Intelligent species configuration and spatial layout optimization method and system for landscaping

Abstract

The invention relates to the technical field of intelligent configuration of garden ecology, and particularly discloses an intelligent species configuration and spatial layout optimization method and system for landscaping, and the method comprises the steps: constructing a soil sensor node network, and collecting soil state data in real time; determining a species suitability score; performing illumination adaptability adjustment by combining an illumination shadow evolution curve acquired by the unmanned aerial vehicle; and outputting a spatial layout optimization result through a multi-constraint graph optimization algorithm. In the prior art, configuration depending on static experience lacks real-time environment response capability, and especially under the condition of a complex ecological industrial park with strong soil heterogeneity and dynamic change of illumination distribution, scientific configuration of species and intelligent cooperation of space are difficult to realize. The intelligent control method fusing multi-modal perception, semantic model construction and a graph optimization mechanism is introduced, so that the dynamic adaptation of species configuration and the multi-objective optimization of spatial layout are realized, and the ecological stability of the park greening system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent configuration of garden ecology, and in particular to a method and system for optimizing intelligent species configuration and spatial layout for garden greening. Background Art

[0002] At present, the landscaping planning and plant configuration in eco-industrial parks still rely mainly on manual experience and traditional map annotation methods for deployment, usually based on simple classification and manual matching of regional soil types, sunshine conditions or historical vegetation data. This traditional method has many technical deficiencies. For example, existing technologies lack the means to dynamically obtain soil physical and chemical properties and high-resolution spatial modeling. This is especially difficult to achieve accurate plant configuration matching in areas where key growth parameters such as pH, moisture content, organic matter content and salinity change frequently. At the same time, due to the characteristics of eco-industrial parks such as residual pollution risks, variable regional microtopography, and significant soil structural heterogeneity after land reclamation, the traditional method of selecting plants by "zoning categories" often leads to low plant survival rates, poor growth conditions, and even frequent rework and maintenance in practice.

[0003] In addition, existing plant configuration technologies often lack a quantitative "plant-soil-light" coupling analysis mechanism. In practical applications, plants have significant heterogeneity in their responses to micro-light environments, especially in industrial parks where tall buildings or large-scale structures block the view. Spatial and temporal characteristics such as sunshine duration, peak illumination, and shadow duration cannot be effectively modeled and matched to the physiological needs of plants, resulting in a disconnect between plant configuration and the real environment, and even light stress, affecting the greening effect. Although some current studies based on remote sensing or satellite images attempt to obtain light distribution information, they have problems such as insufficient accuracy, large spatial delay, and difficulty in depicting local dynamic shadow evolution, and cannot meet the needs of sub-meter-level park greening design.

[0004] Furthermore, when optimizing the spatial layout of species after configuration, existing methods generally employ regular planting patterns or placement methods based on horticultural aesthetics. These methods fail to systematically incorporate multi-objective optimization factors, such as spatial resource constraints (e.g., road accessibility, water network accessibility, and operational and maintenance accessibility), interspecies ecological complementarity, and pest and disease control and isolation strategies, for systematic reasoning. Furthermore, traditional algorithms struggle to balance "local optimality" with "global spatial layout efficiency" and lack mathematical models that balance plant growth suitability with environmental load capacity. This results in low green space utilization efficiency and poor overall ecological performance. Therefore, there is an urgent need for an intelligent landscaping approach that integrates real-time soil multi-factor monitoring, light time series modeling, and plant adaptive learning mechanisms to optimize configuration decisions under multiple constraints. This approach can enhance the scientific nature, stability, and ecological restoration capabilities of greening projects in eco-industrial parks. Summary of the Invention

[0005] In response to the above-mentioned technical deficiencies, the purpose of the present invention is to propose an intelligent species configuration and spatial layout optimization method for landscaping, aiming to solve the technical problem that the existing technology relies on static experience configuration and lacks real-time environmental response capabilities, especially in complex ecological industrial park conditions with strong soil heterogeneity and dynamic changes in light distribution, making it difficult to achieve scientific species configuration and spatial intelligent coordination.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions: The present invention provides a method for optimizing intelligent species configuration and spatial layout for landscaping.

[0007] The method for optimizing intelligent species configuration and spatial layout for landscaping includes:

[0008] Step S10: Deploy a soil sensor node network within the eco-industrial park according to a preset grid strategy, collect soil status data in real time within a sampling period T through the soil sensor node network, and upload the soil status data to a preset central database; wherein the soil status data includes soil pH data, water content data, organic matter content data, and salinity data;

[0009] Step S20: Grid coordinate processing, adaptive interpolation processing and dynamic weighted fusion processing are performed based on the soil state data, and the output is at position Multidimensional soil suitability index ; Where x represents the horizontal coordinate and y represents the vertical coordinate;

[0010] Step S30: Obtain species soil tolerance model data from the preset plant species database, based on the multidimensional soil suitability index and species soil tolerance model data to identify plant species In position Species suitability score ;

[0011] Step S40: Use the drone to cruise during a preset typical day period to collect shadow distribution images of the park and generate location Light and shadow evolution curve , combined with species suitability scores Perform light matching analysis and output optimized species suitability scores adjusted for light adaptability;

[0012] Step S50: performing spatial layout optimization based on the optimized species suitability scores combined with a graph optimization algorithm based on multiple constraints.

[0013] Preferably, in step S10, the step of deploying a soil sensor node network in the eco-industrial park according to a preset grid strategy specifically includes: obtaining park geographic information within the eco-industrial park, and dividing the green area based on the park geographic information into multiple regular grid units; deploying soil sensor nodes at the center positions of the multiple regular grid units; the soil sensor nodes are used to monitor soil status data, and the soil status data includes soil pH data, water content data, organic matter content data, and salinity data; the soil sensor nodes include a pH sensor for monitoring soil pH, a soil moisture sensor for monitoring soil moisture content, an organic matter sensor for monitoring soil organic matter content, and a conductivity sensor for monitoring soil salinity; wherein the pH sensor and the soil moisture sensor are installed at a depth of 20 cm underground; and the organic matter sensor and the conductivity sensor are installed at a depth of 10 cm underground; each sensor node collects corresponding parameter values ​​at a sampling period T and packages them into data packets with timestamps and coordinate information, and the data packets are sent to a preset central database via a preset wireless communication module.

[0014] Preferably, in step S10, the step of obtaining the park geographic information within the eco-industrial park and dividing the green area in the park geographic information into a plurality of regular grid units specifically includes:

[0015] When the shape of the green area in the park's geographic information is a regular rectangle or square, an equidistant regular grid division mechanism is used to evenly divide the green area into multiple regular grid units with the same side length;

[0016] When the shape of the green area in the park's geographic information is an irregular polygon, a regional partitioning mechanism based on Voronoi subdivision is adopted. The center position of the soil sensor node is used as the generator of the Voronoi subdivision regional partitioning mechanism. The green area is automatically divided into multiple polygonal sub-areas as regular grid units. The area of ​​each polygonal sub-area is similar and the geometric distance between the boundary and the center position of the adjacent soil sensor node is equivalent.

[0017] When the shape of the green area in the park geographic information is strip-shaped or long and narrow, a strip division mechanism based on adaptive aspect ratio adjustment is adopted to divide the green area into multiple strip units along the long side direction, and further divide the interior of the strip unit into approximately rectangular small grids as regular grid units.

[0018] Preferably, in step S20, the step of performing grid coordinate processing, adaptive interpolation processing, and dynamic weighted fusion processing based on the soil state data to output a multidimensional soil suitability index specifically includes:

[0019] A two-dimensional rectangular coordinate system is established based on the deployed soil sensor node network. The adaptive interpolation mechanism based on dynamic quantile normalization is used to normalize the multidimensional data of the soil state data to obtain the pH sub-suitability at the position with the horizontal coordinate x and the vertical coordinate y. , water quantum suitability , organic proton suitability and salinity and alkalinity suitability ;

[0020] The pH suitability was evaluated based on the sensitive factor weight mechanism. , water quantum suitability , organic proton suitability and salinity and alkalinity suitability Perform dynamic weighted fusion processing to output a multidimensional soil suitability index .

[0021] Preferably, in step S20, the soil state data is subjected to multidimensional data normalization processing using an adaptive interpolation mechanism based on dynamic quantile normalization to obtain the pH sub-suitability at the position where the horizontal coordinate is x and the vertical coordinate is y. , water quantum suitability , organic proton suitability and salinity and alkalinity suitability The steps include:

[0022] Data distribution acquisition: For soil state data including soil pH value data, water content data, organic matter content data and salinity data, calculate the corresponding empirical distribution function and extract the upper quantile of the soil state data of the corresponding empirical distribution function The quantiles of soil status data ;

[0023] Outlier truncation correction: When the soil state data is higher than the upper quantile of the soil state data Or below the lower quantile of soil status data When The quantiles of soil status data , output optimized soil state data;

[0024] Quantile normalization: The optimized soil state data is mapped to the interval [0,1] to obtain the sub-suitability of each parameter. The sub-suitability of each parameter includes the pH sub-suitability at the position with the horizontal coordinate x and the vertical coordinate y. , water quantum suitability , organic proton suitability and salinity and alkalinity suitability .

[0025] Preferably, step S20 also includes: for missing coordinate points where no sensors are deployed, an adaptive spatial estimation mechanism based on Kriging interpolation is used to calculate the correlation and spatial semi-variance of soil state data collected by neighboring sensor nodes, and the sub-suitability of each parameter of the missing coordinate point is estimated based on the correlation and spatial semi-variance of soil state data collected by neighboring sensor nodes to ensure that each coordinate point in the two-dimensional rectangular coordinate system has complete four sub-suitability indicators.

[0026] Preferably, in step S30, the species soil tolerance model data is obtained from the preset plant species database, and the multidimensional soil suitability index is used to determine the soil suitability model data. and species soil tolerance model data to identify plant species In position Species suitability score The steps include:

[0027] Obtain species soil tolerance model data from the preset plant species database. The species soil tolerance model data includes: target growth parameter data, pH value suitable interval parameter data, organic matter requirement level parameter data, moisture content tolerance interval parameter data, and salinity sensitivity parameter data for the species; construct the corresponding soil tolerance semantic vector based on the species soil tolerance model data. ; Based on the multidimensional soil suitability index Construct the corresponding soil suitability semantic vector ;

[0028] The support vector machine (SVM) algorithm is introduced to calculate the soil tolerance semantic vector and soil suitability semantic vector The concatenation vector As model input, a plant species suitability evaluation model was constructed;

[0029] Plant species suitability evaluation model outputs plant species In position Species suitability score ;

[0030] Among them, the plant species suitability evaluation model outputs plant species In position Species suitability score The steps include model training phase and model application phase;

[0031] The plant species suitability evaluation model in the model training stage specifically includes: obtaining the j-th historical multidimensional soil suitability index sample , Historical species soil tolerance model samples and corresponding plant species growth suitability experimental data , construct training sample pairs ,Will As input, As the output, the species suitability evaluation model is trained by the support vector regression training method combining the minimum structural risk criterion with the kernel function mapping mechanism, and the converged suitability evaluation function model is obtained;

[0032] During the application phase of the plant species suitability evaluation model, the target location Corresponding plant species of and The concatenated vector As the model input, it is input into the converged suitability evaluation function model to obtain the species suitability score Output.

[0033] Preferably, in step S40, a drone is used to cruise and collect shadow distribution images of the park during a preset typical day period to generate a location Light and shadow evolution curve , combined with species suitability scores The steps for performing a light matching analysis and outputting optimized species suitability scores adjusted for light adaptability include:

[0034] Use drones to cruise during a preset typical day to collect shadow distribution images of the park and generate location Light and shadow evolution curve ;

[0035] Based on the light shadow evolution curve Determine the duration of light overlap, the number of consecutive sunlight periods, and the frequency of sunlight interruptions; construct a light adaptability adjustment coefficient based on the duration of light overlap, the number of consecutive sunlight periods, and the frequency of sunlight interruptions;

[0036] Species suitability scores based on light adaptation adjustment coefficients Correction is performed and the optimized species suitability score adjusted for light adaptability is output.

[0037] Preferably, in step S50, the multiple constraints include:

[0038] Position unique configuration constraint: At each position Only one plant species is allowed to be configured to prevent multiple plant species from being configured at the same coordinate point;

[0039] Species ratio control constraint: The proportion of each plant species in the entire park shall not exceed the preset upper limit ratio value, which is used to control the overall balance of species distribution;

[0040] Ecological connectivity constraint: The plant species arranged between adjacent locations must be associated or consistent to enhance the ecological stability of the plant community structure.

[0041] The present invention also provides an intelligent species configuration and space layout optimization system for landscaping, including:

[0042] The soil monitoring and collection module is used to deploy a soil sensor node network within the eco-industrial park according to a preset grid strategy. The soil sensor node network collects soil status data in real time within a sampling period T and uploads the soil status data to a preset central database. The soil status data includes soil pH data, water content data, organic matter content data, and salinity data.

[0043] Soil suitability analysis module is used to perform grid coordinate processing, adaptive interpolation processing and dynamic weighted fusion processing based on soil state data, and output at location Multidimensional soil suitability index ; Where x represents the horizontal coordinate and y represents the vertical coordinate;

[0044] The species suitability assessment module is used to obtain species soil tolerance model data from the preset plant species database based on the multidimensional soil suitability index and species soil tolerance model data to identify plant species In position Species suitability score ;

[0045] The illumination adaptability correction module is used to use the drone to cruise during the preset typical day time to collect the shadow distribution image of the park and generate the location Light and shadow evolution curve , combined with species suitability scores Perform light matching analysis and output optimized species suitability scores adjusted for light adaptability;

[0046] The spatial layout optimization module is used to perform spatial layout optimization based on optimizing species suitability scores combined with a graph optimization algorithm based on multiple constraints.

[0047] The present invention also provides an intelligent species configuration and spatial layout optimization device for landscaping, comprising: a memory, a processor, and an intelligent species configuration and spatial layout optimization program for landscaping stored on the memory and runnable on the processor. When the intelligent species configuration and spatial layout optimization program for landscaping is executed by the processor, an intelligent species configuration and spatial layout optimization method for landscaping is implemented.

[0048] The present invention also provides a computer program product, including an intelligent species configuration and spatial layout optimization program for landscaping. When the intelligent species configuration and spatial layout optimization program for landscaping is executed by a processor, the intelligent species configuration and spatial layout optimization method for landscaping is implemented.

[0049] The beneficial effects of the present invention are as follows: by constructing a soil sensor network and combining adaptive interpolation with a support vector machine model, the present invention achieves precise matching of multidimensional soil properties with plant species suitability, thereby improving the scientific nature and practical adaptability of species configuration.

[0050] The present invention introduces light and shadow evolution analysis and multi-constraint graph optimization mechanism, which effectively solves the problem of traditional landscaping schemes being difficult to dynamically adapt to lighting conditions and space limitations, and improves the overall stability and space utilization efficiency of the ecological park greening system. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 This is a flow chart of a first embodiment of a method for optimizing intelligent species configuration and spatial layout for landscaping according to the present invention.

[0053] Figure 2 This is a schematic diagram of the RMSE reduction rate distribution of traditional interpolation and dynamic weighted fusion of an intelligent species configuration and spatial layout optimization method for landscaping in the present invention.

[0054] Figure 3 A schematic diagram comparing the water content prediction accuracy of an intelligent species configuration and spatial layout optimization method for landscaping according to the present invention.

[0055] Figure 4 This is a schematic diagram of a multi-dimensional soil suitability heat map of an eco-industrial park according to the present invention, which uses an intelligent species configuration and spatial layout optimization method for landscaping.

[0056] Figure 5 This is a schematic diagram of the illumination and shadow evolution curves of typical locations of the intelligent species configuration and spatial layout optimization method for landscaping according to the present invention.

[0057] Figure 6 This is a schematic diagram comparing the light matching scores of sun-loving and shade-tolerant species in an intelligent species configuration and spatial layout optimization method for landscaping according to the present invention.

[0058] Figure 7 This is a schematic diagram of equipment for an intelligent species configuration and spatial layout optimization method for landscaping according to the present invention. DETAILED DESCRIPTION

[0059] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0060] Example 1: Figure 1 , which is a flow chart of the first embodiment of the method for optimizing the intelligent species configuration and spatial layout for landscaping according to the present invention, and provides the first embodiment of the method for optimizing the intelligent species configuration and spatial layout for landscaping according to the present invention.

[0061] In a first embodiment, the method for optimizing intelligent species configuration and spatial layout for landscaping includes:

[0062] Step S10: Deploy a soil sensor node network within the eco-industrial park according to a preset grid strategy, collect soil status data in real time within a sampling period T through the soil sensor node network, and upload the soil status data to a preset central database; wherein the soil status data includes soil pH data, water content data, organic matter content data, and salinity data;

[0063] It should be noted that the "soil sensor node network" described in this step refers to a physical network structure composed of multi-point distributed intelligent soil sensor units. Each sensor unit has independent collection and communication functions, and can automatically monitor the physical and chemical properties of the soil area where it is located and upload data encoding. Its deployment method is based on a preset grid strategy, which divides the park into several adjacent grid units. Each unit is configured with at least one sensor node to achieve spatial coverage of soil state parameters. The collected "soil state data" mainly includes four items, namely soil pH index, soil volume moisture index, organic matter content index and soil salinity index. These data are periodically uploaded to the central database via wired or wireless means for unified storage and management.

[0064] It is understandable that through the deployment and automated collection of the above-mentioned sensor network, the time-varying characteristics of the soil in the entire park can be perceived continuously and frequently, and digital modeling of soil conditions based on spatial grids can be achieved, providing accurate data support for subsequent plant species suitability analysis and spatial layout optimization, avoiding the lag and sampling blind spot problems existing in traditional manual soil surveys.

[0065] It should be understood that, compared with the soil monitoring mode relying on manual sampling detection, sample inspection and low-frequency update in the past, the application forms continuous and high-resolution soil data sensing capability by embedding the soil sensor node network into the space layout of the park, so that the update cycle of the soil state is shortened from several weeks or even months to several hours or minutes, greatly improving the timeliness and accuracy of species configuration.

[0066] For example, in a certain industrial ecological park pilot implementation, according to the density of one set of sensors per one hundred square meters, a total of one hundred and fifty soil monitoring nodes were installed, set to automatically collect data and upload every ten minutes, and the soil state information of each grid unit in the covered area can be updated in real time in the background. It has been verified that the soil data coverage rate reaches 100%, the update time delay is less than 30 minutes, and the data support efficiency in the process of plant species selection and configuration is significantly improved.

[0067] Step S20: performing grid coordinate processing, adaptive interpolation processing and dynamic weighted fusion processing based on the soil state data, and outputting a multi-dimensional soil suitability index at a position ; wherein x represents the horizontal coordinate and y represents the vertical coordinate.

[0068] It should be noted that the "grid coordinate processing" in this step refers to mapping the collected soil state data to a pre-set two-dimensional space grid coordinate system, so that each data point has a clear spatial positioning identifier, facilitating subsequent interpolation and fusion processing. The "adaptive interpolation processing" refers to dynamically selecting an interpolation method (such as inverse distance weighting or spline interpolation) according to the spatial distribution characteristics and data gradient change trend of the adjacent multiple known nodes for the data missing area between grids, to realize high-credibility soil state data filling. The "dynamic weighted fusion processing" refers to comprehensively fusing soil state data collected from different sources and different time periods according to time weight, data volatility and node collection stability, to construct a soil state atlas with high time consistency and spatial continuity. The steps of dynamic weighted fusion processing use the formula:

[0069]

[0070] wherein, represents the target position at time , the robust fusion estimation value of the kth soil state variable (pH, water content, salinity) at the target position is the time stamp of the observation data of node n; is the set of observation nodes in the neighborhood around the target position ​​For node n to target position Dynamic comprehensive weight of the kth type of soil state variables at time t; Target location At the moment The observed soil state value of the kth category; among them, the dynamic comprehensive weight It is determined by combining the preset spatial proximity factor, temporal freshness factor, node collection stability factor, data volatility factor and data source credibility factor.

[0071] As can be seen, the triple processing described above creates a consistent and comprehensive set of multidimensional soil suitability indices across the park's two-dimensional (x, y) coordinate space. This set of indices comprehensively reflects soil pH suitability, organic matter compatibility, water adequacy, and salinity tolerance at each location. It serves as the fundamental data input for subsequent plant species suitability assessments and light adaptability analyses, boasting high spatial resolution, clear physical meaning, and stable trends.

[0072] For example, if Figure 2 As shown, at 5000 test locations selected within a 1000m×1000m area in the eco-industrial park, compared with the traditional inverse distance weighted interpolation method, the "dynamic weighted fusion processing" described in the present invention significantly converges the comprehensive prediction error (RMSE) globally: the error distribution as a whole moves toward the low value range, and the proportion of high error tail samples decreases significantly; statistical results show that the average decrease in RMSE is about 35% to 40%, of which the proportion of samples with a decrease of ≥30% exceeds 80%, indicating that this method has a stable global accuracy improvement effect in heterogeneous soil scenarios. Figure 3 As shown, taking water content as a representative indicator, the fitting relationship between the traditional interpolation prediction value and the dynamic weighted fusion prediction value of the present invention is compared at 500 sampling locations. It can be seen that the dynamic weighted fusion prediction point cloud is closer to the ideal prediction line (y=x), and the average deviation is significantly reduced; 95% of the samples have an absolute deviation within ±2.5%, while the deviation of the traditional method can reach ±7%. This result shows that by introducing the time freshness factor, the node acquisition stability factor and the data volatility factor, the present invention can maintain a high degree of fit to the real trend under the interference of local missing measurements and high volatility, thereby effectively supporting the high-confidence filling of missing grid points. Figure 4As shown, the "multidimensional soil suitability heat map" constructed based on the dynamic weighted fusion results exhibits a smoother, more continuous spatial gradient structure in the two-dimensional coordinate space (x, y). The integrated mapping of soil pH, water content, and salinity shows clear suitability bands and patch boundaries and significantly reduced noise, avoiding the "blocky pseudo-gradients" often seen in traditional methods driven by local outliers. This spatial basemap can be directly used as input for subsequent steps: in step S30, it is multiplied with the light satisfaction to form a location-level comprehensive suitability. In step S40, it is combined with the ecological function objective into a multi-objective optimization model, thereby achieving coordinated optimization of species recommendation and spatial layout. These results demonstrate that the present invention, through the cascaded design of grid coordinate processing, adaptive interpolation, and dynamic weighted fusion, can obtain a set of multidimensional soil suitability indices with high temporal consistency and spatial continuity at the park scale, providing a quantifiable and reusable data foundation and empirical support for subsequent intelligent species allocation and spatial layout optimization.

[0073] Step S30: Obtain species soil tolerance model data from the preset plant species database, based on the multidimensional soil suitability index and species soil tolerance model data to identify plant species In position Species suitability score ;

[0074] It should be noted that the "plant species database" in this step refers to a structured data set that is constructed and stored in advance, which contains the ecological adaptability parameters of various green plants, mainly including the name of the plant species, the pH range suitable for growth, the organic matter requirement threshold, the water tolerance range and the salinity-alkali stress threshold, etc.; the "species soil tolerance model data" refers to a response model in the form of a multi-parameter threshold matrix or function calibrated based on historical sample training or expert experience, which is used to represent the response characteristics of each plant to different soil factors; the "species suitability score" refers to a quantitative evaluation index calculated at a certain location (x, y) based on the degree of match between the soil suitability index at that location and the tolerance model of the plant species, reflecting the growth adaptability of the species at the current location.

[0075] It can be understood that by using the multidimensional soil suitability index as input and combining it with the tolerance models corresponding to different plant species in the database for a matching evaluation, a comprehensive suitability score for each species at that location can be calculated. The scoring process can use methods such as multidimensional membership function matching, minimum distance penalty functions, or ensemble learning-based regression prediction models to achieve quantitative suitability analysis for each candidate plant species at each location in the spatial coordinate system.

[0076] It should be understood that traditional garden configurations often rely on empirical experience or a single factor (such as pH) to select species, ignoring the interactions between multidimensional soil factors and the multifactorial adaptability of plants. This can easily lead to problems such as plant configuration mismatch and reduced survival rates. By introducing a matching mechanism between a species tolerance model and multifactorial soil suitability, this present invention achieves personalized and precise alignment of plant selection with soil conditions, improving the scientific nature and sustainability of plant configurations.

[0077] For example, at a certain location in the park (x=12, y=8), the pH suitability is 0.82, the organic matter suitability is 0.74, the water content suitability is 0.88, and the salinity suitability is 0.65. A leguminous hedgerow plant A was selected, and its tolerance model parameters are: pH range [6.0, 7.5], organic matter ≥2%, moderate water content, and medium salinity tolerance. Its comprehensive matching score calculated by the gradient kernel function regression model is 0.79, and it is judged to be "good" in terms of planting suitability. However, another tree plant B scored only 0.42 and was marked as "low suitability", and was automatically eliminated from the candidate set. This method achieves the quantitative expression of the adaptive differences of different plant species in different spatial locations, significantly improving the spatial fit and biological adaptability of the configuration plan.

[0078] Step S40: Use the drone to cruise during a preset typical day period to collect shadow distribution images of the park and generate location Light and shadow evolution curve , combined with species suitability scores Perform light matching analysis and output optimized species suitability scores adjusted for light adaptability;

[0079] It should be noted that the "light and shadow evolution curve" refers to aerial images of the park collected at different times based on typical days (sufficient sunshine and representative of seasonal characteristics). The image analysis algorithm is used to extract the temporal information of the changes in light and shadow experienced by each grid location during the day, forming a quantitative description of the degree of light exposure at that location; "light adaptability adjustment" refers to the process of adjusting and correcting the original species suitability scores of different plant species based on the ecological response characteristics of light intensity, light duration and shadow frequency, so as to more realistically reflect the actual growth adaptability of plants at that location.

[0080] Among them, for species In position The raw suitability score of , define its light adaptability adjustment factor :

[0081]

[0082] in, For species The benchmark duration of sunshine demand; For species The optimal average light intensity; For species The maximum tolerable shadow alternation frequency; : are the sensitivity weights of species to light duration, light intensity and shadow frequency respectively; The benchmark duration of sunshine demand for measurement; is the average light intensity measured; is the measured shade alternation frequency; the adjusted optimized species suitability score ,in, It is a Sigmoid or normalization function, ensuring that the result falls in the range [0,1].

[0083] It's understandable that by introducing drones for timed cruise image acquisition, combined with computer vision technology to obtain high-spatial and temporal resolution light evolution data, it's possible to efficiently quantify the distribution characteristics of light resources at a plant's location under natural conditions. Combined with the light adaptation ranges registered for each plant species in the database (e.g., full sun, partial shade, shade-tolerant), as well as their tolerance to insufficient or excessive sunlight, a location-species light matching matrix can be constructed to perform multi-factor corrections on the initial species suitability scores, improving the accuracy of spatial adaptability.

[0084] It should be understood that traditional plant placement methods often ignore the dynamic shadows cast by buildings, structures, or large trees in a park, which can easily lead to misjudgment of plant light needs, causing problems such as slow plant growth, leaf yellowing, and even plant death. By introducing a light evolution curve and light adaptability analysis mechanism, this invention can significantly improve the ecological adaptability of plant placement, enhancing the stability and durability of greening.

[0085] For example, if Figure 5 As shown in the figure, a typical location close to the building belt was selected in the eco-industrial park, and aerial images were collected by drone during a typical day (6:00 to 18:00, sampling every 5 minutes). The light intensity was calculated based on the image analysis algorithm to obtain the light and shadow evolution curve of the location. As can be seen from the figure, the light intensity decreases significantly before 9 am and after 4 pm, and remains close to full illumination during the noon period. The statistical results show that the average light intensity at this location is 0.73, the cumulative effective light duration is ≈7.2 hours, and the shadow frequency factor is 0.18, indicating that the area is affected by building shading, the light is stable in the middle period, and the switching is more frequent in the morning and evening. As shown in the figure, the light intensity decreases significantly before 9 am and after 4 pm, and the light intensity is significantly reduced in the morning and evening. Figure 6As shown, based on the light shadow evolution curve and the plant light demand parameters, the light matching scores of sun-loving plants (class A) and shade-tolerant plants (class B) are calculated respectively. The results show that the suitability of class A plants is higher in the central open area, while the suitability is lower in the building shadow frequent area; on the contrary, the suitability of class B plants is higher in the area with high shadow frequency and insufficient cumulative sunshine. The results prove that the "light adaptability adjustment" step can adjust the original species suitability score according to local conditions, so that the species recommendation is more in line with the actual ecological response. Through the generation and analysis of the above light shadow evolution curve, the present application not only provides a quantitative light exposure index, but also directly relates it to the ecological needs of the species, dynamically adjusts the original species suitability score, and avoids the problem of relying only on the average light value in the traditional scheme while ignoring the timing and frequency characteristics, thereby significantly improving the rationality and scientificity of the species configuration.

[0086] Step S50: performing space layout optimization based on the optimized species suitability score combined with a graph optimization algorithm based on multiple constraint conditions.

[0087] It should be noted that the "space layout optimization" in this step refers to, after considering the light-soil suitability scores of each location and each plant, generating a plant space configuration scheme that meets the constraint conditions based on the graph structure representing the space grid and the distribution of candidate species in the park, according to multiple actual constraints such as ecological compatibility between species, visual combination, and maintenance convenience; the "multiple constraint conditions" include symbiotic / antagonistic relationships between species, limitations on the overlap of plant canopies in adjacent locations, path accessibility limitations, local species diversity index requirements, and shrub / tree / ground cover level balance requirements.

[0088] It can be understood that by taking the optimized species suitability score as the initial evaluation basis for the layout weight, a space graph model is reconstructed, where each node represents a grid cell in the park, and each edge represents the plant configuration relationship between adjacent grids. By using a heuristic graph optimization algorithm (such as multi-objective A* search, restricted genetic algorithm, or graph coloring method), the optimal configuration path that meets multiple ecological and aesthetic constraints can be quickly searched in a global range, thereby effectively improving the overall ecological adaptability and landscape performance of the space configuration.

[0089] It should be understood that in traditional garden design, plant species and distribution locations are configured relying on human experience, it is difficult to evaluate the long-term impact of micro ecological condition differences on plant growth, and the dynamic interaction between adjacent plants is often ignored in complex ecology, leading to problems such as uneven plant growth, increased maintenance costs, etc. The present application effectively avoids the above defects by introducing a graph optimization model and a multi-constraint mechanism, thereby enhancing the adaptability, long-term stability, and spatial diversity of the garden greening system.

[0090] For example, within an eco-industrial park, a pre-analysis determined that the suitability scores of plants A, B, and C at different locations (x, y) within a given area were 0.89, 0.83, and 0.76, respectively. During the graph optimization process, the following constraints were imposed: adjacent locations must not contain duplicate tree species with a crown radius greater than 1.5 meters; the same area must contain at least three species of plants from different morphological levels (trees, shrubs, and ground cover); and species B and C must not be adjacent to each other due to root antagonism. Each location was treated as a graph node, and an edge weight function was constructed based on these constraints. This ultimately generated a spatial layout solution that met these requirements, increasing local diversity by 12% and reducing subsequent maintenance costs by 18%. This layout mechanism has significantly improved the sustainability and ecological stability of the greening system in actual deployments.

[0091] Embodiment 2: In addition, the present invention provides an intelligent species configuration and spatial layout optimization system for landscaping, which adopts the intelligent species configuration and spatial layout optimization method for landscaping in the above embodiment, and can solve the technical problem of intelligent species configuration and spatial layout optimization for landscaping. Compared with the existing technology, the beneficial effects of the intelligent species configuration and spatial layout optimization system for landscaping provided by the present invention are the same as the beneficial effects of the intelligent species configuration and spatial layout optimization method for landscaping provided by the above embodiment, and the other technical features of the intelligent species configuration and spatial layout optimization system for landscaping are the same as the features disclosed in the above embodiment method, and are not further described here.

[0092] Example 3: The present invention provides an intelligent species configuration and space layout optimization device for landscaping, please refer to Figure 7A device for intelligent species configuration and spatial layout optimization for landscaping includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method for intelligent species configuration and spatial layout optimization for landscaping in the first embodiment described above. The device for intelligent species configuration and spatial layout optimization for landscaping in the embodiments of the present invention may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. The device for intelligent species configuration and spatial layout optimization for landscaping is merely an example and should not limit the functionality or scope of use of the embodiments of the present invention. An intelligent landscaping species allocation and spatial layout optimization device may include a processing device 1001 (e.g., a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory 1002 or programs loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the intelligent landscaping species allocation and spatial layout optimization device. The processing device 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An I / O interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; a storage device 1003 including, for example, a magnetic tape or hard disk; and a communication device 1009. Communication device 1009 can allow the intelligent landscaping species allocation and spatial layout optimization device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows an intelligent landscaping species allocation and spatial layout optimization device with various systems, it should be understood that implementation or inclusion of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or included.

[0093] Example 4: The present invention also provides a computer program product, comprising a computer program. When executed by a processor, the computer program implements the steps of the aforementioned method for optimizing intelligent species configuration and spatial layout for landscaping. The computer program product provided by the present invention can solve the technical problem of optimizing intelligent species configuration and spatial layout for landscaping. Compared to the prior art, the beneficial effects of the computer program product provided by the present invention are the same as those of the method for optimizing intelligent species configuration and spatial layout for landscaping provided in the aforementioned embodiment, and are not further elaborated here.

[0094] In particular, according to the embodiments disclosed in the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a read-only memory 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present invention are performed.

[0095] It should be understood that the various parts disclosed in the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any appropriate manner in any one or more embodiments or examples.

[0096] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for optimizing intelligent species configuration and spatial layout for landscaping, characterized in that: Methods include: Step S10: Deploy a soil sensor node network within the eco-industrial park according to a preset grid strategy, collect soil status data in real time within a sampling period T through the soil sensor node network, and upload the soil status data to a preset central database; wherein the soil status data includes soil pH data, water content data, organic matter content data, and salinity data; Step S20: Grid coordinate processing, adaptive interpolation processing and dynamic weighted fusion processing are performed based on the soil state data, and the output is at position Multidimensional soil suitability index ; Where x represents the horizontal coordinate and y represents the vertical coordinate; Step S30: Obtain species soil tolerance model data from the preset plant species database, based on the multidimensional soil suitability index and species soil tolerance model data to identify plant species In position Species suitability score ; Step S40: Use the drone to cruise during a preset typical day period to collect shadow distribution images of the park and generate location Light and shadow evolution curve , combined with species suitability scores Perform light matching analysis and output optimized species suitability scores adjusted for light adaptability; Step S50: performing spatial layout optimization based on the optimized species suitability scores combined with a graph optimization algorithm based on multiple constraints.

2. The method for optimizing intelligent species configuration and spatial layout for landscaping according to claim 1, wherein: In step S10, a soil sensor node network is deployed in the eco-industrial park according to a preset grid strategy, specifically including: obtaining geographic information of the eco-industrial park, dividing the green area based on the park geographic information into multiple regular grid units; deploying soil sensor nodes at the center of the multiple regular grid units; the soil sensor nodes are used to monitor soil status data, which includes soil pH data, water content data, organic matter content data, and salinity data; the soil sensor nodes include a pH sensor for monitoring soil pH, a soil moisture sensor for monitoring soil moisture content, an organic matter sensor for monitoring soil organic matter content, and a conductivity sensor for monitoring soil salinity; wherein the pH sensor and soil moisture sensor are installed at a depth of 20 cm underground; and the organic matter sensor and conductivity sensor are installed at a depth of 10 cm underground; each sensor node collects corresponding parameter values ​​at a sampling period T and packages them into data packets with timestamps and coordinate information, and the data packets are sent to a preset central database via a preset wireless communication module.

3. The method for optimizing intelligent species configuration and spatial layout for landscaping according to claim 2, wherein: In step S10, the geographical information of the eco-industrial park is obtained, and the green area in the geographical information is divided into a plurality of regular grid units, specifically including: When the shape of the green area in the park's geographic information is a regular rectangle or square, an equidistant regular grid division mechanism is used to evenly divide the green area into multiple regular grid units with the same side length; When the shape of the green area in the park's geographic information is an irregular polygon, a regional partitioning mechanism based on Voronoi subdivision is adopted. The center position of the soil sensor node is used as the generator of the Voronoi subdivision regional partitioning mechanism. The green area is automatically divided into multiple polygonal sub-areas as regular grid units. The area of ​​each polygonal sub-area is similar and the geometric distance between the boundary and the center position of the adjacent soil sensor node is equivalent. When the shape of the green area in the park geographic information is strip-shaped or long and narrow, a strip division mechanism based on adaptive aspect ratio adjustment is adopted to divide the green area into multiple strip units along the long side direction, and further divide the interior of the strip unit into approximately rectangular small grids as regular grid units.

4. The method for optimizing intelligent species configuration and spatial layout for landscaping according to claim 1, wherein: In step S20, the steps of performing grid coordinate processing, adaptive interpolation processing, and dynamic weighted fusion processing based on the soil state data to output a multidimensional soil suitability index specifically include: A two-dimensional rectangular coordinate system is established based on the deployed soil sensor node network. The adaptive interpolation mechanism based on dynamic quantile normalization is used to normalize the multidimensional data of the soil state data to obtain the pH sub-suitability at the position with the horizontal coordinate x and the vertical coordinate y. , water quantum suitability , organic proton suitability and salinity and alkalinity suitability ; The pH suitability was evaluated based on the sensitive factor weight mechanism. , water quantum suitability , organic proton suitability and salinity and alkalinity suitability Perform dynamic weighted fusion processing to output a multidimensional soil suitability index .

5. The method for optimizing intelligent species configuration and spatial layout for landscaping according to claim 4, characterized in that: In step S20, the soil state data is normalized using an adaptive interpolation mechanism based on dynamic quantile normalization to obtain the pH sub-suitability at the position with the horizontal coordinate x and the vertical coordinate y. , water quantum suitability , organic proton suitability and salinity and alkalinity suitability The steps include: Data distribution acquisition: For soil state data including soil pH data, water content data, organic matter content data and salinity data, calculate the corresponding empirical distribution function and extract the upper quantile of the soil state data of the corresponding empirical distribution function The quantiles of soil status data ; Outlier truncation correction: When the soil state data is higher than the upper quantile of the soil state data Or below the lower quantile of soil status data When The quantiles of soil status data , output optimized soil state data; Quantile normalization: The optimized soil state data is mapped to the interval [0,1] to obtain the sub-suitability of each parameter. The sub-suitability of each parameter includes the pH sub-suitability at the position with the horizontal coordinate x and the vertical coordinate y. , water quantum suitability , organic proton suitability and salinity and alkalinity suitability .

6. The method for optimizing intelligent species configuration and spatial layout for landscaping according to claim 5, characterized in that: Step S20 also includes: for missing coordinate points where no sensors are deployed, an adaptive spatial estimation mechanism based on Kriging interpolation is used to calculate the correlation and spatial semi-variance of the soil state data collected by the neighboring sensor nodes, and the sub-suitability of each parameter of the missing coordinate point is estimated based on the correlation and spatial semi-variance of the soil state data collected by the neighboring sensor nodes to ensure that each coordinate point in the two-dimensional rectangular coordinate system has the complete four sub-suitability indicators.

7. The method for optimizing intelligent species configuration and spatial layout for landscaping according to claim 1, wherein: In step S30, the species soil tolerance model data is obtained from the preset plant species database, and the multidimensional soil suitability index is used to and species soil tolerance model data to identify plant species In position Species suitability score The steps include: Obtain species soil tolerance model data from the preset plant species database. The species soil tolerance model data includes: target growth parameter data, pH value suitable interval parameter data, organic matter requirement level parameter data, moisture content tolerance interval parameter data, and salinity sensitivity parameter data corresponding to the species; construct the corresponding soil tolerance semantic vector based on the species soil tolerance model data ; Based on the multidimensional soil suitability index Construct the corresponding soil suitability semantic vector ; The support vector machine (SVM) algorithm is introduced to calculate the soil tolerance semantic vector and soil suitability semantic vector The concatenation vector As model input, a plant species suitability evaluation model was constructed; Plant species suitability evaluation model outputs plant species In position Species suitability score ; Among them, the plant species suitability evaluation model outputs plant species In position Species suitability score The steps include model training phase and model application phase; The plant species suitability evaluation model in the model training stage specifically includes: obtaining the first Samples of multidimensional soil suitability index , Historical species soil tolerance model samples and corresponding plant species growth suitability experimental data , construct training sample pairs ,Will As input, As the output, the species suitability evaluation model is trained by the support vector regression training method combining the minimum structural risk criterion with the kernel function mapping mechanism, and the converged suitability evaluation function model is obtained; During the application phase of the plant species suitability evaluation model, the target location Corresponding plant species of and The concatenated vector As the model input, it is input into the converged suitability evaluation function model to obtain the species suitability score Output.

8. The method for optimizing intelligent species configuration and spatial layout for landscaping according to claim 1, wherein: In step S40, the drone is used to cruise during a preset typical day period to collect shadow distribution images of the park and generate location Light and shadow evolution curve , combined with species suitability scores The steps for performing a light matching analysis and outputting optimized species suitability scores adjusted for light adaptability include: Use drones to cruise during a preset typical day to collect shadow distribution images of the park and generate location Light and shadow evolution curve ; Based on the light shadow evolution curve Determine the duration of light overlap, the number of consecutive sunlight periods, and the frequency of sunlight interruptions; construct a light adaptability adjustment coefficient based on the duration of light overlap, the number of consecutive sunlight periods, and the frequency of sunlight interruptions; Species suitability scores based on light adaptation adjustment coefficients Correction is performed and the optimized species suitability score adjusted for light adaptability is output.

9. The method for optimizing intelligent species configuration and spatial layout for landscaping according to claim 1, wherein: In step S50, the multiple constraints include: Position unique configuration constraint: At each position Only one plant species is allowed to be configured to prevent multiple plant species from being configured at the same coordinate point; Species ratio control constraint: The proportion of each plant species in the entire park shall not exceed the preset upper limit ratio value, which is used to control the overall balance of species distribution; Ecological connectivity constraint: The plant species arranged between adjacent locations must be associated or consistent to enhance the ecological stability of the plant community structure.

10. An intelligent species configuration and spatial layout optimization system for landscaping, applied to an intelligent species configuration and spatial layout optimization method for landscaping according to any one of claims 1 to 7, characterized in that: The intelligent species configuration and spatial layout optimization system for landscaping includes: The soil monitoring and collection module is used to deploy a soil sensor node network within the eco-industrial park according to a preset grid strategy. The soil sensor node network collects soil status data in real time within a sampling period T and uploads the soil status data to a preset central database. The soil status data includes soil pH data, water content data, organic matter content data, and salinity data. Soil suitability analysis module is used to perform grid coordinate processing, adaptive interpolation processing and dynamic weighted fusion processing based on soil state data, and output at location Multidimensional soil suitability index ; Where x represents the horizontal coordinate and y represents the vertical coordinate; The species suitability assessment module is used to obtain species soil tolerance model data from the preset plant species database based on the multidimensional soil suitability index and species soil tolerance model data to identify plant species In position Species suitability score ; The illumination adaptability correction module is used to use the drone to cruise during the preset typical day time to collect the shadow distribution image of the park and generate the location Light and shadow evolution curve , combined with species suitability scores Perform light matching analysis and output optimized species suitability scores adjusted for light adaptability; The spatial layout optimization module is used to perform spatial layout optimization based on optimizing species suitability scores combined with a graph optimization algorithm based on multiple constraints.

Images