Planting monitoring method based on crop growth data

Abstract

The invention discloses a planting monitoring method based on crop growth data, and particularly relates to the technical field of planting monitoring, and the method comprises the steps: carrying out the real-time monitoring of a tomato growth environment based on RISC-V + OpenHarmony, collecting the environment feature value of a tomato growth process through a sensor, collecting the growth image of the tomato, and carrying out the calculation of the growth image of the tomato, the method comprises the following steps: analyzing a tomato growth image by using a YOLOv8 convolutional neural network, comparing an actually acquired environment characteristic value with an ideal environment characteristic value in a historical record, and determining a difference between a predicted value and an actual value of the tomato growth environment characteristic value through an autoregression model, thereby obtaining tomato growth environment information. The tomato growth state information is determined by analyzing diseases existing in the historical tomato growth process and the RGB color space of the tomato growth image, the abnormal condition existing in the tomato growth process is warned in time through the neural network model, the potential abnormal growth condition of the tomato can be identified, and the tomato growth state information is obtained. The yield and the quality of tomatoes are improved.

Description

Technical Field

[0001] The present invention relates to the field of planting monitoring technology, and more specifically, to a planting monitoring method based on crop growth data. Background Art

[0002] Traditional agricultural management methods often rely on experience and are difficult to achieve scientific and intelligent management, especially in greenhouse and shed cultivation. Environmental factors have a decisive influence on crop growth and yield. Therefore, real-time monitoring and analysis of the crop growth environment, timely identification and resolution of potential diseases and growth abnormalities have become important means to improve agricultural production efficiency and quality. Traditional agricultural monitoring methods often rely on manual observation, resulting in slow disease identification and low accuracy. It is not easy to achieve real-time monitoring of the tomato growth environment, and there is a lack of early warning of potential abnormalities in the growth process of crops.

[0003] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a planting monitoring method based on crop growth data to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: A planting monitoring method based on crop growth data specifically comprises the following steps: S1: Based on RISC-V+OpenHarmony, the tomato growth environment is monitored in real time. The environmental characteristic values ​​of the tomato growth process are collected through sensors, and the growth images of the tomato are collected. The growth images of the tomato are analyzed using the YOLOv8 convolutional neural network; S2: By comparing the actual environmental characteristic values ​​collected with the ideal environmental characteristic values ​​in the historical records, and determining the difference between the predicted value and the actual value of the tomato growth environment characteristic value through the autoregressive model, the growth environment information of the tomato is obtained, and the growth environment evaluation model is constructed; S3: Determine the growth status information of tomatoes by analyzing the diseases existing in the historical tomato growth process and the RGB color space of tomato growth images, and build a health assessment model; S4: Comprehensively analyze the growth environment information and growth status information of tomatoes, and use the neural network model to promptly warn of abnormal conditions in the growth process of tomatoes.

[0006] In a preferred embodiment, the growth environment information of tomatoes includes: The growth environment information is represented by the growth environment similarity coefficient and the growth environment instability coefficient; The logic for obtaining the growth environment similarity coefficient is: obtaining the environmental characteristic values ​​of tomatoes in real time, wherein the environmental characteristic values ​​of tomatoes are temperature, humidity, carbon dioxide concentration, light intensity, and nutrient solution TDS value, and representing the environmental characteristic values ​​of tomatoes obtained in real time in the form of vectors: , the ideal environmental characteristic value of tomatoes is expressed in the form of a vector: ; The environmental characteristic values ​​and ideal environmental characteristic values ​​of tomatoes are processed by minimum-maximum normalization, including determining a reasonable minimum and maximum value for each environmental characteristic value, or using historical data to determine the minimum and maximum range, and marking the environmental characteristic values ​​and ideal environmental characteristic values ​​of tomatoes after normalization as: and , n=1, 2, 3, 4, 5, n is the number of the environmental characteristic value; Calculate the growth environment similarity coefficient, the calculation formula is: ;in, is the growth environment similarity coefficient.

[0007] In a preferred embodiment, the growth environment instability coefficient includes: The logic for obtaining the growth environment instability coefficient is as follows: an autoregressive model is constructed based on the historical environmental characteristic values ​​of tomatoes, and the autoregressive coefficient in the autoregressive model is estimated by the least square method or other methods. The expression of the autoregressive model is: ;in, is the predicted value at the current time t, , , … is the autoregressive coefficient in the autoregressive model, , , … is the historical environmental characteristic value of tomato, is the noise term; Set a monitoring interval, collect the normalized environmental characteristic values ​​of tomatoes within the monitoring interval, and mark the actual values ​​of the normalized environmental characteristic values ​​of tomatoes within the monitoring interval as: , where m=1, 2, 3, ..., M, M is a positive integer, and m is the number of times the environmental characteristic values ​​of tomatoes are collected within the monitoring interval. The environmental characteristic values ​​predicted by the autoregressive model within the monitoring interval are marked as: ; Calculate the growth environment instability coefficient, the calculation formula is: ;in, is the growth environment instability coefficient.

[0008] In a preferred embodiment, constructing a growth environment assessment model includes: The growth environment similarity coefficient and the growth environment instability coefficient are weighted to construct a growth environment assessment model and generate a growth environment assessment coefficient. The expression of the growth environment assessment coefficient is: ;in, is the growth environment assessment coefficient, is the proportional coefficient of the growth environment similarity coefficient, is the proportional coefficient of the instability of the growth environment, , Both are greater than 0.

[0009] In a preferred embodiment, determining the growth status information of tomatoes includes: The growth status information of tomatoes is expressed by disease impact coefficient and maturity status difference coefficient; The logic for obtaining the disease influence coefficient is as follows: extracting disease features through the growth image of tomatoes, and extracting the disease types existing in tomatoes according to the historical data of tomato growth, and combining the disease features existing in the current tomatoes to determine the disease types that the disease features existing in the current tomatoes cause tomato, that is, the disease features existing in the current tomatoes correspond to one or more disease types, and determining the probability that the disease features existing in tomatoes cause diseases in tomatoes according to the historical data of tomato growth, that is, the disease features existing in tomatoes may cause one or more corresponding disease types to appear in the subsequent cultivation process; After the disease characteristics are detected, the actual disease probability of tomatoes under the disease characteristics is determined, and the actual disease probability of tomatoes under the determined disease characteristics is marked as: , where k = 1, 2, 3, ..., K, K is a positive integer, and k is the number of the identified disease feature; The probability that the disease characteristics of tomatoes will cause diseases in tomatoes is marked as: , where i=1, 2, 3, ..., I, I is a positive integer, and i is the number of the disease type that causes tomato disease characteristics; Calculate the entropy of disease characteristics present in tomatoes using the formula: ; Calculate the disease impact coefficient using the following formula: ;in, is the disease impact coefficient.

[0010] In a preferred embodiment, the maturity state difference coefficient includes: The logic for obtaining the maturity state concealment coefficient is as follows: extract the growth image of the tomato fruit, determine the R value and G value of each pixel in the tomato fruit part, and mark the R value and G value of each pixel in the tomato fruit part as: and , where j=1, 2, 3, ..., J, J is a positive integer, and j is the pixel number of the tomato fruit part; Set the R value threshold range and the G value threshold range, and mark the R value threshold range as: , mark the G value threshold range as: , compare the R value and G value of each pixel in the tomato fruit part with the R value threshold range and the G value threshold range respectively, obtain the pixels that are not in the R value threshold range and the G value threshold range respectively, and mark the R value of the pixel that is not in the R value threshold range as: , mark the pixel G values ​​that are not within the G value threshold range as: , where a=1, 2, 3, ..., A, A is a positive integer, a is the pixel number that is not within the R value threshold range, b=1, 2, 3, ..., B, B is a positive integer, b is the pixel number that is not within the G value threshold range; Calculate the maturity state concealment coefficient, the calculation formula is: ;in, is the concealment coefficient of mature state.

[0011] In a preferred embodiment, constructing a health assessment model includes: The disease impact coefficient and the maturity state difference coefficient are weighted and calculated to construct a health assessment model and generate a health assessment coefficient. The expression of the health assessment coefficient is: ;in, is the health assessment coefficient, , are the proportional coefficients of disease impact coefficient and maturity state difference coefficient, , Both are greater than 0.

[0012] In a preferred embodiment, the growth environment information and growth status information of tomatoes are comprehensively analyzed, including: The current tomato growth environment assessment coefficient, health assessment coefficient and tomato growth stage are used as input features for neural network model training, and the growth warning coefficient is used as the output feature for neural network model training. The model is trained by assigning it to 0 or 1, where 0 indicates that the growth warning coefficient is less than the growth warning coefficient threshold, and 1 indicates that the growth warning coefficient is greater than the growth warning coefficient threshold.

[0013] Technical effects and advantages of the present invention: The present invention uses the Hongmeng system to monitor key parameters of tomatoes in real time, such as temperature, humidity, carbon dioxide concentration, light intensity, and TDS value of nutrient solution. It uses the YOLOv8 convolutional neural network (CNN) to automatically extract features from image data to identify diseased areas on leaves, such as lesions and mildew, so as to judge the health of the leaves. It also conducts a comprehensive analysis of the tomato growth feature data monitored by the sensor and the image data, which can provide timely warnings for abnormal conditions in the growth process of tomatoes, help identify potential growth abnormalities of tomatoes, and improve the yield and quality of tomatoes. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings; Figure 1 The present invention is a flow chart of a planting monitoring method based on crop growth data. DETAILED DESCRIPTION

[0015] 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.

[0016] Example 1 like Figure 1 A flow chart of a planting monitoring method based on crop growth data of the present invention is provided, which specifically comprises the following steps: S1: Based on RISC-V+OpenHarmony, the tomato growth environment is monitored in real time. The environmental characteristic values ​​of the tomato growth process are collected through sensors, and the growth images of the tomato are collected. The growth images of the tomato are analyzed using the YOLOv8 convolutional neural network; S2 compares the actual environmental characteristic values ​​collected with the ideal environmental characteristic values ​​in the historical records, and determines the difference between the predicted value and the actual value of the tomato growth environment characteristic value through the autoregressive model, obtains the tomato growth environment information, and constructs a growth environment evaluation model; S3: Determine the growth status information of tomatoes by analyzing the diseases existing in the historical tomato growth process and the RGB color space of tomato growth images, and build a health assessment model; S4: Comprehensively analyze the growth environment information and growth status information of tomatoes, and use the neural network model to provide timely warnings for abnormal conditions in the growth process of tomatoes.

[0017] Based on RISC-V+OpenHarmony, the tomato growth environment is monitored in real time, scientific cultivation management decisions and plans are provided, to optimize tomato growth conditions and improve yield and quality, mainly including: The processor is based on the RISC-V instruction set architecture, taking advantage of its open source, streamlined, easy to implement and highly scalable features, and uses the OpenHarmony operating system as the software platform; Develop a sensor-based environmental monitoring module to collect key parameters such as temperature, humidity, light intensity, soil moisture, etc. in the tomato growing environment in real time. The sensor needs to be effectively connected to the RISC-V processor to ensure accurate data transmission and processing; Using cameras and other image acquisition devices, combined with image processing and recognition algorithms, the growth status of tomatoes can be monitored in real time, including identification of tomato maturity, pests and diseases, etc., providing intuitive basis for decision support; Utilize the edge computing capabilities of the RISC-V processor to perform deep learning analysis and processing on image data, and efficiently transmit sensor data and some calculation results through the MQTT / HTTP protocol to reduce latency; Configure actuators such as irrigation systems and fertilization systems, connect them to the RISC-V processor through control modules such as relays and motor drivers, develop control algorithms and logic, and automatically adjust the working status of the actuators according to the data collected by sensors to achieve precise control of tomato crops; Based on the TCP / IP protocol, use the wireless network to connect the camera, sensor and device system to the same network segment, such as 192.168.1.X, to achieve real-time data exchange between the device and the cloud or remote monitoring center, configure network communication parameters, and ensure that the device can stably connect to the Internet and transmit data.

[0018] The growth environment information of tomatoes is collected by sensors, and after collection, the growth environment information is represented by a growth environment similarity coefficient and a growth environment instability coefficient.

[0019] Among them, the growth environment similarity coefficient is used to measure the similarity between the current growth environment of tomatoes and the ideal growth environment in history. It is determined by comparing the actual collected environmental characteristic values ​​with the ideal environmental characteristic values ​​in historical records, including: Based on the historical best environmental characteristic values ​​of tomatoes at different growth stages, an ideal environmental characteristic value database is established. The ideal environmental characteristic values ​​reflect the growth performance of tomatoes under optimal conditions. They serve as benchmark environmental characteristics. During the actual growth process of tomatoes, sensors and other equipment are used to collect the current environmental characteristic values ​​in real time. The similarity coefficient formula is used to compare the actual characteristic values ​​currently collected with the historical ideal characteristic values.

[0020] The logic for obtaining the growth environment similarity coefficient is: obtaining the environmental characteristic values ​​of tomatoes in real time, wherein the environmental characteristic values ​​of tomatoes are temperature, humidity, carbon dioxide concentration, light intensity, and nutrient solution TDS value, and representing the environmental characteristic values ​​of tomatoes obtained in real time in the form of vectors: , the ideal environmental characteristic value of tomatoes is expressed in the form of a vector: ; It should be noted that the growth rate, flowering, fruiting and fruit quality of tomatoes are closely related to temperature. Humidity will affect the transpiration of tomatoes and the absorption of water and nutrients. Carbon dioxide directly affects the growth rate and yield of tomatoes. The intensity of light directly affects the efficiency of photosynthesis and determines the energy acquisition and growth rate of tomatoes. The TDS value represents the concentration of minerals and nutrients dissolved in the nutrient solution. It is an important indicator for tomatoes to obtain essential nutrients and reflects whether the mineral supply required by the plant is sufficient. The environmental characteristic values ​​of tomatoes can be monitored in real time through modern agricultural sensors and can be adjusted through the system.

[0021] The environmental characteristic values ​​and ideal environmental characteristic values ​​of tomatoes are processed by minimum-maximum normalization, including determining a reasonable minimum and maximum value for each environmental characteristic value, or using historical data to determine the minimum and maximum range, and marking the environmental characteristic values ​​and ideal environmental characteristic values ​​of tomatoes after normalization as: and , n=1, 2, 3, 4, 5, n is the number of the environmental characteristic value; Calculate the growth environment similarity coefficient, the calculation formula is: ;in, is the growth environment similarity coefficient.

[0022] It can be seen from the formula that the larger the growth environment similarity coefficient is, the more similar the current tomato growth environment is to the ideal environment, which means that there is no need to regulate the growth of tomatoes, and the possibility of maintaining the current growth state is higher.

[0023] Among them, the growth environment instability coefficient is measured by the difference between the predicted value and the actual value of the autoregressive model. The autoregressive model is established using the historical environmental characteristic values ​​of the tomato growth process to predict the future environmental characteristic values. The predicted values ​​are compared with the current characteristic values ​​actually collected to evaluate the stability of the current growth environment.

[0024] The logic for obtaining the growth environment instability coefficient is as follows: an autoregressive model is constructed based on the historical environmental characteristic values ​​of tomatoes, and the autoregressive coefficient in the autoregressive model is estimated by the least square method or other methods. The expression of the autoregressive model is: ;in, is the predicted value at the current time t, , , … is the autoregressive coefficient in the autoregressive model, , , … is the historical environmental characteristic value of tomato, is the noise term; It should be noted that the environmental characteristic values ​​of tomatoes usually remain stable. By capturing these stable and regular changes, the autoregressive model can effectively predict future environmental changes and regulate accordingly.

[0025] Set a monitoring interval, collect the normalized environmental characteristic values ​​of tomatoes within the monitoring interval, and mark the actual values ​​of the normalized environmental characteristic values ​​of tomatoes within the monitoring interval as: , where m=1, 2, 3, ..., M, M is a positive integer, and m is the number of times the environmental characteristic values ​​of tomatoes are collected within the monitoring interval. The environmental characteristic values ​​predicted by the autoregressive model within the monitoring interval are marked as: ; It should be noted that the monitoring interval is a specific length of time. The length of the monitoring interval can be set according to the growth cycle of tomatoes, the speed of specific environmental changes and decision-making needs. Within the set monitoring interval, temperature, humidity, carbon dioxide concentration, light intensity, and nutrient solution TDS value are collected in real time. Based on historical environmental characteristic value data, an autoregressive model is used to predict the predicted environmental characteristic values ​​within the monitoring interval.

[0026] Calculate the growth environment instability coefficient, the calculation formula is: ;in, is the growth environment instability coefficient.

[0027] It can be seen from the formula that the larger the growth environment instability coefficient is, the more likely it is that the current tomato growth environment may have undergone adverse changes and intervention is needed, such as adjusting the temperature, humidity, light or nutrient solution formula, indicating that tomato growth may need to be regulated.

[0028] The growth environment similarity coefficient and the growth environment instability coefficient are weighted to construct a growth environment assessment model and generate a growth environment assessment coefficient. The expression of the growth environment assessment coefficient is: ;in, is the growth environment assessment coefficient, is the proportional coefficient of the growth environment similarity coefficient, is the proportional coefficient of the instability of the growth environment, , Both are greater than 0.

[0029] Collect tomato crop growth image data, use visual technology, and identify tomato leaf health based on the yolov8 technology framework, including: Pull real-time images from the network camera through the RTSP protocol, and use the edge gateway computing power of the TH1520 (RISC-V) chip to calculate and detect image data; Use YOLOv8 convolutional neural network (CNN) to automatically extract features from image data to identify diseased areas on leaves, such as lesions and mildew, to determine the health of the leaves; The trained YOLOv8 model is deployed on the edge computing module of the chip, pushing computing tasks and data storage from the cloud to the edge of the network, reducing data transmission delays and improving data processing efficiency, and using the edge computing power of the RISC-V chip to directly process image data locally; Disease spot identification: Identify abnormal spots or discolored areas on leaves through color differences and texture changes. The color of disease spots is usually significantly different from that of healthy leaves. Mildew detection: Mildew often occurs in high humidity environments. By detecting mildew spots, white powder or similar disease characteristics on the leaves, it can be determined whether the leaves are infected with mildew; Color recognition: The color of tomatoes gradually changes at different growth stages, from green to yellow, orange, and finally to red. Through visual recognition technology, YOLOv8 detects the color characteristics of tomato fruits and determines their maturity. The algorithm can distinguish the ratio of different color pixels of the fruit and compare it with the preset maturity standard.

[0030] The growth image of tomatoes is collected by a camera, and the growth status information of tomatoes is extracted. After collection, the growth status information of tomatoes is represented by disease influence coefficient and maturity status difference coefficient.

[0031] Among them, the disease impact coefficient is obtained by recording the diseases that existed in the historical growth process of tomatoes, and marking various diseases, such as fungal diseases (such as leaf spot disease), bacterial diseases (such as soft rot disease), and viral diseases (such as yellow leaf curl virus disease). The impact of each disease on tomatoes is recorded, and the spread of the disease, the duration of the disease, and the impact of the disease on yield, fruit quality, etc. are tracked. The disease impact coefficients of different diseases are determined through long-term observation, data accumulation, and the probability of disease occurrence.

[0032] The logic for obtaining the disease influence coefficient is as follows: extracting disease features through the growth image of tomatoes, and extracting the disease types existing in tomatoes according to the historical data of tomato growth, and combining the disease features existing in the current tomatoes to determine the disease types that the disease features existing in the current tomatoes cause tomato, that is, the disease features existing in the current tomatoes correspond to one or more disease types, and determining the probability that the disease features existing in tomatoes cause diseases in tomatoes according to the historical data of tomato growth, that is, the disease features existing in tomatoes may cause one or more corresponding disease types to appear in the subsequent cultivation process; It should be noted that disease features are features automatically extracted from image data based on the YOLOv8 convolutional neural network. Disease features include color, texture, etc. Based on the disease features, we can determine the possible diseases of tomatoes or the diseases that may occur in the subsequent growth process. Disease features are determined by professional staff, and the probability of disease occurrence after the existence of disease features is determined by long-term observation and data accumulation of tomatoes. There may be multiple disease features in the process of tomato growth, and one disease type may have multiple disease features, and one disease feature may coexist in multiple disease types.

[0033] After the disease characteristics are detected, the actual disease probability of tomatoes under the disease characteristics is determined, and the actual disease probability of tomatoes under the determined disease characteristics is marked as: , where k = 1, 2, 3, ..., K, K is a positive integer, and k is the number of the identified disease feature; The probability that the disease characteristics of tomatoes will cause diseases in tomatoes is marked as: , where i=1, 2, 3, ..., I, I is a positive integer, and i is the number of the disease type that causes tomato disease characteristics; It should be noted that the actual probability of tomato disease under disease characteristics and the probability of tomato disease caused by the disease characteristics of tomatoes are two different concepts. The actual probability of tomato disease under disease characteristics indicates the actual probability of tomato disease after the specific disease characteristics are detected, and the probability of tomato disease caused by the disease characteristics of tomatoes indicates the probability of the occurrence of the disease when specific disease characteristics (such as lesions, color changes, etc.) appear, reflecting the relationship between the appearance of a certain disease characteristic and the occurrence of the disease under specific conditions.

[0034] Calculate the entropy of disease characteristics present in tomatoes using the formula: ; Calculate the disease impact coefficient using the following formula: ;in, is the disease impact coefficient.

[0035] It can be seen from the formula that the larger the disease impact coefficient, the greater the number of diseases that may exist in the current tomato growth process, and the higher the possibility of occurrence, which means that there is a greater risk in the current tomato growth.

[0036] Among them, the maturity state concealment coefficient is determined by analyzing the RGB color space of the tomato growth image. For ripe tomatoes, the R value is usually higher, and the G value of ripe tomatoes is usually relatively low. The difference between ripe and unripe tomatoes in the B channel is not as significant as that of R and G.

[0037] The logic for obtaining the maturity state concealment coefficient is as follows: extract the growth image of the tomato fruit, determine the R value and G value of each pixel in the tomato fruit part, and mark the R value and G value of each pixel in the tomato fruit part as: and , where j=1, 2, 3, ..., J, J is a positive integer, and j is the pixel number of the tomato fruit part; Set the R value threshold range and the G value threshold range, and mark the R value threshold range as: , mark the G value threshold range as: , compare the R value and G value of each pixel in the tomato fruit part with the R value threshold range and the G value threshold range respectively, obtain the pixels that are not in the R value threshold range and the G value threshold range respectively, and mark the R value of the pixel that is not in the R value threshold range as: , mark the pixel G values ​​that are not within the G value threshold range as: , where a=1, 2, 3, ..., A, A is a positive integer, a is the pixel number that is not within the R value threshold range, b=1, 2, 3, ..., B, B is a positive integer, b is the pixel number that is not within the G value threshold range; It should be noted that pixels of tomatoes in different growth states have different R values ​​and G values. Different R value threshold ranges and G value threshold ranges are defined in different growth states. The R value threshold range and G value threshold range are set by professional staff. For example, a too low R value indicates that the tomato may not be mature enough and does not meet the standard. A too high R value indicates that the tomato may have lesions or other problems.

[0038] Calculate the maturity state concealment coefficient, the calculation formula is: ;in, is the concealment coefficient of mature state.

[0039] It can be seen from the formula that the greater the maturity concealment coefficient, the greater the risk of current tomato growth.

[0040] The disease impact coefficient and the maturity state difference coefficient are weighted and calculated to construct a health assessment model and generate a health assessment coefficient. The expression of the health assessment coefficient is: ;in, is the health assessment coefficient, , are the proportional coefficients of disease impact coefficient and maturity state difference coefficient, , Both are greater than 0.

[0041] The growth environment information and growth status information of tomatoes are comprehensively analyzed. The current growth environment assessment coefficient, health assessment coefficient and growth stage of tomatoes are used as input features for training the neural network model. The growth warning coefficient is used as the output feature of the neural network model training and assigned to 0 or 1 to train the model, where 0 indicates that the growth warning coefficient is less than the growth warning coefficient threshold, and 1 indicates that the growth warning coefficient is greater than the growth warning coefficient threshold.

[0042] It should be noted that the growth warning coefficient is set by professional staff. The growth warning coefficient is used to distinguish between normal and abnormal states of tomato growth. When the growth warning coefficient exceeds the growth warning coefficient threshold, the system should trigger an alarm or take safety measures.

[0043] The present invention uses the Hongmeng system to monitor key parameters of tomatoes in real time, such as temperature, humidity, carbon dioxide concentration, light intensity, and TDS value of nutrient solution. It uses the YOLOv8 convolutional neural network (CNN) to automatically extract features from image data to identify diseased areas on leaves, such as lesions and mildew, so as to judge the health of the leaves. It also conducts a comprehensive analysis of the tomato growth feature data monitored by the sensor and the image data, which can provide timely warnings for abnormal conditions in the growth process of tomatoes, help identify potential growth abnormalities of tomatoes, and improve the yield and quality of tomatoes.

[0044] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0045] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0046] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0047] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0048] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0049] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0050] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A planting monitoring method based on crop growth data, characterized in that: The specific steps include: S1: Based on RISC-V+OpenHarmony, the tomato growth environment is monitored in real time. The environmental characteristic values ​​of the tomato growth process are collected through sensors, and the growth images of the tomato are collected. The growth images of the tomato are analyzed using the YOLOv8 convolutional neural network; S2: By comparing the actual environmental characteristic values ​​collected with the ideal environmental characteristic values ​​in the historical records, and determining the difference between the predicted value and the actual value of the tomato growth environment characteristic value through the autoregressive model, the growth environment information of the tomato is obtained, and the growth environment evaluation model is constructed; S3: Determine the growth status information of tomatoes by analyzing the diseases existing in the historical tomato growth process and the RGB color space of tomato growth images, and build a health assessment model; S4: Comprehensively analyze the growth environment information and growth status information of tomatoes, and use the neural network model to provide timely warnings for abnormal conditions in the growth process of tomatoes.

2. A method for monitoring crop growth based on crop growth data according to claim 1, characterized in that: Information about the growing environment of tomatoes, including: The growth environment information is represented by the growth environment similarity coefficient and the growth environment instability coefficient; The logic for obtaining the growth environment similarity coefficient is: obtaining the environmental characteristic values ​​of tomatoes in real time, wherein the environmental characteristic values ​​of tomatoes are temperature, humidity, carbon dioxide concentration, light intensity, and nutrient solution TDS value, and representing the environmental characteristic values ​​of tomatoes obtained in real time in the form of vectors: , the ideal environmental characteristic value of tomatoes is expressed in the form of a vector: ; The environmental characteristic values ​​and ideal environmental characteristic values ​​of tomatoes are processed by minimum-maximum normalization, including determining a reasonable minimum and maximum value for each environmental characteristic value, or using historical data to determine the minimum and maximum range, and marking the environmental characteristic values ​​and ideal environmental characteristic values ​​of tomatoes after normalization as: and , n=1, 2, 3, 4, 5, n is the number of the environmental characteristic value; Calculate the growth environment similarity coefficient, the calculation formula is: ;in, is the growth environment similarity coefficient.

3. A planting monitoring method based on crop growth data according to claim 2, characterized in that: Growth environment instability coefficient, including: The logic for obtaining the growth environment instability coefficient is as follows: an autoregressive model is constructed based on the historical environmental characteristic values ​​of tomatoes, and the autoregressive coefficient in the autoregressive model is estimated by the least square method or other methods. The expression of the autoregressive model is: ;in, is the predicted value at the current time t, , , … is the autoregressive coefficient in the autoregressive model, , , … is the historical environmental characteristic value of tomato, is the noise term; Set a monitoring interval, collect the normalized environmental characteristic values ​​of tomatoes within the monitoring interval, and mark the actual values ​​of the normalized environmental characteristic values ​​of tomatoes within the monitoring interval as: , where m=1, 2, 3, ..., M, M is a positive integer, and m is the number of times the environmental characteristic values ​​of tomatoes are collected within the monitoring interval. The environmental characteristic values ​​predicted by the autoregressive model within the monitoring interval are marked as: ; Calculate the growth environment instability coefficient, the calculation formula is: ;in, is the growth environment instability coefficient.

4. A method for monitoring crop growth based on crop growth data according to claim 3, characterized in that: Construct a growth environment assessment model, including: The growth environment similarity coefficient and the growth environment instability coefficient are weighted to construct a growth environment assessment model and generate a growth environment assessment coefficient. The expression of the growth environment assessment coefficient is: ;in, is the growth environment assessment coefficient, is the proportional coefficient of the growth environment similarity coefficient, is the proportional coefficient of the instability of the growth environment, , Both are greater than 0.

5. A method for monitoring crop growth based on crop growth data according to claim 4, characterized in that: Determine the growth status information of tomatoes, including: The growth status information of tomatoes is expressed by disease impact coefficient and maturity status difference coefficient; The logic for obtaining the disease influence coefficient is as follows: extracting disease features through the growth image of tomatoes, and extracting the disease types existing in tomatoes according to the historical data of tomato growth, and combining the disease features existing in the current tomatoes to determine the disease types that the disease features existing in the current tomatoes cause tomato, that is, the disease features existing in the current tomatoes correspond to one or more disease types, and determining the probability that the disease features existing in tomatoes cause diseases in tomatoes according to the historical data of tomato growth, that is, the disease features existing in tomatoes may cause one or more corresponding disease types to appear in the subsequent cultivation process; After the disease characteristics are detected, the actual disease probability of tomatoes under the disease characteristics is determined, and the actual disease probability of tomatoes under the determined disease characteristics is marked as: , where k = 1, 2, 3, ..., K, K is a positive integer, and k is the number of the identified disease feature; The probability that the disease characteristics of tomatoes will cause diseases in tomatoes is marked as: , where i=1, 2, 3, ..., I, I is a positive integer, and i is the number of the disease type that causes tomato disease characteristics; Calculate the entropy of disease characteristics present in tomatoes using the formula: ; Calculate the disease impact coefficient using the following formula: ;in, is the disease impact coefficient.

6. A method for monitoring crop growth based on crop growth data according to claim 5, characterized in that: Coefficient of variation of maturity status, including: The logic for obtaining the maturity state concealment coefficient is as follows: extract the growth image of the tomato fruit, determine the R value and G value of each pixel in the tomato fruit part, and mark the R value and G value of each pixel in the tomato fruit part as: and , where j=1, 2, 3, ..., J, J is a positive integer, and j is the pixel number of the tomato fruit part; Set the R value threshold range and the G value threshold range, and mark the R value threshold range as: , mark the G value threshold range as: , compare the R value and G value of each pixel in the tomato fruit part with the R value threshold range and the G value threshold range respectively, obtain the pixels that are not in the R value threshold range and the G value threshold range respectively, and mark the R value of the pixel that is not in the R value threshold range as: , mark the pixel G values ​​that are not within the G value threshold range as: , where a=1, 2, 3, ..., A, A is a positive integer, a is the pixel number that is not within the R value threshold range, b=1, 2, 3, ..., B, B is a positive integer, b is the pixel number that is not within the G value threshold range; Calculate the maturity state concealment coefficient, the calculation formula is: ;in, is the concealment coefficient of mature state.

7. A method for monitoring crop growth based on crop growth data according to claim 6, characterized in that: Construct a health assessment model, including: The disease impact coefficient and the maturity state difference coefficient are weighted and calculated to construct a health assessment model and generate a health assessment coefficient. The expression of the health assessment coefficient is: ;in, is the health assessment coefficient, , are the proportional coefficients of disease impact coefficient and maturity state difference coefficient, , Both are greater than 0.

8. The method for monitoring crop growth based on crop growth data according to claim 7, characterized in that: Comprehensively analyze the growth environment information and growth status information of tomatoes, including: The current tomato growth environment assessment coefficient, health assessment coefficient and tomato growth stage are used as input features for neural network model training, and the growth warning coefficient is used as the output feature for neural network model training. The model is trained by assigning it to 0 or 1, where 0 indicates that the growth warning coefficient is less than the growth warning coefficient threshold, and 1 indicates that the growth warning coefficient is greater than the growth warning coefficient threshold.

Images