Intelligent garden plant selection method and system

Abstract

The present invention relates to the field of garden design technology, and in particular to an intelligent garden plant selection method and system. The method comprises the following steps: obtaining garden area ecological condition data; extracting ecological condition characteristics according to the garden area ecological condition data to obtain ecological condition characteristic data; matching plant characteristics according to the ecological condition characteristic data to obtain plant characteristic matching data; performing eco-friendly evaluation according to the plant characteristic matching data to obtain eco-friendly evaluation data; obtaining garden area spatial data, and generating plant configuration schemes according to the garden area spatial data and the eco-friendly evaluation data to obtain plant configuration scheme data. The present invention can select plant species that match the specific ecological conditions of the garden area through the extraction of ecological condition characteristic data and plant characteristic matching, so that the selection of plants adapts to the actual situation of the garden and improves the growth and survival rate of plants.

Description

Technical Field

[0001] The present invention relates to the technical field of garden design, and in particular to an intelligent garden plant selection method and system. Background Art

[0002] Landscape plants are plant materials suitable for landscaping. They include woody and herbaceous flowering, foliage or fruiting plants, as well as protective plants and economic plants suitable for gardens, green spaces and scenic spots. Plants used for indoor flower decoration are also landscape plants. Landscape plants are divided into two categories: woody landscape plants and herbaceous landscape plants. In addition, they also include ferns, aquatic plants, cactus succulents, insectivorous plants and other plant species. There is some overlap between plant species. In the traditional garden design and plant selection process, it usually relies on the experience and knowledge of gardeners or experts. They will choose suitable plant species based on the geographical location, climatic conditions, soil conditions and design requirements of the park. However, this method has some limitations, such as ignoring the impact of certain plant characteristics on the ecosystem and being easily affected by subjective factors. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes an intelligent garden plant selection method and system to solve at least one of the above technical problems.

[0004] The present application provides an intelligent garden plant selection method, comprising the following steps:

[0005] Step S1: Obtaining ecological condition data of the garden area;

[0006] Step S2: extracting ecological condition features according to the garden area ecological condition data to obtain ecological condition feature data;

[0007] Step S3: performing plant characteristic matching according to the ecological condition characteristic data to obtain plant characteristic matching data;

[0008] Step S4: performing an eco-friendly evaluation according to the plant characteristic matching data to obtain eco-friendly evaluation data;

[0009] Step S5: Acquire the garden area spatial data, and generate a plant configuration plan based on the garden area spatial data and the eco-friendly evaluation data to obtain plant configuration plan data.

[0010] By obtaining the ecological condition data of the garden area and extracting the ecological condition characteristics in the present invention, the method can more accurately understand the ecological environment of the garden area, including the conditions of soil, hydrology, climate, etc., which helps to select plants that are more suitable for the current environment and improve the ecological adaptability of garden plants. By matching plant characteristics according to the ecological condition characteristic data, the characteristics of garden plants can be matched with environmental conditions and suitable plant species can be selected. In this way, the introduction of unsuitable plants can be avoided, the adverse effects of plants can be reduced, and the growth rate and survival rate of plants can be improved. By carrying out an eco-friendly assessment on the plant characteristic matching data, the degree of influence of plants on the environment can be assessed, including aspects such as its growth characteristics, water consumption, and nutrient requirements, which helps to select plants with less impact on the ecological environment and protect the health of the ecological environment. In combination with the garden area spatial data and the eco-friendly assessment data, a plant configuration scheme is generated, which can more reasonably plan and design the garden space, make the plant layout more beautiful and reasonable, and protect the ecological environment to the greatest extent.

[0011] Preferably, step S1 specifically includes:

[0012] Get garden location data;

[0013] Extract longitude and latitude data according to the garden location data to obtain the garden longitude and latitude data;

[0014] Searching for climate conditions and regional flora and fauna data according to the garden latitude and longitude data to obtain first garden climate condition data and regional flora and fauna data;

[0015] The garden meteorological data is collected through a sensor network preset in the garden to obtain the second garden climate condition data;

[0016] Garden soil condition data is obtained, and the garden soil condition data, the first garden climate condition data, the regional flora and fauna data and the second garden climate condition data are integrated to obtain the garden area ecological condition data.

[0017] The present invention obtains and integrates various data such as the location, climate, and soil of the garden area, providing a complete data basis for subsequent plant selection and configuration. The meteorological data collected by the sensor can realize real-time monitoring and collection of garden climate conditions, improving the accuracy and practicality of the data. The search for regional animal and plant data and the acquisition of garden soil condition data provide a basis for selecting suitable garden plants, which helps to improve the ecological benefits and sustainable development level of garden landscapes.

[0018] Preferably, step S2 specifically includes:

[0019] Step S21: extracting ecological condition characteristics according to the garden area ecological condition data to obtain preliminary ecological condition characteristic data, wherein the preliminary ecological condition characteristic data includes climate characteristic data and soil characteristic data;

[0020] Step S22: collecting garden images according to the garden location data to obtain garden image data;

[0021] Step S23: extracting garden vegetation features and garden terrain features according to the garden image data to obtain garden vegetation feature data and garden terrain feature data, wherein the garden vegetation feature data includes vegetation coverage feature data and vegetation height feature data, and the garden terrain feature data includes garden altitude feature data and garden surface slope feature data;

[0022] Step S24: performing microecological characteristic association according to the garden vegetation characteristic data, the garden terrain characteristic data and the preliminary ecological condition characteristic data to obtain ecological condition characteristic data.

[0023] The present invention extracts the ecological condition characteristics, vegetation characteristics and terrain characteristics of the garden, which can fully reflect the ecological environment characteristics of the garden area, and provides comprehensive data support for subsequent plant selection and configuration. Through image acquisition and feature extraction, the acquired data is more intuitive and accurate, which can better reflect the actual situation of the garden, and provide more reliable data basis for subsequent plant selection and configuration. The microecological feature association step can comprehensively consider various factors such as vegetation, terrain and ecological conditions, and provide more comprehensive and accurate data support for subsequent plant characteristic matching, which helps to improve the ecological benefits and sustainable development level of garden landscape.

[0024] Preferably, step S24 is specifically:

[0025] Associating the garden vegetation characteristic data with the preliminary ecological condition characteristic data with ecological condition parameters to obtain first ecological condition characteristic data;

[0026] Associating the garden terrain characteristic data with the preliminary ecological condition characteristic data with ecological condition parameters to obtain second ecological condition characteristic data;

[0027] The first ecological condition characteristic data and the second ecological condition characteristic data are subjected to multi-dimensional graph mapping to obtain ecological condition characteristic data.

[0028] In the present invention, the garden vegetation characteristic data is associated with the preliminary ecological condition characteristic data to obtain the first ecological condition characteristic data, and the vegetation characteristics are associated with the ecological condition characteristics to more accurately reflect the relationship between the garden vegetation and the ecological environment. The garden terrain characteristic data is associated with the preliminary ecological condition characteristic data to obtain the second ecological condition characteristic data, and the terrain characteristics are associated with the ecological condition characteristics to more comprehensively consider the impact of the terrain on the ecological environment. The first ecological condition characteristic data and the second ecological condition characteristic data are multi-dimensionally mapped to obtain the ecological condition characteristic data, and the vegetation characteristics, terrain characteristics and ecological condition characteristics are deeply integrated to obtain more comprehensive and accurate ecological condition characteristic data.

[0029] Preferably, the plant characteristic matching data includes first plant characteristic matching data and second plant characteristic matching data, and step S3 is specifically as follows:

[0030] Step S31: Acquire plant data to be matched;

[0031] Step S32: mapping the ecological condition characteristic data to plant growth environment keywords to obtain plant growth environment keyword data;

[0032] Step S33: performing matching according to the plant to-be-matched data and the plant growth environment keyword data to obtain first plant characteristic matching data;

[0033] Step S34: performing vectorization processing according to the plant data to be matched and the ecological condition characteristic data to obtain the plant vector data to be matched and the ecological condition characteristic vectorized data;

[0034] Step S35: performing information entropy calculation on the plant to-be-matched vector data and the ecological condition feature quantized data to obtain the plant to-be-matched information entropy data and the ecological condition feature information entropy data;

[0035] Step S36: performing information entropy similarity matching on the plant information entropy data to be matched and the ecological condition characteristic information entropy data to obtain second plant characteristic matching data; wherein the information entropy similarity matching is specifically:

[0036]

[0037] S is the second plant characteristic matching data, e is the natural index term, d is the relative distance formula between the plant information entropy data to be matched and the ecological condition characteristic information entropy data, σ is the standard deviation data between the plant information entropy data to be matched and the ecological condition characteristic information entropy data, θ is the weather randomness influence parameter data, w is the plant information entropy data to be matched, and q is the ecological condition characteristic information entropy data.

[0038] In the present invention, by obtaining the plant data to be matched, the system can understand the available plant species and related characteristics, and provide basic data for the subsequent matching process. Mapping the ecological condition characteristic data to the plant growth environment keywords helps to identify the growth adaptability of plants under different ecological conditions, so as to match more accurately. By matching the plant data to be matched with the ecological condition keywords, the first plant characteristic matching data can be obtained, which helps to determine the matching degree between the plant species and the ecological conditions of the park. The plant data to be matched and the ecological condition characteristic data are vectorized so that the data can be more conveniently mathematically calculated and analyzed, providing a data basis for subsequent steps. By calculating the information entropy of the plant data to be matched and the ecological condition characteristic data, the similarity or difference between them can be quantified, providing a more objective basis for subsequent matching. Through information entropy similarity matching, the matching degree between the plant and the ecological conditions can be more accurately evaluated, and then the second plant characteristic matching data can be obtained, so as to select the most suitable plant species. The selection based on experience and intuition of the conventional method is easily affected by personal subjective factors, resulting in the selection being not objective and scientific enough. The present invention uses ecological condition feature data and plant characteristic matching data, and uses computer algorithms and artificial intelligence technology to achieve intelligent matching of plants, thereby reducing the interference of subjective factors and improving the objectivity and scientificity of matching. The formula in the present invention converts the similarity between the plant data to be matched and the ecological condition data into a numerical value by calculating the relative distance and undergoing nonlinear mapping, which facilitates the quantitative comparison of the similarity. The weather randomness influence parameter is introduced, and the random influence of climate change on the matching result is considered, so that the matching result is more robust. The parameters w and q can be adjusted according to the specific situation to meet different matching requirements. Starting from the definition of similarity, the concept of information entropy and the idea of ​​distance measurement are used for deduction, and finally a formula is obtained. Compared with the conventional similarity formula (such as distance measurement algorithm), the degree of processing of the information behind the data is improved to better measure the similarity between the plant information entropy data to be matched and the ecological condition characteristic information entropy data, thereby matching plant characteristics.

[0039] Preferably, the plant information entropy data to be matched includes plant linear information entropy data to be matched and plant graph information entropy data to be matched, and the ecological condition characteristic information entropy data includes ecological condition characteristic linear information entropy data and ecological condition characteristic graph information entropy data, and step S35 is specifically as follows:

[0040] The linear information entropy calculation is performed on the plant to-be-matched vector data and the ecological condition characteristic quantized data to obtain the plant to-be-matched linear information entropy data and the ecological condition characteristic linear information entropy data; the linear information entropy calculation is specifically as follows:

[0041]

[0042] E is the linear information entropy data of plants to be matched or the linear information entropy data of ecological condition characteristics, n is the number of data sets, i is the data order item, p ... i is the linear information entropy data to be matched for the i-th plant or the linear information entropy data of ecological condition characteristics, θ i is the i-th random phase angle data;

[0043] Matrix processing is performed on the plant to-be-matched vector data and the ecological condition characteristic vector quantized data to obtain the plant to-be-matched matrix data and the ecological condition characteristic matrix data;

[0044] The graph information entropy is calculated for the plant to-be-matched matrix data and the ecological condition characteristic matrix data to obtain the plant to-be-matched graph information entropy data and the ecological condition characteristic graph information entropy data.

[0045] In the present invention, the complexity of the plant data to be matched and the ecological condition characteristic data can be quantified by calculating the linear information entropy. Linear information entropy is a measure of the complexity of the elements in the vector data set. By calculating the average value of the logarithm and the average value of each element, combined with the information of the probability of occurrence of the element, it can reflect the distribution and change trend of the data, help to understand the characteristics and laws of the data, and provide a basis for subsequent data analysis and processing. Graph information entropy is a measure of the complexity of the elements in the matrix data set. By calculating the graph information entropy, the complexity of the plant data to be matched and the ecological condition characteristic data can be more comprehensively evaluated. Graph information entropy can capture the association and interaction between elements in the data, reflect the overall structure and pattern of the data, and better reveal the inherent laws and characteristics of the data. Combining linear information entropy and graph information entropy, the complexity of the plant data to be matched and the ecological condition characteristic data can be comprehensively evaluated, providing a reference for subsequent data processing and feature matching. This helps to understand the nature and characteristics of the data more accurately and provide more reliable data support for intelligent garden plant selection. In the present invention, the complexity of the data can be evaluated by calculating the linear information entropy of the elements in the data set. Information entropy reflects the uncertainty and confusion of the data, so the higher the linear information entropy, the higher the complexity of the data. By calculating linear information entropy, the complexity of data can be quantified into a numerical value, which facilitates the comparison and analysis of differences between different data sets.

[0046] Preferably, the plant to-be-matched graph information entropy data includes the first plant to-be-matched graph information entropy data and the second plant to-be-matched graph information entropy data, the ecological condition characteristic graph information entropy data includes the first ecological condition characteristic graph information entropy data and the second ecological condition characteristic graph information entropy data, and the graph information entropy calculation is specifically as follows:

[0047] The graph information entropy is calculated for the plant to-be-matched matrix data and the ecological condition characteristic matrix data to obtain the first plant to-be-matched graph information entropy data and the first ecological condition characteristic graph information entropy data; the graph information entropy calculation is specifically as follows:

[0048]

[0049] E is the information entropy data of the first plant to be matched graph or the information entropy data of the first ecological condition characteristic graph, j is the row coordinate data, M is the row quantity data, p is the column coordinate data, Q is the column quantity data, is the parameter correlation data, G jp is the difference value data corresponding to the jth row and the pth column in the plant matrix data to be matched and the ecological condition characteristic matrix data, h is the similarity data between the plant matrix data to be matched and the ecological condition characteristic matrix data, and k is the standard deviation data corresponding to the plant matrix data to be matched and the ecological condition characteristic matrix data;

[0050] Extracting periodic parameters of the plant to-be-matched matrix data and the ecological condition characteristic matrix data to obtain the plant to-be-matched periodic data and the ecological condition characteristic periodic data;

[0051] Performing frequency domain conversion processing on the plant periodic data to be matched and the ecological condition characteristic periodic data to obtain the plant frequency domain conversion data to be matched and the ecological condition characteristic frequency domain conversion data;

[0052] Performing spectrum conversion on the plant to-be-matched frequency domain conversion data and the ecological condition characteristic frequency domain conversion data to obtain the plant to-be-matched frequency spectrum data and the ecological condition characteristic frequency spectrum data;

[0053] Performing gradient calculation on the plant to-be-matched frequency spectrum data and the ecological condition characteristic frequency spectrum data to obtain the plant to-be-matched frequency spectrum gradient data and the ecological condition characteristic frequency spectrum gradient data;

[0054] Information entropy calculation is performed on the gradient data of the plant spectrum map to be matched and the gradient data of the ecological condition characteristic spectrum map to obtain information entropy data of the second plant map to be matched and information entropy data of the second ecological condition characteristic map.

[0055] In the present invention, by calculating the information entropy of frequency domain features, the complexity of data in the frequency domain can be evaluated. Frequency domain features reflect the changes in the frequency distribution of data, so the higher the graph information entropy, the more complex the frequency domain features of the data. By calculating the graph information entropy, the periodicity and frequency domain characteristics of the data can be quantified into a numerical value, which is convenient for comparing and analyzing the differences between different data. Through the steps of frequency domain conversion, spectrum graph conversion and gradient calculation, the characteristics of the data in the frequency domain can be effectively extracted, thereby providing similarity characteristics of the description data based on periodic parameters, rather than simply comparing. Spectrum graph conversion and gradient calculation can convert data into spectrum graphs and spectrum graph gradient data, which can better reflect the spatial distribution and change trend of the data and improve the characterization ability of the data. The information entropy calculation utilizes the spectrum graph gradient data, which can more accurately measure the similarity between the plant data to be matched and the ecological condition characteristic data, thereby realizing more accurate graph information entropy calculation. The data body of graph information entropy data is a matrix. The horizontal data items of the source graph are data of different dimensions, and the vertical data items are different sub-dimensions in the same dimension (such as cold resistance, heat resistance, timing and other temperature influencing factors corresponding to temperature). It reveals the complexity and diversity behind the data, making the characteristic representation more prominent, rather than simply calculating a single data, or the high computational complexity caused by linear calculations. It quantifies the complexity and uncertainty of the data and provides important information about the distribution and structure of the data.

[0056] Preferably, step S4 is specifically:

[0057] According to the plant characteristics matching data, the water and soil impact processing is carried out to obtain the water and soil impact assessment data;

[0058] Process the food chain impact based on the regional animal and plant data and plant characteristic matching data to obtain food chain impact assessment data;

[0059] Generate eco-friendly assessment data based on soil and water impact assessment data and food chain impact assessment data.

[0060] In the present invention, by matching data according to plant characteristics to process the impact of soil and water and processing the impact of the food chain according to regional animal and plant data, the method comprehensively considers the impact of soil and water conditions and the biological environment on garden plants, thereby more comprehensively evaluating the adaptability and growth of plants. By generating eco-friendly evaluation data, the method helps to guide garden planning and design, so that the selected plants are more in line with the local ecological environment and climatic conditions, thereby improving the ecological friendliness of the garden. By considering the impact of soil and water and the food chain, the environmental risks brought about by the introduction of unsuitable plants or animal and plant species can be reduced to prevent them from having a negative impact on the local ecosystem. The generation of eco-friendly evaluation data helps to select plants and food chain combinations that are more adaptable and will not destroy the ecological balance, thereby promoting the healthy development of the garden ecosystem and the maintenance of the ecological balance.

[0061] Preferably, the plant configuration scheme data includes first plant configuration scheme data and second plant configuration scheme data, and step S5 is specifically as follows:

[0062] Obtain spatial data of garden areas;

[0063] Extract plant placement space according to garden area spatial data to obtain plant placement space data;

[0064] Generate an economical plant configuration plan based on the plant placement space data and the eco-friendly evaluation data to obtain first plant configuration plan data;

[0065] A plant configuration plan with minimum human intervention is generated according to the plant placement space data and the eco-friendly assessment data to obtain second plant configuration plan data.

[0066] In the present invention, by acquiring the spatial data of the garden area and extracting the plant placement space, the layout of the plants can be optimized to ensure that the spacing between the plants is appropriate, avoiding crowding or excessive sparseness, so that the entire garden space is used more reasonably. By generating an economical plant configuration plan based on the plant placement space data and the eco-friendly evaluation data, factors such as the cost, maintenance and management of the plants can be considered, making the configuration plan more economically reasonable and feasible. By generating a plant configuration plan with minimal human intervention, the manpower cost of garden management and maintenance can be reduced, and the operating efficiency and sustainability of the garden can be improved. This method takes into account the ecological adaptability and environmental friendliness of the plants, so that the configured plants are more in line with the local ecological environment and climatic conditions, which is conducive to the healthy and stable development of the garden ecosystem.

[0067] Preferably, an intelligent garden plant selection system is used to execute the intelligent garden plant selection method as described above, and the intelligent garden plant selection system comprises:

[0068] The garden area ecological condition data collection module is used to obtain the garden area ecological condition data;

[0069] The ecological condition feature extraction module is used to extract the ecological condition features according to the ecological condition data of the garden area to obtain the ecological condition feature data;

[0070] A plant characteristic matching module is used to match plant characteristics according to ecological condition characteristic data to obtain plant characteristic matching data;

[0071] An eco-friendly evaluation module, used to perform eco-friendly evaluation according to plant characteristic matching data to obtain eco-friendly evaluation data;

[0072] The plant configuration scheme generation module is used to obtain the garden area spatial data, and generate a plant configuration scheme based on the garden area spatial data and the eco-friendly evaluation data to obtain the plant configuration scheme data.

[0073] The beneficial effects of the present invention are as follows: by extracting ecological condition characteristic data and matching plant characteristics, it is possible to select plant species that match the specific ecological conditions of the garden area, so that the selection of plants is more adapted to the actual situation of the garden, which is conducive to improving the growth and survival rate of plants. By carrying out an eco-friendly evaluation on plant characteristic matching data, the degree of influence of plants on the garden ecosystem can be evaluated, including its influence on soil, water source, air quality, etc., which helps to select plants with less impact on the ecological environment and protect the ecological balance and environmental sustainability of the garden. Combining the spatial data of the garden area and the eco-friendly evaluation data, a plant configuration scheme can be generated to optimize the layout of garden plants. By rationally planning the spatial position of plants, the overall aesthetics and ecological benefits of the garden can be improved. The method comprehensively considers factors such as the ecological conditions, plant characteristics and spatial layout of the garden, so that plant selection and configuration are more comprehensive and scientific, improves the overall quality and environmental adaptability of the garden, and enhances the ecological function and ornamental value of the garden. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting implementations made with reference to the following drawings:

[0075] Figure 1 A flowchart showing the steps of an intelligent garden plant selection method according to an embodiment is shown;

[0076] Figure 2 A flowchart showing a method for acquiring ecological condition data of a garden area according to an embodiment is shown;

[0077] Figure 3A flowchart showing a method for extracting ecological condition features according to an embodiment is shown;

[0078] Figure 4 A flow chart showing the steps of a plant characteristic matching method according to an embodiment is shown. DETAILED DESCRIPTION

[0079] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0080] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0081] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0082] See also Figures 1 to 4 , the present application provides an intelligent garden plant selection method, comprising the following steps:

[0083] Step S1: Obtaining ecological condition data of the garden area;

[0084] Specifically, soil samples are collected for analysis of chemical composition and nutrient content to understand soil pH, nutrient content, and other information. Meteorological data for the garden area is collected, including temperature, humidity, rainfall, and seasonal climate change data. Vegetation in the garden area is surveyed to record information such as plant species, distribution, and growth status. Tools such as geographic information systems (GIS) are used to measure and analyze the topography of the garden area to understand terrain undulations, hydrological conditions, and other conditions.

[0085] Step S2: extracting ecological condition features according to the garden area ecological condition data to obtain ecological condition feature data;

[0086] Specifically, features such as soil pH and nutrient content are extracted from soil analysis. Features such as annual average temperature and seasonal changes in precipitation are extracted from climate data. Features such as plant diversity index and plant community structure are extracted from vegetation surveys. Features such as altitude, slope, and water system density are extracted from topographic and geomorphological measurements.

[0087] Step S3: performing plant characteristic matching according to the ecological condition characteristic data to obtain plant characteristic matching data;

[0088] Specifically, plants that are acid-tolerant and prefer specific nutrients are matched based on soil pH and nutrient content. Plants that are cold-tolerant, heat-tolerant, drought-tolerant and wet-tolerant are matched based on climate data. Plant species that grow naturally in the local area are matched based on vegetation survey data.

[0089] Step S4: performing an eco-friendly evaluation according to the plant characteristic matching data to obtain eco-friendly evaluation data;

[0090] Specifically, according to the matching data of plant characteristics, the impact of plants on the ecosystem is evaluated, including the growth rate of plants, the use of soil and water resources, the impact on local biodiversity, etc. The ecological characteristics of plants and the ecological conditions of the garden area are comprehensively considered to evaluate the adaptability and eco-friendliness of plants.

[0091] Step S5: Acquire the garden area spatial data, and generate a plant configuration plan based on the garden area spatial data and the eco-friendly evaluation data to obtain plant configuration plan data.

[0092] Specifically, determine the location and density of plant planting based on the spatial layout and vegetation requirements of the garden area. Select suitable plant species based on the eco-friendly assessment data and the ecological and environmental characteristics of the garden area. Determine the number of each plant to be planted based on factors such as plant growth requirements and stress resistance to maintain ecological balance and promote biodiversity. Based on the data and analysis results of the previous steps, formulate a specific plant configuration plan, including information such as the planting location, quantity, and density of each plant. Consider the interaction between plants, landscape beauty, and ecological benefits, and design a plant configuration plan that takes all factors into consideration. Evaluate the formulated plant configuration plan to check whether it meets the requirements of eco-friendliness and garden aesthetics. If necessary, adjust and optimize the plan to achieve the best ecological benefits and landscape effects.

[0093] Specifically, GIS software was used to perform spatial analysis of garden areas to identify different regional types and characteristics, such as sunlight exposure and terrain undulations. Eco-friendly assessment data was combined with spatial data to calculate the ecological suitability score for each area. Based on the growth requirements and adaptability of plants, a computer model was used to assess the adaptability of each plant in different areas. Plant configuration plans were generated based on the spatial analysis results, eco-friendly assessment data, and plant adaptability analysis results.

[0094] Combined with the eco-friendly assessment data, the ecological suitability score of each area is calculated, taking into account the impact of factors such as climate, soil, and water resources on plant growth. According to the growth requirements and environmental adaptability of plants, different plant species are matched with the characteristics of different regions to determine the suitability of plants in various regions. Multi-objective optimization algorithms, such as genetic algorithms or particle swarm optimization algorithms, are used to comprehensively consider spatial analysis, eco-friendly assessment data, and plant adaptability analysis results to generate the optimal plant configuration plan. Consider the constraints of garden planning, such as space limitations, landscape requirements, and resource availability, to ensure that the generated plan meets practical feasibility. The generated plant configuration plan is evaluated, including landscape effects, ecological benefits, and sustainability. Optimize and adjust the plant species, quantity, and distribution based on the evaluation results to achieve better ecological and environmental effects and aesthetic effects.

[0095] By obtaining the ecological condition data of the garden area and extracting the ecological condition characteristics in the present invention, the method can more accurately understand the ecological environment of the garden area, including the conditions of soil, hydrology, climate, etc., which helps to select plants that are more suitable for the current environment and improve the ecological adaptability of garden plants. By matching plant characteristics according to the ecological condition characteristic data, the characteristics of garden plants can be matched with environmental conditions and suitable plant species can be selected. In this way, the introduction of unsuitable plants can be avoided, the adverse effects of plants can be reduced, and the growth rate and survival rate of plants can be improved. By carrying out an eco-friendly assessment on the plant characteristic matching data, the degree of influence of plants on the environment can be assessed, including aspects such as its growth characteristics, water consumption, and nutrient requirements, which helps to select plants with less impact on the ecological environment and protect the health of the ecological environment. In combination with the garden area spatial data and the eco-friendly assessment data, a plant configuration scheme is generated, which can more reasonably plan and design the garden space, make the plant layout more beautiful and reasonable, and protect the ecological environment to the greatest extent.

[0096] Preferably, step S1 specifically includes:

[0097] Get garden location data;

[0098] Specifically, the location information of the garden is obtained from a map service or a geographic information system.

[0099] Extract longitude and latitude data according to the garden location data to obtain the garden longitude and latitude data;

[0100] Specifically, the acquired garden location data is processed to extract longitude and latitude information therein.

[0101] Searching for climate conditions and regional flora and fauna data according to the garden latitude and longitude data to obtain first garden climate condition data and regional flora and fauna data;

[0102] Specifically, the latitude and longitude information of the garden is used to search for climate condition data and regional flora and fauna data related to the location in the meteorological data and regional flora and fauna database, including querying historical meteorological data, local climate characteristics, vegetation distribution, flora and fauna species information, etc.

[0103] The garden meteorological data is collected through a sensor network preset in the garden to obtain the second garden climate condition data;

[0104] Specifically, a sensor network is deployed in the garden to collect real-time meteorological data in the garden, such as temperature, humidity, wind speed, etc., in order to obtain more accurate climate condition data.

[0105] Garden soil condition data is obtained, and the garden soil condition data, the first garden climate condition data, the regional flora and fauna data and the second garden climate condition data are integrated to obtain the garden area ecological condition data.

[0106] Specifically, garden soil samples are collected, and the soil chemical composition and nutrient content are analyzed to obtain garden soil condition data. Then the garden soil condition data, climate condition data, regional flora and fauna data, etc. are integrated to form complete garden area ecological condition data.

[0107] The present invention obtains and integrates various data such as the location, climate, and soil of the garden area, providing a complete data basis for subsequent plant selection and configuration. The meteorological data collected by the sensor can realize real-time monitoring and collection of garden climate conditions, improving the accuracy and practicality of the data. The search for regional animal and plant data and the acquisition of garden soil condition data provide a basis for selecting suitable garden plants, which helps to improve the ecological benefits and sustainable development level of garden landscapes.

[0108] Preferably, step S2 specifically includes:

[0109] Step S21: extracting ecological condition characteristics according to the garden area ecological condition data to obtain preliminary ecological condition characteristic data, wherein the preliminary ecological condition characteristic data includes climate characteristic data and soil characteristic data;

[0110] Specifically, according to the meteorological data of the garden area, climate characteristic data are extracted, including average temperature, precipitation, relative humidity, etc. For example, according to historical meteorological records, the climate type and seasonal variation patterns of the area where the garden is located are calculated. According to the results of soil sample analysis, soil characteristic data are extracted, including soil texture, organic matter content, pH value, etc. For example, the fertility and pH of the garden soil can be obtained through soil sample testing, or land soil data can be collected by accessing the database of the local geological department, and feature extraction can be performed.

[0111] Step S22: collecting garden images according to the garden location data to obtain garden image data;

[0112] Specifically, a camera is installed in the garden or aerial photography technology is used to collect images of the garden and obtain high-resolution image data of the garden. For example, an aerial drone is used to take aerial photos of the entire garden area to obtain a panoramic image.

[0113] Step S23: extracting garden vegetation features and garden terrain features according to the garden image data to obtain garden vegetation feature data and garden terrain feature data, wherein the garden vegetation feature data includes vegetation coverage feature data and vegetation height feature data, and the garden terrain feature data includes garden altitude feature data and garden surface slope feature data;

[0114] Specifically, the garden image is processed and analyzed to extract vegetation feature data, including vegetation coverage and vegetation height. For example, the range and height information of vegetation are extracted from the image using image segmentation and recognition algorithms. Based on the image data and geographic information, the garden terrain feature data is extracted, including altitude and surface slope. For example, the altitude and slope of each area of ​​the garden are calculated using digital elevation model (DEM) data.

[0115] Step S24: performing microecological characteristic association according to the garden vegetation characteristic data, the garden terrain characteristic data and the preliminary ecological condition characteristic data to obtain ecological condition characteristic data.

[0116] Specifically, based on the garden vegetation characteristics, garden terrain characteristics and ecological condition data, the correlation analysis of microecological characteristics is carried out to obtain comprehensive ecological condition characteristic data. For example, the microclimate environment of the garden area is evaluated by combining factors such as vegetation coverage, altitude and soil texture, so as to better understand the plant growth environment.

[0117] The present invention extracts the ecological condition characteristics, vegetation characteristics and terrain characteristics of the garden, which can fully reflect the ecological environment characteristics of the garden area, and provides comprehensive data support for subsequent plant selection and configuration. Through image acquisition and feature extraction, the acquired data is more intuitive and accurate, which can better reflect the actual situation of the garden, and provide more reliable data basis for subsequent plant selection and configuration. The microecological feature association step can comprehensively consider various factors such as vegetation, terrain and ecological conditions, and provide more comprehensive and accurate data support for subsequent plant characteristic matching, which helps to improve the ecological benefits and sustainable development level of garden landscape.

[0118] Preferably, step S24 is specifically:

[0119] Associating the garden vegetation characteristic data with the preliminary ecological condition characteristic data with ecological condition parameters to obtain first ecological condition characteristic data;

[0120] Specifically, the vegetation coverage and vegetation height data are used to correlate with the preliminary ecological condition characteristic data. For example, the influence of vegetation on climate can be determined by the correlation between vegetation coverage and climate characteristics in the preliminary ecological condition data.

[0121] Associating the garden terrain characteristic data with the preliminary ecological condition characteristic data with ecological condition parameters to obtain second ecological condition characteristic data;

[0122] Specifically, the data of garden terrain characteristics, such as altitude and surface slope, are associated with preliminary ecological condition characteristics data. This helps to determine the impact of terrain on ecological conditions, for example, the impact of altitude on climate and plant growth.

[0123] The first ecological condition characteristic data and the second ecological condition characteristic data are subjected to multi-dimensional graph mapping to obtain ecological condition characteristic data.

[0124] Specifically, the first ecological condition characteristic data and the second ecological condition characteristic data are mapped into a multidimensional graph to better understand the complex relationship of the ecological conditions. The high-dimensional data are mapped into a two-dimensional or three-dimensional space through multidimensional data dimensionality reduction techniques, such as principal component analysis (PCA) or t-distributed neighbor embedding (t-SNE).

[0125] Specifically, in another embodiment, the ecological condition feature data is constructed into a graph structure, where nodes represent features and edges represent relationships between features. Then, a graph neural network model, such as a graph convolutional network (GCN), is used to map the high-dimensional feature data into a low-dimensional graph space.

[0126] Specifically, in another embodiment, local linear embedding (LLE) or isometry mapping (Isomap) is used to map high-dimensional ecological condition feature data into a low-dimensional manifold space to capture the nonlinear structure of the data.

[0127] In the present invention, the garden vegetation characteristic data is associated with the preliminary ecological condition characteristic data to obtain the first ecological condition characteristic data, and the vegetation characteristics are associated with the ecological condition characteristics to more accurately reflect the relationship between the garden vegetation and the ecological environment. The garden terrain characteristic data is associated with the preliminary ecological condition characteristic data to obtain the second ecological condition characteristic data, and the terrain characteristics are associated with the ecological condition characteristics to more comprehensively consider the impact of the terrain on the ecological environment. The first ecological condition characteristic data and the second ecological condition characteristic data are multi-dimensionally mapped to obtain the ecological condition characteristic data, and the vegetation characteristics, terrain characteristics and ecological condition characteristics are deeply integrated to obtain more comprehensive and accurate ecological condition characteristic data.

[0128] Preferably, the plant characteristic matching data includes first plant characteristic matching data and second plant characteristic matching data, and step S3 is specifically as follows:

[0129] Step S31: Acquire plant data to be matched;

[0130] Specifically, plant-related data is obtained from plant databases or other resources, including plant names, characteristic descriptions, growth habits, suitable growth environments, etc. For example, plant information is obtained from botanical professional books, botanical garden materials, or Internet plant databases.

[0131] Step S32: mapping the ecological condition characteristic data to plant growth environment keywords to obtain plant growth environment keyword data;

[0132] Specifically, based on the climate, soil, and topography information in the ecological condition feature data, keywords are extracted and mapped to the plant growth environment keyword data. For example, climate conditions are mapped to descriptions such as "warm and humid", "cold and dry", and soil conditions are mapped to descriptions such as "sandy soil" and "loam".

[0133] Step S33: performing matching according to the plant to-be-matched data and the plant growth environment keyword data to obtain first plant characteristic matching data;

[0134] Specifically, the first plant characteristic matching data is obtained by matching the plant data to be matched and the plant growth environment keyword data. The plant characteristics and the growth environment are matched using a keyword matching algorithm or expert knowledge. For example, according to the plant growth condition requirements, plant species suitable for the current ecological conditions are matched.

[0135] Step S34: performing vectorization processing according to the plant data to be matched and the ecological condition characteristic data to obtain the plant vector data to be matched and the ecological condition characteristic vectorized data;

[0136] Specifically, the plant data to be matched and the ecological condition feature data are vectorized and converted into a numerical vector form. For example, the key features of the plant's growth requirements and ecological conditions are converted into numerical feature vectors for subsequent information entropy calculation and similarity matching.

[0137] Step S35: performing information entropy calculation on the plant to-be-matched vector data and the ecological condition feature quantized data to obtain the plant to-be-matched information entropy data and the ecological condition feature information entropy data;

[0138] Specifically, information entropy calculation is performed on the plant vector data to be matched and the quantized data of ecological condition features ( S is information entropy data, r l is the lth data, l is the data sequence item, and L is the number of data sets), and the information entropy data of plants to be matched and the information entropy data of ecological condition characteristics are obtained. Information entropy calculation can quantify the uncertainty and complexity of data and provide evaluation indicators for subsequent feature matching.

[0139] Step S36: performing information entropy similarity matching on the plant information entropy data to be matched and the ecological condition characteristic information entropy data to obtain second plant characteristic matching data;

[0140] Specifically, information entropy similarity matching is performed based on the information entropy data to be matched with the information entropy data of the ecological condition characteristics to obtain the second plant characteristic matching data. By calculating the similarity between the information entropies (the similarity calculation is performed using, for example, cosine similarity calculation or the calculation formula provided by the present invention), the matching degree between the plant characteristics and the ecological conditions is determined, thereby further screening out plants suitable for the current ecological conditions.

[0141] The information entropy similarity matching is specifically:

[0142]

[0143] S is the second plant characteristic matching data, e is the natural index term, d is the relative distance formula between the plant information entropy data to be matched and the ecological condition characteristic information entropy data, σ is the standard deviation data between the plant information entropy data to be matched and the ecological condition characteristic information entropy data, θ is the weather randomness influence parameter data, w is the plant information entropy data to be matched, and q is the ecological condition characteristic information entropy data.

[0144] Specifically, in one embodiment, the plant information entropy data to be matched obtained through the above steps is: w=3.5, the ecological condition characteristic information entropy data is: q=2.8, the standard deviation is: σ=0.5, and the weather randomness influence parameter is: θ=45°. The second plant characteristic matching data obtained after calculation is S≈2.103.

[0145] In the present invention, by obtaining the plant data to be matched, the system can understand the available plant species and related characteristics, and provide basic data for the subsequent matching process. Mapping the ecological condition characteristic data to the plant growth environment keywords helps to identify the growth adaptability of plants under different ecological conditions, so as to match more accurately. By matching the plant data to be matched with the ecological condition keywords, the first plant characteristic matching data can be obtained, which helps to determine the matching degree between the plant species and the ecological conditions of the park. The plant data to be matched and the ecological condition characteristic data are vectorized so that the data can be more conveniently mathematically calculated and analyzed, providing a data basis for subsequent steps. By calculating the information entropy of the plant data to be matched and the ecological condition characteristic data, the similarity or difference between them can be quantified, providing a more objective basis for subsequent matching. Through information entropy similarity matching, the matching degree between the plant and the ecological conditions can be more accurately evaluated, and then the second plant characteristic matching data can be obtained, so as to select the most suitable plant species. The selection based on experience and intuition of the conventional method is easily affected by personal subjective factors, resulting in the selection being not objective and scientific enough. The present invention uses ecological condition feature data and plant characteristic matching data, and uses computer algorithms and artificial intelligence technology to achieve intelligent matching of plants, thereby reducing the interference of subjective factors and improving the objectivity and scientificity of matching. The formula in the present invention converts the similarity between the plant data to be matched and the ecological condition data into a numerical value by calculating the relative distance and undergoing nonlinear mapping, which facilitates the quantitative comparison of the similarity. The weather randomness influence parameter is introduced, and the random influence of climate change on the matching result is considered, so that the matching result is more robust. The parameters w and q can be adjusted according to the specific situation to meet different matching requirements. Starting from the definition of similarity, the concept of information entropy and the idea of ​​distance measurement are used for deduction, and finally a formula is obtained. Compared with the conventional similarity formula (such as distance measurement algorithm), the degree of processing of the information behind the data is improved to better measure the similarity between the plant information entropy data to be matched and the ecological condition characteristic information entropy data, thereby matching plant characteristics.

[0146] Preferably, the plant information entropy data to be matched includes plant linear information entropy data to be matched and plant graph information entropy data to be matched, and the ecological condition characteristic information entropy data includes ecological condition characteristic linear information entropy data and ecological condition characteristic graph information entropy data, and step S35 is specifically as follows:

[0147] Performing linear information entropy calculation on the plant to-be-matched vector data and the ecological condition characteristic quantized data to obtain the plant to-be-matched linear information entropy data and the ecological condition characteristic linear information entropy data;

[0148] Specifically, there are the following plant vector data to be matched and ecological condition feature vector data: Plants Vector = [1.2, 2.3, 3.1, 4.5, 5.2, 6.8], Ecological Feature Vector = [0.5, 1.1, 2.3, 3.8, 4.2, 5.6]. Take θ i =45°. E≈-0.245.

[0149] The linear information entropy calculation is as follows:

[0150]

[0151] E is the linear information entropy data of plants to be matched or the linear information entropy data of ecological condition characteristics, n is the number of data sets, i is the data order item, p ... i is the linear information entropy data to be matched for the i-th plant or the linear information entropy data of ecological condition characteristics, θ i is the i-th random phase angle data;

[0152] Matrix processing is performed on the plant to-be-matched vector data and the ecological condition characteristic vector quantized data to obtain the plant to-be-matched matrix data and the ecological condition characteristic matrix data;

[0153] Specifically, the plant vector data to be matched and the ecological condition feature vector data are converted into a matrix form, where each row represents a sample and each column represents a feature. For example, the plant vector data to be matched [1.2, 2.3, 3.1, 4.5, 5.2, 6.8] is converted into a matrix form, where each element is a feature value of a sample.

[0154] Specifically, according to the characteristics of the plant vector data to be matched and the ecological condition feature vectorized data, determine the number of rows and columns of the matrix. The number of rows corresponds to different plant or ecological condition features, and the number of columns corresponds to the dimension of the vector or the number of features. According to the determined dimensions, create an empty matrix of the corresponding size. Fill the numerical values ​​in the plant vector data to be matched and the ecological condition feature vectorized data into the corresponding matrix positions according to certain rules, split and reorganize the vector data to ensure that it is correctly mapped to the position in the matrix. Plant vector data to be matched: 5,7,3,95,7,3,9. Ecological condition feature vectorized data: 2,4,6,82,4,6,8, convert it into matrix data according to the following steps: Determine the matrix dimension: choose to create a matrix with 2 rows and 4 columns. Construct the matrix: Create an empty matrix with 2 rows and 4 columns. Fill the matrix: fill the plant vector data to be matched into the first row, and fill the ecological condition feature vectorized data into the second row.

[0155] The graph information entropy is calculated for the plant to-be-matched matrix data and the ecological condition characteristic matrix data to obtain the plant to-be-matched graph information entropy data and the ecological condition characteristic graph information entropy data.

[0156] Specifically, there is a plant to-be-matched matrix data and an ecological condition characteristic matrix data, and a given graph information entropy calculation formula is used for calculation to obtain plant to-be-matched graph information entropy data and ecological condition characteristic graph information entropy data. Alternatively, a weighted method is used to use a conventional information entropy formula for calculation, and a corresponding preset weight is given to the characteristics of each row for weighted processing.

[0157] In the present invention, the complexity of the plant data to be matched and the ecological condition characteristic data can be quantified by calculating the linear information entropy. Linear information entropy is a measure of the complexity of the elements in the vector data set. By calculating the average value of the logarithm and the average value of each element, combined with the information of the probability of occurrence of the element, it can reflect the distribution and change trend of the data, help to understand the characteristics and laws of the data, and provide a basis for subsequent data analysis and processing. Graph information entropy is a measure of the complexity of the elements in the matrix data set. By calculating the graph information entropy, the complexity of the plant data to be matched and the ecological condition characteristic data can be more comprehensively evaluated. Graph information entropy can capture the association and interaction between elements in the data, reflect the overall structure and pattern of the data, and better reveal the inherent laws and characteristics of the data. Combining linear information entropy and graph information entropy, the complexity of the plant data to be matched and the ecological condition characteristic data can be comprehensively evaluated, providing a reference for subsequent data processing and feature matching. This helps to understand the nature and characteristics of the data more accurately and provide more reliable data support for intelligent garden plant selection. In the present invention, the complexity of the data can be evaluated by calculating the linear information entropy of the elements in the data set. Information entropy reflects the uncertainty and confusion of the data, so the higher the linear information entropy, the higher the complexity of the data. By calculating linear information entropy, the complexity of data can be quantified into a numerical value, which facilitates the comparison and analysis of differences between different data sets.

[0158] Preferably, the plant to-be-matched graph information entropy data includes the first plant to-be-matched graph information entropy data and the second plant to-be-matched graph information entropy data, the ecological condition characteristic graph information entropy data includes the first ecological condition characteristic graph information entropy data and the second ecological condition characteristic graph information entropy data, and the graph information entropy calculation is specifically as follows:

[0159] Calculating the graph information entropy of the plant to-be-matched matrix data and the ecological condition characteristic matrix data to obtain the first plant to-be-matched graph information entropy data and the first ecological condition characteristic graph information entropy data;

[0160] Specifically, for the given plant to-be-matched matrix data and ecological condition characteristic matrix data, the first plant to-be-matched graph information entropy data and the first ecological condition characteristic graph information entropy data are calculated according to the graph information entropy calculation formula.

[0161] The specific calculation of graph information entropy is:

[0162]

[0163] E is the information entropy data of the first plant to be matched graph or the information entropy data of the first ecological condition characteristic graph, j is the row coordinate data, M is the row quantity data, p is the column coordinate data, Q is the column quantity data, is the parameter correlation data, G jpis the difference value data corresponding to the hth row and the pth column in the plant matrix data to be matched and the ecological condition characteristic matrix data, h is the similarity data between the plant matrix data to be matched and the ecological condition characteristic matrix data, and k is the standard deviation data corresponding to the plant matrix data to be matched and the ecological condition characteristic matrix data;

[0164] Specifically, Where, M = 3, Q = 3. Set φ = 2, h = 0.5, k = 0.2. E ≈ 1.840.

[0165] Extracting periodic parameters of the plant to-be-matched matrix data and the ecological condition characteristic matrix data to obtain the plant to-be-matched periodic data and the ecological condition characteristic periodic data;

[0166] Specifically, the plant to-be-matched matrix data and the ecological condition characteristic matrix data are Fourier transformed to obtain the plant to-be-matched periodic data and the ecological condition characteristic periodic data. There is a time series containing 12 months of data, which represents the plant growth conditions or ecological condition characteristic values ​​for each month. First, the data is discrete Fourier transformed (DFT). According to the transformed spectrum, the main periodic components are identified, such as annual cycles, seasonal cycles, etc. By analyzing the amplitude and phase information of the spectrum, the amplitude and phase of each periodic component are extracted.

[0167] Performing frequency domain conversion processing on the plant periodic data to be matched and the ecological condition characteristic periodic data to obtain the plant frequency domain conversion data to be matched and the ecological condition characteristic frequency domain conversion data;

[0168] Specifically, the plant periodic data to be matched and the ecological condition characteristic periodic data are processed by FFT to obtain the plant frequency domain conversion data to be matched and the ecological condition characteristic frequency domain conversion data. For each month's data, a discrete Fourier transform (DFT) or a fast Fourier transform (FFT) is first performed. After obtaining the frequency domain data, the spectrum is analyzed to identify the main frequency components. The main frequency components in the spectrum are extracted, such as annual cycles, seasonal cycles, etc. According to the intensity and frequency information of the frequency domain data, the system obtains the changing patterns of plant growth or ecological condition characteristics at different frequencies.

[0169] Performing spectrum conversion on the plant to-be-matched frequency domain conversion data and the ecological condition characteristic frequency domain conversion data to obtain the plant to-be-matched frequency spectrum data and the ecological condition characteristic frequency spectrum data;

[0170] Specifically, a spectrum graph is drawn according to the plant to-be-matched frequency domain conversion data and the ecological condition characteristic frequency domain conversion data to obtain the plant to-be-matched spectrum graph data and the ecological condition characteristic spectrum graph data. The frequency domain data is converted into a spectrum graph, and a spectrum analysis method can be used, such as generating a spectrum graph by corresponding frequency to amplitude. Usually, the horizontal axis of the spectrum graph represents frequency, and the vertical axis represents amplitude or energy.

[0171] For each set of frequency domain conversion data, the Matplotlib library in Python is used to draw a spectrum. The horizontal axis represents frequency and the vertical axis represents amplitude or energy. Spectra are drawn for the plant frequency domain conversion data to be matched and the ecological condition characteristic frequency domain conversion data to compare their energy distribution at different frequencies. The spectrum is analyzed to observe the distribution and intensity of the frequency components to understand the characteristics of the data in the frequency domain.

[0172] Performing gradient calculation on the plant to-be-matched frequency spectrum data and the ecological condition characteristic frequency spectrum data to obtain the plant to-be-matched frequency spectrum gradient data and the ecological condition characteristic frequency spectrum gradient data;

[0173] Specifically, numerical differentiation is performed on the plant to-be-matched spectrum graph data and the ecological condition characteristic spectrum graph data to obtain the plant to-be-matched spectrum graph gradient data and the ecological condition characteristic spectrum graph gradient data. For each spectrum graph, its gradient is calculated. The gradient is calculated using the central difference method. For each frequency point in each spectrum graph, the energy difference between the previous and next frequency points is calculated and divided by the frequency interval to obtain the gradient value.

[0174] For each spectrum graph, first select the appropriate frequency interval and frequency range. For each frequency point in each spectrum graph, calculate its gradient value. Repeat the above steps until the gradient of the entire spectrum graph is calculated. For the plant to-be-matched spectrum graph data and the ecological condition characteristic spectrum graph data, calculate their gradients respectively.

[0175] Information entropy calculation is performed on the gradient data of the plant spectrum map to be matched and the gradient data of the ecological condition characteristic spectrum map to obtain information entropy data of the second plant map to be matched and information entropy data of the second ecological condition characteristic map.

[0176] Specifically, the information entropy data of the plant to-be-matched graph and the information entropy data of the ecological condition characteristic graph are calculated according to the information entropy calculation formula. For each spectrum graph gradient data, the gradient value is first normalized and converted into a probability distribution. For each spectrum graph gradient data, the information entropy is calculated according to the probability distribution of the gradient value. Repeat the above steps until the information entropy of the entire spectrum graph gradient data is calculated. For the plant to-be-matched spectrum graph gradient data and the ecological condition characteristic spectrum graph gradient data, their information entropies are calculated respectively.

[0177] In the present invention, by calculating the information entropy of frequency domain features, the complexity of data in the frequency domain can be evaluated. Frequency domain features reflect the changes in the frequency distribution of data, so the higher the graph information entropy, the more complex the frequency domain features of the data. By calculating the graph information entropy, the periodicity and frequency domain characteristics of the data can be quantified into a numerical value, which is convenient for comparing and analyzing the differences between different data. Through the steps of frequency domain conversion, spectrum graph conversion and gradient calculation, the characteristics of the data in the frequency domain can be effectively extracted, thereby providing similarity characteristics of the description data based on periodic parameters, rather than simply comparing. Spectrum graph conversion and gradient calculation can convert data into spectrum graphs and spectrum graph gradient data, which can better reflect the spatial distribution and change trend of the data and improve the characterization ability of the data. The information entropy calculation utilizes the spectrum graph gradient data, which can more accurately measure the similarity between the plant data to be matched and the ecological condition characteristic data, thereby realizing more accurate graph information entropy calculation. The data body of graph information entropy data is a matrix. The horizontal data items of the source graph are data of different dimensions, and the vertical data items are different sub-dimensions in the same dimension (such as cold resistance, heat resistance, timing and other temperature influencing factors corresponding to temperature). It reveals the complexity and diversity behind the data, making the characteristic representation more prominent, rather than simply calculating a single data, or the high computational complexity caused by linear calculations. It quantifies the complexity and uncertainty of the data and provides important information about the distribution and structure of the data.

[0178] Preferably, step S4 is specifically:

[0179] According to the plant characteristics matching data, the water and soil impact processing is carried out to obtain the water and soil impact assessment data;

[0180] Specifically, based on the plant's growth characteristics, root conditions, water requirements and other characteristics, the plant's absorption and utilization of soil moisture, texture and nutrients is evaluated, and then its impact on the soil, including water balance, soil fertility and soil structure, is analyzed, and soil and water impact assessment data is generated accordingly.

[0181] Process the food chain impact based on the regional animal and plant data and plant characteristic matching data to obtain food chain impact assessment data;

[0182] Specifically, by combining the geographical location of the garden area with the plant characteristics matching data, we analyze the impact of plants on the local ecosystem, including the impact on the local flora and fauna, the maintenance of ecological balance, and the stability of the ecosystem, and then generate food chain impact assessment data.

[0183] Generate eco-friendly assessment data based on soil and water impact assessment data and food chain impact assessment data.

[0184] Specifically, the comprehensive impact of water and soil and food chain on the garden ecological environment is considered, and comprehensive evaluation and analysis are carried out to generate eco-friendly evaluation data. These evaluation data can help evaluate the impact of garden plant selection on the ecosystem, thereby guiding reasonable plant configuration and management measures to achieve the eco-friendly goals of the garden.

[0185] In the present invention, by matching data according to plant characteristics to process the impact of soil and water and processing the impact of the food chain according to regional animal and plant data, the method comprehensively considers the impact of soil and water conditions and the biological environment on garden plants, thereby more comprehensively evaluating the adaptability and growth of plants. By generating eco-friendly evaluation data, the method helps to guide garden planning and design, so that the selected plants are more in line with the local ecological environment and climatic conditions, thereby improving the ecological friendliness of the garden. By considering the impact of soil and water and the food chain, the environmental risks brought about by the introduction of unsuitable plants or animal and plant species can be reduced to prevent them from having a negative impact on the local ecosystem. The generation of eco-friendly evaluation data helps to select plants and food chain combinations that are more adaptable and will not destroy the ecological balance, thereby promoting the healthy development of the garden ecosystem and the maintenance of the ecological balance.

[0186] Preferably, the plant configuration scheme data includes first plant configuration scheme data and second plant configuration scheme data, and step S5 is specifically as follows:

[0187] Obtain spatial data of garden areas;

[0188] Specifically, spatial data of the garden area, including topography, land use, geographical location and other information, is obtained through technical means such as geographic information system (GIS).

[0189] Extract plant placement space according to garden area spatial data to obtain plant placement space data;

[0190] Specifically, through spatial analysis methods, areas in the garden area that are suitable for growing plants are identified, and the placement and spatial range of the plants are determined.

[0191] Generate an economical plant configuration plan based on the plant placement space data and the eco-friendly evaluation data to obtain first plant configuration plan data;

[0192] Specifically, combining the spatial conditions of the garden area and the eco-friendly assessment data, economic indicators (such as cost, maintenance difficulty, etc.) are used as optimization goals to generate an economical plant configuration plan to achieve economically reasonable plant layout and management.

[0193] A plant configuration plan with minimum human intervention is generated according to the plant placement space data and the eco-friendly assessment data to obtain second plant configuration plan data.

[0194] Specifically, considering the need to minimize human intervention, a plant configuration plan with minimum human intervention is designed according to the characteristics of the garden area and eco-friendly assessment data, so as to reduce labor costs and maintenance workload while maintaining the ecological balance and aesthetics of the garden.

[0195] In the present invention, by acquiring the spatial data of the garden area and extracting the plant placement space, the layout of the plants can be optimized to ensure that the spacing between the plants is appropriate, avoiding crowding or excessive sparseness, so that the entire garden space is used more reasonably. By generating an economical plant configuration plan based on the plant placement space data and the eco-friendly evaluation data, factors such as the cost, maintenance and management of the plants can be considered, making the configuration plan more economically reasonable and feasible. By generating a plant configuration plan with minimal human intervention, the manpower cost of garden management and maintenance can be reduced, and the operating efficiency and sustainability of the garden can be improved. This method takes into account the ecological adaptability and environmental friendliness of the plants, so that the configured plants are more in line with the local ecological environment and climatic conditions, which is conducive to the healthy and stable development of the garden ecosystem.

[0196] Preferably, an intelligent garden plant selection system is used to execute the intelligent garden plant selection method as described above, and the intelligent garden plant selection system comprises:

[0197] The garden area ecological condition data collection module is used to obtain the garden area ecological condition data;

[0198] The ecological condition feature extraction module is used to extract the ecological condition features according to the ecological condition data of the garden area to obtain the ecological condition feature data;

[0199] A plant characteristic matching module is used to match plant characteristics according to ecological condition characteristic data to obtain plant characteristic matching data;

[0200] An eco-friendly evaluation module, used to perform eco-friendly evaluation according to plant characteristic matching data to obtain eco-friendly evaluation data;

[0201] The plant configuration scheme generation module is used to obtain the garden area spatial data, and generate a plant configuration scheme based on the garden area spatial data and the eco-friendly evaluation data to obtain the plant configuration scheme data.

[0202] The beneficial effects of the present invention are as follows: by extracting ecological condition characteristic data and matching plant characteristics, it is possible to select plant species that match the specific ecological conditions of the garden area, so that the selection of plants is more adapted to the actual situation of the garden, which is conducive to improving the growth and survival rate of plants. By carrying out an eco-friendly evaluation on plant characteristic matching data, the degree of influence of plants on the garden ecosystem can be evaluated, including its influence on soil, water source, air quality, etc., which helps to select plants with less impact on the ecological environment and protect the ecological balance and environmental sustainability of the garden. Combining the spatial data of the garden area and the eco-friendly evaluation data, a plant configuration scheme can be generated to optimize the layout of garden plants. By rationally planning the spatial position of plants, the overall aesthetics and ecological benefits of the garden can be improved. The method comprehensively considers factors such as the ecological conditions, plant characteristics and spatial layout of the garden, so that plant selection and configuration are more comprehensive and scientific, improves the overall quality and environmental adaptability of the garden, and enhances the ecological function and ornamental value of the garden.

[0203] Therefore, from any point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the attached application documents rather than the above description, and it is intended that all changes falling within the meaning and scope of equivalent elements of the application documents are included in the present invention.

[0204] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent garden plant selection method, characterized in that: The following steps are involved: Step S1: Obtaining ecological condition data of the garden area; Step S2: extracting ecological condition features according to the garden area ecological condition data to obtain ecological condition feature data; Step S3: performing plant characteristic matching according to the ecological condition characteristic data to obtain plant characteristic matching data; Step S4: performing an eco-friendly evaluation according to the plant characteristic matching data to obtain eco-friendly evaluation data; Step S5: obtaining the garden area spatial data, and generating a plant configuration plan according to the garden area spatial data and the eco-friendly evaluation data to obtain plant configuration plan data; The plant characteristic matching data includes first plant characteristic matching data and second plant characteristic matching data, and step S3 is specifically as follows: Step S31: Obtain plant data to be matched; Step S32: mapping the ecological condition characteristic data to plant growth environment keywords to obtain plant growth environment keyword data; Step S33: performing matching according to the plant to-be-matched data and the plant growth environment keyword data to obtain first plant characteristic matching data; Step S34: performing vectorization processing according to the plant data to be matched and the ecological condition characteristic data to obtain the plant vector data to be matched and the ecological condition characteristic vectorized data; Step S35: performing information entropy calculation on the plant to-be-matched vector data and the ecological condition feature quantized data to obtain the plant to-be-matched information entropy data and the ecological condition feature information entropy data; Step S36: performing information entropy similarity matching on the plant information entropy data to be matched and the ecological condition characteristic information entropy data to obtain second plant characteristic matching data; wherein the information entropy similarity matching is specifically: ； Matching data for the second plant characteristic, is the natural exponential term, is the relative distance formula between the information entropy data to be matched by the plant and the information entropy data of ecological condition characteristics, is the standard deviation data between the information entropy data to be matched by the plant and the information entropy data of ecological condition characteristics, is the parameter data of weather randomness, is the information entropy data to be matched by the plant, It is the information entropy data of ecological condition characteristics.

2. The method according to claim 1, characterized in that Step S1 is specifically as follows: Get garden location data; Extract longitude and latitude data according to the garden location data to obtain the garden longitude and latitude data; Searching for climate conditions and regional flora and fauna data according to the garden latitude and longitude data to obtain first garden climate condition data and regional flora and fauna data; The garden meteorological data is collected through a sensor network preset in the garden to obtain the second garden climate condition data; Garden soil condition data is obtained, and the garden soil condition data, the first garden climate condition data, the regional flora and fauna data and the second garden climate condition data are integrated to obtain the garden area ecological condition data.

3. The method according to claim 2, characterized in that Step S2 is specifically as follows: Step S21: extracting ecological condition characteristics according to the garden area ecological condition data to obtain preliminary ecological condition characteristic data, wherein the preliminary ecological condition characteristic data includes climate characteristic data and soil characteristic data; Step S22: collecting garden images according to the garden location data to obtain garden image data; Step S23: extracting garden vegetation features and garden terrain features according to the garden image data to obtain garden vegetation feature data and garden terrain feature data, wherein the garden vegetation feature data includes vegetation coverage feature data and vegetation height feature data, and the garden terrain feature data includes garden altitude feature data and garden surface slope feature data; Step S24: performing microecological characteristic association according to the garden vegetation characteristic data, the garden terrain characteristic data and the preliminary ecological condition characteristic data to obtain ecological condition characteristic data.

4. The method according to claim 3, characterized in that Step S24 is specifically as follows: Associating the garden vegetation characteristic data with the preliminary ecological condition characteristic data with ecological condition parameters to obtain first ecological condition characteristic data; Associating the garden terrain characteristic data with the preliminary ecological condition characteristic data with ecological condition parameters to obtain second ecological condition characteristic data; The first ecological condition characteristic data and the second ecological condition characteristic data are subjected to multi-dimensional graph mapping to obtain ecological condition characteristic data.

5. The method according to claim 1, characterized in that: The plant information entropy data to be matched includes plant linear information entropy data to be matched and plant graph information entropy data to be matched, and the ecological condition characteristic information entropy data includes ecological condition characteristic linear information entropy data and ecological condition characteristic graph information entropy data. Step S35 is specifically as follows: The linear information entropy calculation is performed on the plant to-be-matched vector data and the ecological condition characteristic quantized data to obtain the plant to-be-matched linear information entropy data and the ecological condition characteristic linear information entropy data; the linear information entropy calculation is specifically as follows: ； is the linear information entropy data of plants to be matched or the linear information entropy data of ecological condition characteristics, is the number of data sets, is the data sequence item, For the Plant vector data to be matched or ecological condition feature vector data, For the Random phase angle data; Matrix processing is performed on the plant to-be-matched vector data and the ecological condition characteristic vector quantized data to obtain the plant to-be-matched matrix data and the ecological condition characteristic matrix data; The graph information entropy is calculated for the plant to-be-matched matrix data and the ecological condition characteristic matrix data to obtain the plant to-be-matched graph information entropy data and the ecological condition characteristic graph information entropy data.

6. The method according to claim 5, characterized in that The information entropy data of the plant to-be-matched graph includes the information entropy data of the first plant to-be-matched graph and the information entropy data of the second plant to-be-matched graph, and the information entropy data of the ecological condition characteristic graph includes the information entropy data of the first ecological condition characteristic graph and the information entropy data of the second ecological condition characteristic graph. The graph information entropy calculation is specifically as follows: The graph information entropy is calculated for the plant to-be-matched matrix data and the ecological condition characteristic matrix data to obtain the first plant to-be-matched graph information entropy data and the first ecological condition characteristic graph information entropy data; the graph information entropy calculation is specifically as follows: ； is the information entropy data of the first plant to-be-matched graph or the information entropy data of the first ecological condition characteristic graph, is the row coordinate data, is the row number data, is the column coordinate data, is the column quantity data, is the parameter correlation data, The first Line The difference value data corresponding to the column, is the similarity data of the plant matrix data to be matched and the ecological condition characteristic matrix data, The standard deviation data corresponding to the plant matrix data to be matched and the ecological condition characteristic matrix data; Extracting periodic parameters of the plant to-be-matched matrix data and the ecological condition characteristic matrix data to obtain the plant to-be-matched periodic data and the ecological condition characteristic periodic data; Performing frequency domain conversion processing on the plant periodic data to be matched and the ecological condition characteristic periodic data to obtain the plant frequency domain conversion data to be matched and the ecological condition characteristic frequency domain conversion data; Performing spectrum conversion on the plant to-be-matched frequency domain conversion data and the ecological condition characteristic frequency domain conversion data to obtain the plant to-be-matched frequency spectrum data and the ecological condition characteristic frequency spectrum data; Performing gradient calculation on the plant to-be-matched frequency spectrum data and the ecological condition characteristic frequency spectrum data to obtain the plant to-be-matched frequency spectrum gradient data and the ecological condition characteristic frequency spectrum gradient data; Information entropy calculation is performed on the gradient data of the plant spectrum map to be matched and the gradient data of the ecological condition characteristic spectrum map to obtain information entropy data of the second plant map to be matched and information entropy data of the second ecological condition characteristic map.

7. The method according to claim 2, characterized in that: Step S4 is specifically as follows: According to the plant characteristics matching data, the water and soil impact processing is carried out to obtain the water and soil impact assessment data; Process the food chain impact based on the regional animal and plant data and plant characteristic matching data to obtain food chain impact assessment data; Generate eco-friendly assessment data based on soil and water impact assessment data and food chain impact assessment data.

8. The method according to claim 1, characterized in that: The plant configuration scheme data includes the first plant configuration scheme data and the second plant configuration scheme data, and step S5 is specifically as follows: Obtain spatial data of garden areas; Extract plant placement space according to garden area spatial data to obtain plant placement space data; Generate an economical plant configuration plan based on the plant placement space data and the eco-friendly evaluation data to obtain first plant configuration plan data; A plant configuration plan with minimum human intervention is generated according to the plant placement space data and the eco-friendly assessment data to obtain second plant configuration plan data.

9. An intelligent garden plant selection system, characterized in that: Used to execute the intelligent garden plant selection method as claimed in claim 1, the intelligent garden plant selection system comprises: The garden area ecological condition data collection module is used to obtain the garden area ecological condition data; The ecological condition feature extraction module is used to extract ecological condition features according to the ecological condition data of the garden area to obtain ecological condition feature data; A plant characteristic matching module is used to match plant characteristics according to ecological condition characteristic data to obtain plant characteristic matching data; An eco-friendly evaluation module, used to perform eco-friendly evaluation according to plant characteristic matching data to obtain eco-friendly evaluation data; The plant configuration scheme generation module is used to obtain the garden area spatial data, and generate a plant configuration scheme based on the garden area spatial data and the eco-friendly evaluation data to obtain the plant configuration scheme data.

Images