A plant control method and device based on bubble clay

Abstract

The present application provides a plant control method and device based on bubble clay, relating to the technical field of plant control technology. The key points of its technical solution are as follows: obtaining plant species information; based on the plant species information, matching the type, ratio, and replacement cycle of the bubble clay; monitoring the actual growth state of the plant and calculating the deviation data between the actual growth curve and the standard growth curve; if the deviation data exceeds the preset threshold, generating a bubble clay regulation plan; performing bubble clay adjustment or replacement operations to guide the user to perform environmental collaborative regulation; collecting the plant state after the operation, evaluating the control effect, and dynamically adjusting the subsequent control strategy to make the plant growth state approach the standard growth curve. The plant control method and device based on bubble clay provided by the present application have the advantages of matching the bubble clay configuration with the plant requirements, having more targeted bubble clay selection, reducing fertilizer loss and environmental pollution, more accurate judgment of the timing of bubble clay replacement and adjustment, and more effective plant control.

Description

Technical Field

[0001] The present application relates to the technical field of plant control, and more specifically, to a method and device for plant control based on bubble mud. Background Art

[0002] Home gardening, especially the cultivation of indoor potted ornamental plants, has increasingly gained popularity among the public due to its combination of aesthetic value and air purification function. As a newly emerging soilless cultivation substrate, bubble mud has found extensive applications in the field of home gardening due to its cleanliness, good air permeability, and excellent water retention properties. However, most of the bubble mud products currently available on the market adopt a general-purpose formula design, aiming to provide a unified nutrient ratio for all plants. This general-purpose formula model makes it difficult to accurately match the specific nutrient requirements exhibited by different types of ornamental plants during their growth process.

[0003] Despite the emergence of various bubble mud products on the market, ordinary users often find it difficult to accurately judge and select the product that best suits the characteristics of the plants they grow. When making a choice, users usually rely only on the vague descriptive information of the product or their relatively limited botanical knowledge, which often leads to unsatisfactory plant growth conditions. To make up for the insufficient nutrient supply of bubble mud, users usually need to apply liquid fertilizers additionally during the later stage of plant growth. However, liquid fertilizers are prone to rapid loss from bubble mud after application, resulting in low nutrient utilization efficiency and resource waste. At the same time, it may also cause potential pollution to the indoor environment.

[0004] In addition, different plants also exhibit significant differences in their nutrient requirements at different growth stages. Users usually find it difficult to accurately judge when to replace the bubble mud or when to add additional nutrients, and generally lack scientific and effective plant control methods, resulting in often unsatisfactory plant maintenance management effects.

[0005] In view of the above problems, there is an urgent need for improvement in the existing technology. Summary of the Invention

[0006] The purpose of the present application is to provide a method and device for plant control based on bubble mud, which have the advantages of matching the configuration of bubble mud with plant requirements, being more targeted in the selection of bubble mud, reducing fertilizer loss and environmental pollution, being more accurate in judging the timing of bubble mud replacement and adjustment, and being more effective in plant control.

[0007] In a first aspect, the present application provides a method for plant control based on bubble mud, which is used for the indoor potted plant cultivation scenario and is used to configure bubble mud and regulate the growth state for specific plant species. The technical solution is as follows:

[0008] The method includes:

[0009] Obtain plant species information and establish a standard growth curve including height growth rate, number of leaves, color change, and nutrient absorption;

[0010] Based on the plant species information, match the bubble mud type, ratio, and replacement cycle;

[0011] Monitor the actual growth status of the plant and calculate the deviation data between the actual growth curve and the standard growth curve;

[0012] If the deviation data exceeds the preset threshold, generate a bubble mud regulation plan including composition regulation, structure regulation, and replacement strategy;

[0013] Execute the bubble mud adjustment or replacement operation and guide the user to perform environmental collaborative regulation;

[0014] Collect the plant status after the operation, evaluate the control effect, and dynamically adjust the subsequent control strategy to make the plant growth status approach the standard growth curve.

[0015] Further, in this application, the step of generating a bubble mud regulation plan including composition regulation, structure regulation, and replacement strategy when the deviation data exceeds the preset threshold includes:

[0016] If the deviation data exceeds the preset threshold, obtain the user's personalized planting requirements and establish a user expectation curve including plant height control target and flowering promotion target;

[0017] Integrate the standard growth curve and the user expectation curve to obtain the target growth curve;

[0018] Analyze the deviation data to determine the deviation type and degree between the actual growth status of the plant and the target growth curve;

[0019] According to the deviation type and degree, and the plant species information, select a regulation plan from the bubble mud composition regulation library, structure regulation library, and replacement strategy library, and generate a bubble mud regulation plan including composition regulation instructions, structure regulation instructions, and replacement strategy instructions;

[0020] Among them, the composition regulation instructions include nutrient type, quantity, and release rate, the structure regulation instructions include bubble mud density, layered structure, and air permeability, and the replacement strategy instructions include replacement timing, replacement ratio, and new bubble mud type.

[0021] Further, in this application, the step of analyzing the deviation data to determine the deviation type and degree between the actual growth status of the plant and the target growth curve includes:

[0022] Collect multi-source data on the plant growth status, and the multi-source data includes image data, sensor data, and user input data;

[0023] For the multi-source data, perform data synchronization processing based on timestamps to obtain synchronized multi-source data;

[0024] Preprocess the synchronized multi-source data to obtain preprocessed multi-source data;

[0025] Based on the preprocessed multi-source data, calculate the deviation data of the actual growth state of the plant from the target growth curve in terms of height growth rate, number of leaves, color change, and nutrient absorption;

[0026] According to the deviation data, determine the deviation type and degree between the actual growth state of the plant and the target growth curve. The deviation types include growth retardation, excessive growth, malnutrition, and pests and diseases, and the deviation degrees include mild, moderate, and severe.

[0027] Furthermore, in the present application, the step of selecting a regulation plan from the bubble mud composition regulation library, structure regulation library, and replacement strategy library according to the deviation type, degree, and plant species information, and generating a bubble mud regulation plan including composition regulation instructions, structure regulation instructions, and replacement strategy instructions includes:

[0028] Construct a bubble mud regulation knowledge graph, which includes plant species nodes, deviation type nodes, deviation degree nodes, composition regulation plan nodes, structure regulation plan nodes, replacement strategy nodes, and the association relationships between the nodes;

[0029] Based on the plant species information, deviation type, and degree, perform multi-hop search in the bubble mud regulation knowledge graph to obtain a set of candidate regulation plans. The multi-hop search includes: taking the plant species node as the starting node, performing the first-hop search according to the plant species information to obtain the associated deviation type node set and deviation degree node set; taking the deviation type node set and deviation degree node set as the starting nodes, performing the second-hop search to obtain the associated composition regulation plan node set, structure regulation plan node set, and replacement strategy node set;

[0030] Calculate the confidence score of each regulation plan in the candidate regulation plan set. The confidence score comprehensively considers the association strength of the regulation plan with the plant species, deviation type, and degree, as well as the compatibility between the regulation plans;

[0031] According to the confidence score, select the regulation plan with the highest confidence score from the candidate regulation plan set, and generate a bubble mud regulation plan including composition regulation instructions, structure regulation instructions, and replacement strategy instructions.

[0032] Furthermore, in the present application, the step of calculating the confidence score of each regulation plan in the candidate regulation plan set includes:

[0033] Obtain the association relationship data between nodes in the bubble mud regulation knowledge graph. The association relationship data includes the first association strength between the plant species node and the ingredient regulation plan node, the second association strength between the deviation type node and the ingredient regulation plan node, the third association strength between the deviation degree node and the ingredient regulation plan node, and the compatibility score between ingredient regulation plan nodes;

[0034] For each regulation plan in the candidate regulation plan set, calculate its weighted association strength with the plant species node, deviation type node, and deviation degree node according to the ingredient regulation plan nodes it contains. The weighted association strength is obtained by weighted summation of the first association strength, the second association strength, and the third association strength, and the weight coefficients are determined according to the plant species, deviation type, and deviation degree;

[0035] Calculate the compatibility score of each regulation plan in the candidate regulation plan set. The compatibility score is obtained by weighted averaging the compatibility scores between ingredient regulation plan nodes in the regulation plan, and the weight coefficients are determined according to the function sizes of the ingredient regulation plan nodes;

[0036] Perform weighted summation of the weighted association strength and the compatibility score to obtain the confidence score of each regulation plan in the candidate regulation plan set, and the weight coefficients are determined according to the association strength and compatibility.

[0037] Furthermore, in this application, the step of matching the bubble mud type, ratio, and replacement cycle based on the plant species information includes:

[0038] Obtain the environmental factor data of region, season, and light intensity, and construct an environmental factor database;

[0039] Extract the basic nutrient requirement data of the plant based on the plant species information;

[0040] According to the environmental factor data, use the environmental factor influence model to modify the basic nutrient requirement data of the plant to obtain the target nutrient requirement data. The environmental factor influence model is: Target nutrient requirement data = Basic nutrient requirement data * (1 + regional correction coefficient + seasonal correction coefficient + light correction coefficient);

[0041] According to the target nutrient requirement data, select the bubble mud type and determine the bubble mud ratio;

[0042] Predict the bubble mud replacement cycle, and the prediction of the bubble mud replacement cycle takes into account the plant nutrient absorption rate, the bubble mud nutrient release rate, and the environmental factor influence.

[0043] Further, in the present application, the step of modifying the basic nutrient requirement data of plants according to the environmental factor data by using the environmental factor influence model to obtain the target nutrient requirement data includes:

[0044] Obtain the longitude and latitude coordinates of the plant planting area, query the historical meteorological data of the corresponding area, and obtain the soil composition data, annual average precipitation data, and air humidity data;

[0045] Based on the soil composition data, use the soil nutrient conversion model to calculate the regional correction coefficient. The soil nutrient conversion model is: regional correction coefficient = α * (soil organic matter content / total soil nutrient content) + β * (soil pH value - 7), where α and β are model parameters and are adjusted according to the plant species;

[0046] Obtain the current date, determine the current season according to the preset season division rule, combine the plant growth cycle data, and use the non-linear season influence model to calculate the season correction coefficient. The non-linear season influence model is: season correction coefficient = γ * sin(2πt / T + φ), where γ is the season influence amplitude, t is the current time, T is the plant growth cycle, and φ is the phase offset. γ, T, and φ are adjusted according to the plant species and growth stage;

[0047] Obtain the light intensity data of the location where the plant is located, combine the spectral sensor to obtain the spectral data, and use the photosynthetic active radiation model to calculate the light correction coefficient. The photosynthetic active radiation model is: light correction coefficient = δ * PAR * (red light ratio / blue light ratio), where δ is the light influence factor, PAR is the photosynthetic active radiation intensity, and the red light ratio and blue light ratio are the spectral component ratios. δ is adjusted according to the plant species;

[0048] According to the regional correction coefficient, season correction coefficient, and light correction coefficient, use the environmental factor influence model to calculate the target nutrient requirement data.

[0049] Further, in the present application, the step of generating a bubble clay control plan including composition control, structure control, and replacement strategy if the deviation data exceeds the preset threshold includes:

[0050] If the deviation data exceeds the preset threshold, monitor the humidity, conductivity, and gas composition of the bubble clay, and judge whether there are risks of hardening, nutrient imbalance, and odor exceeding the standard for the bubble clay;

[0051] If there is a risk of hardening, adjust the bubble clay formula, increase the content of fiber materials, reduce the proportion of viscous components, generate a soil loosening instruction, prompt the user to perform a soil loosening operation, and increase the air permeability of the bubble clay;

[0052] If there is a risk of nutrient imbalance, analyze the nutrients in the bubble mud, determine the types of missing nutrients, generate a targeted nutrient supplementation instruction, and prompt the user to add the corresponding nutrients to balance the nutrients in the bubble mud.

[0053] If there is a risk of excessive odor, detect the gas components in the bubble mud, determine the types of odor gases, generate an activated carbon adsorption instruction or a bubble mud replacement instruction, and prompt the user to perform activated carbon adsorption or bubble mud replacement operations to eliminate the odor.

[0054] Further, in this application, the steps of performing bubble mud adjustment or replacement operations and guiding the user to perform environmental collaborative regulation include:

[0055] Evaluate the adaptability of the plant roots to the bubble mud adjustment or replacement, and adjust the light intensity, temperature and humidity according to the adaptability to obtain environmental factor regulation parameters.

[0056] According to the change of the plant transpiration rate, guide the user to adjust the indoor air humidity and ventilation volume to maintain the water balance of the plant.

[0057] Real-time monitor the light intensity of different parts of the plant, and guide the user to adjust the plant placement position or use light supplement equipment to achieve uniform overall illumination of the plant.

[0058] Further, in this application, a plant control device based on bubble mud is also proposed, which is used for the indoor potted plant cultivation scenario of families to configure and regulate the growth state of bubble mud for specific plant species. The device includes:

[0059] An acquisition module for acquiring plant species information and establishing a standard growth curve including height growth rate, leaf number, color change, and nutrient absorption.

[0060] A matching module for matching the bubble mud type, ratio, and replacement cycle based on the plant species information.

[0061] A monitoring module for monitoring the actual growth state of the plant and calculating the deviation data between the actual growth curve and the standard growth curve.

[0062] A generation module for generating a bubble mud regulation plan including composition regulation, structure regulation, and replacement strategy if the deviation data exceeds a preset threshold.

[0063] An execution module for performing bubble mud adjustment or replacement operations and guiding the user to perform environmental collaborative regulation.

[0064] An adjustment module for collecting the plant state after the operation, evaluating the control effect, and dynamically adjusting the subsequent control strategy to make the plant growth state approach the standard growth curve.

[0065] As can be seen from the above, a plant control method and device based on bubble mud provided by the present application configure bubble mud and regulate the growth state for different types of plants, achieving matching of bubble mud configuration with plant requirements, more targeted selection of bubble mud, reduction of fertilizer loss and environmental pollution, more accurate judgment of the timing for replacing and adjusting bubble mud, and more effective plant control. It has the advantages of matching of bubble mud configuration with plant requirements, more targeted selection of bubble mud, reduction of fertilizer loss and environmental pollution, more accurate judgment of the timing for replacing and adjusting bubble mud, and more effective plant control. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 FIG. is a schematic flowchart of a plant control method based on bubble mud provided by the present application.

[0067] Figure 2 FIG. is a schematic structural diagram of a plant control device based on bubble mud provided by the present application.

[0068] In the figure: 210, acquisition module; 220, matching module; 230, monitoring module; 240, generation module; 250, execution module; 260, adjustment module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0069] Next, the technical solutions in the present application will be clearly and completely described in conjunction with the accompanying drawings in the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Components of the present application described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0070] It should be noted that: similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0071] In the scenario of indoor potted plant cultivation in households, bubble clay, as a newly emerging soilless cultivation substrate, has been widely used. However, existing general-purpose bubble clay products are difficult to precisely match the specific nutrient requirements of different ornamental plants. When users choose bubble clay products, they often rely on vague product descriptions or limited botanical knowledge, resulting in poor plant growth conditions. In addition, users lack scientific and effective plant control methods and are difficult to accurately determine when to replace the bubble clay or add nutrients, affecting the effect of plant maintenance and management. These problems urgently require a plant control method based on bubble clay to configure the bubble clay and regulate the growth state for specific plant species.

[0072] Specifically, in a scenario of indoor potted plant cultivation in households, users may cultivate multiple ornamental plants simultaneously, such as Epipremnum aureum, Hedera nepalensis var. sinensis, and Cymbidium, etc. These plants have significant differences in nutrient requirements at different growth stages. For example, Epipremnum aureum requires a higher proportion of nitrogen fertilizer in the initial growth stage to promote leaf growth, while Cymbidium requires more phosphorus and potassium fertilizers during the flowering period. However, existing general-purpose bubble clay products cannot meet these differentiated nutrient requirements. Users may observe problems such as yellowing leaves of Epipremnum aureum, slow growth of Hedera nepalensis var. sinensis, or delayed flowering of Cymbidium, but it is difficult to accurately determine whether to replace the bubble clay or add specific nutrients.

[0073] In response to this, referring to Figure 1 , this application proposes a plant control method based on bubble clay for configuring the bubble clay and regulating the growth state for specific plant species in the scenario of indoor potted plant cultivation in households. This method includes:

[0074] S110. Obtain plant species information and establish a standard growth curve including height growth rate, number of leaves, color change, and nutrient absorption;

[0075] S120. Based on the plant species information, match the type, ratio, and replacement cycle of the bubble clay;

[0076] S130. Monitor the actual growth state of the plant and calculate the deviation data between the actual growth curve and the standard growth curve;

[0077] S140. If the deviation data exceeds the preset threshold, generate a bubble clay regulation plan including composition regulation, structure regulation, and replacement strategy;

[0078] S150. Perform bubble clay adjustment or replacement operations and guide users to conduct environmental collaborative regulation;

[0079] S160. Collect the plant state after the operation, evaluate the control effect, and dynamically adjust the subsequent control strategy to make the plant growth state approach the standard growth curve.

[0080] Among them, the standard growth curve refers to an ideal growth state curve established for a specific plant species, including indicators such as height growth rate, leaf number, color change, nutrient absorption, etc.

[0081] Among them, the bubble mud type refers to bubble mud products with different ingredient ratios and structural characteristics. Specifically, various raw material combinations can be designed, such as fiber materials, water-retaining materials, nutrient-release materials, etc., to meet the growth requirements of different plants.

[0082] Among them, the deviation data refers to the difference value between the actual growth curve and the standard growth curve. Specifically, a weighted calculation method of multi-dimensional indicators can be used to quantify the deviation degree of the plant growth state from the ideal state, providing a basis for the generation of subsequent regulation schemes.

[0083] Among them, the bubble mud regulation scheme refers to the bubble mud adjustment strategy formulated for plant growth deviation. Specifically, it can include ingredient regulation (such as adjusting nutrient ratios), structural regulation (such as changing density), and replacement strategies (such as partially or completely replacing the bubble mud) to optimize the plant growth environment.

[0084] Among them, environmental collaborative regulation refers to the corresponding adjustment of environmental factors such as light, temperature, and humidity while adjusting the bubble mud. Specifically, intelligent device assistance or user manual operation can be used to achieve the comprehensive optimization of the plant growth environment.

[0085] The core innovation of this application is to propose precise bubble mud configuration and growth state regulation for specific plant species by establishing a standard growth curve, matching bubble mud types, monitoring the actual growth state, generating regulation schemes, performing adjustment operations, and dynamically evaluating the effects. This method overcomes the problem that general-purpose bubble mud products are difficult to meet the specific nutrient requirements of different plants, and at the same time provides users with a scientific and effective plant management method, improving the effect of indoor potted plant cultivation and the user experience.

[0086] The working principle of this application is described as follows:

[0087] First, by obtaining plant species information, a standard growth curve including height growth rate, leaf number, color change, and nutrient absorption is established. This step uses a plant growth database or an expert knowledge system to construct an ideal growth state model for each plant.

[0088] Next, based on the plant species information, the bubble mud type, ratio, and replacement cycle are matched. This step selects the most suitable type from the bubble mud product library by analyzing the physiological characteristics and growth requirements of the plant, and determines the initial ratio and estimated replacement cycle.

[0089] Then, continuously monitor the actual growth status of the plant, including analyzing the appearance of the plant using image recognition technology and detecting the environmental parameters of the bubble mud using sensors. Through a data processing algorithm, calculate the deviation data between the actual growth curve and the standard growth curve.

[0090] When the deviation data exceeds the preset threshold, trigger a regulation plan. Considering the plant growth stage, environmental factors, and historical regulation effects, generate a bubble mud regulation plan that includes component regulation, structural regulation, and replacement strategies.

[0091] Subsequently, perform bubble mud adjustment or replacement operations. For component regulation, it may involve adding specific nutrients or adjusting the pH value; for structural regulation, it may include changing the density or layered structure of the bubble mud; for replacement strategies, it may be partial or complete replacement of the bubble mud. At the same time, guide the user to perform environmental co-regulation, such as adjusting the light intensity, humidity, etc.

[0092] Finally, collect the plant status after the operation, and evaluate the control effect by comparing image analysis and sensor data. Based on the evaluation results, the system will dynamically adjust subsequent control strategies, such as adjusting the threshold, optimizing the regulation plan generation algorithm, etc., to form a closed-loop feedback system and continuously optimize the plant growth status.

[0093] As a preferred implementation manner, the present application can be applied to the scenario of growing Epipremnum aureum indoors at home. The specific implementation steps are as follows:

[0094] First, the user inputs the plant species information "Epipremnum aureum" through a mobile application. The system retrieves the standard growth curve of Epipremnum aureum from the database, including the weekly height growth rate (such as 1.5 - 2 cm / week), the leaf number increase rate (such as 1 - 2 leaves / week), the standard value of leaf color (such as chlorophyll content index 40 - 50), and the nutrient absorption curve.

[0095] Then, the system matches the type of bubble mud suitable for the growth of Epipremnum aureum, such as selecting a bubble mud product rich in nitrogen elements and having good water retention performance. The initial ratio may be 70% bubble mud substrate + 30% water retention particles, and the estimated replacement cycle is 3 months.

[0096] Collect the growth data of Epipremnum aureum every day through the camera and sensors installed on the flower pot. For example, use image processing technology to measure the plant height and the number of leaves, use a chromaticity sensor to detect the leaf color, and monitor the nutrient content in the bubble mud through a conductivity sensor.

[0097] Suppose that after 45 days of planting, the system detects a deviation in the actual growth curve of Epipremnum aureum: the height growth rate drops to 1 cm / week, and the leaf color turns yellow (the chlorophyll content index drops to 35). These deviation data exceed the preset 20% threshold.

[0098] System-generated regulation plan: Component regulation: Increase the nitrogen element content and add 5g of slow-release nitrogen fertilizer; Structure regulation: Increase the proportion of water-retaining particles by 10% to improve the water retention capacity; Replacement strategy: It is recommended to replace 25% of the bubble mud after 30 days.

[0099] The user performs the regulation operation according to the system guidance. At the same time, the system recommends moving the Epipremnum aureum to a place with more sufficient light and appropriately increasing the indoor humidity.

[0100] One week after implementing the regulation measures, the system collects the state data of the Epipremnum aureum again. It is found that the height growth rate has rebounded to 1.8 cm / week, and the leaf color has returned to normal (the chlorophyll content index reaches 45). The system evaluates that the regulation effect is good and incorporates this successful experience into the algorithm optimization for future handling of similar situations.

[0101] Through this continuous cycle of monitoring, analysis, regulation, and evaluation, the system can keep the growth state of the Epipremnum aureum always close to the optimal curve, achieving precise plant control based on bubble mud.

[0102] In some of the above embodiments of this application, a bubble mud regulation plan including component regulation, structure regulation, and replacement strategy is proposed to address plant growth deviations. However, there are the following problems in this process: First, the consideration of users' personalized planting needs is lacking, and it is difficult to meet different users' specific expectations for the plant growth state; Second, no clear target growth curve is established, and it is impossible to accurately measure the deviation between the actual growth state of the plant and the expected state; Third, the lack of detailed analysis of the deviation type and degree makes it difficult to formulate targeted regulation plans; Finally, the generation process of the regulation plan lacks systematicness and comprehensiveness, which may lead to poor regulation effects.

[0103] In response, this application further proposes that if the deviation data exceeds the preset threshold, obtain the users' personalized planting needs and establish a user expectation curve including plant height control goals and flowering promotion goals; fuse the standard growth curve and the user expectation curve to obtain the target growth curve; analyze the deviation data to determine the deviation type and degree between the actual growth state of the plant and the target growth curve; select a regulation plan from the bubble mud component regulation library, structure regulation library, and replacement strategy library according to the deviation type and degree and plant species information, and generate a bubble mud regulation plan including component regulation instructions, structure regulation instructions, and replacement strategy instructions; among them, the component regulation instructions include nutrient type, quantity, and release rate, the structure regulation instructions include bubble mud density, layered structure, and air permeability, and the replacement strategy instructions include replacement timing, replacement ratio, and new bubble mud type.

[0104] The technical solution of this application aims at the indoor household potted plant cultivation scenario. Considering the problem that different users have different expectations for plants and general maintenance guidance is difficult to meet the customized needs of users, a customized maintenance guidance method is provided. Specifically, this method includes the following main steps:

[0105] First, obtain the user's personalized cultivation needs and establish a user expectation curve including plant height control goals and flowering promotion goals. This step can be achieved through various methods. For example, a user interaction interface can be designed to allow users to input their specific expectations for plant height and flowering time. Additionally, the user expectation curve can be automatically generated by analyzing the user's historical cultivation data and preferences.

[0106] Second, fuse the standard growth curve and the user expectation curve to obtain the target growth curve. This step can adopt the method of weighted average to fuse the standard growth curve and the user expectation curve. The weights can be dynamically adjusted according to the characteristics of the plant species and the rationality of the user's expectations. For example, for some plants with relatively fixed growth characteristics, a higher weight can be given to the standard growth curve; while for some ornamental plants with more flexible growth, the weight of the user expectation curve can be appropriately increased.

[0107] Next, analyze the deviation data to determine the deviation type and degree between the actual growth state of the plant and the target growth curve. This step can be achieved by establishing a multi-dimensional deviation evaluation model. This model can consider multiple indicators such as the height, number of leaves, color, and flowering situation of the plant, calculate the deviation values in each dimension by comparing with the target growth curve, and then classify the deviations into different types (such as slow growth, excessive growth, etc.) and degrees (such as slight, moderate, severe) according to the preset thresholds.

[0108] Finally, according to the deviation type and degree and the plant species information, select a regulation plan from the bubble mud composition regulation library, structure regulation library, and replacement strategy library, and generate a bubble mud regulation plan including composition regulation instructions, structure regulation instructions, and replacement strategy instructions. This step can be achieved by establishing a decision tree or a rule library. For example, for the case of slow growth, a plan to increase the nutrient release rate may be selected from the composition regulation library; for the case of excessive growth, a plan to increase the porosity of the bubble mud may be selected from the structure regulation library. At the same time, the compatibility between different regulation plans needs to be considered to ensure that the generated comprehensive regulation plan is feasible and efficient.

[0109] Through the above steps, the technical solution of this application can achieve refined and personalized management of indoor household potted plants.

[0110] As a specific embodiment, consider the planting scenario of an indoor ornamental plant, such as Epipremnum aureum. The user hopes that the Epipremnum aureum can reach a height of 50 cm within 3 months and start to have new branches after 2 months. Based on these requirements, the system first establishes the user's expected curve. Then, the system combines this user's expected curve with the standard growth curve of Epipremnum aureum to obtain the target growth curve.

[0111] During the planting process, the system monitors the actual growth status of Epipremnum aureum every day through image recognition technology. Suppose that after 1 month of planting, the system finds that the actual height of Epipremnum aureum is 15 cm, while the height on the target growth curve should be 20 cm. Then, this deviation is determined as "growth retardation" and the degree of deviation is "moderate".

[0112] Based on this judgment, a scheme to increase the nitrogen element release rate is selected from the bubble mud composition regulation library, and a scheme to increase the air permeability of the bubble mud is selected from the structure regulation library. Specifically, the composition regulation instruction includes: increasing the nitrogen element release rate from the original 2 mg / day to 3 mg / day; the structure regulation instruction includes: reducing the density of the bubble mud from the original 0.3 g / cm 3 to 0.25 g / cm 3 to increase the air permeability.

[0113] At the same time, a replacement strategy instruction is also generated: if the growth rate of Epipremnum aureum still does not reach the target within the next two weeks, it is recommended that the user replace 25% of the existing bubble mud with new bubble mud with a higher nutrient content.

[0114] In this way, the technical solution of this application can provide users with refined and personalized plant management solutions, effectively improving the success rate of indoor potted plant cultivation and user satisfaction.

[0115] In some of the above embodiments of this application, steps of analyzing deviation data and determining the deviation type and degree between the actual growth status of the plant and the target growth curve are proposed to determine the difference between the plant growth status and the expected target. However, in this process, there are problems such as incomplete data collection, inaccurate data processing, and insufficient deviation analysis. This may lead to inaccurate assessment of the plant growth status, thus affecting the formulation and implementation effect of the subsequent bubble mud regulation plan.

[0116] In response to this, the present application further proposes to collect multi-source data on the growth state of plants, where the multi-source data includes image data, sensor data, and user input data; for the multi-source data, data synchronization processing is performed based on timestamps to obtain synchronized multi-source data; the synchronized multi-source data is preprocessed to obtain preprocessed multi-source data; based on the preprocessed multi-source data, deviation data on the height growth rate, number of leaves, color change, and nutrient absorption between the actual growth state of the plant and the target growth curve is calculated; according to the deviation data, the deviation type and deviation degree between the actual growth state of the plant and the target growth curve are determined, where the deviation type includes growth retardation, excessive growth, malnutrition, and pests and diseases, and the deviation degree includes slight, moderate, and severe.

[0117] The present application collects multi-source data on the growth state of plants, including image data, sensor data, and user input data. The image data can be obtained through high-definition cameras installed around the plants to capture the appearance characteristics of the plants, such as plant height, number of leaves, and color change. The sensor data can be collected through multi-functional sensors implanted in the bubble mud, including parameters such as temperature, humidity, pH value, and conductivity. The user input data is collected through a mobile application or a web interface, including the user's subjective evaluation and observation records of the plant growth status.

[0118] For the multi-source data, the present application performs data synchronization processing based on timestamps. Specifically, a unified data collection period can be set, for example, collecting data once per hour. At each collection, the same timestamp is marked for the data of all data sources. In this way, it is ensured that the data from different sources is consistent in time, providing a reliable data basis for subsequent analysis.

[0119] The synchronized multi-source data is preprocessed to obtain preprocessed multi-source data. The preprocessing steps include image data denoising, sensor data calibration, and user input data cleaning. Image data denoising can use algorithms such as Gaussian filtering or median filtering to eliminate random noise in the image. Sensor data calibration is performed through comparison tests with standard devices to establish a calibration curve and correct the systematic errors of the sensors. User input data cleaning is achieved by setting reasonable numerical ranges and logical checks to eliminate obviously incorrect or abnormal inputs.

[0120] Based on the preprocessed multi-source data, the present application calculates the deviation data on the height growth rate, number of leaves, color change, and nutrient absorption between the actual growth state of the plant and the target growth curve. The height growth rate can be obtained through the analysis of consecutive image data, the number of leaves is automatically counted through an image recognition algorithm, and the color change is quantified by comparing the RGB value changes of the plant leaves in the image. Nutrient absorption can be indirectly evaluated by analyzing the conductivity changes in the sensor data.

[0121] Based on the calculated deviation data, the present application determines the deviation type and degree between the actual growth state of the plant and the target growth curve. The deviation types include growth retardation, excessive growth, malnutrition, and pests and diseases. For example, when the height growth rate is significantly lower than the target curve, it can be determined as growth retardation; when the number of leaves decreases sharply or the color is abnormal, it may indicate problems of malnutrition or pests and diseases. The deviation degree is divided into three levels: mild, moderate, and severe, which can be divided by setting different thresholds. For example, for the height growth rate, a deviation less than 10% from the target curve can be defined as mild, 10%-30% as moderate, and greater than 30% as severe.

[0122] By adopting the method of multi-source data acquisition and synchronous processing, the present application significantly improves the comprehensiveness and accuracy of the data. The fusion of multi-source data makes the evaluation of the plant growth state more comprehensive and objective, avoiding the one-sidedness that may be brought by a single data source. Timestamp synchronization ensures the time consistency of data from different sources, providing a reliable data basis for subsequent analysis. The data preprocessing step further improves the data quality and reduces the influence of noise and errors on the analysis results.

[0123] Based on high-quality multi-source data, the present application can more accurately calculate the deviation between the actual growth state of the plant and the target growth curve. By comprehensively considering multiple aspects such as height growth rate, number of leaves, color change, and nutrient absorption, a comprehensive evaluation of the plant growth state is carried out. This multi-dimensional deviation analysis method can identify abnormal situations in plant growth earlier and more accurately.

[0124] Furthermore, the present application provides a more refined and targeted basis for formulating subsequent bubble mud regulation schemes by combining the deviation type and degree. For example, for plants determined to be moderately malnourished, corresponding bubble mud nutrient supplementation strategies can be formulated; for slightly excessive growth, the structure of the bubble mud may need to be adjusted to appropriately control the growth rate.

[0125] As a preferred implementation manner, the present application can be implemented in a home intelligent plant growth system. The system includes a multi-functional sensor module installed near the plant pot, integrating a high-definition camera, temperature and humidity sensors, pH sensors, and conductivity sensors. The system is also equipped with a central processing unit responsible for data acquisition, synchronization, and preprocessing. Users can interact with the system through a smartphone application, input observation records, and view analysis results.

[0126] Specifically, the system automatically collects multi-source data once an hour. The image data is captured by a high-definition camera with a resolution of 4K, ensuring that the subtle changes of plants can be clearly captured. The user input data is collected through the structured form of the application, including the plant appearance score (1-5 points) and the description of abnormal phenomena.

[0127] The data synchronization process uses NTP (Network Time Protocol) to ensure the time consistency of all devices. In the preprocessing stage, the image data is denoised using a 3x3 Gaussian filter, the sensor data is corrected through a pre-established quadratic polynomial calibration curve, and the user input data is cleaned of abnormal inputs through setting a reasonable numerical range (such as a score of 1-5) and keyword detection.

[0128] Machine learning algorithms (such as convolutional neural networks) are used to extract information on plant height and the number of leaves from the images. The color change is quantified by comparing the average HSV values of the leaf areas in consecutive images. The nutrient uptake is evaluated by analyzing the trend of the conductivity change.

[0129] The determination of the deviation type and degree is based on a preset decision tree model. For example, when the height growth rate for three consecutive days is lower than 80% of the target curve, it is determined as mild growth retardation; when it is lower than 60%, it is determined as moderate growth retardation; when it is lower than 40%, it is determined as severe growth retardation. Similarly, corresponding thresholds are set for the indicators of the number of leaves, color change, and nutrient uptake.

[0130] In this way, the system can generate a detailed plant growth status report every day, including the specific values of various indicators and the determination results of the deviation type and degree. This information provides accurate decision-making basis for users and the automated bubble mud regulation system, significantly improving the scientificity and success rate of home plant cultivation.

[0131] In some of the above embodiments of the present application, steps are proposed to generate a bubble mud regulation plan by selecting a regulation plan from the bubble mud composition regulation library, structure regulation library, and replacement strategy library according to the deviation type, deviation degree, and plant species information, and generating a bubble mud regulation plan containing composition regulation instructions, structure regulation instructions, and replacement strategy instructions. However, in this process, how to effectively integrate multi-dimensional information such as plant species, deviation type, and deviation degree, and quickly and accurately select the most suitable plan from a large number of regulation plans is still a challenge. In addition, how to ensure that the selected regulation plan is not only effective for a single factor but can also coordinately improve the plant growth status in multiple aspects is also a problem that needs to be solved.

[0132] In response to this, the present application further proposes a technical solution for constructing a bubble mud regulation knowledge graph, performing multi-hop search based on plant species information, deviation type, and deviation degree, calculating the confidence scores of candidate regulation schemes, and selecting the regulation scheme with the highest confidence score to generate a bubble mud regulation scheme.

[0133] The present application constructs a bubble mud regulation knowledge graph, which includes plant species nodes, deviation type nodes, deviation degree nodes, component regulation scheme nodes, structural regulation scheme nodes, replacement strategy nodes, and the association relationships between the nodes. This structured knowledge representation method can effectively integrate and associate multi-dimensional information, providing a comprehensive knowledge basis for subsequent selection of regulation schemes.

[0134] Based on the constructed knowledge graph, the present application uses multi-hop search to obtain a set of candidate regulation schemes. Specifically, starting from the plant species node, the first-hop search is performed according to the plant species information to obtain the associated sets of deviation type nodes and deviation degree nodes. Then, starting from these nodes, the second-hop search is performed to obtain the associated sets of component regulation scheme nodes, structural regulation scheme nodes, and replacement strategy nodes. This multi-hop search method can effectively utilize the association relationships in the knowledge graph to quickly locate the regulation schemes related to the current plant condition.

[0135] In order to select the most suitable scheme from the candidate regulation schemes, the present application introduces a confidence score mechanism. The confidence score comprehensively considers the association strength between the regulation scheme and plant species, deviation type, and deviation degree, as well as the compatibility between regulation schemes. This multi-dimensional scoring mechanism can comprehensively evaluate the applicability and effectiveness of each regulation scheme.

[0136] Finally, the present application selects the regulation scheme with the highest confidence score from the set of candidate regulation schemes according to the calculated confidence scores, and generates a bubble mud regulation scheme including component regulation instructions, structural regulation instructions, and replacement strategy instructions. This scoring-based selection method can ensure that the selected regulation scheme can coordinately improve the plant growth state in multiple aspects.

[0137] The present application realizes the structured representation of the complex relationship between plant species, deviation type, deviation degree, and regulation scheme by constructing a bubble mud regulation knowledge graph. This structured knowledge representation provides a comprehensive knowledge basis for subsequent selection of regulation schemes, avoiding selection difficulties caused by insufficient information.

[0138] Based on the knowledge graph, this application uses a multi-hop search method to obtain a set of candidate regulation solutions. This search method can make full use of the association relationships in the knowledge graph to quickly locate regulation solutions related to the current plant situation. Compared with traditional methods of one-by-one matching or rule query, multi-hop search can handle complex association relationships more efficiently, greatly improving the efficiency of retrieving regulation solutions.

[0139] As a specific implementation, the bubble clay regulation knowledge graph of this application can be implemented using a graph database. In this graph database, plant species nodes can contain attributes such as "species name", "growth cycle", "suitable temperature range", etc.; deviation type nodes can contain attributes such as "deviation name", "influence degree", etc.; deviation degree nodes can contain attributes such as "degree level", "numerical range", etc.; regulation solution nodes (including composition regulation solutions, structure regulation solutions, and replacement strategies) can contain attributes such as "solution name", "applicable conditions", "expected effects", etc.

[0140] When performing multi-hop search, the Cypher query language can be used to achieve it. For example, for a rose with slow growth, the Cypher query for the first-hop search may be as follows:

[0141] ```

[0142] MATCH(p:PlantSpecies{name:'Rose'})-[:HAS_DEVIATION]->(d:DeviationType{name:'Slow growth'})

[0143] RETURN p,d

[0144] ```

[0145] The Cypher query for the second-hop search may be as follows:

[0146] ```

[0147] MATCH(d:DeviationType{name:'Slow growth'})-[:HAS_SOLUTION]->(s:Solution)

[0148] WHERE s:CompositionControl OR s:StructureControl OR s:ReplacementStrategy

[0149] RETURN s

[0150] ```

[0151] When calculating the confidence score, the method of weighted summation can be adopted. For example, for a regulation scheme s, its confidence score can be expressed as:

[0152] Score(s) = w1 * R(s, p) + w2 * R(s, d) + w3 * C(s);

[0153] Among them, R(s, p) represents the association strength between the regulation scheme s and the plant species p, R(s, d) represents the association strength between the regulation scheme s and the deviation type d, C(s) represents the compatibility score of the regulation scheme s, and w1, w2, and w3 are weight coefficients.

[0154] In this way, this application can provide customized bubble mud regulation schemes for different plant species and growth conditions, significantly improving the use effect of bubble mud in the family indoor potted plant cultivation scenario. At the same time, this method based on the knowledge graph and multi-dimensional scoring also has good scalability and can continuously optimize the regulation effect with the accumulation of knowledge.

[0155] In some of the above embodiments of this application, steps for calculating the confidence scores of each regulation scheme in the candidate regulation scheme set are proposed to select the most suitable regulation scheme from the candidate regulation scheme set. However, in this process, there are still challenges in how to comprehensively consider the association strengths of the regulation scheme with the plant species, deviation type, and deviation degree, as well as the compatibility between regulation schemes, so as to calculate an accurate confidence score. Simply linearly weighting each factor may not fully reflect the complex association relationship and it is also difficult to ensure the effectiveness of the selected regulation scheme in practical applications.

[0156] In response to this, the present application further proposes to obtain the association relationship data between each node in the bubble mud regulation knowledge graph. The association relationship data includes the first association strength between the plant species node and the ingredient regulation scheme node, the second association strength between the deviation type node and the ingredient regulation scheme node, the third association strength between the deviation degree node and the ingredient regulation scheme node, and the compatibility score between the ingredient regulation scheme nodes. For each regulation scheme in the candidate regulation scheme set, according to the ingredient regulation scheme nodes it contains, calculate its weighted association strength with the plant species node, the deviation type node, and the deviation degree node. The weighted association strength is obtained by weighted summation of the first association strength, the second association strength, and the third association strength, and the weight coefficient is determined according to the plant species, the deviation type, and the deviation degree. Calculate the compatibility score of each regulation scheme in the candidate regulation scheme set. The compatibility score is obtained by weighted averaging the compatibility scores between the ingredient regulation scheme nodes in the regulation scheme, and the weight coefficient is determined according to the role size of each ingredient regulation scheme node. Perform a weighted summation of the weighted association strength and the compatibility score to obtain the confidence score of each regulation scheme in the candidate regulation scheme set, and the weight coefficient is determined according to the association strength and the compatibility.

[0157] The technical solution proposed by the present application first obtains the association relationship data between each node in the bubble mud regulation knowledge graph. These data include the first association strength between the plant species node and the ingredient regulation scheme node, the second association strength between the deviation type node and the ingredient regulation scheme node, the third association strength between the deviation degree node and the ingredient regulation scheme node, and the compatibility score between the ingredient regulation scheme nodes. By obtaining these association relationship data, a comprehensive data basis is provided for the subsequent confidence score calculation.

[0158] Next, for each regulation scheme in the candidate regulation scheme set, calculate its weighted association strength with the plant species node, the deviation type node, and the deviation degree node. This step is achieved by weighted summation of the first association strength, the second association strength, and the third association strength. The determination of the weight coefficient is based on the plant species, the deviation type, and the deviation degree. In this way, the weight can be dynamically adjusted according to the importance of different factors to improve the accuracy of the evaluation. For example, for certain plant species, the influence of the deviation type may be more emphasized, and at this time, the weight of the second association strength can be increased; while for other plant species, the deviation degree may be more concerned, and the weight of the third association strength can be correspondingly increased.

[0159] Then, calculate the compatibility scores of each regulatory scheme in the candidate regulatory scheme set. This step is achieved by performing a weighted average of the compatibility scores between the component regulatory scheme nodes in the regulatory scheme. The weight coefficients are determined based on the magnitudes of the effects of the component regulatory scheme nodes, which can more accurately reflect the importance of different components in the overall regulatory scheme. For example, for certain regulatory schemes, a specific component may play a key role, so the weight of the corresponding node of this component can be increased; for other regulatory schemes, multiple components may act together, and the weights can be relatively evenly distributed.

[0160] Finally, perform a weighted sum of the weighted association strength and the compatibility score to obtain the confidence scores of each regulatory scheme in the candidate regulatory scheme set. The weight coefficients are determined based on the importance degrees of the association strength and the compatibility, so that the correlation between the regulatory scheme and the plant growth state and the compatibility of the components within the regulatory scheme can be balanced in the final score.

[0161] In this way, the technical solution of the present application can more comprehensively and accurately evaluate the effectiveness of the candidate regulatory schemes. The calculation of the weighted association strength takes into account the association degrees of the regulatory scheme with the plant species, the deviation type, and the deviation degree, ensuring that the selected regulatory scheme can precisely regulate the growth condition of a specific plant. The calculation of the compatibility score takes into account the interactions between the components within the regulatory scheme, avoiding situations where the components in the selected regulatory scheme conflict or cancel each other out in practical applications.

[0162] The final confidence score can better reflect the overall performance of the regulatory scheme by comprehensively considering the weighted association strength and the compatibility score. This scoring method not only considers the matching degree between the regulatory scheme and the plant growth state but also considers the feasibility of the regulatory scheme itself, thereby improving the accuracy of selecting the most suitable regulatory scheme.

[0163] As a specific embodiment, the following scenario can be considered: Suppose there is an indoor ornamental plant with slow growth. Through the foregoing steps, the deviation type has been determined to be "growth retardation" and the deviation degree is "moderate". Now, it is necessary to select the most suitable regulatory scheme from the candidate regulatory scheme set.

[0164] First, obtain the association relationship data from the bubble clay regulation knowledge graph. For example, for the plant species "indoor ornamental plant", the first association strength with the component regulatory scheme "increase nitrogen fertilizer" is 0.8, the second association strength with the deviation type "growth retardation" is 0.9, and the third association strength with the deviation degree "moderate" is 0.7. At the same time, the compatibility score between "increase nitrogen fertilizer" and "increase phosphate fertilizer" is 0.85.

[0165] Then, calculate the weighted association strength. Assuming that according to the current situation, the weights of plant species, deviation type, and deviation degree are determined to be 0.3, 0.4, and 0.3 respectively. Then, for the regulation plan containing "increasing nitrogen fertilizer", its weighted association strength is: 0.8 * 0.3 + 0.9 * 0.4 + 0.7 * 0.3 = 0.81.

[0166] Next, calculate the compatibility score. Assuming that the regulation plan contains two components, "increasing nitrogen fertilizer" and "increasing phosphate fertilizer", and their weights of action sizes are 0.6 and 0.4 respectively. Then, the compatibility score of this regulation plan is: 0.85 * 0.6 + 0.85 * 0.4 = 0.85.

[0167] Finally, calculate the confidence score. Assuming that the weights of the weighted association strength and the compatibility score are 0.7 and 0.3 respectively. Then, the final confidence score of this regulation plan is: 0.81 * 0.7 + 0.85 * 0.3 = 0.822.

[0168] In this way, a confidence score can be calculated for each plan in the candidate regulation plan set, and the plan with the highest score is selected as the final bubble clay regulation plan. This scoring method can comprehensively consider the matching degree of the regulation plan with the plant growth status and the feasibility of the regulation plan itself, thereby improving the accuracy of selecting the most suitable regulation plan and further enhancing the effect of plant control.

[0169] In some of the above embodiments of the present application, steps of matching the bubble clay type, ratio, and replacement cycle based on plant species information are proposed to provide a suitable growth environment for different plants. However, in this process, relying solely on plant species information may not fully consider the impact of environmental factors on plant growth. Under different geographical locations, seasons, and light conditions, even the same plant may show different nutrient requirements. Therefore, a more accurate and dynamic method is needed to determine the configuration parameters of the bubble clay to adapt to the actual growth requirements of plants in different environments.

[0170] For this, the present application further proposes to obtain environmental factor data of geographical location, season, and light intensity, and construct an environmental factor database; extract the basic nutrient requirement data of plants based on plant species information; according to the environmental factor data, use the environmental factor influence model to correct the basic nutrient requirement data of plants to obtain the target nutrient requirement data, and the environmental factor influence model is: target nutrient requirement data = basic nutrient requirement data * (1 + geographical correction coefficient + season correction coefficient + light correction coefficient); according to the target nutrient requirement data, select the bubble clay type and determine the bubble clay ratio; predict the bubble clay replacement cycle, and the prediction of the bubble clay replacement cycle considers the plant nutrient absorption rate, the nutrient release rate of the bubble clay, and the influence of environmental factors.

[0171] The technical solution proposed in this application first obtains environmental factor data such as region, season, and light intensity, and constructs an environmental factor database. This step provides an environmental parameter basis for subsequent correction of plant nutrient requirements, effectively solving the problem of unreasonable configuration of bubble mud caused by ignoring environmental factors. The construction of the environmental factor database realizes the centralized management and rapid query of environmental factor data, ensuring the efficiency of data acquisition.

[0172] Extracting the basic nutrient requirement data of plants based on plant species information is the second key step of this solution. This provides basic data for subsequent correction of nutrient requirements, solving the problem of inaccurate configuration of bubble mud caused by lack of plant nutrient requirement information. Different plant species have different requirements for nutrients such as nitrogen, phosphorus, and potassium, and this step provides a basic basis for the configuration of bubble mud.

[0173] The introduction of the environmental factor influence model is the core innovation point of this solution. Through the formula: Target nutrient requirement data = Basic nutrient requirement data * (1 + Region correction coefficient + Season correction coefficient + Light correction coefficient), the dynamic adjustment of plant nutrient requirements is achieved. This solves the problem of inapplicable configuration of bubble mud caused by environmental changes. The use of correction coefficients quantitatively evaluates the influence of environmental factors, ensuring the accuracy of correction results.

[0174] Selecting the type of bubble mud and determining the ratio according to the target nutrient requirement data is the implementation step of this solution. This realizes the precise selection and ratio of the type of bubble mud, solving the problem of poor plant growth caused by mismatched type or improper ratio of bubble mud. Different types of bubble mud contain different nutrient combinations and contents, and this step ensures that the selected bubble mud can meet the growth requirements of plants.

[0175] Finally, this solution considers the prediction of the bubble mud replacement cycle. By comprehensively considering the plant nutrient absorption rate, the nutrient release rate of bubble mud, and the influence of environmental factors, a reasonable prediction of the bubble mud replacement time is achieved. This solves the problem of affecting plant growth due to untimely or frequent replacement, ensuring the accuracy of prediction results.

[0176] As a preferred implementation method, the environmental factor influence model can be further refined. For example, the calculation of the region correction coefficient can adopt the soil nutrient transformation model: Region correction coefficient = α * (Soil organic matter content / Total soil nutrient content) + β * (Soil pH value - 7). Where α and β are model parameters, adjusted according to plant species. This method considers the influence of soil organic matter content, total nutrient content, and pH value on plant nutrient absorption, making the region correction more accurate.

[0177] The seasonal correction coefficient can adopt a non - linear seasonal influence model: Seasonal correction coefficient = γ * sin(2πt / T + φ). Where, γ is the amplitude of seasonal influence, t is the current time, T is the plant growth cycle, and φ is the phase offset. γ, T, and φ are adjusted according to the plant species and growth stage. This periodic function can better simulate the changes in nutrient requirements of plants at different growth stages.

[0178] The light correction coefficient can adopt a photosynthetic active radiation model: Light correction coefficient = δ * PAR * (red light ratio / blue light ratio). Where, δ is the light influence factor, PAR is the intensity of photosynthetic active radiation, and the red light ratio and blue light ratio are the spectral component ratios. δ is adjusted according to the plant species. This method not only considers the light intensity but also the influence of spectral components on plant growth, making the light correction more comprehensive.

[0179] In practical applications, the technical solution of this application can be implemented through the following steps:

[0180] First, obtain the longitude and latitude coordinates of the plant planting area, query the historical meteorological data of the corresponding area, and obtain soil composition data, annual average precipitation data, and air humidity data. For example, for an indoor foliage plant in a certain area, the data obtained may be: soil organic matter content 2.5%, total soil nutrient content 3%, soil pH value 7.2, annual average precipitation 540 mm, and average relative humidity 50%.

[0181] Then, based on these data, use the soil nutrient conversion model to calculate the regional correction coefficient. Assume α = 0.5, β = 0.2, then the regional correction coefficient = 0.5 * (2.5% / 3%) + 0.2 * (7.2 - 7) = 0.457.

[0182] Next, obtain the current date, and determine the current season according to the preset season division rules. Assume the current is spring and the plant is in the initial growth stage. Set γ = 0.3, T = 365 days, φ = π / 2, then the seasonal correction coefficient = 0.3 * sin(2π * 60 / 365 + π / 2) ≈ 0.295.

[0183] Furthermore, obtain the light intensity data and spectral data of the location where the plant is located. Assume the PAR value is 200 μmol / (m 2 ·s), the red light ratio is 60%, the blue light ratio is 30%, and δ = 0.001, then the light correction coefficient = 0.001 * 200 * (60% / 30%) = 0.4.

[0184] Finally, calculate the target nutrient requirement data according to the environmental factor influence model. Assume the basic nutrient requirement data is 100 units, then the target nutrient requirement data = 100 * (1 + 0.457 + 0.295 + 0.4) = 215.2 units.

[0185] Based on this target nutrient requirement data, a suitable type of bubble mud can be selected and the ratio can be determined. For example, a type of bubble mud with high nitrogen, medium phosphorus, and low potassium may be selected, with a ratio of 70% base bubble mud + 20% nitrogen fertilizer bubble mud + 10% water-retaining bubble mud.

[0186] In some specific embodiments, since the soil may be obtained by means of online purchase, the regional correction factor can be removed.

[0187] In some of the above embodiments of the present application, steps are proposed to adjust the nutrient requirements of plants by correcting the basic nutrient requirement data of plants using an environmental factor impact model based on environmental factor data to obtain target nutrient requirement data. However, in this process, there is a lack of precise consideration and quantitative processing of specific environmental factors, making it difficult to accurately reflect the impact of different regions, seasons, and light conditions on the nutrient requirements of plants. This may lead to inaccurate calculation of the target nutrient requirement data, thus affecting the adjustment of the subsequent bubble mud formula and the effect of plant growth management.

[0188] In response to this, the present application further proposes to obtain the longitude and latitude coordinates of the plant planting area, query the historical meteorological data of the corresponding area to obtain soil composition data, annual average precipitation data, and air humidity data; based on the soil composition data, calculate the regional correction factor using a soil nutrient transformation model; obtain the current date, determine the current season according to the preset season division rules, and combine the plant growth cycle data to calculate the season correction factor using a non-linear season impact model; obtain the light intensity data at the location where the plant is located, combine the spectral sensor to obtain spectral data, and calculate the light correction factor using a photosynthetic active radiation model; and calculate the target nutrient requirement data using the environmental factor impact model according to the regional correction factor, season correction factor, and light correction factor.

[0189] The technical solution of the present application realizes the refined regulation of plant nutrient requirements by introducing multiple precise environmental factor models. Specifically, the soil nutrient transformation model takes into account the effects of soil organic matter content, total nutrient content, and pH value on plant nutrient absorption. These parameters directly reflect the fertility status and nutrient availability of the soil, which are key factors affecting plant nutrient absorption. By adjusting the model parameters α and β, personalized adjustments can be made for different plant species, improving the accuracy and applicability of the regional correction factor.

[0190] The non-linear season impact model uses a sine function to simulate the impact of seasonal changes on plants. The advantage of this method is that it can better reflect the impact of seasonal cyclic changes on plant growth. The parameters γ, T, and φ in the model can be adjusted according to the plant species and growth stage, making the season correction factor more accurately reflect the seasonal demand changes of different plants at different growth stages.

[0191] The photosynthetically active radiation model takes into account the effects of light intensity and spectral composition on the nutrient requirements of plants. This model not only considers the photosynthetically active radiation intensity (PAR), but also introduces the red light ratio and blue light ratio, which reflect the different effects of different spectral components on plant growth. By adjusting the light influence factor δ, personalized adjustments can be made for different plant species to improve the accuracy of the light correction coefficient.

[0192] The combined use of these three models enables this application to comprehensively consider the effects of key environmental factors such as region, season, and light on the nutrient requirements of plants. Through the environmental factor influence model, these correction coefficients are integrated into the calculation of the target nutrient requirement data, achieving precise correction of the nutrient requirements of plants.

[0193] The technical solution of this application realizes more precise adjustment of the bubble clay formula and plant growth management by precisely quantifying the influence of environmental factors on the nutrient requirements of plants. This method first obtains the precise geographical location information of the plant planting area and obtains key environmental data such as soil composition, precipitation, and air humidity by querying historical meteorological data. Then, the regional correction coefficient is calculated using the soil nutrient transformation model, which takes into account the effects of soil organic matter content, total nutrient content, and pH value, and these factors are directly related to the nutrient absorption ability of plants.

[0194] Next, this application considers the influence of seasonal factors on plant growth. By obtaining the current date and combining the preset season division rules, the current season is determined. Combining the growth cycle data of plants, a non-linear seasonal influence model is used to calculate the seasonal correction coefficient. This model uses a sine function to simulate seasonal changes and can better reflect the periodic characteristics of plant growth.

[0195] The light condition, as another important factor affecting plant growth, is also taken into consideration. This application obtains the light intensity data of the location where the plant is located and combines the spectral data obtained by the spectral sensor, and uses the photosynthetically active radiation model to calculate the light correction coefficient. This model not only considers the light intensity, but also the spectral composition, especially the ratio of red light and blue light, which has an important impact on the photosynthesis and growth and development of plants.

[0196] Finally, this application comprehensively considers the regional correction coefficient, seasonal correction coefficient, and light correction coefficient, and uses the environmental factor influence model to calculate the final target nutrient requirement data. This method of comprehensively considering multiple environmental factors can more accurately reflect the actual nutrient requirements of plants in a specific environment.

[0197] Through this refined analysis and quantification of environmental factors, the present application can provide more accurate bubble mud formulations for different types of plants, at different geographical locations, in different seasons and under different lighting conditions. This method not only improves the pertinence of the bubble mud formulation, but also better meets the nutrient requirements of plants at different growth stages, thereby promoting the healthy growth of plants and increasing the success rate of home gardening.

[0198] In some of the above embodiments of the present application, it is proposed that if the deviation data exceeds a preset threshold, a bubble mud regulation scheme including composition regulation, structure regulation, and replacement strategy is generated to regulate the plant growth state. However, in this process, some problems with the bubble mud itself may occur, such as hardening, nutrient imbalance, and excessive odor, etc. These problems may affect the normal growth of plants and are difficult to solve through simple composition regulation, structure regulation, or replacement strategy. Therefore, a more comprehensive and refined bubble mud regulation scheme is needed to address these potential problems.

[0199] In response to this, the present application further proposes that if the deviation data exceeds a preset threshold, monitor the humidity, conductivity, and gas composition of the bubble mud, and determine whether there are risks of hardening, nutrient imbalance, and excessive odor in the bubble mud; if there is a risk of hardening, adjust the bubble mud formulation, increase the content of fiber materials, reduce the proportion of viscous components, generate a soil loosening instruction, and prompt the user to perform a soil loosening operation to increase the air permeability of the bubble mud; if there is a risk of nutrient imbalance, analyze the nutrients in the bubble mud, determine the types of missing nutrients, generate a targeted nutrient supplementation instruction, and prompt the user to add the corresponding nutrients to balance the nutrients in the bubble mud; if there is a risk of excessive odor, detect the gas composition of the bubble mud, determine the types of odor gases, generate an activated carbon adsorption instruction or a bubble mud replacement instruction, and prompt the user to perform an activated carbon adsorption or bubble mud replacement operation to eliminate the odor.

[0200] The technical solution of the present application relates to the steps of generating a bubble mud regulation scheme, and provides a bubble mud regulation scheme for the problems that the bubble mud is prone to hardening, nutrient imbalance, and odor generation during long-term use in the scenario of home indoor potted plant cultivation. Specifically, this scheme includes the following main steps:

[0201] First, monitor the humidity, conductivity, and gas composition of the bubble mud. This step can be achieved in various ways. For example, a humidity sensor can be used to measure the water content of the bubble mud, a conductivity sensor to measure the conductivity of the bubble mud, and a gas sensor to detect the gas composition released by the bubble mud. These sensors can be integrated into an intelligent monitoring device to collect data regularly or in real time.

[0202] Second, monitoring data is used to determine whether the bubble mud presents risks of compaction, nutrient imbalance, and excessive odor. This determination can be based on preset thresholds. For example, when humidity falls below a certain threshold, there may be a risk of compaction; when conductivity exceeds a certain range, there may be a risk of nutrient imbalance; and when the concentration of certain gas components exceeds the standard, there may be a risk of odor. These thresholds can be dynamically adjusted based on different plant species and growth stages.

[0203] Furthermore, in response to different risks, this application proposes corresponding regulatory measures:

[0204] To address the risk of compaction, adjust the bubble mud formula to increase the fiber content and reduce the proportion of sticky ingredients. Specifically, increase the proportion of loose materials such as coconut coir and vermiculite and reduce the proportion of sticky materials such as clay. At the same time, generate a soil loosening instruction, prompting the user to loosen the soil. Loosening can be achieved with specialized loosening tools or simply by turning the soil to increase the permeability of the bubble mud.

[0205] To identify nutrient imbalance risks, the bubble mud is analyzed to determine the missing nutrients. This can be done using a portable nutrient meter or laboratory analysis. Based on the analysis results, targeted nutrient replenishment instructions are generated, prompting the user to add the corresponding nutrients. For example, if nitrogen deficiency is detected, the user can be instructed to add a fertilizer with a high nitrogen content.

[0206] To address the risk of excessive odor, the mud gas composition is tested to determine the type of odorous gas. This can be accomplished using equipment such as gas chromatography-mass spectrometry. Based on the test results, instructions for activated carbon adsorption or mud replacement are generated. Activated carbon adsorption can be achieved by sprinkling a layer of activated carbon granules on the mud surface. Replacement requires the user to replace all or part of the mud according to the instructions.

[0207] Therefore, the technical solution of this application comprehensively monitors the state of the bubble mud and specifically addresses potential problems, thereby ensuring the normal growth of plants. Compared with simple ingredient regulation or replacement strategies, this method is more sophisticated and targeted, and can better adapt to the growth needs of different plants and environmental changes.

[0208] In some of the above-mentioned embodiments of the present application, it is proposed to perform bubble mud adjustment or replacement operations to guide users to coordinate environmental regulation to adapt to plant growth needs. However, the following problems may exist in this process: the degree of adaptation of plant roots to the adjustment or replacement of bubble mud may be different, which may lead to unstable growth; changes in plant transpiration rate may cause water imbalance; and uneven light intensity in different parts of the plant may affect overall growth. If these problems are not effectively solved, they may affect the healthy growth and ornamental effect of the plants.

[0209] In response to this, the present application further proposes to evaluate the adaptability of plant roots to the adjustment or replacement of bubble mud, adjust the light intensity, temperature and humidity according to the adaptability, and obtain environmental factor regulation parameters; according to the change of plant transpiration rate, guide the user to adjust the indoor air humidity and ventilation volume to maintain the water balance of the plant; and monitor the light intensity of different parts of the plant in real time, guide the user to adjust the plant placement position or use a supplementary lighting device to achieve uniform overall illumination of the plant.

[0210] The present application relates to the steps of performing the operation of adjusting or replacing the bubble mud and guiding the user to perform environmental collaborative regulation. In view of the differences in the adaptability of plant roots to the new environment in the indoor potted plant cultivation scenario at home, factors such as uneven light distribution and poor air circulation in the indoor environment will exacerbate the instability of the plant growth state, and an environmental collaborative regulation scheme is provided.

[0211] Evaluate the adaptability of plant roots to the adjustment or replacement of the bubble mud, and adjust the light intensity, temperature and humidity according to the adaptability to obtain environmental factor regulation parameters. This step is aimed at the problem that in the indoor potted plant cultivation scenario at home, the adaptability of plant roots to the new bubble mud environment is uncertain, and directly adjusting the environment may cause discomfort to the plant. By evaluating the adaptability of plant roots to the adjustment or replacement of the bubble mud, quantifying the acceptance degree of the plant to the new environment, and adjusting the light intensity, temperature and humidity according to the adaptability, the environmental factor regulation parameters are matched with the adaptability of plant roots, avoiding adverse effects on the plant caused by environmental mutations, and ensuring a smooth transition of the plant.

[0212] In specific implementation, various methods can be used to evaluate the adaptability of plant roots. For example, the growth state of plant roots can be observed, such as indicators like the color, length, and distribution density of the roots, to evaluate. Another method is to use impedance measurement technology to judge the adaptability by measuring the resistance change between the roots and the bubble mud. According to the evaluation results, a progressive adjustment strategy can be adopted to gradually change the light intensity and temperature and humidity, enabling the plant to gradually adapt to the new environment.

[0213] According to the change of plant transpiration rate, guide the user to adjust the indoor air humidity and ventilation volume to maintain the water balance of the plant. This step is aimed at the problem that after the adjustment or replacement of the bubble mud in the indoor potted plant cultivation scenario at home, the plant transpiration rate may change, affecting the water balance of the plant. By adjusting the indoor air humidity and ventilation volume according to the change of plant transpiration rate, which reflects the water demand of the plant in real time, the environmental factors are coordinated with the plant transpiration rate to maintain the water balance of the plant, avoiding the growth inhibition of the plant due to water shortage or excessive water.

[0214] When implementing this step, a leaf temperature sensor and an ambient humidity sensor can be used to monitor the transpiration rate of the plant. When a change in the transpiration rate is detected, the system can adjust the indoor air humidity through a smart humidifier or dehumidifier, and at the same time control the smart window or fan to adjust the ventilation volume. For example, when the transpiration rate increases, the system may recommend the user to increase the indoor humidity and reduce the ventilation to reduce water loss; conversely, when the transpiration rate decreases, it may recommend reducing the humidity and increasing the ventilation to prevent excessive water accumulation.

[0215] Real-time monitor the light intensity of different parts of the plant, guide the user to adjust the plant placement position or use lighting equipment to achieve uniform overall lighting of the plant. This step aims at the problem in the scenario of indoor potted plant cultivation at home that the indoor light distribution is uneven, the light intensity of different parts of the plant varies greatly, and it affects the overall growth of the plant. By using an indoor light sensor and image recognition technology, the light intensity of different parts of the plant is monitored in real time, the light conditions of each part of the plant are quantified, and the user is guided to adjust the plant placement position or use lighting equipment to ensure uniform overall lighting of the plant and promote the balanced growth of the plant.

[0216] In practical applications, multiple light sensors or a movable light sensor can be used to measure the light intensity of different parts of the plant. Combining image recognition technology, the system can identify the leaf distribution of the plant and associate the light data with the leaf position. Based on these data, the system can generate a heat map of the light distribution of the plant, visually showing the areas with uneven light.

[0217] According to the light distribution situation, the system can provide specific adjustment suggestions. For example, if it is detected that the top of the plant has sufficient light while the bottom has insufficient light, the system may recommend the user to rotate the plant by a certain angle or add lighting equipment at the bottom. For large plants, the system may recommend using multiple low-power LED grow lights distributed around the plant to achieve more uniform lighting.

[0218] In this way, the technical solution of this application can achieve refined control of the plant growth environment. Evaluating the adaptability of the plant roots and correspondingly adjusting environmental factors can reduce the stress response of the plant after the bubble mud is replaced or adjusted, and improve the survival rate and growth quality of the plant. Adjusting the indoor humidity and ventilation according to the change in the transpiration rate can better maintain the water balance of the plant and reduce the growth obstacles caused by water problems. Real-time monitoring and adjusting the light distribution can ensure that each part of the plant obtains uniform light, promote the overall balanced growth of the plant, and improve the ornamental value.

[0219] In the second aspect, referring to Figure 2, this application also proposes a plant control device based on bubble clay, which is used in the scenario of indoor potted plant cultivation in households to configure bubble clay and regulate the growth state for specific plant species. The device includes:

[0220] An acquisition module 210, configured to acquire plant species information and establish a standard growth curve including height growth rate, leaf number, color change, and nutrient absorption;

[0221] A matching module 220, configured to match the bubble clay type, ratio, and replacement period based on the plant species information;

[0222] A monitoring module 230, configured to monitor the actual growth state of the plant and calculate the deviation data between the actual growth curve and the standard growth curve;

[0223] A generation module 240, configured to generate a bubble clay regulation plan including composition regulation, structure regulation, and replacement strategy if the deviation data exceeds a preset threshold;

[0224] An execution module 250, configured to execute the bubble clay adjustment or replacement operation and guide the user to perform environmental collaborative regulation;

[0225] An adjustment module 260, configured to collect the plant state after the operation, evaluate the control effect, and dynamically adjust the subsequent control strategy to make the plant growth state approach the standard growth curve.

[0226] By configuring bubble clay and regulating the growth state for different plant species, it is possible to match the bubble clay configuration with the plant requirements, make the bubble clay selection more targeted, reduce fertilizer loss and environmental pollution, judge the timing of bubble clay replacement and adjustment more accurately, and control plants more effectively. It has the advantages of matching the bubble clay configuration with the plant requirements, making the bubble clay selection more targeted, reducing fertilizer loss and environmental pollution, judging the timing of bubble clay replacement and adjustment more accurately, and controlling plants more effectively.

[0227] The above are only the embodiments of this application and are not used to limit the protection scope of this application. For those skilled in the art, this application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included in the protection scope of this application.

Claims

1. A plant management method based on bubble mud, which is used in the scene of indoor potted plant cultivation at home, and performs bubble mud configuration and growth state regulation according to plant species, characterized in that: The method includes: Obtain plant species information and establish a standard growth curve including height growth rate, leaf number, color change, and nutrient absorption; Match the type, ratio, and replacement cycle of bubble mud based on plant species information; Monitor the actual growth status of plants and calculate the deviation data between the actual growth curve and the standard growth curve; If the deviation data exceeds the preset threshold, a bubble mud control plan including ingredient control, structure control, and replacement strategy is generated; Perform bubble mud adjustment or replacement operations to guide users to coordinate environmental control; Collect plant status after operation, evaluate control effects, and dynamically adjust subsequent control strategies to make plant growth status closer to the standard growth curve; The step of matching the type, ratio, and replacement cycle of bubble mud based on the plant species information includes: Obtain environmental factor data on region, season, and light intensity, and build an environmental factor database; Extract basic nutrient requirement data of plants based on plant species information; Based on the environmental factor data, the basic nutrient requirement data of the plant is corrected using the environmental factor impact model to obtain the target nutrient requirement data. The environmental factor impact model is as follows: target nutrient requirement data = basic nutrient requirement data * (1 + regional correction factor + seasonal correction factor + light correction factor); According to the target nutrient requirement data, select the type of bubble mud and determine the bubble mud ratio; Predict the bubble mud replacement cycle. The bubble mud replacement cycle prediction takes into account the plant nutrient absorption rate, bubble mud nutrient release rate and environmental factors.

2. A plant control method based on bubble mud according to claim 1, characterized in that: If the deviation data exceeds a preset threshold, the step of generating a bubble mud control plan including ingredient control, structure control, and replacement strategy includes: If the deviation data exceeds the preset threshold, the user's personalized planting needs are obtained and a user expectation curve including plant height control goals and flowering promotion goals is established; The target growth curve is obtained by integrating the standard growth curve and the user expectation curve; Analyze deviation data to determine the type and degree of deviation between the actual plant growth status and the target growth curve; According to the deviation type and degree, and plant species information, a control scheme is selected from the bubble mud component control library, the structure control library, and the replacement strategy library to generate a bubble mud control scheme including component control instructions, structure control instructions, and replacement strategy instructions; Among them, ingredient control instructions include nutrient type, quantity, and release rate; structure control instructions include bubble mud density, layered structure, and air permeability; replacement strategy instructions include replacement timing, replacement ratio, and new bubble mud type.

3. A plant control method based on bubble mud according to claim 2, characterized in that: The step of analyzing the deviation data to determine the type and degree of deviation between the actual growth state of the plant and the target growth curve includes: Collecting multi-source data on plant growth status, wherein the multi-source data includes image data, sensor data, and user input data; Performing data synchronization processing on the multi-source data based on timestamps to obtain synchronized multi-source data; Preprocessing the synchronized multi-source data to obtain preprocessed multi-source data; Based on the pre-processed multi-source data, the deviation data between the actual growth state of the plant and the target growth curve in terms of height growth rate, leaf number, color change and nutrient absorption are calculated; Based on the deviation data, the deviation type and degree of deviation between the actual growth status of the plant and the target growth curve are determined. The deviation types include growth retardation, excessive growth, malnutrition and pests and diseases, and the deviation degrees include mild, moderate and severe.

4. The plant control method based on bubble mud according to claim 2, characterized in that: The step of selecting a control scheme from a bubble mud component control library, a structure control library, and a replacement strategy library according to the deviation type and degree and plant species information to generate a bubble mud control scheme including component control instructions, structure control instructions, and replacement strategy instructions comprises: Constructing a bubble mud regulation knowledge graph, wherein the bubble mud regulation knowledge graph includes plant species nodes, deviation type nodes, deviation degree nodes, component regulation scheme nodes, structure regulation scheme nodes, replacement strategy nodes, and association relationships between the nodes; Based on the plant species information, deviation type and deviation degree, a multi-hop search is performed in the bubble mud regulation knowledge graph to obtain a set of candidate regulation schemes, wherein the multi-hop search includes: taking the plant species node as the starting node, performing a first-hop search based on the plant species information to obtain a set of associated deviation type nodes and a set of deviation degree nodes; taking the set of deviation type nodes and the set of deviation degree nodes as the starting nodes, performing a second-hop search to obtain a set of associated component regulation scheme nodes, a set of structural regulation scheme nodes and a set of replacement strategy nodes; Calculating a confidence score for each regulation scheme in the set of candidate regulation schemes, the confidence score comprehensively considering the strength of association between the regulation scheme and the plant species, the deviation type and degree, and the compatibility between the regulation schemes; According to the confidence score, a control scheme with the highest confidence score is selected from the candidate control scheme set to generate a bubble mud control scheme including component control instructions, structure control instructions and replacement strategy instructions.

5. The plant control method based on bubble mud according to claim 4, characterized in that: The step of calculating the confidence score of each control scheme in the candidate control scheme set includes: Obtaining association relationship data between nodes in the bubble mud regulation knowledge graph, the association relationship data including a first association strength between a plant species node and a component regulation solution node, a second association strength between a deviation type node and a component regulation solution node, a third association strength between a deviation degree node and a component regulation solution node, and a compatibility score between component regulation solution nodes; For each control scheme in the candidate control scheme set, based on the component control scheme nodes contained therein, calculate the weighted association strength between the control scheme and the plant species node, the deviation type node, and the deviation degree node, wherein the weighted association strength is obtained by weighted summation of the first association strength, the second association strength, and the third association strength, and the weight coefficient is determined according to the plant species, the deviation type, and the deviation degree; Calculate the compatibility score of each control scheme in the set of candidate control schemes, where the compatibility score is obtained by taking a weighted average of the compatibility scores between the nodes of each component control scheme in the control scheme, and the weight coefficient is determined according to the effect of each component control scheme node; The weighted association strength and compatibility score are weightedly summed to obtain the confidence score of each regulation scheme in the candidate regulation scheme set, and the weight coefficient is determined according to the association strength and compatibility.

6. The plant control method based on bubble mud according to claim 1, characterized in that: The step of correcting the basic nutrient requirement data of the plant using the environmental factor impact model based on the environmental factor data to obtain the target nutrient requirement data includes: Obtain the longitude and latitude coordinates of the plant planting area, query the historical meteorological data of the corresponding area, and obtain soil composition data, annual average precipitation data, and air humidity data; Based on soil composition data, a regional correction coefficient was calculated using a soil nutrient conversion model: regional correction coefficient = α*(soil organic matter content / soil total nutrient content) + β*(soil pH - 7), where α and β are model parameters and are adjusted according to plant species. Obtain the current date, determine the current season according to the preset seasonal division rules, and calculate the seasonal correction coefficient using a nonlinear seasonal impact model based on the plant growth cycle data. The nonlinear seasonal impact model is as follows: seasonal correction coefficient = γ*sin(2πt / T+φ), where γ is the seasonal impact amplitude, t is the current time, T is the plant growth cycle, and φ is the phase offset. γ, T, and φ are adjusted according to the plant species and growth stage. Obtain light intensity data for the plant's location, combine it with spectral data obtained by a spectral sensor, and calculate a light correction coefficient using a photosynthetically active radiation model. The photosynthetically active radiation model is as follows: Light correction coefficient = δ * PAR * (red light ratio / blue light ratio), where δ is the light influencing factor, PAR is the photosynthetically active radiation intensity, and the red light ratio and blue light ratio are the spectral component ratios. δ is adjusted according to the plant species. Based on the regional correction coefficient, seasonal correction coefficient and light correction coefficient, the target nutrient requirement data is calculated using the environmental factor impact model.

7. The plant control method based on bubble mud according to claim 1, characterized in that: If the deviation data exceeds a preset threshold, the step of generating a bubble mud control plan including ingredient control, structure control, and replacement strategy includes: If the deviation data exceeds the preset threshold, the bubble mud's humidity, conductivity, and gas composition will be monitored to determine whether the bubble mud has the risk of hardening, nutrient imbalance, or excessive odor. If there is a risk of compaction, the bubble mud formula will be adjusted to increase the fiber content, reduce the proportion of sticky components, and generate a loosening instruction to prompt the user to loosen the soil and increase the permeability of the bubble mud; If there is a risk of nutrient imbalance, the bubble mud nutrients will be analyzed to determine the types of missing nutrients, and a targeted nutrient supplement instruction will be generated to prompt the user to add the corresponding nutrients to balance the bubble mud nutrients; If there is a risk of odor exceeding the standard, the bubble mud gas composition will be detected to determine the type of odorous gas, and an activated carbon adsorption instruction or a bubble mud replacement instruction will be generated to prompt the user to perform activated carbon adsorption or replace the bubble mud to eliminate the odor.

8. The plant control method based on bubble mud according to claim 1, characterized in that: The step of performing the bubble mud adjustment or replacement operation and guiding the user to perform environmental collaborative control includes: Evaluate the adaptability of plant roots to the adjustment or replacement of bubble mud, adjust light intensity, temperature and humidity according to the adaptability, and obtain environmental factor control parameters; According to the changes in plant transpiration rate, guide users to adjust indoor air humidity and ventilation to maintain plant water balance; Monitor the light intensity of different parts of the plant in real time, and guide users to adjust the plant placement or use supplementary lighting equipment to achieve uniform lighting for the entire plant.

9. A plant control device based on bubble mud, used in indoor potted plant planting scenarios at home, to configure bubble mud and control the growth status of plants according to plant species, characterized in that: The device includes: The acquisition module is used to obtain plant species information and establish a standard growth curve including height growth rate, leaf number, color change, and nutrient absorption; A matching module is used to match the type, ratio, and replacement cycle of bubble mud based on plant species information; The monitoring module is used to monitor the actual growth status of the plant and calculate the deviation data between the actual growth curve and the standard growth curve; A generation module is used to generate a bubble mud control plan including component control, structure control, and replacement strategy if the deviation data exceeds a preset threshold; The execution module is used to perform bubble mud adjustment or replacement operations and guide users to perform collaborative environmental control; The adjustment module is used to collect plant status after operation, evaluate the control effect, and dynamically adjust subsequent control strategies to make the plant growth status closer to the standard growth curve; The matching of bubble mud type, ratio, and replacement cycle based on plant species information includes: Obtain environmental factor data on region, season, and light intensity, and build an environmental factor database; Extract basic nutrient requirement data of plants based on plant species information; Based on the environmental factor data, the basic nutrient requirement data of the plant is corrected using the environmental factor impact model to obtain the target nutrient requirement data. The environmental factor impact model is as follows: target nutrient requirement data = basic nutrient requirement data * (1 + regional correction factor + seasonal correction factor + light correction factor); According to the target nutrient requirement data, select the type of bubble mud and determine the bubble mud ratio; Predict the bubble mud replacement cycle. The bubble mud replacement cycle prediction takes into account the plant nutrient absorption rate, bubble mud nutrient release rate and environmental factors.

Images