A licorice growing environment monitoring method and system

Abstract

The application provides a licorice growth environment monitoring method and system, and relates to the technical field of environment monitoring.The method comprises the following steps: obtaining a plurality of sample licorices; acquiring a plurality of high-definition sample licorice images and growth height data of the sample licorices; inputting the high-definition sample licorice images into a trained prediction pest probability model to obtain prediction pest probability data of the plurality of sample licorices at a plurality of time points in a current monitoring period; determining a growth anomaly score according to the prediction pest probability data and the growth height data; acquiring climate parameters; determining a climate anomaly score according to the climate parameters; obtaining nutrient element content information and water content information in soil samples; determining a soil anomaly score according to the nutrient element content information and the water content information; and generating a licorice growth environment monitoring report.According to the application, the probability of licorice being damaged by pests can be predicted, and the comprehensiveness of monitoring the licorice growth environment is improved.

Description

Technical Field

[0001] This invention relates to the field of environmental monitoring technology, and in particular to a method and system for monitoring the growth environment of licorice. Background Technology

[0002] In related technologies, CN115266610A provides a plant growth monitoring method and system. The method is applied to a plant growth monitoring system, which includes: a spectral data monitoring module, a growth environment data monitoring module, a main control module, and an Internet of Things (IoT) communication component module, all located within the plant's growth area. The method includes: acquiring plant reflectance spectral data under a preset wavelength band of sunlight using the spectral data monitoring module; acquiring plant growth environment parameter data using the growth environment data monitoring module; acquiring the plant's location information using the main control module, storing the spectral data, the growth environment parameter data, and the location information, and calculating a vegetation index based on the spectral data and the growth environment parameter data; and sending the growth environment parameter data, the vegetation index, and the location information to an IoT cloud using the IoT communication component module.

[0003] CN107121535A provides an effective crop growth environment monitoring system, including an information acquisition module, a controller module, an information transmission module, and a remote monitoring module. The information acquisition module collects data and video information about the crop growth environment. The information transmission module wirelessly transmits the collected data and video information to the remote monitoring module. The remote monitoring module judges the condition of the crop growth environment based on the received data and generates corresponding operation commands based on the judgment results. These operation commands are transmitted to the controller module through the information transmission module, and the controller module performs corresponding operations based on the received commands. The beneficial effects of this solution are: it achieves effective monitoring of environmental factors affecting crop growth, and allows for corresponding measures to be taken based on the monitoring results, ensuring a healthy crop growth environment.

[0004] Therefore, although the relevant technologies can monitor the growth environment, they do not consider the probability of pests during the growth process. That is, it is difficult to predict the probability of licorice being affected by pests, thus making it difficult to comprehensively monitor the growth environment of licorice.

[0005] The information disclosed in the background section of this application is intended only to enhance the understanding of the general background of this application and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0006] This invention provides a method and system for monitoring the growth environment of licorice, which can solve the technical problems of related technologies being unable to predict the probability of licorice being affected by pests and being unable to comprehensively monitor the growth environment of licorice.

[0007] According to a first aspect of the present invention, a method for monitoring the licorice growth environment is provided, comprising: sampling licorice in a licorice growth area to obtain multiple sample licorice; taking high-definition photos of the sample licorice at multiple times during the current monitoring period to obtain multiple high-definition sample licorice images and growth height data of the sample licorice; inputting the high-definition sample licorice images into a trained pest prediction probability model to obtain predicted pest probability data of the multiple sample licorice at multiple times during the current monitoring period; determining a growth anomaly score based on the predicted pest probability data and the growth height data; obtaining climate parameters of the licorice growth area at multiple times during the current monitoring period, wherein the climate parameters include temperature parameters, humidity parameters, and light intensity parameters; determining a climate anomaly score based on the climate parameters; collecting soil samples from the licorice growth area at multiple times during the current monitoring period and performing spectral component analysis to obtain nutrient element content information and moisture content information in the soil samples; determining a soil anomaly score based on the nutrient element content information and the moisture content information; and generating a licorice growth environment monitoring report based on the growth anomaly score, the climate anomaly score, and the soil anomaly score.

[0008] Further, the training steps of the pest prediction probability model include: acquiring historical high-resolution licorice images at multiple times across multiple historical monitoring periods, wherein the previous historical monitoring period is the first historical monitoring period; inputting the historical high-resolution licorice images into the trained pest prediction probability model to obtain historical pest prediction probability data for multiple licorice samples at multiple times across multiple historical monitoring periods; performing feature extraction processing on the licorice root and stem region in the historical high-resolution licorice images through the root and stem feature encoding layer of the trained image recognition neural network model to obtain historical root and stem feature vectors for each historical licorice sample; performing feature extraction processing on the licorice leaf region in the historical high-resolution licorice images through the leaf feature encoding layer of the trained image recognition neural network model to obtain historical leaf feature vectors for each historical licorice sample; performing feature extraction processing on the licorice fruit region in the historical high-resolution licorice images through the fruit feature encoding layer of the trained image recognition neural network model to obtain historical fruit feature vectors for each historical licorice sample; acquiring historical pest probability data for multiple licorice samples at multiple times across multiple historical monitoring periods; and according to the formula...

[0009] Determine the training loss function Loss for the pest probability prediction model, where R i，s，kLet be the historical root and stem feature vector of the licorice root sample at time k in the s-th historical monitoring period. For the s-th historical monitoring period, the n-th k The historical root and stem feature vector of the licorice at time i. For R i，s，k The transpose of X i，s，k Let i be the historical leaf feature vector of the licorice sample at time k in the s-th historical monitoring period. For the s-th historical monitoring period, the n-th k The historical leaf feature vector of the licorice sample at time i. For X i，s，k The transpose vector, Y i，s，k Let be the historical fruit feature vector of the licorice sample at time k in the s-th historical monitoring period. For the s-th historical monitoring period, the n-th k The historical fruit feature vector of the licorice at time i. For Y i，s，k The transpose of G i，s，k G represents the historical pest probability data of the licorice sample at time k in the s-th historical monitoring period. i，s，p For the historical predicted pest probability data of licorice at time k in the s-th historical monitoring period, n i n represents the number of licorice samples. s n represents the number of historical monitoring periods. k The number of time points in the monitoring period, i≤n i , s≤n s , k≤n k And i, s, k, n i n s and n k All are positive integers; the predicted pest probability model is trained according to the training loss function to obtain the trained predicted pest probability model.

[0010] Further, based on the predicted pest probability data and the growth height data, a growth anomaly score is determined, including: fitting the growth height data with multiple moments in the current monitoring period to obtain a growth height function; determining the growth height derivative function based on the growth height function; determining the growth height change rate based on the growth height derivative function; and determining the growth anomaly score based on the predicted pest probability data and the growth height change rate.

[0011] Further, based on the predicted pest probability data and the growth height change rate, a growth anomaly score is determined, including: according to the formula and Determine the growth abnormality score A1, where H′ i，k H′ represents the rate of change in the growth height of the i-th sample of licorice at the k-th time point in the current monitoring period. p G is the threshold for the rate of change in growth height. F1 is a piecewise function that compares the rate of change in growth height of the i-th sample of licorice at the k-th time of the current monitoring period with the threshold for the rate of change in growth height. i，k，p This provides the predicted pest probability data for the i-th sample of licorice at the k-th time of the current monitoring period, where α1 and α2 are preset weights, and α1 + α2 = 1, n i n represents the number of licorice samples. k The number of time points in the monitoring period, i≤n i , k≤n k , and i, k, n i and n k All are positive integers.

[0012] Further, based on the climate parameters, a climate anomaly score is determined, including: obtaining suitable climate parameters for the licorice growing area, wherein the suitable climate parameters include suitable temperature parameters, suitable humidity parameters, and suitable light intensity parameters; obtaining historical climate parameters for the licorice growing area at multiple times in the previous historical monitoring period, wherein the historical climate parameters include historical temperature parameters, historical humidity parameters, and historical light intensity parameters; and determining a climate anomaly score based on the suitable climate parameters, the historical climate parameters, and the climate parameters.

[0013] Further, based on the suitable climate parameters, the historical climate parameters, and the climate parameters, a climate anomaly score is determined, including: according to the formula... Determine the climate anomaly score A2, where t k Let t be the temperature parameter at the k-th moment of the current monitoring cycle. p For suitable temperature parameters, w k Let w be the humidity parameter at the k-th moment of the current monitoring cycle. p For suitable humidity parameters, m k Let m be the light intensity parameter at the k-th moment of the current monitoring period. p For suitable light intensity parameters, t k，h w represents the historical temperature parameter at the k-th moment of the previous historical monitoring cycle. k，h Let m be the historical humidity parameter at the k-th moment of the previous historical monitoring cycle. k，h Here, β1 and β2 are the historical light intensity parameters at the k-th moment of the previous historical monitoring cycle, and β1 + β2 = 1, n k To monitor the number of time points in the cycle, k≤n k And k and n k All are positive integers, and max is the function to find the maximum value.

[0014] Further, based on the nutrient element content information and the moisture content information, a soil anomaly score is determined, including: acquiring the content information of multiple standard nutrient elements and the standard moisture content information in the licorice soil; determining the standard soil state vector of the licorice soil based on the standard nutrient element content information and the standard moisture content information; determining the real-time soil state vector of the licorice soil based on the nutrient element content information and the moisture content information; and determining the soil anomaly score based on the standard soil state vector and the real-time soil state vector.

[0015] Further, based on the standard soil state vector and the real-time soil state vector, a soil anomaly score is determined, including: according to the formula... The soil anomaly score was determined to be A3, where C 1，k C 2，k ..., C N，k For the content information of the 1st, 2nd, ..., Nth nutrient elements at the kth time point of the current monitoring period, C 1，T C 2，T ..., C N,T For the content information of the 1st, 2nd, ..., Nth standard nutrient elements, S k For the moisture content information at time k in the current monitoring period, S T For standard moisture content information, γ1, γ2, ..., γ N and γ N+1 To preset the weights, This is the real-time soil state vector at the k-th moment of the current monitoring cycle. Let N be the standard soil state vector, and n be the number of different nutrient elements. k To monitor the number of time points in the cycle, k≤n k And k, N and n k All are positive integers.

[0016] Further, based on the growth anomaly score, the climate anomaly score, and the soil anomaly score, a licorice growth environment monitoring report is generated, including: generating a growth monitoring report when the growth anomaly score is greater than a growth anomaly score threshold; generating a climate monitoring report when the climate anomaly score is greater than a climate anomaly score threshold; and generating a soil monitoring report when the soil anomaly score is greater than a soil anomaly score threshold. According to a second aspect of the present invention, a licorice growth environment monitoring system is provided, comprising: a sample licorice module for sampling licorice in a licorice growth area to obtain multiple sample licorice; a high-definition sample licorice image and growth height data module for taking high-definition photos of the sample licorice at multiple times during the current monitoring period to obtain multiple high-definition sample licorice images and growth height data of the sample licorice; a pest prediction probability model module for inputting the high-definition sample licorice images into a trained pest prediction probability model to obtain predicted pest probability data of multiple sample licorice at multiple times during the current monitoring period; a growth anomaly scoring module for determining a growth anomaly score based on the predicted pest probability data and the growth height data; and a climate parameter... The system comprises the following modules: a data acquisition module for acquiring climate parameters of the licorice growing area at multiple times during the current monitoring period, including temperature, humidity, and light intensity parameters; a climate anomaly scoring module for determining a climate anomaly score based on the climate parameters; a soil sample module for collecting soil samples from the licorice growing area at multiple times during the current monitoring period and performing spectral component analysis to obtain information on nutrient element content and moisture content in the soil samples; a soil anomaly scoring module for determining a soil anomaly score based on the nutrient element content and moisture content information; and a licorice growing environment monitoring report module for generating a licorice growing environment monitoring report based on the growing anomaly score, the climate anomaly score, and the soil anomaly score.

[0017] Technical Effects: According to the present invention, the probability of licorice being affected by pests can be predicted by a pest prediction model, thereby reducing the impact of pests on licorice growth. By performing spectral composition analysis on soil samples to obtain information on nutrient element content and moisture content, the influence of soil conditions on licorice growth can be identified, and targeted soil improvement can be carried out. Through comprehensive evaluation of growth anomaly scores, climate anomaly scores, and soil anomaly scores, the quality of the licorice growth environment can be reflected from multiple dimensions, improving the comprehensiveness of monitoring the licorice growth environment. When determining the training loss function of the pest prediction probability model, the influence of historical root and stem feature vectors, historical leaf feature vectors, and historical fruit feature vectors on the probability of licorice being affected by pests can be used to determine the influence of the above data on the error of the predicted pest probability. Based on this influence, and the relative error of historical predicted pest probabilities, and based on the characteristics that shorter time intervals and shorter period intervals result in higher prediction accuracy, weights are set to train the loss function to improve the objectivity and accuracy of the loss function. This reduces the training loss function during the training process, thereby increasing training intensity and efficiency, and improving the accuracy of the pest prediction probability model. When determining the growth anomaly score, the average predicted pest probability and the average degree of anomaly in growth height of licorice can be used to determine the score. By considering both pest probability and growth height change rate, the growth status of licorice can be more comprehensively assessed, facilitating timely detection of growth anomalies and improving the comprehensiveness and accuracy of the score. When determining the climate anomaly score, suitable climate parameters, historical climate parameters, and current climate parameters can be used to determine the score, effectively assessing the climate anomaly situation in the licorice growing area. By comparing climate parameters of temperature, humidity, and light intensity, the deviation between current and suitable climate parameters is comprehensively assessed, helping to fully understand the impact of climate on licorice growth. Comparing current and historical climate parameters helps identify climate change trends, improving the comprehensiveness, scientific rigor, and objectivity of the climate anomaly score. When determining the soil anomaly score, the cosine similarity between a weighted real-time soil state vector and a weighted standard soil state vector can be used to determine the score. Weights are set based on the relative importance of different nutrients and water to licorice growth, making soil state assessment more accurate and contributing to the monitoring and improvement of the soil environment.

[0018] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Other features and aspects of the invention will become clearer from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained based on these drawings without creative effort.

[0020] Figure 1 A schematic flowchart of a licorice growth environment monitoring method according to an embodiment of the present invention is shown as an example;

[0021] Figure 2 A block diagram of a licorice growth environment monitoring system according to an embodiment of the present invention is shown as an example. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0024] Figure 1An exemplary flowchart of a licorice growth environment monitoring method according to an embodiment of the present invention is shown. The method includes: step S101, sampling licorice in a licorice growth area to obtain multiple sample licorice; step S102, taking high-definition photos of the sample licorice at multiple times during the current monitoring period to obtain multiple high-definition sample licorice images and growth height data of the sample licorice; step S103, inputting the high-definition sample licorice images into a trained pest prediction probability model to obtain predicted pest probability data of multiple sample licorice at multiple times during the current monitoring period; step S104, determining a growth abnormality score based on the predicted pest probability data and the growth height data; step... Step S105: Obtain climate parameters of the licorice growing area at multiple times during the current monitoring period, including temperature, humidity, and light intensity parameters; Step S106: Determine a climate anomaly score based on the climate parameters; Step S107: Collect soil samples from the licorice growing area at multiple times during the current monitoring period and perform spectral component analysis to obtain nutrient element content and moisture content information in the soil samples; Step S108: Determine a soil anomaly score based on the nutrient element content and moisture content information; Step S109: Generate a licorice growing environment monitoring report based on the growth anomaly score, the climate anomaly score, and the soil anomaly score.

[0025] The licorice growth environment monitoring method according to embodiments of the present invention can predict the probability of licorice being affected by pests using a pest probability prediction model, thereby reducing the impact of pests on licorice growth. By performing spectral composition analysis on soil samples to obtain nutrient element content and moisture content information, the influence of soil conditions on licorice growth can be identified, allowing for targeted soil improvement. Through a comprehensive evaluation of growth anomaly scores, climate anomaly scores, and soil anomaly scores, the quality of the licorice growth environment can be reflected from multiple dimensions, improving the comprehensiveness of monitoring the licorice growth environment.

[0026] According to one embodiment of the present invention, in step S101, several licorice plants are randomly selected for sampling within the licorice growing area, so that the selected sample licorice can represent the licorice growth status of the entire licorice growing area.

[0027] According to one embodiment of the present invention, in step S102, each monitoring cycle can be set to three days, seven days, etc., and the interval between adjacent moments can be set to 12 hours, 24 hours, etc., and the present invention does not limit this. High-resolution camera equipment is used to capture clear, high-definition images of the licorice samples for subsequent analysis and evaluation. Simultaneously with the image capture, the growth height of each licorice sample is measured; a ruler or dedicated measuring equipment can be used to record the actual height data of each licorice sample.

[0028] According to an embodiment of the present invention, in step S103, a high-resolution sample licorice image is input into a pre-trained pest prediction probability model. The pest prediction probability model can be a neural network model, which is trained based on a large amount of historical data through machine learning or deep learning techniques. It can analyze high-resolution sample licorice images and predict the probability of licorice pests occurring.

[0029] According to an embodiment of the present invention, the training step of the pest prediction probability model includes: acquiring historical high-resolution licorice images at multiple times during multiple historical monitoring periods, wherein the previous historical monitoring period before the current monitoring period is the first historical monitoring period; inputting the historical high-resolution licorice images into the trained pest prediction probability model to obtain historical predicted pest probability data of licorice samples at multiple times during multiple historical monitoring periods; and performing feature extraction processing on the licorice root and stem regions in the historical high-resolution licorice images through the root and stem feature encoding layer of the trained image recognition neural network model to obtain the historical root and stem data of each historical licorice sample. Stem feature vector; through the leaf feature encoding level of the trained image recognition neural network model, feature extraction processing is performed on the licorice leaf region in the historical high-definition sample licorice image to obtain the historical leaf feature vector of each historical sample licorice; through the fruit feature encoding level of the trained image recognition neural network model, feature extraction processing is performed on the licorice fruit region in the historical high-definition sample licorice image to obtain the historical fruit feature vector of each historical sample licorice; historical pest probability data of multiple samples of licorice at multiple times in multiple historical monitoring cycles are obtained; the training loss function Loss of the pest probability prediction model is determined according to formula (1),

[0030]

[0031] Among them, R i，s,k Let be the historical root and stem feature vector of the licorice root sample at time k in the s-th historical monitoring period. For the s-th historical monitoring period, the n-th k The historical root and stem feature vector of the licorice at time i. For R i，s，k The transpose of X i，s，k Let i be the historical leaf feature vector of the licorice sample at time k in the s-th historical monitoring period. For the s-th historical monitoring period, the n-th k The historical leaf feature vector of the licorice sample at time i. For X i，s，k The transpose vector, Y i，s，k Let be the historical fruit feature vector of the licorice sample at time k in the s-th historical monitoring period. For the s-th historical monitoring period, the n-thk The historical fruit feature vector of the licorice at time i. For Y i，s，k The transpose of G i，s， k represents the historical pest probability data of the i-th sample of licorice at the k-th moment in the s-th historical monitoring period, G i，s，k，p For the historical predicted pest probability data of licorice at time k in the s-th historical monitoring period, n i n represents the number of licorice samples. s n represents the number of historical monitoring periods. k The number of time points in the monitoring period, i≤n i , s≤n s , k≤n k And i, s, k, n i n s and n k All are positive integers; the predicted pest probability model is trained according to the training loss function to obtain the trained predicted pest probability model.

[0032] According to one embodiment of the present invention, the image recognition neural network model can be a convolutional neural network model. Through the root and stem feature encoding layer, leaf feature encoding layer, and fruit feature encoding layer of the trained image recognition neural network model, feature extraction processing is performed on the licorice root and stem region, licorice leaf region, and licorice fruit region in historical high-definition sample licorice images, respectively, to obtain historical root and stem feature vectors, historical leaf feature vectors, and historical fruit feature vectors. The historical root and stem feature vector typically includes external features of the root and stem, such as root and stem length, number of branches, and color, and can be used to analyze and identify the health status of the root and stem. The historical leaf feature vector typically includes external features of the leaf, such as leaf texture, area, edge shape, and color, and can be used to analyze and identify the health status of the leaf. The historical fruit feature vector typically includes external features of the fruit, such as fruit size, shape, and color, and can be used to analyze and identify the health status of the fruit. Pest infestations of licorice are diverse; for example, after feeding on the short-haired grass weevil, the licorice leaf margins show notches. Therefore, the historical root and stem feature vectors, historical leaf feature vectors, and historical fruit feature vectors affect the probability of licorice being affected by pests. Historical pest probability data is based on historical monitoring records and reflects the occurrence of licorice pests at different time points. For each sample of licorice, historical pest probability data can be obtained from the recorded pest occurrence probabilities. For example, if a sample of licorice has pests, the historical pest probability data for that sample of licorice is 1; if a sample of licorice has no pests, the historical pest probability data for that sample of licorice is 0.

[0033] According to one embodiment of the present invention, as licorice grows, its root system gradually develops, enhancing its ability to absorb nutrients and water from the soil, and correspondingly improving its resistance to pests. In any monitoring period, at the nth... k The prediction error for the probability of pest infestation at a given time point is relatively small, and the prediction result is more accurate. Therefore, in formula (1), Let the historical root and stem feature vector of the licorice sample at time k in the s-th historical monitoring period be the same as the feature vector of the licorice sample at time n in the s-th historical monitoring period. k The similarity of the historical root and stem feature vector of the licorice at time i is used to determine the impact of changes in the licorice root and stem on the probability of pest infestation. The closer the similarity is to 1, the smaller the impact of changes in the historical root and stem feature vector on the error of predicting the probability of pest infestation. Let the historical leaf feature vector of the licorice sample at time k in the s-th historical monitoring period be the same as the historical leaf feature vector of the n-th sample in the s-th historical monitoring period. k The similarity of the historical leaf feature vectors of the licorice sample at time i is the value of the similarity. The closer the similarity is to 1, the smaller the impact of the changes in the licorice leaves on the probability of pest infestation. Thus, the smaller the impact of the changes in the historical leaf feature vectors on the error of predicting the probability of pest infestation. Let the historical fruit feature vector of the licorice sample at time k in the s-th historical monitoring period be the same as the historical fruit feature vector at time n in the s-th historical monitoring period. k The similarity of the historical fruit feature vectors of the licorice sample at time ith is calculated. The closer this similarity is to 1, the smaller the impact of changes in the licorice fruit on the pest probability, and thus the smaller the impact of changes in the historical fruit feature vectors on the error in predicting the pest probability. The historical root and stem feature vectors, historical leaf feature vectors, and historical fruit feature vectors at time ith in the s-th historical monitoring period are combined with the historical root and stem feature vectors at time ith in the n-th historical monitoring period. k The more similar the feature vectors at each time point, that is, and The larger the value of , the lower the probability of pest infestation, and the smaller the impact on the error of predicting the probability of pest infestation. Therefore, the reciprocal of the product of the above three items is taken. The larger the reciprocal, the higher the probability of pest infestation, and the greater the impact on the error of predicting the probability of pest infestation. The relative error between the historical pest probability data of the licorice sample at time k in the s-th historical monitoring period and the historical predicted pest probability data of the licorice sample at time k in the s-th historical monitoring period. The weight at time k is used to reasonably weight the relative errors at different times in the loss function. For the s-th historical monitoring period, the accuracy of the historical predicted pest probability data at time k output by the pest probability prediction model is usually lower than the accuracy of the historical predicted pest probability data at time k+1. That is, the accuracy at a certain time in a certain historical monitoring period is lower than that at time n. kThe longer the time interval between moments, the less accurate the prediction, and therefore the lower its weight. Conversely, the more accurate the prediction, the higher its weight.

[0034] This represents a weighted summation of the relative errors at each moment within the s-th historical monitoring period. Let be the weight of the s-th historical monitoring period. The previous historical monitoring period is the first historical monitoring period. The longer the growth cycle of licorice, the lower the probability of it being affected by pests. For example, during the seedling stage, licorice has limited ability to absorb nutrients and water from the soil because its root system is not fully developed. Therefore, it is less resistant to pests. That is, the longer the time interval between a certain historical monitoring period and the current monitoring period, the less accurate the prediction result, and therefore the lower its weight. Conversely, the more accurate the prediction result, the higher its weight. Using the weights of the historical monitoring periods, the weighted sum of the relative errors at each moment within the s-th historical monitoring period is summed to obtain the loss function of the pest prediction probability model. During training, the model parameters are adjusted by backpropagating the loss function to minimize it, thereby improving the accuracy of the pest prediction probability model and obtaining the trained pest prediction probability model.

[0035] In this way, the influence of historical root and stem feature vectors, historical leaf feature vectors, and historical fruit feature vectors on the probability of licorice being affected by pests can be used to determine the impact of the above data on the error of predicting the probability of pests. Based on this impact, as well as the relative error of historically predicted pest probabilities, and by setting weights according to the characteristics that the shorter the time interval and the shorter the period interval, the higher the prediction accuracy, the loss function is trained to improve the objectivity and accuracy of the loss function. This reduces the training loss function during the training process, thereby improving the training intensity and efficiency, and improving the accuracy of the pest probability prediction model.

[0036] According to an embodiment of the present invention, in step S104, a growth abnormality score is determined based on the predicted pest probability data and the growth height data.

[0037] According to an embodiment of the present invention, step S104 includes: fitting the growth height data with multiple moments in the current monitoring period to obtain a growth height function; determining a growth height derivative function based on the growth height function; determining a growth height change rate based on the growth height derivative function; and determining a growth anomaly score based on the predicted pest probability data and the growth height change rate.

[0038] According to one embodiment of the present invention, growth height data and time points in the current monitoring period are fitted to obtain a growth height function that describes the change of growth height data over time in the current monitoring period. The growth height function is differentiated to obtain a growth height derivative function. Multiple growth height data are substituted into the growth height derivative function to determine the growth height change rate at multiple time points in the current monitoring period.

[0039] According to one embodiment of the present invention, a growth anomaly score is determined based on the predicted pest probability data and the growth height change rate, including: determining the growth anomaly score A1 according to formulas (2) and (3).

[0040]

[0041] Among them, H′ i，k H′ represents the rate of change in the growth height of the i-th sample of licorice at the k-th time point in the current monitoring period. p G is the threshold for the rate of change in growth height. F1 is a piecewise function that compares the rate of change in growth height of the i-th sample of licorice at the k-th time of the current monitoring period with the threshold for the rate of change in growth height. i，k，p This provides the predicted pest probability data for the i-th sample of licorice at the k-th time of the current monitoring period, where α1 and α2 are preset weights, and α1 + α2 = 1, n i n represents the number of licorice samples. k The number of time points in the monitoring period, i≤n i , k≤n k , and i, k, n i and n k All are positive integers.

[0042] According to an embodiment of the present invention, in formula (2), This indicates that when the growth height change rate of the licorice sample at time k in the current monitoring period is less than the growth height change rate threshold, the value is taken as follows: When the growth height change rate of the licorice sample at time k in the current monitoring period is greater than or equal to the growth height change rate threshold, the value is set to 0. The relative difference between the growth height change rate of the i-th sample licorice at the k-th time of the current monitoring period and the growth height change rate threshold represents the degree of abnormality in the growth height of the sample licorice. The larger the relative difference, the more abnormal the growth height of the sample licorice; the smaller the relative difference, the more normal the growth height of the sample licorice. In formula (3), This means that by averaging the predicted pest probability data of multiple licorice samples at multiple times during the current monitoring period, the average predicted pest probability of multiple licorice samples within the current monitoring period can be obtained. This means that averaging the piecewise function values ​​corresponding to multiple licorice samples at multiple times within the current monitoring period yields the average degree of abnormality in the growth height of multiple licorice samples within the current monitoring period. A weighted sum of the average predicted pest probability and the average degree of abnormality in growth height of the multiple licorice samples within the current monitoring period yields a growth abnormality score. The higher the growth abnormality score, the more abnormal the growth condition of the licorice.

[0043] In this way, a growth anomaly score can be determined by using the average predicted pest probability and the average degree of abnormality in growth height of licorice. By considering both pest probability and the rate of change in growth height, the growth status of licorice can be assessed more comprehensively, which helps to detect growth anomalies in a timely manner and improves the comprehensiveness and accuracy of the growth anomaly score.

[0044] According to one embodiment of the present invention, in step S105, the temperature, humidity and light intensity of the licorice growing area are measured by using a temperature sensor, a humidity sensor and a light intensity sensor, and the climate parameters are recorded for subsequent analysis.

[0045] According to one embodiment of the present invention, in step S106, a climate anomaly score is determined based on the climate parameters.

[0046] According to an embodiment of the present invention, step S106 includes: obtaining suitable climate parameters for the licorice growing area, wherein the suitable climate parameters include suitable temperature parameters, suitable humidity parameters, and suitable light intensity parameters; obtaining historical climate parameters for the licorice growing area at multiple times in the previous historical monitoring period, wherein the historical climate parameters include historical temperature parameters, historical humidity parameters, and historical light intensity parameters; and determining a climate anomaly score based on the suitable climate parameters, the historical climate parameters, and the climate parameters.

[0047] According to one embodiment of the present invention, the suitable temperature parameter is the optimal temperature for licorice growth, for example, 20°C or 25°C, which is beneficial for licorice seed germination, seedling growth, and root development. The suitable humidity parameter is the optimal humidity for licorice growth, for example, 60% or 70%, which is beneficial for licorice roots to absorb water and nutrients, promoting plant growth and development. The suitable light intensity parameter is the optimal light intensity for promoting licorice photosynthesis, for example, 3000 or 4000 lux, which is beneficial for licorice seed germination and seedling growth. By comparing the current climate parameters with suitable climate parameters and historical climate parameters, the gap between the current climate parameters and the suitable climate parameters for licorice growth can be identified.

[0048] According to one embodiment of the present invention, determining a climate anomaly score based on the suitable climate parameters, the historical climate parameters, and the climate parameters includes: determining a climate anomaly score A2 according to formula (4).

[0049]

[0050] Among them, t k Let t be the temperature parameter at the k-th moment of the current monitoring cycle. p For suitable temperature parameters, w k Let w be the humidity parameter at the k-th moment of the current monitoring cycle. p For suitable humidity parameters, m k Let m be the light intensity parameter at the k-th moment of the current monitoring period. p For suitable light intensity parameters, t k，h w represents the historical temperature parameter at the k-th moment of the previous historical monitoring cycle. k，h Let m be the historical humidity parameter at the k-th moment of the previous historical monitoring cycle. k，h Here, β1 and β2 are the historical light intensity parameters at the k-th moment of the previous historical monitoring cycle, and β1 + β2 = 1, n k To monitor the number of time points in the cycle, k≤n k And k and n k All are positive integers, and max is the function to find the maximum value.

[0051] According to one embodiment of the present invention, in formula (4), The relative difference between the temperature parameter at time k in the current monitoring cycle and the suitable temperature parameter indicates the degree of deviation of the current temperature. The larger the relative difference, the less suitable the current temperature is for licorice growth, and the smaller the relative difference, the more suitable the current temperature is for licorice growth. The relative difference between the humidity parameter at the k-th moment of the current monitoring cycle and the suitable humidity parameter indicates the degree of deviation of the current humidity. The larger the relative difference, the less suitable the current humidity is for licorice growth, and the smaller the relative difference, the more suitable the current humidity is for licorice growth. The relative difference between the light intensity parameter at time k of the current monitoring period and the suitable light intensity parameter represents the degree of deviation of the current light intensity. The larger the relative difference, the less suitable the current light intensity is for licorice growth; the smaller the relative difference, the more suitable the current light intensity is for licorice growth. Multiplying the above three terms and averaging them yields the degree of deviation of the current climate parameter from the suitable climate parameter. The larger the deviation, the less suitable the current climate parameter is for licorice growth.

[0052] According to one embodiment of the present invention, in formula (4), This is the maximum relative difference between the temperature parameters at multiple times in the current monitoring period and the average of the historical temperature parameters at multiple times in the previous historical monitoring period. The larger this maximum value is, the greater the degree of temperature change at multiple times in the current monitoring period relative to the historical average temperature of the previous historical monitoring period, and the more abnormal the temperature in the licorice growing area. This is the maximum relative difference between the humidity parameters at multiple times in the current monitoring period and the average of the historical humidity parameters at multiple times in the previous historical monitoring period. The larger this maximum value is, the greater the change in humidity at multiple times in the current monitoring period relative to the historical average humidity of the previous historical monitoring period, and the more abnormal the humidity in the licorice growing area is. This refers to the maximum relative difference between the light intensity parameters at multiple times during the current monitoring period and the average historical light intensity parameters at multiple times during the previous historical monitoring period. The larger this maximum value, the greater the change in light intensity at multiple times during the current monitoring period relative to the historical average light intensity of the previous historical monitoring period, and the more abnormal the light intensity in the licorice growing area. The maximum value of the above three items is taken as the degree of change of climate parameters in the licorice growing area.

[0053] According to one embodiment of the present invention, a climate anomaly score can be obtained by weighted summing the degree of deviation of the current climate parameters from the suitable climate parameters and the degree of change of the climate parameters in the licorice growing area. The higher the climate anomaly score, the more abnormal the climate in the licorice growing area.

[0054] In this way, a climate anomaly score can be determined by considering suitable, historical, and current climate parameters, thereby effectively assessing climate anomalies in licorice-growing areas. By comparing temperature, humidity, and light intensity, the deviation between current and suitable climate parameters is comprehensively evaluated, contributing to a holistic understanding of the impact of climate on licorice growth. Furthermore, comparing current and historical climate parameters helps identify climate change trends, enhancing the comprehensiveness, scientific rigor, and objectivity of the climate anomaly score.

[0055] According to one embodiment of the present invention, in step S107, soil samples are collected at multiple times during the current monitoring period, wherein the soil samples at multiple times are obtained from the same location and depth. Spectral composition analysis identifies substances and determines their chemical composition and relative content based on their spectra. Spectral composition analysis technology is used to detect and analyze soil samples at multiple times during the current monitoring period. Through spectral composition analysis, information on the content of nutrients and moisture in the soil samples is obtained, such as major nutrients like nitrogen, phosphorus, and potassium.

[0056] According to an embodiment of the present invention, in step S108, a soil anomaly score is determined based on the nutrient element content information and the moisture content information.

[0057] According to an embodiment of the present invention, step S108 includes: acquiring information on the content of multiple standard nutrients and the content of standard moisture in licorice soil; determining a standard soil state vector of licorice soil based on the information on the content of standard nutrients and the content of standard moisture; determining a real-time soil state vector of licorice soil based on the information on the content of nutrient elements and the content of moisture; and determining a soil anomaly score based on the standard soil state vector and the real-time soil state vector.

[0058] According to one embodiment of the present invention, the standard nutrient element content and standard moisture content information in licorice soil need to be determined based on the growth requirements of licorice. For example, the standard nutrient element content information for nitrogen is 3%, and the standard moisture content information for soil required for licorice seed germination is 7.5%. The content of each nutrient element and the moisture content are combined into a multi-dimensional data structure, namely a standard soil state vector. This standard soil state vector reflects the ideal soil conditions for licorice growth and provides a benchmark for subsequent real-time monitoring. The nutrient element content and moisture content information in the actually monitored licorice soil are combined into a multi-dimensional data structure, namely a real-time soil state vector. This real-time state vector reflects the actual nutrient status and moisture status of the soil at different times.

[0059] According to one embodiment of the present invention, determining a soil anomaly score based on the standard soil state vector and the real-time soil state vector includes: determining a soil anomaly score A3 according to formula (5).

[0060]

[0061] Among them, C 1，k C 2，k ..., C N，k For the content information of the 1st, 2nd, ..., Nth nutrient elements at the kth time point of the current monitoring period, C 1，T C 2，T ..., C N，T For the content information of the 1st, 2nd, ..., Nth standard nutrient elements, S k For the moisture content information at time k in the current monitoring period, S T For standard moisture content information, γ1, γ2, ..., γ N and γ N+1 To preset the weights, This is the real-time soil state vector at the k-th moment of the current monitoring cycle. Let N be the standard soil state vector, and n be the number of different nutrient elements. k To monitor the number of time points in the cycle, k≤n k And k, N and n kAll are positive integers.

[0062] According to one embodiment of the present invention, in formula (5), The cosine similarity between the weighted real-time soil state vector and the weighted standard soil state vector is used. The closer this cosine similarity is to 1, the closer the weighted real-time soil state vector is to the weighted standard soil state vector at time k in the current monitoring period, indicating a better soil condition at time k. The preset weights are multiplied by the corresponding nutrient and moisture content information to represent the relative importance of different nutrient and moisture content information in the soil condition. The result of subtracting the cosine similarity from 1 is obtained; the closer this result is to 1, the less similar the weighted real-time soil state vector is to the weighted standard soil state vector at time k in the current monitoring period, indicating a worse soil condition at time k. The average of this result across multiple times in the current monitoring period is used as the soil anomaly score. A higher soil anomaly score indicates a worse soil condition in the licorice growing area, requiring soil environment improvement, such as developing a reasonable fertilization plan, timely drainage, and irrigation. A lower soil anomaly score indicates a better soil condition in the licorice growing area, suitable for licorice growth.

[0063] In this way, soil anomaly scores can be determined based on the cosine similarity between a weighted real-time soil state vector and a weighted standard soil state vector. Weights can also be set based on the relative importance of different nutrients and water to licorice growth, making soil state assessment more accurate and helping to monitor and improve the soil environment.

[0064] According to an embodiment of the present invention, in step S109, a licorice growth environment monitoring report is generated based on the growth anomaly score, the climate anomaly score, and the soil anomaly score.

[0065] According to an embodiment of the present invention, step S109 includes: generating a growth monitoring report when the growth anomaly score is greater than a growth anomaly score threshold; generating a climate monitoring report when the climate anomaly score is greater than a climate anomaly score threshold; and generating a soil monitoring report when the soil anomaly score is greater than a soil anomaly score threshold.

[0066] According to one embodiment of the present invention, when the growth anomaly score is greater than the growth anomaly score threshold, it indicates that the current growth status is abnormal, and a growth monitoring report needs to be generated. This growth monitoring report will record in detail the probability and height changes of the licorice plant being affected by pests, and provide corresponding solutions. When the climate anomaly score is greater than the climate anomaly score threshold, it indicates that the current climate parameters are abnormal, and a climate monitoring report needs to be generated. This climate monitoring report will include current climate data, anomaly scores, and an analysis of the possible impacts of abnormal climate on plant growth. When the soil anomaly score is greater than the soil anomaly score threshold, it indicates that the current soil condition is abnormal, and a soil monitoring report needs to be generated. This soil monitoring report will describe in detail the chemical properties and microbial community status of the soil, analyze the causes of the anomaly, and propose suggestions for improving soil quality.

[0067] According to embodiments of the present invention, the licorice growth environment monitoring method can predict the probability of licorice being affected by pests using a pest probability prediction model, thereby reducing the impact of pests on licorice growth. By performing spectral composition analysis on soil samples to obtain nutrient and moisture content information, the influence of soil conditions on licorice growth can be identified, allowing for targeted soil improvement. A comprehensive evaluation of growth anomaly scores, climate anomaly scores, and soil anomaly scores can reflect the quality of the licorice growth environment from multiple dimensions, improving the comprehensiveness of monitoring the licorice growth environment. When determining the training loss function for the pest probability prediction model, the influence of historical root and stem feature vectors, historical leaf feature vectors, and historical fruit feature vectors on the probability of licorice being affected by pests can be used to determine the error in predicting the pest probability. Based on this influence, the relative error of historical pest probability predictions, and the characteristic that shorter time intervals and period intervals result in higher prediction accuracy, weights are set to train the loss function, improving its objectivity and accuracy. This reduces the training loss function during training, increasing training intensity and efficiency, and improving the accuracy of the pest probability prediction model. When determining the growth anomaly score, the average predicted pest probability and the average degree of anomaly in growth height of licorice can be used to determine the score. By considering both pest probability and growth height change rate, the growth status of licorice can be more comprehensively assessed, facilitating timely detection of growth anomalies and improving the comprehensiveness and accuracy of the score. When determining the climate anomaly score, suitable climate parameters, historical climate parameters, and current climate parameters can be used to determine the score, effectively assessing the climate anomaly situation in the licorice growing area. By comparing climate parameters of temperature, humidity, and light intensity, the deviation between current and suitable climate parameters is comprehensively assessed, helping to fully understand the impact of climate on licorice growth. Comparing current and historical climate parameters helps identify climate change trends, improving the comprehensiveness, scientific rigor, and objectivity of the climate anomaly score. When determining the soil anomaly score, the cosine similarity between a weighted real-time soil state vector and a weighted standard soil state vector can be used to determine the score. Weights are set based on the relative importance of different nutrients and water to licorice growth, making soil state assessment more accurate and contributing to the monitoring and improvement of the soil environment.

[0068] Figure 2An exemplary block diagram of a licorice growth environment monitoring system according to an embodiment of the present invention is shown. The system includes: a sample licorice module for sampling licorice in a licorice growth area to obtain multiple sample licorice; a high-definition sample licorice image and growth height data module for taking high-definition photos of the sample licorice at multiple times during the current monitoring period to obtain multiple high-definition sample licorice images and growth height data of the sample licorice; a pest prediction probability model module for inputting the high-definition sample licorice images into a trained pest prediction probability model to obtain predicted pest probability data of multiple sample licorice at multiple times during the current monitoring period; and a growth anomaly scoring module for determining a growth anomaly score based on the predicted pest probability data and the growth height data. The system includes a climate parameter module for acquiring climate parameters of the licorice growing area at multiple times during the current monitoring period, including temperature, humidity, and light intensity parameters; a climate anomaly scoring module for determining a climate anomaly score based on the climate parameters; a soil sample module for collecting soil samples from the licorice growing area at multiple times during the current monitoring period and performing spectral composition analysis to obtain information on nutrient element content and moisture content in the soil samples; a soil anomaly scoring module for determining a soil anomaly score based on the nutrient element content and moisture content information; and a licorice growth environment monitoring report module for generating a licorice growth environment monitoring report based on the growth anomaly score, the climate anomaly score, and the soil anomaly score.

[0069] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are merely examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functions and structural principles of the present invention have been demonstrated and explained in the embodiments, and any variations or modifications may be made to the implementation of the present invention without departing from the stated principles.

Claims

1. A method for monitoring the growth environment of licorice, characterized in that, include: Multiple samples of licorice are obtained by sampling the licorice growing area. High-resolution images of the licorice samples are taken at multiple times during the current monitoring period, along with data on their growth height. These high-resolution images are then input into a trained pest prediction probability model to obtain predicted pest probability data for the multiple licorice samples at multiple times during the current monitoring period. A growth anomaly score is determined based on the predicted pest probability data and the growth height data. Climate parameters of the licorice growing area, including temperature, humidity, and light intensity, are obtained at multiple times during the current monitoring period. A climate anomaly score is determined based on these parameters. Soil samples from the licorice growing area are collected at multiple times during the current monitoring period and subjected to spectral composition analysis to obtain information on nutrient and moisture content in the soil samples. A soil anomaly score is determined based on the nutrient and moisture content information. A licorice growing environment monitoring report is generated based on the growth anomaly score, the climate anomaly score, and the soil anomaly score. The training steps of the pest prediction probability model include… The process includes: acquiring historical high-resolution licorice images at multiple times across multiple historical monitoring periods, wherein the previous historical monitoring period is the first historical monitoring period; inputting the historical high-resolution licorice images into a trained pest prediction probability model to obtain historical predicted pest probability data for multiple licorice samples at multiple times across multiple historical monitoring periods; performing feature extraction processing on the licorice root and stem regions in the historical high-resolution licorice images using the root and stem feature encoding layer of a trained image recognition neural network model to obtain historical root and stem feature vectors for each historical licorice sample; performing feature extraction processing on the licorice leaf regions in the historical high-resolution licorice images using the leaf feature encoding layer of a trained image recognition neural network model to obtain historical leaf feature vectors for each historical licorice sample; performing feature extraction processing on the licorice fruit regions in the historical high-resolution licorice images using the fruit feature encoding layer of a trained image recognition neural network model to obtain historical fruit feature vectors for each historical licorice sample; acquiring historical pest probability data for multiple licorice samples at multiple times across multiple historical monitoring periods; and applying the formula... Determine the training loss function Loss for the pest probability prediction model, where R i，s，k Let be the historical root and stem feature vector of the licorice root sample at time k in the s-th historical monitoring period. For the s-th historical monitoring period, the n-th k The historical root and stem feature vector of the licorice at time i. For R i，s，k The transpose of X i，s，k Let i be the historical leaf feature vector of the licorice sample at time k in the s-th historical monitoring period. For the s-th historical monitoring period, the n-th k The historical leaf feature vector of the i-th sample of licorice at time i. For X i，s，k The transpose vector, Y i，s，k Let be the historical fruit feature vector of the licorice sample at time k in the s-th historical monitoring period. For the s-th historical monitoring period, the n-th k The historical fruit feature vector of the licorice at time i. For Y i，s，k The transpose of G i，s，k G represents the historical pest probability data of the licorice sample at time k in the s-th historical monitoring period. i，s，k，p For the historical predicted pest probability data of licorice at time k in the s-th historical monitoring period, n i n represents the number of licorice samples. s n represents the number of historical monitoring periods. k The number of time points in the monitoring period, i≤n i , s≤n s , k≤n k And i, s, k, n i n s and n k All are positive integers; the predicted pest probability model is trained according to the training loss function to obtain the trained predicted pest probability model.

2. The method for monitoring the growth environment of licorice according to claim 1, characterized in that, The growth anomaly score is determined based on the predicted pest probability data and the growth height data, including: fitting the growth height data with multiple time points in the current monitoring period to obtain a growth height function; determining the growth height derivative function based on the growth height function; determining the growth height change rate based on the growth height derivative function; and determining the growth anomaly score based on the predicted pest probability data and the growth height change rate.

3. The method for monitoring the growth environment of licorice according to claim 2, characterized in that, Based on the predicted pest probability data and the growth height change rate, a growth anomaly score is determined, including: according to the formula and Determine the growth abnormality score A1, where H′ i，k H′ represents the rate of change in the growth height of the i-th sample of licorice at the k-th time point in the current monitoring period. p G is the threshold for the rate of change in growth height. F1 is a piecewise function that compares the rate of change in growth height of the i-th sample of licorice at the k-th time of the current monitoring period with the threshold for the rate of change in growth height. i，k，p This provides the predicted pest probability data for the i-th sample of licorice at the k-th time of the current monitoring period, where α1 and α2 are preset weights, and α1 + α2 = 1, n i n represents the number of licorice samples. k The number of time points in the monitoring period, i≤n i , k≤n k , and i, k, n i and n k All are positive integers.

4. The method for monitoring the growth environment of licorice according to claim 1, characterized in that, The climate anomaly score is determined based on the climate parameters, including: obtaining suitable climate parameters for the licorice growing area, wherein the suitable climate parameters include suitable temperature parameters, suitable humidity parameters, and suitable light intensity parameters; obtaining historical climate parameters for the licorice growing area at multiple times in the previous historical monitoring period, wherein the historical climate parameters include historical temperature parameters, historical humidity parameters, and historical light intensity parameters; and determining the climate anomaly score based on the suitable climate parameters, the historical climate parameters, and the climate parameters.

5. The method for monitoring the licorice growth environment according to claim 4, characterized in that, Based on the suitable climate parameters, the historical climate parameters, and the climate parameters, a climate anomaly score is determined, including: according to the formula... Determine the climate anomaly score A2, where t k Let t be the temperature parameter at the k-th moment of the current monitoring cycle. p For suitable temperature parameters, w k Let w be the humidity parameter at the k-th moment of the current monitoring cycle. p For suitable humidity parameters, m k Let m be the light intensity parameter at the k-th moment of the current monitoring period. p For suitable light intensity parameters, t k，h w represents the historical temperature parameter at the k-th moment of the previous historical monitoring period. k，h Let m be the historical humidity parameter at the k-th moment of the previous historical monitoring cycle. k，h Here, β1 and β2 are the historical light intensity parameters at the k-th moment of the previous historical monitoring cycle, and β1 + β2 = 1, n k To monitor the number of time points in the cycle, k≤n k And k and n k All are positive integers, and max is the function to find the maximum value.

6. The method for monitoring the growth environment of licorice according to claim 1, characterized in that, Based on the nutrient element content information and the moisture content information, a soil anomaly score is determined, including: acquiring standard nutrient element content information and standard moisture content information in licorice soil; determining a standard soil state vector for licorice soil based on the standard nutrient element content information and the standard moisture content information; determining a real-time soil state vector for licorice soil based on the nutrient element content information and the moisture content information; and determining a soil anomaly score based on the standard soil state vector and the real-time soil state vector.

7. The method for monitoring the licorice growth environment according to claim 6, characterized in that, Based on the standard soil state vector and the real-time soil state vector, a soil anomaly score is determined, including: according to the formula... The soil anomaly score was determined to be A3, where C 1，k C 2，k ..., C N，k For the content information of the 1st, 2nd, ..., Nth nutrient elements at the kth time point of the current monitoring period, C 1，T C 2，T ..., C N，T For the content information of the 1st, 2nd, ..., Nth standard nutrient elements, S k For the moisture content information at time k in the current monitoring period, S T For standard moisture content information, γ1, γ2, ..., γ N and γ N+1 To preset weights, This is the real-time soil state vector at the k-th moment of the current monitoring cycle. Let N be the standard soil state vector, and n be the number of different nutrient elements. k To monitor the number of time points in the cycle, k≤n k And k, N and n k All are positive integers.

8. The method for monitoring the growth environment of licorice according to claim 1, characterized in that, Based on the growth anomaly score, the climate anomaly score, and the soil anomaly score, a licorice growth environment monitoring report is generated, including: generating a growth monitoring report when the growth anomaly score is greater than a growth anomaly score threshold; generating a climate monitoring report when the climate anomaly score is greater than a climate anomaly score threshold; and generating a soil monitoring report when the soil anomaly score is greater than a soil anomaly score threshold.

9. A licorice growth environment monitoring system, characterized in that, include: The sample licorice module is used to sample licorice from the licorice growing area to obtain multiple sample licorice. The system includes a high-resolution licorice image and growth height data module, used to capture high-resolution images of the licorice samples at multiple times during the current monitoring period, acquiring multiple high-resolution licorice sample images and growth height data; a pest probability prediction model module, used to input the high-resolution licorice sample images into a trained pest probability prediction model to obtain predicted pest probability data for multiple licorice samples at multiple times during the current monitoring period; a growth anomaly scoring module, used to determine a growth anomaly score based on the predicted pest probability data and the growth height data; a climate parameter module, used to acquire climate parameters of the licorice growth area at multiple times during the current monitoring period, wherein the climate parameters include temperature parameters, humidity parameters, and light intensity parameters; and a climate anomaly scoring module, used to determine a climate anomaly score based on the climate parameters. The soil sample module is used to collect soil samples from the licorice growing area at multiple times during the current monitoring period and perform spectral composition analysis to obtain information on the nutrient element content and moisture content in the soil samples; the soil anomaly scoring module is used to determine the soil anomaly score based on the nutrient element content information and the moisture content information; the licorice growth environment monitoring report module is used to generate a licorice growth environment monitoring report based on the growth anomaly score, the climate anomaly score, and the soil anomaly score.

Images