Landscaping configuration method based on big data

Abstract

The invention discloses a landscaping configuration method based on big data, relates to the technical field of data processing, and can solve the technical problem of how to improve the accuracy and environmental adaptability of landscaping plant configuration recommendation based on big data, and the method comprises the steps: obtaining the garden data of a to-be-configured garden and a plurality of reference gardens; wherein the garden data comprises environment data, scale data and plant configuration data; determining an environmental sensitivity coefficient of each type of plants according to the environmental data and the plant configuration data of the plurality of reference gardens; according to the environment data of each reference garden, the environment sensitivity coefficient of each type of plants and the garden data of the to-be-configured garden, the comprehensive similarity of each reference garden and the to-be-configured garden on each type of plants is determined; determining the recommendation degree of each type of plants according to the comprehensive similarity of each reference garden and the to-be-configured garden on each type of plants and the plant configuration data of each reference garden; and performing plant configuration on the to-be-configured garden according to the recommendation degree.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to a landscaping configuration method based on big data. BACKGROUND

[0002] Landscape greening is an important part of urban ecology and landscape planning, and its reasonable layout plays a key role in improving the quality of living environment and promoting ecological balance. Traditional garden plant configuration relies on artificial experience, and it is difficult to systematically consider various environmental factors and plant growth characteristics, resulting in limitations in design efficiency and scientificity. With the development of big data technology, some studies have attempted to use recommendation algorithms such as collaborative filtering to analyze historical garden data, and to provide plant configuration reference for new garden projects by calculating the similarity of plant planting proportions.

[0003] However, the existing method usually only matches based on plant species or proportion when measuring the similarity between gardens, and fails to fully integrate multi-dimensional influencing factors such as environmental conditions and garden size, resulting in insufficient adaptability and accuracy of the recommended results in the actual planting environment, affecting the overall effect and feasibility of plant configuration. SUMMARY

[0004] In order to solve the technical problem of how to improve the accuracy and environmental adaptability of the current big data-based garden plant configuration recommendation, the purpose of the present application is to provide a landscaping configuration method based on big data, and the technical solution adopted is as follows: In a first aspect, the present application provides a landscaping configuration method based on big data, comprising: obtaining garden data of a to-be-configured garden and a plurality of reference gardens; wherein the garden data comprises environmental data, size data and plant configuration data; determining the environmental sensitivity coefficient of each plant according to the environmental data and plant configuration data of the plurality of reference gardens; wherein the environmental sensitivity coefficient is used to represent the sensitivity of each plant to environmental changes; determining the comprehensive similarity of each reference garden and the to-be-configured garden on each plant according to the environmental data of each reference garden, the environmental sensitivity coefficient of each plant and the garden data of the to-be-configured garden; determining the recommendation degree of each plant according to the comprehensive similarity of each reference garden and the to-be-configured garden on each plant, and the plant configuration data of each reference garden; and performing plant configuration on the to-be-configured garden according to the recommendation degree.

[0005] In one possible implementation, environmental data is used to characterize the soil conditions and climate of the garden, and plant configuration data is used to characterize the number of plant species and the proportion of each plant species in the garden. Based on the environmental data and plant configuration data of multiple reference gardens, the environmental sensitivity coefficient of each plant species is determined. Specifically, this includes: determining the planting extent of each plant species in the reference gardens based on the number of gardens in which each plant species is planted and the total number of all reference gardens; determining the environmental parameter range of each plant species in multiple environmental dimensions based on the environmental data of multiple gardens; wherein, the environmental parameter range is used to characterize the range of parameter variation of each plant species in environmental dimensions; and determining the environmental sensitivity coefficient based on the planting extent of each plant species and the environmental parameter range in multiple environmental dimensions.

[0006] In one possible implementation, scale data is used to characterize the area occupied by the garden; based on the environmental data of each reference garden, the environmental sensitivity coefficient of each plant type, and the garden data of the garden to be configured, the comprehensive similarity between each reference garden and the garden to be configured in each plant type is determined. Specifically, this includes: determining the environmental similarity between each reference garden and the garden to be configured in each plant type based on the environmental data of the reference garden and the environmental data of the garden to be configured; determining the scale similarity between each reference garden and the garden to be configured based on the scale data of the reference garden and the scale data of the garden to be configured; and determining the comprehensive similarity between each reference garden and the garden to be configured in each plant type based on the environmental similarity, scale similarity, and environmental sensitivity coefficient.

[0007] In one possible implementation, based on the environmental data of the reference garden and the environmental data of the garden to be configured, the environmental similarity between each reference garden and the garden to be configured for each type of plant is determined. Specifically, this includes: determining the parameter differences between each reference garden and the garden to be configured for each environmental dimension based on the environmental data of each reference garden and the environmental data of the garden to be configured; determining a total deviation parameter, which is used to characterize the sum of the degree of deviation of each reference garden and the garden to be configured from the suitable growth range of each type of plant in each environmental dimension; and determining the environmental similarity between each reference garden and the garden to be configured for each type of plant based on the parameter differences of all environmental dimensions and the total deviation parameter.

[0008] In one possible implementation, the scale similarity between each reference garden and the garden to be configured is determined based on the scale data of the reference garden and the scale data of the garden to be configured. Specifically, this includes: determining the difference in land area between each reference garden and the garden to be configured based on the scale data of the reference garden and the scale data of the garden to be configured; and determining the scale similarity between each reference garden and the garden to be configured based on the difference in land area between each reference garden and the garden to be configured, as well as the number of plant species in each reference garden.

[0009] In one possible implementation, the comprehensive similarity between each reference garden and the garden to be configured for each type of plant is determined based on environmental similarity, scale similarity, and environmental sensitivity coefficient. Specifically, this includes determining the first weight of environmental similarity and the second weight of scale similarity based on the environmental sensitivity coefficient. Based on environmental similarity, scale similarity, first weight, and second weight, the overall similarity between each reference garden and the garden to be configured is determined for each type of plant.

[0010] In one possible implementation, the recommendation level for each type of plant is determined based on the overall similarity between each reference garden and the garden to be configured for each type of plant, and the plant configuration data of each reference garden. Specifically, this includes: for each reference garden and each type of plant, determining the score of each reference garden for each type of plant based on the plant configuration data of each reference garden; and for each type of plant, determining the recommendation level for each type of plant based on the overall similarity of all reference gardens and the scores for each type of plant.

[0011] In one possible implementation, a score for each type of plant is determined for each reference garden based on the plant configuration data of each reference garden. Specifically, this includes: if each type of plant is planted in the reference garden, the percentage of the planting area of ​​each type of plant in the reference garden is used as the score; if each type of plant is not planted in the reference garden, the negative value of the average percentage of the planting area of ​​each type of plant in all reference gardens is used as the score.

[0012] In one possible implementation, the plants in the garden to be configured are arranged according to the recommendation level, specifically including: sorting each type of plant from high to low recommendation level to form a recommendation sequence; selecting plants to be configured according to the recommendation sequence to determine the final plant configuration scheme.

[0013] In one possible implementation, when acquiring garden data from multiple reference gardens, a reference garden located in the same or adjacent ecological zone as the garden to be configured is selected.

[0014] Secondly, this invention provides a big data-based landscape greening configuration system, comprising: a data acquisition module for acquiring landscape data of the landscape to be configured and multiple reference landscapes; wherein the landscape data includes environmental data, scale data, and plant configuration data; an environmental sensitivity assessment module 12 for determining the environmental sensitivity coefficient of each type of plant based on the environmental data and plant configuration data of multiple reference landscapes; wherein the environmental sensitivity coefficient is used to characterize the sensitivity of each type of plant to environmental changes; a comprehensive similarity assessment module 13 for determining the comprehensive similarity between each reference landscape and the landscape to be configured in each type of plant based on the environmental data of each reference landscape, the environmental sensitivity coefficient of each type of plant, and the landscape data of the landscape to be configured; a recommendation degree calculation module 14 for determining the recommendation degree of each type of plant based on the comprehensive similarity between each reference landscape and the landscape to be configured in each type of plant, and the plant configuration data of each reference landscape; and a plant configuration module 15 for configuring plants in the landscape to be configured based on the recommendation degree.

[0015] Thirdly, the present invention provides an electronic device, comprising: a processor and a memory; wherein the memory is used to store one or more programs, the one or more programs including computer execution instructions, and when the electronic device is running, the processor executes the computer execution instructions stored in the memory to cause the electronic device to perform the big data-based landscaping configuration method as described in the first aspect and any possible implementation thereof.

[0016] Fourthly, the present invention provides a computer-readable storage medium for storing one or more programs, the one or more programs including instructions that, when executed by an electronic device of the present invention, cause the electronic device to perform the big data-based landscaping configuration method as described in the first aspect and any possible implementation thereof.

[0017] Fifthly, the present invention provides a computer program product containing instructions that, when executed on a computer, cause the electronic device of the present invention to perform the big data-based landscaping configuration method as described in the first aspect and any possible implementation thereof.

[0018] Sixthly, the present invention provides a chip system applied to a big data-based landscaping configuration device; the chip system includes one or more interface circuits and one or more processors. The interface circuits and the processors are interconnected via lines; the interface circuits are used to receive signals from the memory of the big data-based landscaping configuration device and send the signals to the processors, the signals including computer instructions stored in the memory. When the processor executes the computer instructions, the big data-based landscaping configuration device performs the big data-based landscaping configuration method as described in the first aspect and any possible design of the first aspect.

[0019] This invention has the following beneficial effects: By integrating multi-dimensional environmental data and garden scale characteristics, it innovatively introduces a plant environmental sensitivity coefficient to achieve dynamic weight allocation, and constructs a plant recommendation model based on comprehensive similarity assessment, which significantly improves the scientificity and adaptability of garden plant configuration; this scheme effectively overcomes the subjectivity and data coverage limitations of traditional methods that rely on human experience, and at the same time solves the problem that existing recommendation algorithms ignore environmental adaptability, ultimately achieving the optimization of landscape effects while ensuring the ecological suitability of plants, and providing accurate and efficient decision support for landscape garden greening layout. Attached Figure Description

[0020] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of the architecture of a big data-based landscaping configuration system provided in one embodiment of the present invention; Figure 2 This is a schematic diagram of the architecture of a comprehensive similarity evaluation module provided in one embodiment of the present invention; Figure 3 This is a schematic diagram of the architecture of a recommendation calculation module provided in one embodiment of the present invention; Figure 4 This is a flowchart illustrating a big data-based landscaping configuration method according to an embodiment of the present invention. Figure 5 This is a flowchart illustrating a big data-based landscaping configuration method according to an embodiment of the present invention. Figure 6 This is a flowchart illustrating a big data-based landscaping configuration method according to an embodiment of the present invention. Figure 7 This is a flowchart illustrating a big data-based landscaping configuration method provided in one embodiment of the present invention. Detailed Implementation

[0022] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the specific implementation methods, structures, features, and effects of the present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0024] In all division and logarithmic operations involved in this invention, a smoothing mechanism is employed to prevent computer program crashes or invalid values ​​from being generated due to a zero denominator or zero input. Specifically, a positive correction factor ε (e.g., 10 to the power of negative 5) is superimposed on the denominator term of the division operation or the argument term of the logarithmic function to ensure the robustness and feasibility of the algorithm under extreme conditions.

[0025] The following description, in conjunction with the accompanying drawings, details a specific scheme for a big data-based landscape greening configuration method provided by the present invention.

[0026] For example, such as Figure 1 The diagram shown illustrates the architecture of a big data-based landscaping configuration system according to an embodiment of the present invention. The landscaping configuration system 10 includes: a data acquisition module 11, an environmental sensitivity assessment module 12, a comprehensive similarity assessment module 13, a recommendation calculation module 14, and a plant configuration module 15. The modules are described below in sequence: (1) Data acquisition module 11.

[0027] The data acquisition module 11 is responsible for collecting garden data from the garden to be configured and multiple reference gardens, providing raw data support for the calculations of all subsequent modules. The environmental data, scale data, and plant configuration data output by the data acquisition module 11 will directly serve as the core input source for the environmental sensitivity assessment module 12, the comprehensive similarity assessment module 13, and the recommendation calculation module 14.

[0028] Optionally, the data acquisition module 11 is used to acquire garden data of the garden to be configured and multiple reference gardens. The garden data includes environmental data, scale data, and plant configuration data. Environmental data characterizes the soil conditions and climate of the garden; plant configuration data characterizes the number of plant species in the garden and the percentage of each species planted; and scale data characterizes the area of ​​the garden.

[0029] For example, the data acquisition module 11 collects three types of core data for the reference garden and the garden to be configured: environmental data, including soil conditions and climate conditions, such as soil pH value, soil organic matter content, monthly temperature range, monthly minimum temperature, monthly maximum temperature, and monthly average precipitation; scale data, including the garden area; and plant configuration data, including the number of plant species currently planted in the garden and the planting area ratio of each plant species.

[0030] (2) Environmental Sensitivity Assessment Module 12.

[0031] The environmental sensitivity assessment module 12 is responsible for calculating the environmental sensitivity coefficient for each type of plant based on the reference garden environment data and plant configuration data output by the data acquisition module 11. This environmental sensitivity coefficient is used to characterize the sensitivity of each type of plant to environmental changes and is a key basis for the "weight allocation of environmental similarity and scale similarity" in the subsequent comprehensive similarity assessment module 13.

[0032] Optionally, the environmental sensitivity assessment module 12 is used to determine the environmental sensitivity coefficient of each type of plant based on environmental data and plant configuration data from multiple reference gardens.

[0033] For example, the environmental sensitivity assessment module 12 first counts the planting prevalence of each type of plant in the reference gardens. Specifically, for the i-th type of plant, all reference gardens planting this type of plant are selected, and the ratio of its number n to the total number of reference gardens N is calculated. The larger the ratio, the stronger the plant's adaptability.

[0034] Subsequently, the environmental sensitivity assessment module 12 calculates the cumulative range of parameters for each plant type across multiple environmental dimensions. Based on five dimensions—soil pH, organic matter content, monthly average precipitation, monthly minimum temperature, and monthly maximum temperature—the range of each dimension for each plant type within the planting area is calculated, and the cumulative product of the ranges of all dimensions is obtained. The larger this value, the stronger the plant's tolerance to environmental changes.

[0035] Finally, the environmental sensitivity assessment module 12 calculates the environmental sensitivity coefficient by combining the product of planting extent and range using an inverse proportional normalization formula. Specifically, the coefficient is equal to the negative exponent of the product of planting extent and range, with the result ranging from 0 to 1. A larger coefficient indicates greater plant sensitivity to the environment, resulting in a higher weighting of environmental factors in subsequent similarity assessments. The environmental sensitivity assessment module 12 outputs the environmental sensitivity coefficients of all plants to the comprehensive similarity assessment module 13 for further processing.

[0036] (3) Comprehensive similarity assessment module 13.

[0037] The comprehensive similarity assessment module 13 is responsible for combining the data of the garden to be configured and the reference garden from the data acquisition module 11 and the environmental sensitivity coefficient from the environmental sensitivity assessment module 12 to calculate the comprehensive similarity of each reference garden and the garden to be configured for each type of plant.

[0038] Optionally, the comprehensive similarity assessment module 13 is used to determine the comprehensive similarity between each reference garden and the garden to be configured in each type of plant, based on the environmental data of each reference garden, the environmental sensitivity coefficient of each type of plant, and the garden data of the garden to be configured.

[0039] For example, such as Figure 2 As shown, the comprehensive similarity assessment module 13 may include three sub-modules: an environmental similarity calculation module 131, a scale similarity calculation module 132, and a comprehensive similarity weighting sub-module 133. These three sub-modules are described below: (3.1) Environmental similarity calculation module 131.

[0040] Optionally, the environmental similarity calculation module 131 is used to determine the environmental similarity between each reference garden and the garden to be configured for each type of plant, based on the environmental data of the reference garden and the environmental data of the garden to be configured.

[0041] Specifically, the environmental similarity calculation module 131 calculates environmental similarity for each type of plant and each reference garden through a multi-step process. This submodule first calculates the parameter differences between the two gardens in various environmental dimensions, then assesses the degree of deviation of the parameters of both gardens from the suitable growth range of the plants, and finally combines the parameter differences with the degree of deviation through an inverse proportional normalization formula to generate an environmental similarity index with a value between 0 and 1. The higher the value, the closer the two gardens are in the growth environment conditions of specific plants.

[0042] (3.2) Scale similarity calculation module 132.

[0043] Optionally, the scale similarity calculation module 132 is used to determine the scale similarity between each reference garden and the garden to be configured based on the scale data of the reference garden and the scale data of the garden to be configured.

[0044] Specifically, the scale similarity calculation module 132 calculates scale similarity by comparing the differences in the area of ​​the two gardens and combining the normalized results of the number of plant species. This submodule first calculates the absolute difference in the area of ​​the two gardens, then performs linear normalization on the number of plant species in the reference garden, and finally combines the area difference with the normalized value of the number of species through an exponential function to output a scale similarity between 0 and 1, which reflects the degree of matching between the two gardens in terms of scale characteristics.

[0045] (3.3) Weighted submodule of comprehensive similarity 133.

[0046] Optionally, the comprehensive similarity weighted submodule 133 is used to determine the comprehensive similarity between each reference garden and the garden to be configured in each type of plant based on environmental similarity, scale similarity and environmental sensitivity coefficient.

[0047] Specifically, the comprehensive similarity weighted submodule 133 integrates the outputs of the first two submodules through a dynamic weight allocation mechanism. This submodule uses the environmental sensitivity coefficient as the weight for environmental similarity and its complement as the weight for scale similarity, generating the final comprehensive similarity through weighted summation. This design ensures that environmentally sensitive plants are given more emphasis on environmental similarity, while environmentally tolerant plants are given more emphasis on the coordination between the reference garden and the garden to be configured in terms of landscape spatial scale (reflected through scale similarity), so that the recommendation results simultaneously meet the requirements of ecological adaptability and landscape aesthetics.

[0048] The comprehensive similarity evaluation module 13 outputs all comprehensive similarity data to the recommendation calculation module 14 for subsequent processing.

[0049] (4) Recommendation calculation module 14.

[0050] The recommendation degree calculation module 14 is responsible for calculating the recommendation degree of each type of plant based on the comprehensive similarity output by the comprehensive similarity evaluation module 13 and the reference garden plant configuration data obtained by the data acquisition module 11. The recommendation degree directly determines the priority of plant selection in the plant configuration module 15.

[0051] Optionally, the recommendation calculation module 14 is used to determine the recommendation of each type of plant based on the comprehensive similarity between each reference garden and the garden to be configured in each type of plant, and the plant configuration data of each reference garden.

[0052] For example, such as Figure 3As shown, the recommendation calculation module 14 may include two sub-modules: a plant rating calculation sub-module 141 and a recommendation weighting calculation sub-module 142. These two sub-modules are described below: (4.1) Plant scoring calculation submodule 141.

[0053] Optionally, the plant rating calculation submodule 141 is used to determine the rating of each reference garden for each type of plant based on the plant configuration data of each reference garden.

[0054] Specifically, the plant scoring calculation submodule 141 adopts a differentiated scoring strategy based on the actual planting situation of the reference gardens: for plant categories that have already been planted, their planting area percentage in the garden is directly used as the score; for plant categories that have not been planted, the score is calculated by multiplying the negative value of the average planting area percentage of that category in all reference gardens by a penalty decay coefficient, where the penalty decay coefficient is a constant between 0 and 1, exemplarily set to 0.3. This scoring mechanism reflects both the positive recommendation value of planted plants and the negative impact of unplanted plants.

[0055] (4.2) Recommendation weighted calculation submodule 142.

[0056] Optionally, a recommendation weighted calculation submodule 142 is used to determine the recommendation level for each plant category based on the overall similarity of all reference gardens and the score for each plant category.

[0057] Specifically, the recommendation weighted calculation submodule 142 uses the overall similarity as a weighting coefficient to perform a weighted sum of the plant scores of each reference garden, and then normalizes the results by dividing by the total similarity. This calculation process ensures that reference gardens with higher similarity have a greater impact on the recommendation score, and the final output recommendation score accurately reflects the suitability of each type of plant with the garden to be configured.

[0058] Therefore, the recommendation calculation module 14 outputs the complete plant recommendation list to the plant configuration module 15, completing the quantitative evaluation stage of plant configuration.

[0059] (5) Plant configuration module 15.

[0060] The plant configuration module 15 is responsible for generating the final plant configuration scheme for the garden to be configured, based on the plant recommendation list output by the recommendation calculation module 14 and combined with elements such as rocks, water bodies, and garden buildings in the garden to be configured.

[0061] Optionally, the plant configuration module 15 is used to configure the plants in the garden to be configured based on the recommendation level.

[0062] Specifically, the plant configuration module 15 first sorts all plant categories in descending order of their recommendation level to form a priority order of plant recommendations, in which plants that are earlier in the sequence have higher environmental adaptability and scale matching degree.

[0063] Based on the generated recommended sequences, the plant configuration module 15 further incorporates the specific landscape characteristics of the garden to be configured, including elements such as rockery layout, water feature distribution, and architectural style, to conduct the final selection of plant species and allocation of planting proportions. This module selects plant categories that harmonize with the site's landscape characteristics based on the priority order of the recommended sequences, while also considering the relative recommendation scores of each plant to rationally allocate the planting area proportion of each type of plant, ensuring that plants with higher recommendation scores receive more significant configuration weights.

[0064] Finally, the plant configuration module 15 outputs a complete configuration scheme containing recommended plant species and their corresponding planting ratios, providing configuration decision support for landscape architecture and greening layout.

[0065] The above provides an introduction to the landscaping configuration system 10 and its included modules.

[0066] For example, such as Figure 4 The diagram shown is a flowchart illustrating a big data-based landscaping configuration method according to an embodiment of the present invention, comprising the following steps: S401. Obtain the garden data of the garden to be configured and multiple reference gardens.

[0067] The garden data includes environmental data, scale data, and plant configuration data. Optionally, environmental data is used to characterize the soil conditions and climate of the garden; plant configuration data is used to characterize the number of plant species in the garden and the proportion of each plant species in the planting area; and scale data is used to characterize the area of ​​the garden.

[0068] For example, this step can be performed by the data acquisition module 11 in the landscape greening configuration system 10 described above. Specifically, the data acquisition module 11 collects three types of core data for the reference landscape and the landscape to be configured: environmental data, including soil conditions and climate conditions, such as soil pH value, soil organic matter content, monthly temperature range, monthly minimum temperature, monthly maximum temperature, and monthly average precipitation; scale data, including the area of ​​the landscape; and plant configuration data, including the number of plant species currently planted in the landscape and the proportion of planting area corresponding to each plant species.

[0069] Optionally, when acquiring garden data from multiple reference gardens, the data acquisition module 11 selects reference gardens located in the same or adjacent ecological regions as the garden to be configured. In this way, by limiting the selection of reference gardens to those in the same or adjacent ecological regions as the garden to be configured, the data acquisition module 11 effectively ensures the environmental adaptability and ecological safety of the recommended plants, increases the survival rate of the recommended plants in the garden to be configured, and thus improves the feasibility and scientific validity of the recommendation results from the outset.

[0070] S402. Based on environmental data and plant configuration data from multiple reference gardens, determine the environmental sensitivity coefficient for each type of plant.

[0071] Among them, the environmental sensitivity coefficient is used to characterize the sensitivity of each type of plant to environmental changes.

[0072] For example, this step can be performed by the environmental sensitivity assessment module 12 in the landscape greening configuration system 10 described above. Specifically, it includes: First, the environmental sensitivity assessment module 12 determines the planting extent based on the number of reference gardens where each type of plant is planted and the total number of all reference gardens; then, based on environmental data from multiple gardens, the environmental sensitivity assessment module 12 determines the environmental parameter range for each type of plant across multiple environmental dimensions. The environmental parameter range characterizes the range of parameter variation for each type of plant across environmental dimensions; finally, the environmental sensitivity assessment module 12 determines the environmental sensitivity coefficient based on the planting extent of each type of plant and the environmental parameter range across multiple environmental dimensions. It should be noted that the specific process for the environmental sensitivity assessment module 12 to calculate the environmental sensitivity coefficient based on the aforementioned three sub-steps is described in S501-S503 below, and will not be repeated here.

[0073] In another possible implementation, the environmental sensitivity assessment module 12 can also use a combination of planting frequency and environmental parameter standard deviation when calculating the environmental sensitivity coefficient. Planting frequency is characterized by the proportion of a certain type of plant appearing in a reference garden, reflecting its distribution breadth. The coverage of environmental parameters is reflected by calculating the mean of the standard deviations of each environmental dimension parameter within the planting range of each type of plant, reflecting the degree of dispersion of environmental conditions. Finally, the planting frequency is used as the weight of the mean of the environmental parameter standard deviations, and the environmental sensitivity coefficient is generated through an inverse proportional normalization function.

[0074] Alternatively, the environmental sensitivity assessment module 12 can also employ a calculation method combining geographical distribution coverage and the interquartile range of environmental parameters. This scheme assesses the spatial distribution breadth of a particular plant by statistically analyzing the proportion of geographical sub-regions where a certain type of plant is planted, while simultaneously using the sum of the interquartile ranges of each environmental dimension to measure the robust coverage of environmental parameters. Finally, geographical distribution coverage is used as the weight of the sum of the interquartile ranges of environmental parameters, and the environmental sensitivity coefficient is calculated through inverse proportional normalization.

[0075] Therefore, the environmental sensitivity assessment module 12 quantifies the adaptability of each type of plant to environmental changes, providing a basis for the subsequent weight allocation of environmental similarity and scale similarity, and ensuring that the plant recommendation results fit the actual environmental characteristics of the garden to be configured.

[0076] S403. Based on the environmental data of each reference garden, the environmental sensitivity coefficient of each type of plant, and the garden data of the garden to be configured, determine the comprehensive similarity between each reference garden and the garden to be configured in terms of each type of plant.

[0077] For example, this step can be performed by the comprehensive similarity evaluation module 13 in the landscape greening configuration system 10 described above. Specifically, it includes: First, the comprehensive similarity evaluation module 13 determines the environmental similarity between each reference garden and the garden to be configured for each type of plant, based on the environmental data of the reference garden and the environmental data of the garden to be configured. Then, the comprehensive similarity evaluation module 13 determines the scale similarity between each reference garden and the garden to be configured, based on the scale data of the reference garden and the scale data of the garden to be configured. Finally, the comprehensive similarity evaluation module 13 determines the comprehensive similarity between each reference garden and the garden to be configured for each type of plant, based on environmental similarity, scale similarity, and environmental sensitivity coefficient. It should be noted that the specific process of the comprehensive similarity evaluation module 13 calculating the comprehensive similarity based on the aforementioned three sub-steps is described in S601-S603 below, and will not be repeated here.

[0078] In another possible implementation, the comprehensive similarity assessment module 13 can also employ a combination of environmental vector matching and multi-dimensional scale assessment when calculating the comprehensive similarity. This scheme assesses environmental matching by constructing environmental feature vectors and calculating cosine similarity, while simultaneously correcting for dimensions that exceed the plant suitability range. For scale assessment, it comprehensively considers multi-dimensional differences such as land area, number of plant species, and plant density per unit area, obtaining scale similarity through weighted fusion and normalization. Finally, based on the exponential weighting result of the environmental sensitivity coefficient, it dynamically assigns weights to the two types of similarity and performs weighted fusion to generate the final comprehensive similarity index.

[0079] Alternatively, the comprehensive similarity assessment module 13 calculates the comprehensive similarity based on the calculation logic of environmental distance normalization and plant capacity matching. This scheme assesses environmental similarity by calculating the Euclidean distance of environmental parameters and performing normalization transformation, while providing similarity enhancement processing for plants with strong environmental sensitivity. In the scale assessment dimension, the concept of plant capacity is introduced, and the degree of scale matching is assessed by combining standardized parameters such as green coverage rate and number of plants per unit area through capacity difference analysis. Finally, the analytic hierarchy process (AHP) is used to construct a dynamic weight allocation mechanism based on the environmental sensitivity coefficient, achieving a scientific fusion of the two types of similarity and forming a comprehensive similarity assessment result.

[0080] Therefore, the comprehensive similarity assessment module 13 integrates environmental matching degree and scale matching degree, and dynamically allocates the weights of the two with the environmental sensitivity coefficient, so as to ensure that the core influencing factors of plants with different environmental sensitivities—environment and scale—are accurately reflected in the similarity assessment, providing a scientific weight basis for subsequent recommendation degree calculation.

[0081] S404. Based on the overall similarity between each reference garden and the garden to be configured in each type of plant, and the plant configuration data of each reference garden, determine the recommendation level of each type of plant.

[0082] For example, this step can be performed by the recommendation calculation module 14 in the landscape greening configuration system 10 described above. Specifically, it includes: First, for each reference garden and each type of plant, the recommendation calculation module 14 determines the score of each reference garden for each type of plant based on the plant configuration data of each reference garden; then, for each type of plant, the recommendation calculation module 14 determines the recommendation degree of each type of plant based on the comprehensive similarity of all reference gardens and the score of each type of plant. It should be noted that the specific process of the recommendation calculation module 14 calculating the comprehensive similarity according to the aforementioned three sub-steps is described in S701-S702 below, and will not be repeated here.

[0083] In another possible implementation, when calculating the overall similarity, the recommendation calculation module 14 can use a calculation method that combines score correction and similarity tier weighting. This scheme introduces dual correction factors—plant growth status and reasons for not planting—into the basic score, significantly enhancing the actual reference value of the score. Simultaneously, by tiering the overall similarity and assigning differentiated weight coefficients, it effectively strengthens the decision-making influence of highly similar reference gardens, making the recommendation results closer to the actual planting effects and differences in reference value.

[0084] In another possible implementation, when calculating the overall similarity, the recommendation calculation module 14 can also use a simplified model based on a weighted sum of preference level scores and similarity scores. This scheme transforms the plant configuration of the reference garden into five standardized preference levels, directly using level scores instead of precise proportion calculations. In the recommendation calculation, the sum of the products of similarity and level scores is directly used as the final recommendation index, simplifying the calculation process and conforming to the actual working mode of plant importance classification in garden design.

[0085] Therefore, the recommendation calculation module 14 weights and integrates the plant preferences of the reference garden with the reference value of the reference garden, quantifies the adaptation priority of each type of plant to the garden to be configured, and provides a direct basis for subsequent plant configuration schemes.

[0086] S405. Based on the recommendation level, plant configuration shall be carried out for the garden to be configured.

[0087] For example, this step can be performed by the plant configuration module 15 in the landscape greening configuration system 10 described above, and specifically includes the following steps: (1) Sort each type of plant in descending order of recommendation to form a recommendation sequence.

[0088] Specifically, the plant configuration module 15 sorts the recommendation scores of all plant categories in descending order to generate a plant recommendation sequence with clear priorities. Plants with higher recommendation scores are placed earlier in the sequence, indicating a higher degree of compatibility with the garden to be configured.

[0089] For example, the recommendation set is as follows ,in Let represent the recommendation score of the i-th plant category, and m be the total number of plant categories. These recommendation scores are sorted in descending order using a sorting algorithm to obtain an ordered sequence. ,in It has the highest recommendation rating. It has the lowest recommendation rating. Used to refer to any element in the sequence, corresponding to a specific plant category j and its recommendation value.

[0090] (2) Select plants according to the recommended sequence and determine the final plant configuration scheme.

[0091] In this step, after obtaining the recommended plant sequence, the plant configuration module 15 formulates a plant configuration plan based on this sequence. First, based on the actual landscape layout characteristics of the garden to be configured, including elements such as rock distribution, water features, and architectural style, plant species that match the ecological habits and ornamental characteristics are selected from the recommended sequence. Simultaneously, considering the relative positions of each plant in the recommended sequence, a reasonable planting area proportion is allocated to each type of plant, with plant species with higher recommendation rates receiving a larger planting proportion.

[0092] For example, for the top k plant categories in sequence Q, the planting area percentage is determined based on their relative recommendation degree. Let the plant categories be... The planting area accounts for ,but and The recommendation score is positively correlated with the plant configuration. The final output plant configuration plan includes a list of recommended plant species and the corresponding planting area ratio for each species, providing a scientific basis for the greening layout of the garden to be configured.

[0093] Based on the above technical solutions, this invention innovatively introduces a plant environmental sensitivity coefficient to achieve dynamic weight allocation by integrating multi-dimensional environmental data and garden scale characteristics, and constructs a plant recommendation model based on comprehensive similarity assessment, which significantly improves the scientificity and adaptability of garden plant configuration. This solution effectively overcomes the subjectivity and data coverage limitations of traditional methods that rely on human experience, while also solving the problem of existing recommendation algorithms neglecting environmental adaptability. Ultimately, it optimizes the landscape effect while ensuring the ecological suitability of plants, providing accurate and efficient decision support for landscape garden greening layout.

[0094] For example, in combination Figure 4 ,like Figure 5 The diagram shown illustrates another big data-based landscape greening configuration method according to an embodiment of the present invention. In this method, the environmental sensitivity coefficient of each type of plant is determined based on environmental data and plant configuration data from multiple reference landscapes. Specifically, the method includes the following steps: S501. Determine the planting extent of each type of plant in the reference gardens based on the number of gardens in which each type of plant is planted and the total number of all reference gardens.

[0095] Specifically, the environmental sensitivity assessment module 12, based on the plant configuration data of reference gardens, first filters out all reference gardens that plant a certain type of plant (denoted as type i), and counts their number, denoted as n. Then, the environmental sensitivity assessment module 12 combines the total number of all reference gardens (denoted as N) and quantifies the prevalence of this type of plant in the reference gardens by calculating the planting prevalence as n / N. The larger this index value, the wider the planting distribution range of this type of plant and the stronger its basic environmental adaptability.

[0096] S502. Based on environmental data from multiple gardens, determine the environmental parameter range for each type of plant in multiple environmental dimensions.

[0097] Among them, the environmental parameter range is used to characterize the range of parameter variation for each type of plant in the environmental dimension.

[0098] Specifically, based on the environmental data of the reference gardens, for the i-th type of plant, the environmental sensitivity assessment module 12 first determines the environmental parameters of all reference gardens within its planting range, which may cover environmental dimensions such as soil pH, soil organic matter content, monthly average precipitation, monthly minimum temperature, and monthly maximum temperature. It should be noted that the environmental sensitivity assessment module 12 performs Min-Max normalization on the environmental parameters to ensure that the values ​​of each dimension are within the range of [0,1] before calculating the range, thus avoiding the unclear calculation meaning caused by multiplying parameters with different dimensions.

[0099] Then, the environmental sensitivity assessment module 12 calculates the difference between the maximum value of the parameter within the planting range and the minimum value of the parameter within the planting range for each environmental dimension, which is the environmental parameter range.

[0100] S503. Determine the environmental sensitivity coefficient based on the planting coverage of each type of plant and the range of environmental parameters in multiple environmental dimensions.

[0101] For example, the environmental sensitivity assessment module 12 calculates the environmental sensitivity coefficient using the following formula: In the above formula, Let represent the environmental sensitivity coefficient of the i-th plant type, n represent the number of reference gardens included in the planting range of the i-th plant type, N represent the total number of reference gardens, and R represent the total number of environmental dimensions. This indicates the environmental parameter range with the i-th plant type being the worst in the r-th dimension. This means first calculating the cumulative product of the ranges of all environmental parameters across all dimensions, then taking the R-th power to obtain the geometric mean. This indicates inverse proportional normalization, ensuring that the coefficient values ​​are between 0 and 1. Therefore, the environmental sensitivity assessment module 12 obtains the environmental sensitivity coefficient for the i-th type of plant; that is, the higher the planting coverage and the wider the range of environmental parameters, the smaller the environmental sensitivity coefficient, and the stronger the plant's tolerance to environmental changes.

[0102] It should be noted that in the above calculation, planting prevalence represents the degree of popularity of plant type i in the reference gardens—the larger this proportion, the more reference gardens plant type i can grow in, indirectly reflecting its stronger adaptability to different environments. For example, if 12 out of 15 reference gardens plant this plant, =0.8, indicating that it can adapt to the environment of most reference gardens. Planting breadth An increase in the weighted product in the formula leads to an increase in the weighted product, which in turn reduces the overall content on the right side of the equation (after inverse proportional normalization). Therefore, the planting coverage and environmental sensitivity coefficient... It is a negative correlation.

[0103] Similarly, extremely poor environmental parameters With environmental sensitivity coefficient It is also negatively correlated. Environmental parameters are extremely poor. In formula calculations, the product is accumulated based on the environmental range. The larger the product, the smaller the overall content on the right side of the equation. This reflects the formula's calculation logic that a stronger comprehensive adaptability results in lower environmental sensitivity.

[0104] Based on the above technical solution, this invention effectively quantifies the sensitivity of different plants to environmental changes by combining the dual indicators of planting breadth and the cumulative product of environmental parameter ranges. It not only considers the distribution breadth of plants in the reference garden, but also reflects their adaptability to multi-dimensional environmental conditions, thereby significantly improving the scientificity and comprehensiveness of the environmental sensitivity coefficient calculation. This provides a more accurate basis for weight allocation for subsequent similarity assessment, and ultimately enhances the environmental adaptability and decision reliability of plant configuration recommendations.

[0105] For example, in combination Figure 4 ,like Figure 6 The diagram shown illustrates another big data-based landscape greening configuration method according to an embodiment of the present invention. In this method, based on the environmental data of each reference garden, the environmental sensitivity coefficient of each plant type, and the garden data of the garden to be configured, the comprehensive similarity between each reference garden and the garden to be configured in terms of each plant type is determined. Specifically, the method includes the following steps: S601. Based on the environmental data of the reference garden and the environmental data of the garden to be configured, determine the environmental similarity between each reference garden and the garden to be configured for each type of plant.

[0106] For example, this step can be performed by the environment similarity calculation module 131 in the comprehensive similarity evaluation module 13 described above, and specifically includes the following steps: (1) Based on the environmental data of each reference garden and the environmental data of the garden to be configured, determine the parameter differences between each reference garden and the garden to be configured in each environmental dimension.

[0107] Specifically, for each environmental dimension, the environmental similarity calculation module 131 calculates the parameter differences between the t-th reference garden and the garden to be configured in that environmental dimension, denoted as . Specifically, the absolute value of the difference between the corresponding dimensional parameter values ​​of the two gardens is taken to represent the magnitude of the difference in the basic environment. It should be noted that the environmental similarity calculation module 131 is determined... Then, normalization is performed to avoid unclear calculation meaning caused by multiplying parameters with different dimensions in the following formula.

[0108] Among them, the environmental dimension r ranges from 1 to 5, that is, when r is 1 to 5, it corresponds to the soil pH value, soil organic matter content, monthly average precipitation, monthly minimum temperature and monthly maximum temperature obtained in S401 above.

[0109] (2) Determine the total deviation parameter, which is used to characterize the sum of the deviations of each reference garden and the garden to be configured from the suitable growth range of each type of plant in each environmental dimension.

[0110] In this step, for the i-th type of plant, the environmental similarity calculation module 131 determines its suitable growth range, calculates the deviation of the t-th reference garden from the garden to be configured in terms of environmental dimension r within this range, and sums them up as the total deviation parameter. It should be noted that if the parameters corresponding to the environmental dimension r of both gardens are within the appropriate range, =0 indicates that the difference in this environmental dimension has little impact on plant selection; if one parameter exceeds the suitable range... Taking the absolute value of the excess indicates that the difference in this environmental dimension has a significant impact on plant selection; if two parameters exceed the suitable range, the absolute values ​​of the two excess values ​​are added together to determine the result. This indicates that the differences in this environmental dimension have a significant impact on plant selection. It should be noted that the environmental similarity calculation module 131 determines... Then, a nonlinear function (such as the sigmoid function) is used to map it to the interval [0,1) to avoid the unclear calculation meaning caused by multiplying parameters with different dimensions in the following formula.

[0111] Optionally, the environmental similarity calculation module 131 determines the suitable growth range (i.e., the aforementioned suitable range) for each type of plant based on a public plant database or local greening standards.

[0112] In one implementation of this invention, the aforementioned suitable growth range can be statistically derived from environmental data of multiple reference gardens where this type of plant grows well. For example, the average value plus or minus the standard deviation range can be used. .

[0113] (3) Based on the parameter differences and total deviation parameters of all environmental dimensions, determine the environmental similarity between each reference garden and the garden to be configured for each type of plant.

[0114] For example, the environment similarity calculation module 131 calculates environment similarity using the following formula: In the above formula, This represents the environmental similarity between the t-th garden and the garden to be configured when recommending the i-th type of plant. This represents the degree of deviation between the t-th garden and the garden to be configured in the r-th environmental dimension regarding the growth range of the i-th type of plant (i.e., the total deviation parameter). R represents the total number of environmental dimensions. This represents the difference between the t-th garden and the garden to be configured in the r-th environmental dimension. This indicates inverse proportional normalization.

[0115] It should be noted that, This represents the fundamental environmental difference between the two gardens in the r-th environmental dimension—the greater the difference, the less suitable the environmental conditions in that dimension are for the uniform growth needs of the i-th type of plant. For example, a soil pH difference of 0.8 is more likely to lead to different plant growth states than a difference of 0.2. Therefore, and It is negatively correlated, and the specific path of influence is as follows: Enlargement leads to " The value of the term increases, which in turn leads to an increase in the summation result. Enlargement, leading to The reduction directly reflects the formula logic that the smaller the difference in the basic environment, the higher the similarity of the environment.

[0116] Similarly, and It is also negatively correlated. It is a corrective factor for plant growth adaptability—the further the deviation from the suitable range for plant type i, the less suitable the environment of the two gardens is for the plant's growth needs, even with basic differences. Even if the value is relatively small, it may lead to a decrease in actual adaptability due to deviation from the suitable range. For the specific impact path, please refer to the previous paragraph, which will not be repeated here.

[0117] S602. Based on the scale data of the reference garden and the scale data of the garden to be configured, determine the scale similarity between each reference garden and the garden to be configured.

[0118] For example, this step can be performed by the scale similarity calculation module 132 in the comprehensive similarity evaluation module 13 described above, and specifically includes the following steps: (1) Based on the scale data of the reference garden and the scale data of the garden to be configured, determine the difference in the area occupied by each reference garden and the garden to be configured.

[0119] In this step, the scale similarity calculation module 132 calculates the difference in area between each reference garden and the garden to be configured, based on their respective area sizes, and denotes it as... Specifically, the absolute value of the difference between the areas occupied by the two gardens represents the magnitude of the difference in their basic scale.

[0120] (2) Based on the difference in area between each reference garden and the garden to be configured, and the number of plant species in each reference garden, determine the scale similarity between each reference garden and the garden to be configured.

[0121] For example, the scale similarity calculation module 132 calculates the scale similarity between each reference garden and the garden to be configured using the following formula: In the above formula, This represents the scale similarity between the t-th reference garden and the garden to be configured. This represents the difference in area between the t-th garden and the garden to be configured. This represents the maximum-minimum normalization function, used to map the range of values ​​for the parameters within the parentheses to 0 to 1, thus avoiding excessive influence on the calculation results when the areas of the two gardens differ significantly. Let represent the number of plant species in the t-th garden. This indicates that the results are adjusted using the number of plant species to avoid errors in the recommended results due to the difference in the number of species between large-scale and small-scale gardens.

[0122] It should be noted that the above formula is derived through logarithmic transformation. By compressing large-scale differences and enhancing the distinguishability of small- and medium-sized garden differences, and then normalizing, the results are obtained. ; To obtain the number of plant species in the garden as a reference, linear normalization was performed. The formula combines the normalized logarithmic difference with the normalized value of the number of species in the form of an exponential function, outputting a scale similarity between 0 and 1. This value reflects the degree of matching between the two gardens in terms of scale characteristics, where... and Negative correlation, meaning the smaller the area difference, the higher the similarity; and Positive correlation, meaning that the greater the number of plant species, the greater the positive contribution to scale similarity, thus taking into account both area difference and the matching degree of plant species number in the assessment.

[0123] S603. Based on environmental similarity, scale similarity, and environmental sensitivity coefficient, determine the comprehensive similarity between each reference garden and the garden to be configured in each type of plant.

[0124] For example, this step can be performed by the comprehensive similarity weighting submodule 133 in the comprehensive similarity evaluation module 13 described above. Combining S601 and S602 above, the comprehensive similarity weighting submodule 133 calculates the scale similarity between each reference garden and the garden to be configured, based on the sensitivity coefficient of each plant type. Then, the comprehensive similarity weighting submodule 133 determines the comprehensive similarity between each reference garden and the garden to be configured for each plant type, specifically including the following steps: (1) Determine the first weight of environmental similarity and the second weight of scale similarity based on the environmental sensitivity coefficient.

[0125] In this step, the environmental sensitivity coefficient is used. As environmental similarity The first weight, with As for scale similarity The second weight.

[0126] It should be noted that when plants are highly sensitive to environmental conditions ( When the plant's environmental sensitivity is high, environmental matching is a key factor influencing its recommendation; therefore, environmental similarity is given a high weight. When plants are small, environmental factors no longer limit their growth. At this stage, plant selection should focus more on the harmony of landscape scale (such as matching large trees with open parks, and pairing small flowers with delicate courtyards), and the similarity of scale. This reflects the degree of spatial scale matching between the reference garden and the garden to be configured, and therefore it is given a high weight. This ensures both the environmental adaptability of sensitive plants and that the recommendations for tolerant plants conform to the principles of landscape aesthetics and spatial proportion.

[0127] It is understandable that the sum of the two weights is 1, ensuring that the weight allocation is directly related to the plant's environmental sensitivity.

[0128] (2) Determine the comprehensive similarity between each reference garden and the garden to be configured in each type of plant according to environmental similarity, scale similarity, first weight and second weight.

[0129] For example, the comprehensive similarity weighting submodule 133 calculates the comprehensive similarity according to the following formula: In the above formula, This represents the overall similarity between the t-th garden under the i-th plant category and the garden to be configured. This represents the environmental similarity between the t-th garden and the garden to be configured when recommending the i-th type of plant. This represents the scale similarity between the t-th reference garden and the garden to be configured. This represents the environmental sensitivity coefficient of the i-th plant species, which is used as the environmental similarity in this formula. The first weight. Correspondingly, In this formula, it is used as the scale similarity. The second weight.

[0130] Understandably, based on the above formula, environmental similarity... Scale similarity All are related to the overall similarity The correlation is positive, and the correlation is affected by the environmental sensitivity coefficient. Regulation. That is, Not related to overall similarity It is not directly positively or negatively correlated, but rather through regulation. and The weight of the number of people indirectly affects the weight of the number of people. The final value. This reflects the environmental sensitivity coefficient. Its core function is to make the calculation logic of comprehensive similarity fit the environmental sensitivity characteristics of plants themselves, so as to achieve differentiated assessment of sensitive plants based on their environment and tolerant plants based on their scale.

[0131] For example, in combination Figure 4 ,like Figure 7 The diagram shown illustrates another big data-based landscape greening configuration method according to an embodiment of the present invention. In this method, the recommendation level for each type of plant is determined based on the comprehensive similarity between each reference garden and the garden to be configured in each type of plant, and the plant configuration data of each reference garden. Specifically, the method includes the following steps: S701. For each reference garden and each type of plant, determine the score for each reference garden for each type of plant based on the plant configuration data of each reference garden.

[0132] For example, this step can be performed by the plant rating calculation submodule 141 in the recommendation calculation module 14 described above, and specifically includes the following steps: (1) When each type of plant is planted in the reference garden, the percentage of the planting area of ​​each type of plant in the reference garden is used as the score.

[0133] In the scenario corresponding to this sub-step, the percentage of the planting area of ​​the i-th type of plant in the t-th reference garden is directly used as the score. That is, the higher the percentage of the planting area, the higher the reference garden's preference for that plant. For example, if the i-th type of plant accounts for 40% in a reference garden, the score is 0.4, which conforms to the intuitive logic that a higher percentage means greater acceptance.

[0134] (2) In the case that no plant of each type is planted in the reference garden, the score is determined based on the average planting area ratio of each type of plant in all reference gardens and the penalty decay coefficient.

[0135] In the scenario corresponding to this sub-step, the negative impact of not planting needs to be considered. The negative value of the average planting area percentage of each type of plant in all reference gardens is multiplied by a penalty attenuation coefficient to obtain the score. This penalty attenuation coefficient is a constant between 0 and 1, used to reduce the intensity of the penalty caused by non-environmental factors resulting from non-planting. For example, the penalty attenuation coefficient can be set to 0.3.

[0136] This reflects the logic that most gardens recognize a certain type of plant, but a certain garden does not plant it, indicating that the garden has a high degree of rejection towards it.

[0137] S702. For each type of plant, determine the recommendation level of each type of plant based on the overall similarity of all reference gardens and the score of each type of plant.

[0138] For example, this step can be performed by the recommendation weighted calculation submodule 142 in the recommendation calculation module 14 described above, and the recommendation score can be calculated using the following formula: In the above formula, This represents the total number of all reference gardens. This represents the overall similarity between the t-th garden under the i-th plant category and the garden to be configured. This represents the score given by the t-th reference garden to the i-th type of plant.

[0139] It is understandable that in the above formula calculations, , With recommendation It is positively correlated. Specifically, the overall similarity... It acts as a weight in this formula. It determines the score of the t-th reference garden. For the final recommendation The extent of its influence. The value is always positive, therefore, it is related to the recommendation level. An indirect positive correlation is formed: the higher the overall similarity between a reference garden and the garden to be configured, the greater the impact of its score on the final recommendation result.

[0140] In summary, overall similarity It acts as an amplifier of influence. The larger it is, the more weight the reference garden's opinion carries in the final decision. Plant rating The reference garden's contribution direction is determined by its sign. Its positive or negative sign directly determines whether the reference garden's contribution increases or decreases the final recommendation. Therefore, the synergistic effect of the above formula is: strongly recommending plants widely planted in gardens highly similar to the garden to be configured; and strongly discouraging plants generally not planted in gardens highly similar to the garden to be configured. This allows the recommendation system to not only focus on positive examples but also effectively utilize negative example information, thereby deriving more accurate and reliable recommendation results.

[0141] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0142] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for configuring landscaping and greening based on big data, characterized in that, The method includes: Acquire garden data for the garden to be configured and multiple reference gardens; wherein, the garden data includes environmental data, scale data, and plant configuration data; Based on the environmental data and plant configuration data of the multiple reference gardens, an environmental sensitivity coefficient for each type of plant is determined; wherein, the environmental sensitivity coefficient is used to characterize the sensitivity of each type of plant to environmental changes; Based on the environmental data of each reference garden, the environmental sensitivity coefficient of each type of plant, and the garden data of the garden to be configured, the comprehensive similarity between each reference garden and the garden to be configured in terms of each type of plant is determined. The recommendation level of each type of plant is determined based on the comprehensive similarity between each reference garden and the garden to be configured for each type of plant, and the plant configuration data of each reference garden. Based on the recommendation level, plant configuration is carried out for the garden to be configured.

2. The big data-based landscape greening configuration method according to claim 1, characterized in that, The environmental data is used to characterize the soil conditions and climate conditions of the garden, and the plant configuration data is used to characterize the number of plant species in the garden and the proportion of planting area of ​​each type of plant. Based on the environmental data and plant configuration data of the multiple reference gardens, the environmental sensitivity coefficient of each type of plant is determined, specifically including: The planting extent of each type of plant in the reference garden is determined based on the number of gardens in which each type of plant is planted and the total number of all reference gardens. Based on environmental data from multiple gardens, the environmental parameter ranges for each type of plant in multiple environmental dimensions are determined; wherein, the environmental parameter ranges are used to characterize the range of parameter variation for each type of plant in the environmental dimensions. The environmental sensitivity coefficient is determined based on the planting prevalence of each type of plant and the range of environmental parameters across multiple environmental dimensions.

3. The big data-based landscape greening configuration method according to claim 1, characterized in that, The scale data is used to characterize the area occupied by the garden; based on the environmental data of each reference garden, the environmental sensitivity coefficient of each type of plant, and the garden data of the garden to be configured, the comprehensive similarity between each reference garden and the garden to be configured in terms of each type of plant is determined, specifically including: Based on the environmental data of the reference garden and the environmental data of the garden to be configured, the environmental similarity between each reference garden and the garden to be configured for each type of plant is determined; Based on the scale data of the reference garden and the scale data of the garden to be configured, the scale similarity between each reference garden and the garden to be configured is determined; Based on the environmental similarity, the scale similarity, and the environmental sensitivity coefficient, the overall similarity between each reference garden and the garden to be configured in terms of each type of plant is determined.

4. The big data-based landscape greening configuration method according to claim 3, characterized in that, Based on the environmental data of the reference garden and the environmental data of the garden to be configured, the environmental similarity between each reference garden and the garden to be configured for each type of plant is determined, specifically including: Based on the environmental data of each reference garden and the environmental data of the garden to be configured, determine the parameter differences between each reference garden and the garden to be configured in each environmental dimension; A total deviation parameter is determined, which is used to characterize the sum of the deviations of each reference garden and the garden to be configured from the suitable growth range of each type of plant in each environmental dimension; Based on the parameter differences across all environmental dimensions and the total deviation parameter, the environmental similarity between each reference garden and the garden to be configured for each type of plant is determined.

5. The big data-based landscape greening configuration method according to claim 3, characterized in that, Based on the scale data of the reference gardens and the scale data of the gardens to be configured, the scale similarity between each reference garden and the garden to be configured is determined, specifically including: Based on the scale data of the reference garden and the scale data of the garden to be configured, the difference in land area between each reference garden and the garden to be configured is determined; Based on the difference in area between each reference garden and the garden to be configured, and the number of plant species in each reference garden, the scale similarity between each reference garden and the garden to be configured is determined.

6. The big data-based landscape greening configuration method according to claim 3, characterized in that, Based on the environmental similarity, the scale similarity, and the environmental sensitivity coefficient, the comprehensive similarity between each reference garden and the garden to be configured for each type of plant is determined, specifically including: Based on the environmental sensitivity coefficient, determine the first weight of the environmental similarity and the second weight of the scale similarity; Based on the environmental similarity, the scale similarity, the first weight, and the second weight, the comprehensive similarity between each reference garden and the garden to be configured in each type of plant is determined.

7. The big data-based landscape greening configuration method according to claim 1, characterized in that, Based on the comprehensive similarity between each reference garden and the garden to be configured for each type of plant, and the plant configuration data of each reference garden, the recommendation level for each type of plant is determined, specifically including: For each reference garden and each type of plant, a score for each reference garden on each type of plant is determined based on the plant configuration data of each reference garden. For each plant category, the recommendation level for each plant category is determined based on the overall similarity of all reference gardens and the score for each plant category.

8. The big data-based landscape greening configuration method according to claim 7, characterized in that, Based on the plant configuration data of each reference garden, determine the score of each reference garden for each type of plant, specifically including: When each type of plant is planted in the reference garden, the percentage of the planting area of ​​each type of plant in the reference garden is used as the score; If the reference garden does not plant each type of plant, the negative value of the average planting area percentage of each type of plant in all reference gardens is used as the score.

9. The big data-based landscape greening configuration method according to claim 1, characterized in that, Based on the recommendation level, plant configuration is performed for the garden to be configured, specifically including: Each type of plant is sorted from high to low according to its recommendation level to form a recommendation sequence; Select plants according to the recommended sequence to determine the final plant configuration scheme.

10. The big data-based landscape greening configuration method according to claim 1, characterized in that, When acquiring garden data from multiple reference gardens, select the reference garden that is in the same or adjacent ecological zone as the garden to be configured.

Images