises: analyzing the planting location distribution information in the forest community space configuration scheme to extract relative coordinate information corresponding to each planting location, the relative coordinate information being determined based on a pre-set forest area reference point; convert the relative coordinate information into absolute geographical coordinate information, and combine the geographical coordinate system parameters of the forest area in the conversion process to make the absolute geographical coordinate information correspond one-to-one to the actual geographical space position; performing marking processing on the absolute geographical coordinate information, assigning a unique coordinate identifier to each absolute geographical coordinate information, and generating geographical coordinate markers corresponding to the planting location distribution information; analyzing the planting density planning information in the forest community space configuration scheme to extract planting density parameters of different tree species in each geographical area; calculate the planting quantity of different tree species in each geographical area according to the planting density parameters and the area information of each geographical area to obtain planting quantity calculation results; formulate planting quantity allocation rules based on the planting quantity calculation results, the planting quantity allocation rules containing the corresponding relationship between tree species types and planting quantities and the corresponding relationship between geographical areas and planting quantities; fuse the geographical coordinate markers and the planting quantity allocation rules to generate community planting layout instructions according to a pre-set instruction format specification. 2.The forest community space construction method using an AI model optimization according to claim 1, characterized in that, The forest community space configuration scheme comprises: performing topographic type classification processing on the topographic feature information in the forest basic environment data set to identify the slope distribution, elevation change, and slope direction distribution in the topographic feature information to obtain a topographic classification result; calculate the growth suitability parameters of different tree species in each topographic area based on the topographic classification result; performing component analysis processing on the soil property information in the forest basic environment data set to extract the organic matter content, pH value, and nutrient element content in the soil property information to obtain a soil component analysis result; According to the soil composition analysis result, determine the demand matching degree parameter of different tree species to the soil condition; Perform time period statistical processing on the climate condition information in the forest basic environment data set, obtain the temperature variation range, precipitation distribution and illumination duration distribution in the climate condition information, and obtain climate statistical results; Combine the climate statistical results to calculate the adaptability parameter of different tree species to the climate condition; After standardization conversion of the growth suitability parameter, the demand matching degree parameter and the adaptability parameter, generate the community adaptability evaluation result of different tree species through weighted splicing calculation, and the weight of the weighted splicing calculation is set based on the priority of the key influence factors of tree growth. 3.The forest community space construction method using an AI model optimization according to claim 1, characterized in that, The pre-trained community space optimization model is called to perform spatial configuration calculation processing on the community adaptability evaluation result, and a forest community space configuration scheme is obtained, including: The community adaptability evaluation result is input into the feature input layer of the community space optimization model, the feature input layer performs dimension regularization processing on the community adaptability evaluation result, so that the feature dimension of the community adaptability evaluation result is consistent with the preset input dimension of the community space optimization model, and a regularized adaptability feature is obtained; The regularized adaptability feature is input into the space correlation layer of the community space optimization model, the space correlation layer analyzes the mutual influence relationship between the regularized adaptability features of different tree species, identifies tree species combinations with symbiotic promotion effect and tree species combinations with competitive inhibition effect, and obtains a tree species correlation analysis result; Based on the tree species correlation analysis result, the configuration generation layer of the community space optimization model constructs an initial space configuration matrix, each matrix element in the initial space configuration matrix corresponds to a tree species distribution identifier of a geographic region; The optimization adjustment layer of the community space optimization model is called to perform iterative optimization processing on the initial space configuration matrix, and in each iteration process, the tree species distribution identifier of the matrix element is adjusted according to the tree species adaptability difference between adjacent geographic regions, until the iteration result meets the preset space configuration uniformity index; After the iterative optimization processing is completed, the output layer of the community space optimization model performs analysis processing on the optimized space configuration matrix, extracts the tree species planting position distribution information and planting density planning information corresponding to each geographic region, and obtains a forest community space configuration scheme. 4.The forest community space construction method using an AI model optimization according to claim 3, characterized in that, The regularized adaptability feature is input into the space correlation layer of the community space optimization model, the space correlation layer analyzes the mutual influence relationship between the regularized adaptability features of different tree species, identifies tree species combinations with symbiotic promotion effect and tree species combinations with competitive inhibition effect, and obtains a tree species correlation analysis result, including: In the space correlation layer of the community space optimization model, key influence factors in the regularized adaptability features of different tree species are extracted, including terrain adaptation factors, soil demand factors and climate adaptation factors; The similarity coefficient between the key influence factors of any two tree species is calculated; According to the similarity coefficient, a similarity level is divided, when the similarity coefficient is in a preset high similarity interval, it is determined that the two corresponding tree species are in a potential competitive relationship, and when the similarity coefficient is in a preset low similarity interval, it is determined that the two corresponding tree species are in a potential symbiotic relationship; For the tree species combination in the potential symbiotic relationship, further analysis is made on the resource complementation in the growth process, including water utilization complementation, nutrient absorption complementation and light utilization complementation, and a symbiotic promotion coefficient is calculated; For the tree species combination in the potential competitive relationship, analysis is made on the resource competition in the growth process, including soil nutrient competition, light resource competition and growth space competition, and a competitive inhibition coefficient is calculated; Based on the symbiotic promotion coefficient and the competitive inhibition coefficient, all tree species combinations are classified and marked to generate a tree species correlation analysis result including a symbiotic promotion tree species combination list and a competitive inhibition tree species combination list. 5.The forest community space construction method using an AI model optimization according to claim 3, characterized in that, The optimization adjustment layer calling the community space optimization model performs iterative optimization processing on the initial space configuration matrix, and in each iteration process, the tree species allocation identifier of the matrix element is adjusted according to the difference in tree species adaptability of adjacent geographical areas until the iteration result meets a preset space configuration uniformity index, including: In the first iteration, the difference between the community adaptability evaluation result of the tree species corresponding to each matrix element in the initial space configuration matrix and the community adaptability evaluation result of the tree species corresponding to the adjacent matrix element is calculated to obtain a set of adaptability difference values; A difference overrun area is determined according to the set of adaptability difference values, and the difference overrun area is a geographical area corresponding to adjacent matrix elements whose adaptability difference values exceed a preset difference threshold; For the matrix elements in the difference overrun area, the tree species allocation identifier is re-allocated, and in the re-allocation process, a tree species having a symbiotic promotion relationship with the tree species corresponding to the adjacent matrix element is preferentially selected, and the community adaptability evaluation result of the re-allocated tree species meets a preset adaptability requirement; After the re-allocation is completed, a new space configuration matrix is generated, and a space configuration uniformity index of the new space configuration matrix is calculated, and the space configuration uniformity index is obtained by calculating the average value of the adaptability difference values of all adjacent matrix elements; It is judged whether the space configuration uniformity index meets a preset uniformity standard, if not, the new space configuration matrix is taken as the initial matrix of the current iteration, and the steps of calculating the set of adaptability difference values, determining the difference overrun area, re-allocating the tree species allocation identifier and calculating the space configuration uniformity index are repeatedly executed; If the preset uniformity standard is met, the iteration process is stopped, and the current space configuration matrix is taken as the optimized space configuration matrix. 6.The forest community space construction method using an AI model optimization of claim 1, wherein, The conversion of the relative coordinate information into absolute geographical coordinate information includes: Obtaining geographical coordinate system parameters of the forest area, the geographical coordinate system parameters including coordinate system type, reference surface parameters and projection parameters; According to the coordinate system type, a coordinate conversion algorithm is determined, different coordinate system types correspond to different coordinate conversion algorithms, and the coordinate conversion algorithm is used to realize mathematical conversion of relative coordinates to absolute geographical coordinates; Inputting the relative coordinate information and the geographic coordinate system parameters of the forest area into the coordinate conversion algorithm to obtain initial absolute geographic coordinate information; Performing error correction processing on the initial absolute geographic coordinate information, introducing known geographic control point coordinates in the forest area in the correction process, and calculating the deviation value of the initial absolute geographic coordinate information and the geographic control point coordinates; Adjusting the parameters in the coordinate conversion algorithm according to the deviation value to re-calculate the corrected absolute geographic coordinate information; Verifying the accuracy of the corrected absolute geographic coordinate information, and the verification method is to randomly select part of the corrected absolute geographic coordinate information, compare it with the geographic coordinate information measured in the field, and calculate the comparison error; If the comparison error is less than the preset error threshold, it is determined that the corrected absolute geographic coordinate information is valid; if the comparison error is greater than or equal to the preset error threshold, the error correction processing step is re-executed until the comparison error is less than the preset error threshold, so that the absolute geographic coordinate information corresponds to the actual geographic space position one by one. 7.The forest community space construction method using an AI model optimization of claim 1, wherein, The planting quantity allocation rule is formulated based on the planting quantity calculation result, including: Classifying and counting the planting quantity calculation result, grouping the planting quantity according to tree species types, obtaining the total planting quantity corresponding to each tree species type, and generating a first correspondence table of tree species types and total planting quantities; Grouping the planting quantity calculation result according to geographic areas to obtain the planting quantity of different tree species types in each geographic area, and generating a second correspondence table of geographic areas and tree species planting quantities; Analyzing the total planting quantity proportion of each tree species type in the first correspondence table, determining the tree species priority order according to the total planting quantity proportion, and the tree species type with higher total planting quantity proportion has higher tree species priority order; Analyzing the planting quantity distribution of each geographic area in the second correspondence table, identifying the planting quantity intensive area and the planting quantity sparse area, and allocating priority planting resources to the planting quantity intensive area; Formulate a planting order rule based on the tree species priority order and the geographic area planting quantity distribution, which specifies the planting order of different tree species types in different geographic areas; Integrate the first correspondence table, the second correspondence table and the planting order rule to form a planting quantity allocation rule containing the correspondence between tree species types and planting quantities, the correspondence between geographic areas and planting quantities, and the planting order requirement; Logically verify the planting quantity allocation rule to check whether there is a mismatch between the planting quantity of the tree species type and the geographic area, and if there is, adjust the planting quantity of the corresponding geographic area or the tree species type allocation until the logical verification passes. 8.The forest community space construction method using an AI model optimization of claim 1, wherein, The community planting layout instruction is sent to the forest planting execution system to trigger the forest planting execution system to perform community planting layout operation according to the geographic coordinate marking and planting quantity allocation rule, including: A communication connection is established with the forest planting execution system, and the community planting layout instruction is sent to the forest planting execution system, so that the forest planting execution system receives the original community planting layout instruction and analyzes the geographic coordinate markers and the planting quantity allocation rules in the community planting layout instruction after receiving the community planting layout instruction; The forest planting execution system is controlled to plan a planting path according to the analyzed geographic coordinate markers, and obstacles in the forest area are avoided during the planting path planning process; The forest planting execution system is controlled to allocate corresponding tree seedlings to each planting position according to the analyzed planting quantity allocation rules; The forest planting execution system is controlled to control the planting device to move to each planting position according to the planned planting path, to perform a planting operation according to the planting quantity allocation rules, and to record the actual planting situation of each planting position during the planting operation process, and to generate a planting operation record; After the planting operation is completed, the planting operation record uploaded by the forest planting execution system is obtained, and the planting operation record is stored. 9.A forest community space construction system optimized using an AI model, characterized by, A processor and a memory are included, the memory is connected with the processor, the memory is used to store programs, instructions or codes, and the processor is used to run the programs, instructions or codes in the memory to realize the forest community space construction method optimized by the AI model in any one of claims 1-8.

Images