Smart Growth Control Apparatus Using AIoT-Based Integrated Growth Data Analysis and Ultrafine Bubble Nutrient Prescription

Abstract

The present invention relates to the fields of smart farm, precision agriculture, AI-based agricultural control, and AIoT (AI + Internet of Things) technology. More specifically, it relates to a smart growth control device utilizing AIoT-based integrated growth data analysis and ultrafine bubble nutrient prescription, which integrally collects plant growth data and soil physical and chemical data, analyzes the collected data based on artificial intelligence to diagnose the growth status of a target crop, and performs intelligent growth control by linking with an ultrafine bubble-based nutrient supply system.

Description

Technology Field

[0001] The present invention relates to a smart growth control device, and more specifically, to a smart growth control device utilizing AIoT-based integrated growth data analysis and ultrafine bubble nutrient prescription. The present invention relates to the fields of smart farm, precision agriculture, AI-based agricultural control, and AIoT (AI + Internet of Things) technology. More specifically, it relates to a smart growth control device utilizing AIoT-based integrated growth data analysis and ultrafine bubble nutrient prescription capable of integrally collecting plant growth data and soil physical and chemical data, analyzing the collected data based on artificial intelligence to diagnose the growth status of a target crop, and performing intelligent growth control in conjunction with the supply of nutrients based on ultrafine bubbles. Background Technology

[0002] With the recent advancement of smart farm technology, various agricultural sensors and automatic control systems are being developed. Conventional smart farm systems are primarily structured to control ventilation, irrigation, or heating and cooling systems by collecting limited environmental data, such as temperature, humidity, light intensity, and soil moisture.

[0003] However, conventional technology has the problem of failing to accurately reflect the actual crop condition because it performs control based solely on simple environmental values ​​without directly analyzing the growth status of the plant itself. Furthermore, the inability to comprehensively analyze soil and plant conditions leads to growth variability and reduced nutrient utilization efficiency.

[0004] In particular, conventional smart farm systems use fixed sensors, which makes it difficult to flexibly adjust sensor positions according to crop growth and poses a problem of difficulty in ultra-close measurement of specific leaves or locations. Additionally, the lack of a feedback-based relearning structure utilizing growth change results makes it difficult to continuously improve control performance.

[0005] Meanwhile, since most existing nutrient supply technologies operate on a fixed cycle basis, adaptive control responding to actual changes in growth conditions is difficult, and control technologies to compensate for insufficient collected data due to data loss or communication failures have been inadequate. Furthermore, despite soil and plant conditions varying depending on the cultivation location within the same farm, a method of supplying the same amount of nutrients to the entire area is generally used, leading to problems such as potential over- or under-supply of nutrients.

[0006] Therefore, there is a need for a new type of smart growth control device capable of simultaneously collecting plant growth data and soil physical and chemical data, precisely determining growth conditions through AI-based analysis, and performing ultrafine bubble-based nutrient prescription and adaptive control.

[0007] (Prior Literature)

[0008] 1. Korean Published Patent Application No. 10-2025-0132250

[0009] 2. Korean Published Patent Application No. 10-2022-0093647

[0010] 3. Korean Published Patent Application No. 10-2022-0011902

[0011] 4. Korean Published Patent Application No. 10-2022-0116876

[0012] 5. Korean Published Patent Application No. 10-2024-0043912 The problem to be solved

[0013] The present invention aims to solve the aforementioned problems by providing an AIoT-based smart growth control device capable of simultaneously collecting plant growth data and soil physical and chemical data, and integrating and analyzing them to precisely determine the growth status of a target crop.

[0014] In addition, the present invention aims to provide a smart growth control device capable of performing precise measurements in various cultivation environments by providing a variable sensor structure based on a multi-joint arm that enables ultra-close measurement of the plant leaf surface.

[0015] Furthermore, the present invention aims to provide a smart growth control device capable of improving the nutrient absorption efficiency of a target crop by linking with an ultrafine bubble-based nutrient supply device, and performing relearning-based feedback control using the results of growth changes. means of solving the problem

[0016] To achieve the above objective, a smart growth control device according to one embodiment of the present invention comprises: a support pole; a waterproof main housing coupled to the support pole; a plant sensor unit electrically connected to the main housing and collecting plant growth data of a target crop; a soil sensor unit inserted into the soil and collecting soil physical and chemical data; a multi-joint arm that supports the plant sensor unit so as to be position-adjustable in the direction of the target crop; and an artificial intelligence analysis unit that analyzes data collected from the plant sensor unit and the soil sensor unit to determine the growth status of the target crop and generate nutrient prescription information.

[0017] The above plant sensor unit includes a hyperspectral sensor, an RGB camera sensor, a leaf surface temperature sensor, a humidity sensor, a carbon dioxide sensor, a volatile organic compound sensor, an ammonia sensor, and an ethylene sensor.

[0018] The soil sensor unit includes a soil moisture sensor, a soil temperature sensor, a soil pH sensor, a soil electrical conductivity sensor, a nitrogen sensor, a phosphorus sensor, a potassium sensor, and a soil salinity sensor.

[0019] The above-mentioned artificial intelligence analysis unit integrates and analyzes plant growth data and soil physical and chemical data to calculate the condition scores of the target crop's plants and soil.

[0020] The above-mentioned artificial intelligence analysis unit generates nutrient prescription information required for the target crop based on the calculated plant and soil condition score or the plant and soil growth condition index. Based on the generated nutrient prescription information, the supply ratio of nitrogen, phosphorus, and potassium, the nutrient supply amount, the nutrient supply cycle, and the irrigation conditions of the nutrient supply device are set.

[0021] A solar panel is attached to the upper part of the support column, and the solar panel is connected to a battery and a conversion control unit to supply independent power to the smart growth control device. A status display unit is provided on the outer side of the main housing to display sensor abnormality status, communication status, and power status. The status display unit is configured to visually display sensor abnormality status, communication status, and power status using a plurality of colors or flashing patterns.

[0022] The main housing includes a communication module, a power module, and a storage device. The communication module transmits data collected from the plant sensor unit and the soil sensor unit to an external server, and also transmits data collected from the plant sensor unit and the soil sensor unit to an external server along with time information using at least one wireless communication method among LoRa, WiFi, ZigBee, LTE, and Bluetooth. The storage device is configured to store data collected from the plant sensor unit and the soil sensor unit. The artificial intelligence analysis unit analyzes the growth status of the target crop using the stored data and real-time collected data.

[0023] The above multi-joint arm includes a plurality of rotational joints to adjust the height of the plant sensor unit from the ground, the distance from the plant, and the angle from the plant, and the plant sensor unit is positioned within a preset distance from the leaf surface of the target crop.

[0024] The artificial intelligence analysis unit further includes a multi-joint arm distance control unit linked to the type of target crop, and generates distance data between the plant sensor unit and the leaf surface of the target crop linked to the type of target crop. The multi-joint arm distance control unit linked to the type of target crop generates distance data between the plant sensor unit and the leaf surface of the target crop when the distance between the first target crop and the plant sensor unit is defined as t1, the distance between the second target crop and the plant sensor unit is defined as t2, the amount of gas ejected from the leaf of the first target crop is defined as v1, and the amount of gas ejected from the leaf of the second target crop is defined as v2, and t1 > t2 when v1 > v2, wherein the amount of gas is any one selected from carbon dioxide, volatile organic compounds, ammonia, and ethylene gas, and the multi-joint arm distance control unit linked to the type of target crop calculates the distance between the target crop and the plant sensor unit for each of carbon dioxide, volatile organic compounds, ammonia, and ethylene gas.

[0025] The above artificial intelligence analysis unit determines the plant and soil condition scores according to the following Equation 1. It produces,

[0026] (Equation 1)

[0027] (Here, is a feature value, is the weight corresponding to each feature value, and n represents the total number of feature data used to calculate the plant and soil condition scores.

[0028] The above plant and soil condition scores are plant and soil growth condition indices normalized by Equation 2 below It is converted to,

[0029] (Equation 2)

[0030] (Here, and represents the maximum and minimum values ​​in the training dataset)

[0031] Based on the growth status index of the above plants and soil, the current state of the target crop is classified into one or more of the following states: normal state, nitrogen deficiency state, phosphorus deficiency state, potassium deficiency state, water deficiency state, salt stress state, high temperature stress state, and disease potential state. Effects of the invention

[0032] According to the present invention, plant growth data and soil physical and chemical data can be collected simultaneously, thereby enabling more precise analysis of the condition of the target crop. Additionally, by utilizing a hyperspectral sensor and a stress gas sensor, the growth status, nutritional status, and stress status of the plant can be precisely diagnosed.

[0033] Furthermore, the multi-joint arm-based structure enables ultra-close measurement of plant leaf surfaces, thereby improving measurement accuracy. Additionally, the ultra-fine bubble-based nutrient supply structure can enhance nutrient transfer and absorption efficiency. Brief explanation of the drawing

[0034] FIG. 1 is a conceptual diagram of a smart growth control device according to one embodiment of the present invention. Figure 2 is a diagram illustrating the combined structure of the plant sensor unit and the soil sensor unit. Figure 3 is a diagram illustrating a multi-joint arm-based sensor placement structure. Figure 4 is a drawing illustrating the internal configuration of the main housing. FIG. 5(a) is a diagram showing the connection relationship of the main control unit, and FIG. 5(b) is a diagram showing the detailed configuration of the plant sensor unit and the soil sensor unit. Figure 6 is a diagram illustrating a solar-based independent power supply structure. Figure 7 is a diagram illustrating the structure of the status display unit. Figure 8 is a diagram illustrating a wireless communication configuration. FIG. 9(a) is a drawing illustrating an example of a facility house installation, and FIG. 9(b) is a drawing illustrating an example of an open field installation. Figure 10 is a diagram illustrating a structure for measuring close contact with the surface of a plant leaf. Figure 11 is a diagram illustrating an artificial intelligence analysis and an ultrafine bubble-based nutrient prescription linkage structure. Figure 12 is a diagram illustrating an example of a real-time growth monitoring screen. Specific details for implementing the invention

[0035] Expressions such as “comprising” or “may comprise” that may be used in various embodiments of the present disclosure indicate the presence of the disclosed corresponding function, operation, or component, etc., and do not limit one or more additional functions, operations, or components, etc. Furthermore, in various embodiments of the present disclosure, terms such as “comprising” or “having” are intended to specify the presence of the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0036] In various embodiments of the present disclosure, expressions such as “or” include any and all combinations of the words listed together. For example, “A or B” may include A, may include B, or may include both A and B.

[0037] Expressions such as "first," "second," "first," or "second" used in various embodiments of the present disclosure may modify various components of the various embodiments, but do not limit such components. For example, such expressions do not limit the order and / or importance of such components. Such expressions may be used to distinguish one component from another. For example, the first user device and the second user device are both user devices and represent different user devices. For example, without departing from the scope of the various embodiments of the present disclosure, the first component may be named the second component, and similarly, the second component may be named the first component.

[0038] When it is stated that a component is "connected" or "connected" to another component, it should be understood that the component may be directly connected or connected to the other component, but that a new component may exist between the component and the other component. On the other hand, when it is stated that a component is "directly connected" or "directly connected" to another component, it should be understood that no new component exists between the component and the other component.

[0039] In embodiments of the present disclosure, terms such as "module," "unit," "part," etc. are used to refer to a component that performs at least one function or operation, and such component may be implemented in hardware or software, or a combination of hardware and software. Additionally, a plurality of "modules," "units," "parts," etc. may be integrated into at least one module or chip and implemented as at least one processor, except where each needs to be implemented in specific individual hardware.

[0040] The terms used in the various embodiments of this disclosure are used merely to describe specific embodiments and are not intended to limit the various embodiments of this disclosure. The singular expression includes the plural expression unless the context clearly indicates otherwise.

[0041] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the various embodiments of this disclosure pertain. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in the various embodiments of this disclosure.

[0042] The present invention relates to a smart growth control device, and more specifically, to a smart growth control device utilizing AIoT-based integrated growth data analysis and ultrafine bubble nutrient prescription. Here, the term "smart growth control device" may be used as "smart growth control system." It will be described in detail below with reference to the drawings.

[0043] FIG. 1 is a conceptual diagram of a smart growth control device according to an embodiment of the present invention, FIG. 2 is a diagram illustrating a combined structure of a plant sensor unit (120) and a soil sensor unit (130), and FIG. 3 is a diagram illustrating a sensor arrangement structure based on a multi-joint arm (140). As shown in FIG. 1 to 3, a smart growth control device according to an embodiment of the present invention comprises: a support pole (150); a waterproof main housing (110) coupled to the support pole (150); a plant sensor unit (120) electrically connected to the main housing (110) and collecting plant growth data of a target crop; a soil sensor unit (130) inserted into the soil and collecting soil physical and chemical data; a multi-joint arm (140) that supports the plant sensor unit (120) so as to be position-adjustable in the direction of the target crop; and an artificial intelligence analysis unit that analyzes the data collected from the plant sensor unit (120) and the soil sensor unit (130) to determine the growth state of the target crop and generate nutrient prescription information.

[0044] The support post (150) is a structure for stably installing and supporting the smart growth control device of the present invention on the ground or a cultivation structure. The support post (150) may be configured to support the main housing (110), multi-joint arm (140), plant sensor unit (120), solar panel (117), and status display unit (115) at a certain height, and may be formed to be installable in a greenhouse or open field environment. The support post (150) may be formed as a metal frame structure, and may be made of stainless steel or aluminum to improve durability and corrosion resistance. In addition, a base structure for ground fixation may be formed at the bottom of the support post (150), and the solar panel (117) and multi-joint arm (140) may be connected to the top. Accordingly, the support post (150) can function as a support structure that stably supports the sensor unit and the control unit, allowing the device to operate stably in various cultivation environments.

[0045] The above plant sensor unit (120) may be configured to be position-adjustable in the direction of the target crop by being coupled to the end of the multi-joint arm (140), and collects eight types of plant growth data including hyperspectral wavelength (nm), growth status image, leaf surface temperature, leaf surface humidity, volatile organic compounds (VOC), carbon dioxide (CO2) content, ammonia (NH3) content, and ethylene (C2H4) content of the target crop, and collects various growth data from the leaves, stems, or fruits of the target crop in order to measure the growth status, stress status, and nutritional status of the target crop in real time. The above plant sensor unit (120) includes one or more selected from a hyperspectral sensor, an RGB camera sensor, a leaf surface temperature sensor, a humidity sensor, a carbon dioxide sensor, a volatile organic compound (VOC) sensor, an ammonia sensor, and an ethylene sensor, and the soil physical and chemical data collected therefrom may be transmitted through a communication module (112).

[0046] The hyperspectral sensor described above can measure the light spectrum reflected from the leaf surface of a target crop, thereby allowing for the analysis of chlorophyll content, photosynthetic activity, water content, nitrogen deficiency status, and growth vitality. For example, changes in reflectance at specific wavelengths can be used to determine the plant's stress or nutrient deficiency status at an early stage. The RGB camera sensor described above captures external images of the target crop to analyze changes in leaf color, growth size, fruit condition, the presence of lesions, and growth uniformity. Additionally, an image analysis algorithm can be used to calculate leaf area, the number of fruits, and the growth rate. The leaf surface temperature sensor described above can measure the temperature of the plant leaf surface, thereby allowing for the determination of transpiration status, water stress status, and abnormal growth. For example, if the leaf surface temperature rises above a reference temperature, it can be determined as a state of water deficiency or growth stress. The humidity sensor described above can measure the relative humidity around the plant and analyze the microenvironmental conditions surrounding the target crop. The carbon dioxide sensor can measure the CO₂ concentration around plants and analyze the photosynthetic activity and ventilation status. The volatile organic compound (VOC) sensor can detect volatile gases emitted from plants and can determine the occurrence of diseases, stress conditions, or abnormal growth conditions at an early stage. The ammonia sensor can measure the ammonia concentration in the cultivation environment and analyze excessive nitrogen components or fertilizer abnormal conditions. The ethylene sensor can measure ethylene gas emitted from plants and analyze fruit ripening conditions, aging conditions, or stress response conditions.

[0047] The soil sensor unit (130) is inserted into the soil and collects eight types of soil physical and chemical data, including pH, electrical conductivity (EC), humidity, temperature, salinity, nitrogen (N) content, phosphorus (P) content, and potassium (K) content of the target soil. It can be configured to measure the physical and chemical conditions of the soil in which the target crop is cultivated in real time and to be inserted into the soil around the roots of the target crop to collect various soil physical and chemical data. The soil sensor unit (130) includes one or more selected from a soil moisture sensor, a soil temperature sensor, a soil pH sensor, a soil electrical conductivity sensor, a nitrogen sensor, a phosphorus sensor, a potassium sensor, and a soil salinity sensor, and the soil physical and chemical data collected therefrom can be transmitted through a communication module (112).

[0048] The soil moisture sensor can analyze irrigation and soil dryness conditions by measuring the moisture content within the soil. The soil temperature sensor can analyze the root growth environment of the target crop by measuring the internal soil temperature. The soil pH sensor can determine whether the soil conditions are suitable for crop growth by measuring the acidity or alkalinity of the soil. The soil electrical conductivity sensor can analyze fertilizer concentration, nutrient concentration, and salt accumulation conditions by measuring the ion concentration within the soil. Additionally, the nitrogen, phosphorus, and potassium sensors can analyze nutrient deficiency or excess conditions of the target crop by measuring the concentration of major nutrient components within the soil. The soil salinity sensor can determine whether growth is inhibited due to salt accumulation by measuring the salt concentration within the soil.

[0049] The multi-joint arm (140) may be controlled by a control signal from a main control unit (111), and the multi-joint arm (140) may include a first joint portion rotatably coupled to a main housing (110) or a support column (150), a first arm portion connected to the first joint portion, a second joint portion rotatably coupled to the end of the first arm portion, and a second arm portion supporting the plant sensor portion (120). Additionally, the multi-joint arm (140) may include a fixing member for fixing the rotational position of each joint portion, and may be configured so that the user can fix the position of the plant sensor portion (120) at a desired position after adjusting the position according to the growth position of the target crop.

[0050] The multi-joint arm (140) may be configured to adjust the height of the plant sensor unit (120) from the ground, the distance from the target crop, and the angle of inclination from the target crop using a plurality of rotating joints. Specifically, the multi-joint arm (140) may adjust the vertical height of the plant sensor unit (120) according to the growth height of the target crop, and may adjust the horizontal position according to the position change of the leaf or fruit. In addition, the multi-joint arm (140) may be configured to adjust the angle of inclination of the plant sensor unit (120) so that the sensor is precisely positioned toward the leaf surface of the target crop. The plant sensor unit (120) may be coupled to the end of the multi-joint arm (140) and positioned within a preset distance from the leaf surface of the target crop, and preferably, position control may be maintained within a range of about 1 cm to 3 cm.

[0051] The soil physical and chemical data collected by the soil sensor unit (130) is transmitted to the artificial intelligence analysis unit and can be used as data for analyzing the growth status of the target crop, analyzing the nutrient status, and controlling the nutrient prescription. Therefore, the soil sensor unit (130) can function as a core sensor component for precisely analyzing the root environment status and soil nutrient status of the target crop.

[0052] The above artificial intelligence analysis unit is configured to determine the growth status, nutritional status, and stress status of a target crop by integrating and analyzing data collected from the plant sensor unit (120) and the soil sensor unit (130), and can be implemented by being included in the main control unit (111) or an external server.

[0053] The artificial intelligence analysis unit described above can receive plant growth data and soil physical and chemical data as input data, and the input data may include at least one of hyperspectral data, RGB image data, leaf surface temperature data, humidity data, carbon dioxide data, volatile organic compound data, ammonia data, ethylene data, soil moisture data, soil temperature data, soil pH data, soil electrical conductivity data, and nitrogen, phosphorus, and potassium data.

[0054] The AI ​​analysis unit described above can receive collected plant growth data and soil physical and chemical data and perform a pre-processing process. This pre-processing process may include missing value correction, noise removal, data normalization, outlier removal, and time-series synchronization. For example, if a measurement value is missing from a specific sensor, the missing value can be corrected using data from a previous time point or an average-based interpolation technique, and sensor noise can be removed using a moving average filter, a Kalman filter, or a low-pass filter. Additionally, Min-Max normalization or Z-score normalization can be performed to integrate and analyze data with different units.

[0055] The artificial intelligence analysis unit described above can extract features representing plant and soil conditions from preprocessed plant growth data and soil physical and chemical data. In the feature extraction process, specific wavelength range reflectance of hyperspectral data, color distribution and leaf area index (LAI) of growth condition images, leaf surface temperature change rate, VOC concentration change pattern, soil pH change rate, EC change rate, and NPK concentration distribution can be extracted as feature values.

[0056] For example, the artificial intelligence analysis unit can extract leaf area, leaf color change, lesion pattern, and growth uniformity from growth status images using a Convolutional Neural Network (CNN)-based image analysis model, and can analyze time-series changing soil and plant data using a Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), or Transformer-based time-series analysis model. In addition, the artificial intelligence analysis unit can calculate plant and soil condition scores by fusing the feature extraction results.

[0057] The condition scores of the above plants and soil can be calculated by the following mathematical formula.

[0058]

[0059] (Here, is the growth status score, and is each sensor data or feature value, and (where is the weight corresponding to each feature value, and n represents the total number of feature data or sensor data used to calculate the state score.) For example, if 8 types of plant growth data and 8 types of soil physical and chemical data are used, n represents 16. The above feature values ​​represent feature values ​​related to plant growth data and soil physical and chemical data.

[0060] In addition, the above condition score can be converted into a growth condition index in the range of 0 to 100 through a normalization process, which can be calculated by the following mathematical formula.

[0061]

[0062] (Here, is a normalized growth status index, and and represents the maximum and minimum values ​​in the training dataset)

[0063] The artificial intelligence analysis unit described above can classify the current state of the target crop into a normal state, nitrogen-deficient state, phosphorus-deficient state, potassium-deficient state, water-deficient state, salt stress state, high-temperature stress state, or disease-prone state based on the growth state index and soil state index. Furthermore, the artificial intelligence analysis unit can predict not only the current state but also the growth state after a certain period, and can calculate the optimal nutrient prescription amount based on this.

[0064] In addition, the artificial intelligence analysis unit can perform time-series-based growth change analysis using past growth data and real-time collected data stored in the storage device (118), and can predict the future growth status or the possibility of disease occurrence of the target crop.

[0065] The above-described multi-joint arm (140) may be configured to include a plurality of rotating joints to allow adjustment of the height of the plant sensor unit (120), the distance from the target crop, and the tilt angle. The plant sensor unit (120) may be positioned within a preset distance from the leaf surface of the target crop to measure plant growth information and gas information. Additionally, depending on the type of target crop, the emission amounts of carbon dioxide, volatile organic compounds (VOC), ammonia, and ethylene gas may vary. Accordingly, the artificial intelligence analysis unit may include a multi-joint arm distance adjustment unit linked to the type of target crop, and may calculate the optimal distance between the plant sensor unit (120) and the leaf surface according to the type of target crop and the gas emission amount. For example, if the gas emission amount (v1) of the first target crop is greater than the gas emission amount (v2) of the second target crop (v1 > v2), the distance control unit can generate distance data such that the distance (t1) between the first target crop and the plant sensor unit (120) is greater than the distance (t2) between the second target crop and the plant sensor unit (120) (t1 > t2). That is, the crop with a large gas emission amount can be measured at a relatively distanced distance to prevent sensor saturation, and the crop with a small gas emission amount can be measured at a closer distance to improve measurement sensitivity. In addition, the distance control unit can calculate individual optimal measurement distances for carbon dioxide, volatile organic compounds, ammonia, and ethylene gas, respectively, and can automatically adjust the position of the multi-joint arm (140) based on the calculated distance data.

[0066] For example, fruit and vegetable crops such as tomatoes, strawberries, bell peppers, cucumbers, and eggplants may show relatively high emissions of ethylene gas or volatile organic compounds (VOCs). On the other hand, leafy vegetable crops such as lettuce, spinach, bok choy, and kale have relatively low ethylene emissions, but may show significant changes in volatile organic compounds (VOCs) under water stress conditions. Additionally, herb crops such as basil, rosemary, mint, and lavender may emit relatively large amounts of aromatic volatile organic compounds (VOCs). For example, in the case of a first target crop with high ethylene emissions, such as tomatoes, the distance between the plant sensor unit (120) and the leaf surface can be set relatively large, and in the case of a second target crop with low ethylene emissions, such as lettuce, the plant sensor unit (120) can be placed closer to the leaf surface. Accordingly, the present invention can improve gas sensing accuracy and growth status analysis accuracy by optimizing the distance between the plant sensor unit (120) and the leaf surface according to the gas emission characteristics of each type of target crop.

[0067] The above artificial intelligence analysis unit can generate a control signal including a nutrient supply amount, a nutrient supply cycle, an irrigation amount, or environmental control conditions based on the analysis results, and the generated control signal can be transmitted to a nutrient supply unit (160).

[0068] In addition, the aforementioned artificial intelligence analysis unit can perform a retraining function using the results of growth changes. For example, it can continuously update the learning model by analyzing the error between the growth data re-collected after nutrient supply and the target growth state. Therefore, the artificial intelligence analysis unit can function as a core analysis component for integrally analyzing plant growth and soil conditions, and for performing optimal nutrient prescriptions and growth control corresponding to the state of the target crop.

[0069] A status display unit (115) may be provided on the outer side of the main housing (110). The status display unit (115) visually provides the user with the operating status of the smart growth control device.

[0070] FIG. 4 is a drawing illustrating the internal configuration of the main housing (110). FIG. 5(a) is a drawing illustrating the connection relationship of the main control unit (111), and FIG. 5(b) is a drawing illustrating the detailed configuration of the plant sensor unit (120) and the soil sensor unit (130). As shown in FIG. 4 and 5, the main housing (110) is a structure for accommodating and protecting the electrical components of the smart growth control device, and can be formed to have a waterproof and dustproof structure.

[0071] The interior of the main housing (110) may include a main control unit (111), a communication module (112), a power module (113), and a storage device (118). The main control unit (111) may be electrically connected to the plant sensor unit (120), the soil sensor unit (130), the communication module (112), the power module (113), the storage device (118), and the artificial intelligence analysis unit to integrate and control the operation of each component. It may receive data input from the plant sensor unit (120) and the soil sensor unit (130) in real time and perform preprocessing processes including noise removal, data correction, and outlier removal. Additionally, the main control unit (111) may improve the operational efficiency of the device by controlling the sensor measurement cycle, the data transmission cycle, and the power usage status.

[0072] The communication module (112) may be configured to transmit data collected from the plant sensor unit (120) and the soil sensor unit (130) to an external server using at least one wireless communication method among LoRa, WiFi, ZigBee, LTE, and Bluetooth. Specifically, the LoRa method may be used to perform long-distance low-power communication, and the WiFi method may be used to perform high-speed data transmission in a network environment inside a greenhouse. In addition, the ZigBee method may be used to configure a low-power sensor network, and the LTE method may be used to perform remote data transmission based on mobile communication. The Bluetooth method may be used for connection with a short-range user terminal (190) or for transmitting and receiving data for maintenance purposes.

[0073] The communication module (112) can transmit data collected from the plant sensor unit (120) and the soil sensor unit (130) to an external server along with time information. The time information may include the time of data measurement, the time of data storage, or the time of data transmission, and can be configured to enable time-series analysis of growth changes. The external server may be implemented in the form of a cloud server (180) and may include a database for storing and analyzing the collected data.

[0074] The storage device (118) is configured to store data collected from the plant sensor unit (120) and the soil sensor unit (130) and may include flash memory, an SSD (Solid State Drive), an SD card, or a non-volatile memory device. The storage device (118) can store not only real-time sensor data but also past growth data, nutrient supply history, environmental change history, and artificial intelligence analysis results. Additionally, the storage device (118) can temporarily store data in the event of a communication failure or network instability, and can retransmit the stored data to an external server when communication is restored.

[0075] FIG. 6 is a diagram illustrating a solar-based independent power supply structure. As shown in FIG. 6, a solar panel (117) may be attached to the upper part of the support post (150), and the solar panel (117) may be configured to convert solar energy into electrical energy and supply power to a smart growth control device. The solar panel (117) may be installed on the upper part of the support post (150) at a certain angle of inclination and may be positioned in a direction corresponding to the direction of sunlight in the target area to improve solar light reception efficiency. In addition, the solar panel (117) may be electrically connected to a power module (113) through a charging controller (117-1), a battery (119), and a power conversion unit (117-2). The charging controller (117-1) is configured to stably charge the power generated from the solar panel (117) and may be configured to prevent overcharging, over-discharging, and overcurrent conditions. The battery (119) is configured to store charged power and may include at least one of a lithium-ion battery (119), a lithium iron phosphate battery (119), or a lead-acid battery. The power module (113) may be configured to control power supplied from the solar panel (117) and the battery (119) to supply a stable operating voltage to the plant sensor unit (120), the soil sensor unit (130), the communication module (112), and the artificial intelligence analysis unit. Accordingly, the smart growth control device of the present invention can be operated independently for a long time even in greenhouse or open-field environments where external commercial power supply is difficult.

[0076] FIG. 7 is a diagram illustrating the structure of a status display unit (115). As shown in FIG. 7, the status display unit (115) can visually display the device status using lamps such as a red lamp (115-11), a yellow lamp (115-2), and a green lamp (115-3). For example, a green light state can be displayed in a normal state, and a yellow flashing state can be displayed in a communication delay state or a low battery state. Additionally, a red flashing state can be displayed in a sensor abnormal state or a system error state. Furthermore, the status display unit (115) can provide more detailed status information by changing the flashing speed or the lighting pattern. For example, low-speed flashing can be configured to display a warning state, and high-speed flashing can be configured to display an emergency error state. Thus, the status display unit (115) can perform the function of improving maintenance convenience and system management efficiency by allowing the user to intuitively check the operating status of the smart growth control device. When the red lamp emits light, a warning sound can be emitted externally through a buzzer (115-4).

[0077] FIG. 8 is a diagram illustrating a wireless communication configuration. As shown in FIG. 8, data transmitted from a plant sensor unit (120) and a soil sensor unit (130) is received by a remote communication module (112-1) located at a certain distance, and the received data can be stored in a cloud server (180) and utilized by a user terminal (190). The remote communication module (112-1) can receive data from multiple sensor devices separated by a certain distance or more and can act as a gateway in a smart farm or greenhouse environment. The remote communication module (112-1) can transmit data received from the plant sensor unit (120) and the soil sensor unit (130) to the cloud server (180). The cloud server (180) can store the received growth data and soil data and can perform data analysis, learning data management, and artificial intelligence analysis functions. In addition, the cloud server (180) can store data history by time and area to analyze the growth change trends of the target crop. The user terminal (190) may include a smartphone, tablet PC, laptop, or desktop computer and may be connected to the cloud server (180) via communication. The user terminal (190) may display real-time growth data, soil data, artificial intelligence analysis results, and nutrient prescription information.

[0078] FIG. 9(a) is a drawing illustrating an example of installation in a greenhouse, FIG. 9(b) is a drawing illustrating an example of installation in an open field, and FIG. 10 is a drawing illustrating a structure for measuring contact with the surface of a plant leaf. As shown in FIG. 9 and 10, the smart growth control device of the present invention may be located inside a greenhouse or outside a greenhouse so that the plant sensor unit (120) can measure the condition of the plant.

[0079] FIG. 11 is a diagram illustrating an artificial intelligence analysis and an ultrafine bubble-based nutrient prescription linkage structure. Referring to FIG. 11, the smart growth control device of the present invention can collect plant growth data and soil physical and chemical data of a target crop using a plant sensor unit (120) and a soil sensor unit (130). Here, the artificial intelligence analysis unit can determine the growth status, nutritional status, and stress status of the target crop by integrating and analyzing the plant growth data and soil physical and chemical data. Specifically, the artificial intelligence analysis unit can calculate the growth status score, nutritional status score, and stress index of the target crop, and can analyze the nitrogen deficiency status, water stress status, or the possibility of disease occurrence. In addition, the artificial intelligence analysis unit can generate nutrient prescription information required for the target crop based on the analysis results. The nutrient prescription information may include the supply ratio of nitrogen, phosphorus, and potassium, the amount of nutrients supplied, the nutrient supply cycle, and irrigation conditions. The above nutrient prescription information can be transmitted to a nutrient supply unit (160), and the nutrient supply unit (160) may include a plurality of nutrient storage tanks, a pump, and a flow rate control unit. Additionally, the nutrient supply unit (160) can control the mixing ratio and supply amount of the nutrient solution supplied to the target crop based on the nutrient prescription information generated by the artificial intelligence analysis unit. The ultrafine bubble generator (170) may be configured to generate ultrafine bubbles within the nutrient solution. The ultrafine bubbles may be generated in the form of microbubbles or nanobubbles, and can improve the root activity of the target crop by increasing the amount of dissolved oxygen in the nutrient solution. Furthermore, the ultrafine bubbles can improve nutrient delivery efficiency and root absorption efficiency, and can increase the oxygen supply efficiency in the soil or growing medium. Growth data collected after the nutrient supply can be used as feedback data.The artificial intelligence analysis unit described above can analyze errors in the nutrient prescription results using the feedback data, and can retrain the artificial intelligence model by reusing the analysis results as training data. Therefore, the present invention has the advantage of improving the growth efficiency and nutrient absorption efficiency of target crops by linking real-time growth data-based artificial intelligence analysis with ultrafine bubble-based nutrient supply technology.

[0080] The above-described ultrafine bubble generator (170) may include a receiving unit, a valve unit, a control unit, a bubble generation unit, and a spraying unit. The receiving unit may receive control signals regarding pH buffer solution, nitrogen (N), phosphorus (P), potassium (K), and irrigation amount via wired or wireless communication. The valve unit may include a plurality of valves for individually adjusting the supply amounts of pH buffer solution, nitrogen (N), phosphorus (P), potassium (K), and irrigation solution, and may control the mixing ratio and supply amount of each component according to the soil condition and growth condition of the target crop. The control unit may control the opening time, opening sequence, and flow rate of each valve according to the received control signal to adjust the mixing ratio of the nutrient solution, and may correct the actual supply amount in real time by linking with a flow sensor or a pressure sensor. The bubble generation unit may be configured to generate ultrafine bubbles within the mixed nutrient solution, and may improve the dissolved oxygen content and nutrient transfer efficiency by utilizing the ultrafine bubbles. The above-described spraying unit is configured to automatically spray a nutrient solution containing ultrafine bubbles onto a target crop and may include a spray nozzle, a fine spray nozzle, or a drip irrigation nozzle. Additionally, the spraying unit can control the spraying pressure, spraying time, and spraying angle according to the type of target crop and cultivation environment to ensure that nutrients are supplied uniformly to the target crop.

[0081] Additionally, the artificial intelligence analysis unit may further include an error value-dependent injection cycle control unit for dynamically adjusting the nutrient supply cycle based on the error value for each item by comparing the actual value after nutrient supply with the nutrient prescription target value. The error value-dependent injection cycle control unit controls a cycle signal for injecting the corresponding nutrient from the ultrafine bubble generator (170) when the calculated error value exceeds a preset reference range. Here, as the error value increases, the number of injections for the same total amount of water or the same total amount of nutrient can be increased, and the individual injection interval can be shortened. For example, if a total of 100 units of nutrient is supplied in 5 installments for a first error value, an injection cycle signal can be generated to supply the same 100 units of nutrient in 10 installments when a second error value greater than the first error value occurs. Accordingly, the amount of nutrients supplied per unit time decreases while the supply frequency increases, thereby improving the nutrient absorption efficiency of the target crop roots or soil. The above error value can be calculated for each item by comparing the actual measured value after nutrient supply with the nutrient prescription target value. For example, if the target pH value is 6.5 and the actual measured pH value is 6.1, the pH error value can be calculated as 0.4.

[0082] Meanwhile, the artificial intelligence analysis unit further includes a data quantity-dependent spraying amount control unit for correcting the nutrient supply amount based on the data quantity of collected plant growth data and soil physical and chemical data, and can control the ultrafine bubble generator (170) to increase the spraying amount of the corresponding nutrient when the amount of collected plant growth data and soil physical and chemical data is less than a preset reference value. This is because the prediction accuracy of the artificial intelligence analysis unit may be relatively low when the data quantity is insufficient. Therefore, in order to compensate for prediction errors that may occur in a state of insufficient data, the present invention can control the nutrient amount increased from the reference spraying amount within an allowable range that does not adversely affect the target crop in the form of a margin.

[0083] FIG. 12 is a diagram illustrating an embodiment of a real-time growth monitoring screen. Referring to FIG. 12, the real-time growth monitoring screen may be configured to display the growth status and soil status of a target crop in real time through a user terminal (190). The user terminal (190) may include a smartphone, tablet PC, laptop, or desktop computer and may be connected to an external server through a communication module (112). The real-time growth monitoring screen may include a crop status area, a plant growth data area, a soil growth data area, and an artificial intelligence analysis result area. The crop status area may display an image of the target crop, the growth stage, and crop status information. For example, the current growth stage of the target crop may be displayed as the flowering stage, the fruit setting stage, or the harvesting stage. The plant growth data area may display data measured by a plant sensor unit (120). Specifically, information such as temperature, humidity, carbon dioxide concentration, light intensity, ethylene concentration, and stress index may be displayed in real time. The above soil biological data area can display data measured by the soil sensor unit (130). For example, information on soil pH, electrical conductivity (EC), moisture content, soil temperature, and nitrogen, phosphorus, and potassium concentrations can be displayed. The above artificial intelligence analysis result area can display growth evaluation results and recommended nutrient prescription information analyzed by the artificial intelligence analysis unit. For example, the growth status can be displayed as normal, caution, or danger, and the recommended increase or decrease in supply of nitrogen, phosphorus, and potassium can be displayed. In addition, the above real-time growth monitoring screen may include a graph display function, a notification function, and a setting function. The above notification function can provide a warning notification to the user terminal (190) when a sensor malfunction, a communication malfunction, a nutrient deficiency, or an increase in the stress index occurs.In addition, the above graph display function can display growth change data and soil change data over time as a time-series graph. Therefore, the present invention has the advantage of improving cultivation management efficiency and growth control accuracy by visualizing and providing the growth and nutrient status of the target crop to the user in real time.

[0084] The device described above may be implemented as a hardware component, a software component, or a combination of a hardware component and a software component. For example, the system and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are also possible.

[0085] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave in order to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0086] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0087] Although the embodiments have been described above with reference to limited examples and drawings, those skilled in the art can make various modifications and variations from the description above. For example, suitable results can be achieved even if the described techniques are performed in a different order than described, and / or the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0088] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below. Explanation of the symbols

[0089] 110 : Main Housing 111 : Main control unit 112 : Communication module 113 : Power module 114 : Wiring Management Department 115: Status display 117 : Solar panel 118 : Storage device 119 : Battery 120: Plant sensor unit 130 : Soil sensor unit 140 : Multi-joint arm 150 : Support post 160 : Nutrient supply unit 170 : Ultrafine bubble generator 180 : Cloud Server 190 : User terminal

Claims

Claim 1 Support post; a waterproof main housing coupled to the support post; a plant sensor unit electrically connected to the main housing and collecting plant growth data of a target crop; a soil sensor unit inserted into the soil and collecting soil physical and chemical data; and a multi-joint arm that supports the plant sensor unit so as to be position-adjustable in the direction of the target crop. and an artificial intelligence analysis unit that analyzes data collected from the plant sensor unit and the soil sensor unit to determine the growth status of the target crop and generates nutrient prescription information; wherein the plant sensor unit includes a hyperspectral sensor, an RGB camera sensor, a leaf surface temperature sensor, a humidity sensor, a carbon dioxide sensor, a volatile organic compound sensor, an ammonia sensor, and an ethylene sensor; wherein the soil sensor unit includes a soil moisture sensor, a soil temperature sensor, a soil pH sensor, a soil electrical conductivity sensor, a nitrogen sensor, a phosphorus sensor, a potassium sensor, and a soil salinity sensor; wherein the artificial intelligence analysis unit integrates and analyzes plant growth data and soil physical and chemical data to calculate a state score of the target crop's plant and soil, and generates nutrient prescription information required for the target crop based on the calculated state score of the target crop's plant and soil; wherein a solar panel is coupled to the upper part of the support pole, and the solar panel is connected to a battery and a conversion control unit to supply independent power; wherein a status display unit is provided on the outer side of the main housing to display a sensor abnormality status, a communication status, and a power status, and the status display unit uses a plurality of colors or flashing patterns to display the sensor abnormality status, the communication status, and the power status It is configured to display visually, and the main housing includes a communication module, a power module, and a storage device. The communication module transmits data collected from the plant sensor unit and the soil sensor unit to an external server, and also transmits data collected from the plant sensor unit and the soil sensor unit to an external server along with time information using at least one wireless communication method among LoRa, WiFi, ZigBee, LTE, and Bluetooth.The above storage device is configured to store data collected from the plant sensor unit and the soil sensor unit, and the artificial intelligence analysis unit analyzes the growth status of the target crop using the stored data and real-time collected data. The above multi-joint arm is configured to include a plurality of rotational joints to adjust the height of the plant sensor unit from the ground, the distance from the plant, and the angle from the plant. The above plant sensor unit is positioned within a preset distance from the leaf surface of the target crop. The artificial intelligence analysis unit further includes a target crop type-linked multi-joint arm distance adjustment unit, which generates distance data between the plant sensor unit and the leaf surface of the target crop linked to the type of target crop. The target crop type-linked multi-joint arm distance adjustment unit generates distance data between the plant sensor unit and the leaf surface of the target crop as t1 when v1 > v2, where t1 is defined as the distance between the first target crop and the plant sensor unit, t2 as the distance between the second target crop and the plant sensor unit, v1 as the amount of gas emitted from the leaf of the first target crop, and v2 as the amount of gas emitted from the leaf of the second target crop. The amount of gas is carbon dioxide, volatile A smart growth control device using AIoT-based integrated growth data analysis and ultrafine bubble nutrient prescription, characterized in that the target crop type-linked multi-joint arm distance control unit is selected from organic compounds, ammonia, and ethylene gas, and calculates the distance between the target crop and the plant sensor unit for each of carbon dioxide, volatile organic compounds, ammonia, and ethylene gas. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 In claim 1, the artificial intelligence analysis unit determines the condition scores of plants and soil by the following formula 1. It produces, (Equation 1)(here, is a feature value, ε₀ represents the weight corresponding to each feature value, and n represents the total number of feature data used to calculate the plant and soil condition scores.) The above plant and soil condition scores are the plant and soil growth condition indices normalized by Equation 2 below. It is converted to, (Equation 2)(here, and A smart growth control device using AIoT-based integrated growth data analysis and ultrafine bubble nutrient prescription, characterized by classifying the current state of the target crop into one or more selected states—normal state, nitrogen deficiency state, phosphorus deficiency state, potassium deficiency state, water deficiency state, salt stress state, high temperature stress state, and disease potential state—based on the growth state index of the plant and soil.

Images