Wireless plant audio controller

Abstract

The invention discloses a wireless plant audio controller. The wireless plant audio controller comprises a voice recognition module; the monitoring module is responsible for monitoring sound signals emitted by plants in real time and analyzing response of the plants to sound wave stimulation; the plant state monitoring module is responsible for monitoring plant growth conditions and environmental conditions in real time; the feedback learning module is responsible for analyzing the response of the plant to the sound wave stimulation through a support vector machine algorithm and optimizing a regulation and control strategy; the self-adaptive regulation and control module is responsible for analyzing feedback data in real time and automatically adjusting sound wave stimulation parameters to optimize plant growth; according to the invention, the output of the feedback learning module provides key information for the self-adaptive regulation and control module, so that the self-adaptive regulation and control module can automatically adjust the frequency, intensity, duration and other parameters of sound wave stimulation based on the real-time response of the plant. The dynamic adjustment ensures accurate matching between sound wave stimulation and plant requirements, the regulation and control accuracy is improved, and the best growth and development promoting effect on plants is achieved conveniently.

Description

Technical Field

[0001] The invention relates to the technical field of sound wave promoting plant growth, and in particular to a wireless plant audio controller. Background Art

[0002] Plant sound frequency control technology is a modern physical agricultural technology based on the theory of plant acoustic biology. This technology accurately measures the frequency of spontaneous sound and received sound of different plants, and summarizes the quantitative relationship between the frequency of spontaneous sound of plants and major environmental factors (such as temperature, humidity and tissue water content), and then develops plant sound frequency generators to perform sound frequency treatment on different plants. Its basic principle is to use a plant sound frequency generator to apply sound waves of a specific frequency to plants, resonate with plants, thereby promoting plants to absorb, transmit and transform various nutrients, enhance photosynthesis and absorption capacity of plants, promote growth and development, and achieve the purpose of increasing production, increasing income, quality and disease resistance.

[0003] After searching, the Chinese patent number CN203311195U discloses a wireless plant audio controller. The wireless plant audio controller includes: a Holtek MCU module for analyzing and processing plant physiological information and surrounding environment information; a sensor module for obtaining plant physiological characteristics and surrounding environment; a wireless module for wirelessly controlling an audio device; an audio processing module for reading audio information, playing audio and amplifying audio; a timing module for timed playback; a display module for displaying information; an input module for inputting information; a storage module for storing data; a power supply module for providing system operation; The advantages of this patent are: using wireless control, easy to operate, and installation is not restricted by conditions such as height and position. The controller has a timing function that can set the audio playback time period every day, so that audio playback can be performed automatically without the need for personnel to wait. In addition, the controller can automatically adjust the played tracks according to the surrounding environment of the plant, so that suitable audio tracks can be played automatically.

[0004] However, in actual use, the above invention lacks a real-time feedback learning system, making it difficult to understand the response of plants to sound wave stimulation, and difficult to accurately control parameters such as the frequency, intensity and duration of sound wave stimulation in real time, making it difficult to achieve the best effect of promoting growth and development. Therefore, a wireless plant audio controller is proposed. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art, such as the lack of a real-time feedback learning system, the difficulty in understanding the response of plants to sound wave stimulation, the difficulty in real-time and accurate control of parameters such as the frequency, intensity and duration of sound wave stimulation, and the difficulty in achieving the best effect of promoting growth and development, and to propose a wireless plant audio controller.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A wireless plant audio controller, comprising:

[0008] Sound recognition module: responsible for real-time monitoring of the sound signals emitted by plants and analyzing the response of plants to sound wave stimulation;

[0009] Plant status monitoring module: responsible for real-time monitoring of plant growth status and environmental conditions;

[0010] Feedback learning module: responsible for analyzing the plant's response to sound wave stimulation through the support vector machine algorithm and optimizing the control strategy;

[0011] Adaptive control module: responsible for real-time analysis of feedback data and automatic adjustment of acoustic stimulation parameters to optimize plant growth;

[0012] Acoustic wave stimulation control module: responsible for real-time generation and output of acoustic wave stimulation signals;

[0013] User interface module: responsible for providing a user-friendly operation interface, including real-time monitoring of plant status, viewing feedback data, and adjusting sonic settings;

[0014] The sound recognition module needs to receive the sound emitted by the plant and perform recognition and analysis on it. The sound recognition module outputs the analyzed response of the plant to the sound wave stimulation to the feedback learning module. The plant state monitoring module outputs the detected plant growth state and environmental conditions to the feedback learning module. The feedback learning module combines the inputs of the sound recognition module and the plant state monitoring module, and uses a vector machine algorithm to comprehensively analyze the response of the plant to the sound wave stimulation. The feedback learning module outputs the comprehensive analysis of the response of the plant to the sound wave stimulation to the adaptive module. The adaptive module uses a control algorithm to automatically adjust the frequency, intensity and duration parameters of the sound wave stimulation according to the output of the feedback learning module. The adaptive module outputs the adjusted sound wave parameters to the sound wave stimulation control module, and the sound wave stimulation control module generates and outputs the sound wave stimulation signal in real time.

[0015] The above technical solution further includes:

[0016] Preferably, the sound recognition module includes an audio acquisition unit, a signal processing unit, a feature extraction unit, a module recognition unit and a result output unit, the audio acquisition unit is responsible for collecting sound signals of plants through an audio sensor, the audio acquisition unit transmits the collected sound signals to the signal processing unit, the signal processing unit is responsible for preprocessing and analyzing the collected sound signals, the signal processing unit transmits the processed information to the feature extraction unit, the feature extraction unit is responsible for extracting important features from the processed sound signals, the feature extraction unit transmits the extracted features to the module recognition unit, the module recognition unit is responsible for classifying and identifying the extracted features and judging the reaction state of the plants, the module recognition unit transmits the judged plant reaction state to the result output unit, and the module is responsible for transmitting the judged plant reaction state to the feedback learning module.

[0017] Preferably, the plant status monitoring module includes a data acquisition and processing unit, a status evaluation unit, and a result output unit. The data acquisition and processing unit is responsible for using a single-chip microcomputer to collect various sensor data in real time and preprocess the collected data. The data acquisition and processing unit transmits the preprocessed data to the status evaluation and early warning unit. The status evaluation unit is responsible for generating a plant health score based on the preprocessed data to help evaluate whether the plant growth is normal. The status evaluation unit is responsible for transmitting the evaluation data to the result output unit. The result output unit is responsible for transmitting the evaluation data to the feedback learning module and the user interface module.

[0018] Preferably, the various types of sensors include environmental monitoring sensors, plant growth status sensors and growth parameter sensors. The environmental monitoring sensors are responsible for monitoring the temperature of the plant growth environment, measuring the humidity of the air and soil, and detecting the light intensity. The plant growth status sensors are responsible for measuring the height of the plant, monitoring the growth status and health of the root system, and monitoring the color, shape and area of ​​the leaves. The growth parameter sensors are responsible for monitoring the biomass of the plant and measuring the chlorophyll content and photosynthesis rate.

[0019] Preferably, the feedback learning module includes a data acquisition unit, a data processing and analysis unit, a model building and optimization unit, a result output unit and an evaluation and decision unit. The data acquisition unit is responsible for collecting data input by the sound recognition module and the plant status monitoring module. The data acquisition unit transmits the collected data to the data processing and analysis unit. The data processing and analysis unit is responsible for preprocessing the collected data and extracting key features. The data processing and analysis unit transmits the extracted key feature data to the model building and optimization unit. The model building and optimization unit is responsible for using the support vector machine algorithm to establish a relationship model between plant growth and sound wave stimulation, and uses historical data and real-time data to train and adjust the model. The model building and optimization unit transmits the model output results and real-time data to the result data unit. The result output unit is responsible for transmitting the model output results and real-time data to the adaptive control module and the user interface module. The evaluation and decision unit is responsible for evaluating the impact of sound wave stimulation on plant growth, analyzing whether the expected effect is achieved, and providing adjustment suggestions based on the evaluation results.

[0020] Preferably, the specific steps of using the support vector machine algorithm to establish the relationship model between plant growth and sound wave stimulation are:

[0021] Data preparation and preprocessing: Collect data input from the sound recognition module and the plant status monitoring module, clean the collected data, and extract features that affect plant growth from the raw data;

[0022] Model training: Select a suitable kernel function based on the characteristics of the problem, determine the parameters of the support vector machine model, and use the training data set to train the support vector machine model;

[0023] Model evaluation and optimization: Use the test set to test the model to evaluate model performance, and adjust parameters and kernel function parameters based on the evaluation results;

[0024] Model application: Apply the trained support vector machine model to the wireless plant audio controller.

[0025] Preferably, the adaptive control module uses a genetic algorithm to determine the optimal sound wave stimulation parameters according to the output result of the feedback learning module, and the determined sound wave stimulation parameters include frequency adjustment, intensity adjustment and duration adjustment.

[0026] Preferably, the specific steps of the genetic algorithm are:

[0027] Step 1: Set the range of the frequency f, intensity i and duration t parameters of the acoustic stimulus, and randomly generate N individuals, each of which consists of a set of parameters;

[0028] Step 2: Based on the output of the feedback learning model, define a fitness function F(x), where x = (f, i, t), and perform fitness evaluation on each individual x in the population P(t) to obtain its fitness value;

[0029] Step 3: Determine the individuals to be retained based on their fitness, and use the tournament strategy to select the individuals with the highest fitness, and the other individuals are replaced by new individuals;

[0030] Step 4: For the selected parent individuals, generate offspring individuals through crossover operation, and mutate the offspring individuals with a certain probability to increase the diversity of the population;

[0031] Step 5: Add the new offspring individuals generated after selection, crossover and mutation operations to the new population to form the next generation population, and repeat the fitness evaluation, selection operation, crossover operation and mutation operation until the preset number of iterations is reached or other termination conditions are met;

[0032] Step 6: In the final population, select the individual with the highest fitness value as the optimal solution, and output the sound wave stimulation parameters corresponding to the optimal individual as the optimal control parameters of the wireless plant audio controller;

[0033] Preferably, the user interface module includes:

[0034] Main control panel: responsible for setting the sound wave parameters and controlling the start and stop of sound wave stimulation;

[0035] Real-time monitoring display: responsible for displaying the current plant growth data and current acoustic stimulation parameters;

[0036] Feedback learning system interface: responsible for users to record and input observations of plant responses and display past feedback and its corresponding system response;

[0037] Digital visualization unit: responsible for displaying plant growth trends and sound wave stimulation effects through line graphs or bar graphs;

[0038] Wireless communication unit: responsible for displaying the connection status with mobile devices and networks;

[0039] Notification and alarm unit: responsible for issuing an alarm when the plant status is abnormal or the system requires user attention.

[0040] The present invention has the following beneficial effects:

[0041] 1. In the present invention, by introducing a feedback learning module, the controller can monitor and analyze the response of plants to acoustic stimulation in real time. Using the support vector machine algorithm, the feedback learning module can efficiently learn from the data collected by the sound recognition module and the plant status monitoring module, thereby achieving a deep understanding of the plant response.

[0042] 2. In the present invention, the output of the feedback learning module provides key information for the adaptive control module, enabling it to automatically adjust the frequency, intensity, duration and other parameters of the acoustic stimulation based on the real-time response of the plant. This dynamic adjustment ensures the precise match between the acoustic stimulation and the needs of the plant, improves the accuracy of the control, and facilitates the best growth and development promotion effect on the plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a system architecture diagram of a wireless plant audio controller proposed in the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] like Figure 1 As shown, a wireless plant audio controller proposed by the present invention includes:

[0046] Sound recognition module: responsible for real-time monitoring of the sound signals emitted by plants and analyzing the response of plants to sound wave stimulation;

[0047] Plant status monitoring module: responsible for real-time monitoring of plant growth status and environmental conditions;

[0048] Feedback learning module: responsible for analyzing the plant's response to sound wave stimulation through the support vector machine algorithm and optimizing the control strategy;

[0049] Adaptive control module: responsible for real-time analysis of feedback data and automatic adjustment of acoustic stimulation parameters to optimize plant growth;

[0050] Acoustic wave stimulation control module: responsible for real-time generation and output of acoustic wave stimulation signals;

[0051] User interface module: responsible for providing a user-friendly operation interface, including real-time monitoring of plant status, viewing feedback data, and adjusting sonic settings;

[0052] The sound recognition module needs to receive the sounds emitted by the plants and perform recognition and analysis on them. The sound recognition module outputs the analyzed responses of the plants to the sound wave stimulation to the feedback learning module. The plant status monitoring module outputs the detected plant growth status and environmental conditions to the feedback learning module. The feedback learning module combines the inputs of the sound recognition module and the plant status monitoring module, and uses the vector machine algorithm to comprehensively analyze the responses of the plants to the sound wave stimulation. The feedback learning module outputs the comprehensively analyzed responses of the plants to the sound wave stimulation to the adaptive module. The adaptive module uses a control algorithm to automatically adjust the frequency, intensity and duration parameters of the sound wave stimulation according to the output of the feedback learning module. The adaptive module outputs the adjusted sound wave parameters to the sound wave stimulation control module, and the sound wave stimulation control module generates and outputs the sound wave stimulation signal in real time.

[0053] In the embodiment of the present invention, the sound signal from the plant is first received by the sound recognition module, including the vibration of the plant due to the sound wave stimulation, the natural sound during the growth process, etc., and then the sound recognition module recognizes and analyzes the received sound signal to judge the response of the plant to the sound wave stimulation. It includes extracting sound features, identifying sound patterns, and evaluating the intensity and frequency of the sound signal. The plant state monitoring module simultaneously monitors the growth status of the plant, such as leaf color, growth rate, flowering status, etc., as well as environmental conditions, such as temperature, humidity, light intensity, etc. The feedback learning module receives the data transmitted from the sound recognition module and the plant state monitoring module, and uses the support vector machine algorithm to comprehensively analyze these data to understand the specific response of the plant to the sound wave stimulation. At the same time, based on the analysis results, the feedback learning module optimizes the control strategy of the sound wave stimulation. The adaptive control module receives the optimized control strategy output from the feedback learning module. The adaptive module adopts an appropriate control algorithm to automatically adjust the parameters such as the frequency, intensity and duration of the sound wave stimulation according to the control strategy. Finally, the sound wave stimulation control module generates and outputs the sound wave stimulation signal in real time, and transmits these sound wave stimulation signals to the plant through wireless transmission to stimulate it.

[0054] In one embodiment, the sound recognition module includes an audio acquisition unit, a signal processing unit, a feature extraction unit, a module recognition unit and a result output unit. The audio acquisition unit is responsible for collecting the sound signals of the plants through an audio sensor. The audio acquisition unit transmits the collected sound signals to the signal processing unit. The signal processing unit is responsible for preprocessing and analyzing the collected sound signals. The signal processing unit transmits the processed information to the feature extraction unit. The feature extraction unit is responsible for extracting important features from the processed sound signals. The feature extraction unit transmits the extracted features to the module recognition unit. The module recognition unit is responsible for classifying and identifying the extracted features and judging the reaction state of the plants. The module recognition unit transmits the judged plant reaction state to the result output unit, which is responsible for transmitting the judged plant reaction state to the feedback learning module.

[0055] In an embodiment of the present invention, important features including the frequency, amplitude, duration, spectrum distribution, etc. of the sound are extracted from the preprocessed sound signal. These features can reflect the response state of the plant to the sound wave stimulation. The module recognition unit maps the features to specific plant response states, such as normal, excited, stressed, etc.

[0056] In one embodiment, the plant status monitoring module includes a data acquisition and processing unit, a status evaluation unit, and a result output unit. The data acquisition and processing unit is responsible for using a single-chip microcomputer to collect various sensor data in real time and preprocess the collected data. The data acquisition and processing unit transmits the preprocessed data to the status evaluation and early warning unit. The status evaluation unit is responsible for generating a plant health score based on the preprocessed data to help evaluate whether the plant growth is normal. The status evaluation unit is responsible for transmitting the evaluation data to the result output unit, and the result output unit is responsible for transmitting the evaluation data to the feedback learning module and the user interface module.

[0057] In the embodiment of the present invention, the state evaluation unit can also predict the future growth state of the plant according to the change trend of the historical data and the current data.

[0058] In one embodiment, the various types of sensors include environmental monitoring sensors, plant growth status sensors and growth parameter sensors. The environmental monitoring sensors are responsible for monitoring the temperature of the plant growth environment, measuring the humidity of the air and soil, and detecting the light intensity. The plant growth status sensors are responsible for measuring the height of the plant, monitoring the growth status and health of the root system, and monitoring the color, shape and area of ​​the leaves. The growth parameter sensors are responsible for monitoring the biomass of the plant and measuring the chlorophyll content and photosynthesis rate.

[0059] In one embodiment, the feedback learning module includes a data acquisition unit, a data processing and analysis unit, a model building and optimization unit, a result output unit and an evaluation and decision unit. The data acquisition unit is responsible for collecting data input by the sound recognition module and the plant status monitoring module. The data acquisition unit transmits the collected data to the data processing and analysis unit. The data processing and analysis unit is responsible for preprocessing the collected data and extracting key features. The data processing and analysis unit transmits the extracted key feature data to the model building and optimization unit. The model building and optimization unit is responsible for using the support vector machine algorithm to establish a relationship model between plant growth and sound wave stimulation, and uses historical data and real-time data to train and adjust the model. The model building and optimization unit transmits the model output results and real-time data to the result data unit. The result output unit is responsible for transmitting the model output results and real-time data to the adaptive control module and the user interface module. The evaluation and decision unit is responsible for evaluating the impact of sound wave stimulation on plant growth, analyzing whether the expected effect is achieved, and providing adjustment suggestions based on the evaluation results.

[0060] In the embodiment of the present invention, the formula for effect evaluation by the evaluation and decision-making unit can be expressed by the following formula:

[0061]

[0062] Among them, E is the effect evaluation value, y i is the actual plant growth data, is the model's predicted value.

[0063] The recommended adjustment formula is:

[0064] ΔP=k·(E-∈)

[0065] Where ΔP represents the recommended adjustment amount, k represents the adjustment coefficient, and ∈ represents the acceptable error range.

[0066] In one embodiment, the specific steps of using the support vector machine algorithm to establish a relationship model between plant growth and sound wave stimulation are:

[0067] Data preparation and preprocessing: Collect data input from the sound recognition module and the plant status monitoring module, clean the collected data, and extract features that affect plant growth from the raw data;

[0068] Model training: Select a suitable kernel function based on the characteristics of the problem, determine the parameters of the support vector machine model, and use the training data set to train the support vector machine model;

[0069] Model evaluation and optimization: Use the test set to test the model to evaluate model performance, and adjust parameters and kernel function parameters based on the evaluation results;

[0070] Model application: Apply the trained support vector machine model to the wireless plant audio controller.

[0071] In one embodiment, the adaptive control module uses a genetic algorithm to determine the optimal sound wave stimulation parameters according to the output results of the feedback learning module, and the determined sound wave stimulation parameters include frequency adjustment, intensity adjustment and duration adjustment.

[0072] In one embodiment, the specific steps of the genetic algorithm are:

[0073] Step 1: Set the range of the frequency f, intensity i and duration t parameters of the acoustic stimulus, and randomly generate N individuals, each of which consists of a set of parameters;

[0074] Step 2: Based on the output of the feedback learning model, define a fitness function F(x), where x = (f, i, t), and perform fitness evaluation on each individual x in the population P(t) to obtain its fitness value;

[0075] Step 3: Determine the individuals to be retained based on their fitness, and use the tournament strategy to select the individuals with the highest fitness, and the other individuals are replaced by new individuals;

[0076] Step 4: For the selected parent individuals, generate offspring individuals through crossover operation, and mutate the offspring individuals with a certain probability to increase the diversity of the population;

[0077] Step 5: Add the new offspring individuals generated after selection, crossover and mutation operations to the new population to form the next generation population, and repeat the fitness evaluation, selection operation, crossover operation and mutation operation until the preset number of iterations is reached or other termination conditions are met;

[0078] Step 6: In the final population, select the individual with the highest fitness value as the optimal solution, and output the sound wave stimulation parameters corresponding to the optimal individual as the optimal control parameters of the wireless plant audio controller.

[0079] In one embodiment, the user interface module includes:

[0080] Main control panel: responsible for setting the sound wave parameters and controlling the start and stop of sound wave stimulation;

[0081] Real-time monitoring display: responsible for displaying the current plant growth data and current acoustic stimulation parameters;

[0082] Feedback learning system interface: responsible for users to record and input observations of plant responses and display past feedback and its corresponding system response;

[0083] Digital visualization unit: responsible for displaying plant growth trends and sound wave stimulation effects through line graphs or bar graphs;

[0084] Wireless communication unit: responsible for displaying the connection status with mobile devices and networks;

[0085] Notification and alarm unit: responsible for issuing an alarm when the plant status is abnormal or the system requires user attention.

[0086] In the embodiment of the present invention, the average value of the data in the digital visualization unit can be calculated by the following formula:

[0087]

[0088] in, is the mean value of the data, y i is the value for each data point.

[0089] The standard deviation, which is used to show volatility, can be calculated by the following formula:

[0090]

[0091] The abnormal threshold setting in the notification and alarm unit can be expressed as:

[0092] A1=μ+kσ

[0093] Among them, A1 represents the abnormal threshold, μ is the mean of the normal value, σ is the standard deviation, and k is a constant, usually 2 or 3.

[0094] The alarm triggering condition can be expressed by the following formula:

[0095]

[0096] Wherein, A represents the currently monitored plant status data.

[0097] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A wireless plant audio controller, characterized in that: include: Voice recognition module; Responsible for real-time monitoring of the sound signals emitted by plants and analyzing the response of plants to sound wave stimulation; Plant status monitoring module: responsible for real-time monitoring of plant growth status and environmental conditions; Feedback learning module: responsible for analyzing the plant's response to sound wave stimulation through the support vector machine algorithm and optimizing the control strategy; Adaptive control module: responsible for real-time analysis of feedback data and automatic adjustment of acoustic stimulation parameters to optimize plant growth; Acoustic wave stimulation control module: responsible for real-time generation and output of acoustic wave stimulation signals; User interface module: responsible for providing a user-friendly operation interface, including real-time monitoring of plant status, viewing feedback data, and adjusting sonic settings; The sound recognition module needs to receive the sound emitted by the plant and perform recognition and analysis on it. The sound recognition module outputs the analyzed response of the plant to the sound wave stimulation to the feedback learning module. The plant state monitoring module outputs the detected plant growth state and environmental conditions to the feedback learning module. The feedback learning module combines the inputs of the sound recognition module and the plant state monitoring module, and uses a vector machine algorithm to comprehensively analyze the response of the plant to the sound wave stimulation. The feedback learning module outputs the comprehensive analysis of the response of the plant to the sound wave stimulation to the adaptive module. The adaptive module uses a control algorithm to automatically adjust the frequency, intensity and duration parameters of the sound wave stimulation according to the output of the feedback learning module. The adaptive module outputs the adjusted sound wave parameters to the sound wave stimulation control module, and the sound wave stimulation control module generates and outputs the sound wave stimulation signal in real time.

2. A wireless plant audio controller according to claim 1, characterized in that: The sound recognition module includes an audio acquisition unit, a signal processing unit, a feature extraction unit, a module recognition unit and a result output unit. The audio acquisition unit is responsible for collecting plant sound signals through an audio sensor. The audio acquisition unit transmits the collected sound signals to the signal processing unit. The signal processing unit is responsible for preprocessing and analyzing the collected sound signals. The signal processing unit transmits the processed information to the feature extraction unit. The feature extraction unit is responsible for extracting important features from the processed sound signals. The feature extraction unit transmits the extracted features to the module recognition unit. The module recognition unit is responsible for classifying and identifying the extracted features and judging the reaction state of the plants. The module recognition unit transmits the judged plant reaction state to the result output unit. The module is responsible for transmitting the judged plant reaction state to the feedback learning module.

3. A wireless plant audio controller according to claim 1, characterized in that: The plant status monitoring module includes a data acquisition and processing unit, a status evaluation unit, and a result output unit. The data acquisition and processing unit is responsible for using a single-chip microcomputer to collect various sensor data in real time and preprocess the collected data. The data acquisition and processing unit transmits the preprocessed data to the status evaluation and early warning unit. The status evaluation unit is responsible for generating a plant health score based on the preprocessed data to help evaluate whether the plant growth is normal. The status evaluation unit is responsible for transmitting the evaluation data to the result output unit, and the result output unit is responsible for transmitting the evaluation data to the feedback learning module and the user interface module.

4. A wireless plant audio controller according to claim 3, characterized in that: The various types of sensors include environmental monitoring sensors, plant growth status sensors and growth parameter sensors. The environmental monitoring sensors are responsible for monitoring the temperature of the plant growth environment, measuring the humidity of the air and soil and detecting the light intensity. The plant growth status sensors are responsible for measuring the plant height, monitoring the root growth status and health, and monitoring the color, shape and area of ​​the leaves. The growth parameter sensors are responsible for monitoring the plant biomass and measuring the chlorophyll content and photosynthesis rate.

5. A wireless plant audio controller according to claim 1, characterized in that: The feedback learning module includes a data acquisition unit, a data processing and analysis unit, a model building and optimization unit, a result output unit and an evaluation and decision unit. The data acquisition unit is responsible for collecting data input by the sound recognition module and the plant status monitoring module. The data acquisition unit transmits the collected data to the data processing and analysis unit. The data processing and analysis unit is responsible for preprocessing the collected data and extracting key features. The data processing and analysis unit transmits the extracted key feature data to the model building and optimization unit. The model building and optimization unit is responsible for using the support vector machine algorithm to establish a relationship model between plant growth and sound wave stimulation, and uses historical data and real-time data to train and adjust the model. The model building and optimization unit transmits the model output results and real-time data to the result data unit. The result output unit is responsible for transmitting the model output results and real-time data to the adaptive control module and the user interface module. The evaluation and decision unit is responsible for evaluating the impact of sound wave stimulation on plant growth, analyzing whether the expected effect is achieved, and providing adjustment suggestions based on the evaluation results.

6. A wireless plant audio controller according to claim 5, characterized in that: The specific steps of using the support vector machine algorithm to establish the relationship model between plant growth and sound wave stimulation are: Data preparation and preprocessing: Collect data input from the sound recognition module and the plant status monitoring module, clean the collected data, and extract features that affect plant growth from the raw data; Model training: Select a suitable kernel function based on the characteristics of the problem, determine the parameters of the support vector machine model, and use the training data set to train the support vector machine model; Model evaluation and optimization: Use the test set to test the model to evaluate model performance, and adjust parameters and kernel function parameters based on the evaluation results; Model application: Apply the trained support vector machine model to the wireless plant audio controller.

7. A wireless plant audio controller according to claim 1, characterized in that: The adaptive control module uses a genetic algorithm to determine the optimal sound wave stimulation parameters according to the output result of the feedback learning module. The determined sound wave stimulation parameters include frequency adjustment, intensity adjustment and duration adjustment.

8. A wireless plant audio controller according to claim 7, characterized in that: The specific steps of the genetic algorithm are: Step 1: Set the range of the frequency f, intensity i and duration t parameters of the acoustic stimulus, and randomly generate N individuals, each of which consists of a set of parameters; Step 2: Based on the output of the feedback learning model, define a fitness function F(x), where x = (f, i, t), and perform fitness evaluation on each individual x in the population P(t) to obtain its fitness value; Step 3: Determine the individuals to be retained based on their fitness, and use the tournament strategy to select the individuals with the highest fitness, and the other individuals are replaced by new individuals; Step 4: For the selected parent individuals, generate offspring individuals through crossover operation, and mutate the offspring individuals with a certain probability to increase the diversity of the population; Step 5: Add the new offspring individuals generated after selection, crossover and mutation operations to the new population to form the next generation population, and repeat the fitness evaluation, selection operation, crossover operation and mutation operation until the preset number of iterations is reached or other termination conditions are met; Step 6: In the final population, select the individual with the highest fitness value as the optimal solution, and output the sound wave stimulation parameters corresponding to the optimal individual as the optimal control parameters of the wireless plant audio controller.

9. A wireless plant audio controller according to claim 1, characterized in that: The user interface module comprises: Main control panel: responsible for setting the sound wave parameters and controlling the start and stop of sound wave stimulation; Real-time monitoring display: responsible for displaying the current plant growth data and current acoustic stimulation parameters; Feedback learning system interface: responsible for users to record and input observations of plant responses and display past feedback and its corresponding system response; Digital visualization unit: responsible for displaying plant growth trends and sound wave stimulation effects through line graphs or bar graphs; Wireless communication unit: responsible for displaying the connection status with mobile devices and networks; Notification and alarm unit: responsible for issuing an alarm when the plant status is abnormal or the system requires user attention.

Images