Method and device for optimizing sweetness and brittleness of crisp and honey kumquats, terminal and storage medium

Abstract

The invention is suitable for the field of agricultural production, and provides a method and a device for optimizing sweetness and brittleness of crisp and honey kumquats, a terminal and a storage medium, and the method comprises the following steps: obtaining spectral data and growth soil data of a crisp and honey kumquat tree; performing data analysis based on the spectral data to obtain various plant characteristic parameters; inputting the various plant characteristic parameters into a prediction model to obtain predicted sweetness and predicted brittleness; based on the predicted sweetness, the predicted brittleness, the growth soil data and reference nutrition information, performing nutrition data analysis on the crisp and honey kumquat tree to generate nutrition control suggestion information; and sending the nutrition control suggestion information to a fertilization control system. According to the scheme, the scientificity and the accuracy of the optimization method are improved.

Description

Technical Field

[0001] The present application belongs to the field of agricultural production, and in particular relates to a method, device, terminal and storage medium for optimizing the sweetness and crispness of crispy kumquat. Background Art

[0002] Crunchy kumquat is famous for its sweet and crisp taste. Sweetness and crispness are the core quality characteristics of Crunchy kumquat, which directly affect consumers' purchasing intention and eating experience. Optimizing the sweetness and crispness of Crunchy kumquat can improve the overall quality and market competitiveness of Crunchy kumquat. At present, the growth conditions of Crunchy kumquat trees are controlled by artificial experience to optimize the sweetness and crispness of Crunchy kumquat. However, the scientificity and accuracy of this optimization method are poor. Summary of the invention

[0003] The embodiments of the present application provide a method, device, terminal and storage medium for optimizing the sweetness and crispness of crisp honey kumquat to solve the problem of poor scientificity and accuracy of traditional methods for optimizing the sweetness and crispness of crisp honey kumquat.

[0004] A first aspect of the embodiments of the present application provides a method for optimizing the sweetness and crispness of a crisp honey kumquat, comprising:

[0005] Obtain the spectral data and soil data of the Crisp Honey Kumquat tree;

[0006] Performing data analysis based on the spectral data to obtain a variety of plant characteristic parameters;

[0007] Inputting a plurality of the plant characteristic parameters into a prediction model to obtain predicted sweetness and predicted crispness;

[0008] Performing nutrition data analysis on the Crispy Honey Kumquat tree based on the predicted sweetness, the predicted crispness, the growth soil data and reference nutrition information to generate nutrition control suggestion information;

[0009] The nutrition control suggestion information is sent to a fertilization control system.

[0010] A second aspect of the embodiments of the present application provides a device for optimizing the sweetness and crispness of a crispy kumquat, comprising:

[0011] An acquisition module is used to obtain the spectrum data and growth soil data of the Crisp Honey Kumquat tree;

[0012] A spectral analysis module, used to perform data analysis based on the spectral data to obtain a variety of plant characteristic parameters;

[0013] A prediction module, used for inputting a plurality of the plant characteristic parameters into a prediction model to obtain predicted sweetness and predicted crispness;

[0014] A nutrition analysis module, used for performing nutrition data analysis on the Crispy Honey Kumquat tree based on the predicted sweetness, the predicted crispness, the growth soil data and reference nutrition information, and generating nutrition control suggestion information;

[0015] The sending module is used to send the nutrition control suggestion information to the fertilization control system.

[0016] A third aspect of an embodiment of the present application provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect when executing the computer program.

[0017] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0018] A fifth aspect of the present application provides a computer program product, which, when executed on a terminal, enables the terminal to execute the steps of the method described in the first aspect.

[0019] As can be seen from the above, the present application first obtains the spectral data and growth soil data of the crisp honey kumquat tree, and performs data analysis based on the spectral data, that is, the growth state of the crisp honey kumquat tree is scientifically, immediately and accurately evaluated using the non-destructive testing technology of spectral analysis technology, and a variety of plant characteristic parameters closely related to sweetness and crispness are obtained. Afterwards, the plant characteristic parameters are input into the prediction model to obtain the predicted sweetness and predicted crispness corresponding to the current growth state. Subsequently, the nutritional status of the crisp honey kumquat tree is analyzed using the predicted sweetness, predicted crispness, growth soil data and reference nutritional information, and nutritional problems are accurately identified, and nutritional control recommendation information is tailored for the crisp honey kumquat tree. The generated nutritional control recommendation information is then sent to the fertilization control system, and the nutritional status of the crisp honey kumquat tree is controlled using the fertilization control system to achieve scientific and accurate optimization of the sweetness and crispness of the crisp honey kumquat. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 It is a flow chart of a method for optimizing the sweetness and crispness of a crisp honey kumquat provided in an embodiment of the present application;

[0022] Figure 2 is a flow chart of a prediction model training method provided in an embodiment of the present application;

[0023] Figure 3 It is a structural diagram of a sweetness and crispness optimization device for a crisp honey kumquat provided in an embodiment of the present application;

[0024] Figure 4 It is a structural diagram of a terminal provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0026] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0027] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0028] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0029] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0030] In a specific implementation, the terminal described in the embodiments of the present application includes, but is not limited to, other portable devices such as mobile phones, laptop computers, or tablet computers with touch-sensitive surfaces (e.g., touch screen displays and / or touch pads). It should also be understood that in some embodiments, the device is not a portable communication device, but a desktop computer with a touch-sensitive surface (e.g., touch screen displays and / or touch pads).

[0031] In the following discussion, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, mouse and / or joystick.

[0032] The terminal supports various applications, such as one or more of the following: a drawing application, a presentation application, a word processing application, a website creation application, a disk burning application, a spreadsheet application, a game application, a telephone application, a video conferencing application, an email application, an instant messaging application, a workout support application, a photo management application, a digital camera application, a digital camcorder application, a web browsing application, a digital music player application, and / or a digital video player application.

[0033] Various applications that can be executed on the terminal can use at least one common physical user interface device such as a touch-sensitive surface. One or more functions of the touch-sensitive surface and corresponding information displayed on the terminal can be adjusted and / or changed between applications and / or within corresponding applications. In this way, the common physical architecture of the terminal (e.g., the touch-sensitive surface) can support various applications with user interfaces that are intuitive and transparent to the user.

[0034] It should be understood that the size of the serial numbers of the steps in this embodiment 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 embodiment of the present application.

[0035] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0036] See also Figure 1 , Figure 1 Flow chart of a method for optimizing the sweetness and crispness of a crispy kumquat provided in an embodiment of the present application. Figure 1 As shown, a method for optimizing the sweetness and crispness of crisp honey kumquat, the method comprising the following steps:

[0037] Step 101, obtaining spectral data and growth soil data of the Crisp Honey Kumquat tree.

[0038] A spectrum collection device is installed in the growth area of ​​the Crisp Honey Kumquat tree, and the spectrum data of the Crisp Honey Kumquat tree is collected by the spectrum collection device.

[0039] During installation, the following installation principles should be followed: (1) Install in the main growth area of ​​the Crisp Honey Kumquat trees to ensure that most of the Crisp Honey Kumquat trees are covered; (2) Install in typical locations in the Crisp Honey Kumquat planting area, such as areas with dense fruit trees, areas with high fruit yields, areas with different soil types, etc., so as to collect more abundant data and improve and upgrade the optimization method described in this application; (3) Install in a location where it is easy for staff to maintain and operate the equipment; (4) Install in an area that can monitor the different growth stages of the Crisp Honey Kumquat trees to achieve all-round monitoring of the entire growth period.

[0040] In addition, without affecting the collection of spectral data, the influence of factors such as soil quality, light, and rain should be considered to provide safety protection for the spectral collection equipment.

[0041] Specifically, the spectrum data collected by the spectrum collection device include visible light spectrum and infrared spectrum. The spectrum collection device can be a high-precision near infrared spectrometer (Near Infrared Spectrum Instrument, NIRS) and a hyperspectral imager.

[0042] In some embodiments, obtaining the spectral data of the Crisp Honey Kumquat tree includes: using a spectral acquisition device to collect data on specific plant parts of the Crisp Honey Kumquat tree to obtain the spectral data, and the specific plant parts are at least one of leaves, flowers and fruits.

[0043] Collecting spectral data of specific plant parts is highly targeted and can reduce the interference caused by spectral data of other irrelevant parts, thereby improving the precision and accuracy of data analysis. At the same time, compared with the spectral data collection of the whole plant or large area of ​​land, the data collection of specific plant parts is more economical and efficient, which can save manpower, material resources and time costs.

[0044] The growth period of the Crisp Honey Kumquat tree includes the budding period, flowering period, fruit formation period, fruit expansion period, fruit ripening period, fruit harvesting period and dormancy period. Different plant parts are monitored and collected in different growth periods, that is, the specific plant parts change with the growth period of the Crisp Honey Kumquat tree. The leaves are monitored and collected throughout the whole cycle, the flowers are monitored and collected during the flowering period, and the Crisp Honey Kumquat fruits are monitored and collected after the fruits grow.

[0045] In some embodiments, the growth soil data includes data such as the content of nutrient elements such as nitrogen, phosphorus and potassium in the soil and the water content.

[0046] In the embodiment of the present application, the growth soil data may be obtained by directly measuring the soil.

[0047] Alternatively, the existing soil measurement data is directly transmitted and acquired from the existing equipment / system, wherein the existing equipment / system is, for example, a fertilizer control system or other equipment / system having soil measurement data.

[0048] The fertilization control system here includes, for example, a sensor, a controller and an automatic fertilization device, wherein the sensor has the function of monitoring the soil in the planting area, and the fertilization control system can collect and obtain the growth soil data.

[0049] This process directly obtains soil measurement data from existing equipment / systems without the need for manual field observation, thus saving labor costs and increasing efficiency.

[0050] Step 102: performing data analysis based on the spectral data to obtain a variety of plant characteristic parameters.

[0051] Spectral data is an optical mapping of the growth status of the Crisp Honey Kumquat tree. By analyzing the acquired spectral data, we can obtain relevant parameters of plant characteristics that are closely related to the sweetness and crispness of the Crisp Honey Kumquat.

[0052] In some embodiments, the plant characteristics related to the sweetness and crispness of the crisp honey kumquat mainly include sugar, water, chlorophyll, nutrients and plant fiber. Accordingly, the plant characteristic parameters include sugar content, water content, chlorophyll content, nutrient content and fiber characteristics. Among them, the nutrients mainly refer to nitrogen, phosphorus and potassium. The plant characteristics given in this application are only examples, and other plant characteristics that affect sweetness and crispness can be added to the optimization method described in this application for use.

[0053] In different growth stages, different plant parts are collected and different plant characteristics are obtained through analysis, that is, the types of the multiple plant characteristic parameters change with the specific plant parts, and the multiple types of the multiple plant characteristic parameters are at least three of sugar, water, chlorophyll, nutrients and plant fiber.

[0054] In some embodiments, the water content, chlorophyll content, and nutrient content of the leaves are analyzed based on the spectral data corresponding to the leaves. The water content and nutrient content of the flowers are analyzed based on the spectral data corresponding to the flowers. The sugar content, water content, and fiber characteristics of the fruits are analyzed based on the spectral data corresponding to the fruits.

[0055] In some embodiments, the data analysis is performed based on the spectral data to obtain a plurality of plant characteristic parameters, including: screening out a plurality of target spectral bands from the spectral data according to a band screening rule for a plant part to which the spectral data belongs; based on each of the target spectral bands, extracting a target spectral feature required to calculate the plant characteristic parameter; based on a mapping relationship between spectral features and plant features, converting the target spectral features to obtain a plurality of the plant characteristic parameters.

[0056] In order to improve the optimization effect, the acquired spectral data is preprocessed by denoising, normalization and baseline correction to improve the data quality. For example, filtering and smoothing are used to remove noise in the spectral data, normalization is used to eliminate the influence of different measurement conditions on the data, and baseline correction is used to eliminate the influence of background signals.

[0057] The target spectral bands capable of extracting and calculating the characteristic parameters of the plant are screened out from the preprocessed spectral data.

[0058] When screening, accurate screening should be carried out based on the plant part to which the spectral data belongs, and different band screening rules should be used for different plant parts.

[0059] In some embodiments, for the spectral data corresponding to leaves, the blue light region of 430-450nm and the red light region of 640-680nm are screened for analyzing the chlorophyll content, the blue light region and the green light region of 450-550nm are screened for analyzing the nitrogen content, and the near-infrared light region of 1450-1550nm is screened for analyzing the moisture content. For the spectral data corresponding to flowers, the blue light region and the green light region of 450-550nm are screened for analyzing the nitrogen content, and the near-infrared light region of 1450-1550nm is screened for analyzing the moisture content. For the spectral data corresponding to fruits, the near-infrared light region of 900-1000nm is screened for analyzing the sugar content, the near-infrared light region of 1200-1300nm is screened for analyzing the fiber characteristics, and the near-infrared light region of 1450-1550nm is screened for analyzing the moisture content.

[0060] For different spectral bands in different parts, different characteristics of the bands are extracted to obtain the target spectral characteristics. The characteristic types of spectral characteristics include characteristic peak intensity, band combination relationship and spectral shape parameters. Among them, the characteristic peak is the absorption peak or reflection peak, the band combination relationship is the reflectance ratio, and the spectral curve parameters are parameters such as the slope or curvature of the spectral curve.

[0061] In some embodiments, the reflection spectrum is extracted from the blue light region of 430-450nm and the red light region of 640-680nm obtained by screening, and the chlorophyll absorption peak is extracted based on this, and the corresponding absorption peak intensity is obtained, which is used to calculate the chlorophyll content of the crisp honey kumquat tree leaves. The reflection spectrum is extracted from the near-infrared light region of 900-1000nm obtained by screening, and the sugar absorption peak intensity and reflectance ratio are extracted to calculate the sugar content of the crisp honey kumquat. The absorption peak intensity of cellulose and lignin is extracted from the near-infrared light region of 1200-1300nm to calculate the fiber characteristics of the crisp honey kumquat. The moisture absorption peak intensity is extracted from the reflection spectrum of the near-infrared light region of 1450-1550nm to calculate the moisture content of the crisp honey kumquat.

[0062] After the target spectral feature is obtained, the plant feature parameter is calculated based on the target spectral feature and the mapping relationship between the spectral feature and the plant feature to achieve feature conversion, thereby obtaining a variety of plant feature parameters.

[0063] The embodiment of the present application constructs a plant feature calculation model for calculating the plant feature parameters, inputs the target spectral feature into the corresponding model, and the model outputs the corresponding plant feature parameters. The plant feature calculation model is trained based on the spectral feature corresponding to the plant feature and the measured plant feature, and a mapping relationship is embedded in the plant feature calculation model. The plant feature calculation model can be trained using methods such as chemometrics, spectral derivatives, principal component analysis (PCA), partial least squares regression (PLS) and / or multivariate regression analysis.

[0064] This application is based on spectral analysis technology. Without the need for manual on-site testing or destructive testing of the Crisp Honey Kumquat tree, it obtains plant characteristic parameters closely related to sweetness and crispness, and conducts a scientific, immediate and accurate assessment of the growth status of the Crisp Honey Kumquat tree.

[0065] Step 103, inputting the plurality of plant characteristic parameters into a prediction model to obtain predicted sweetness and predicted crispness.

[0066] Specifically, the prediction model is a pre-trained model. The prediction model is a sweetness prediction model and a crispness prediction model, or a comprehensive prediction model integrating the sweetness prediction function and the crispness prediction function.

[0067] A plurality of plant characteristic parameters are input into the prediction model, and the prediction model predicts the sweetness and crispness of the Crunchy Honey Kumquat during the fruit harvest period according to the current plant state of the Crunchy Honey Kumquat tree.

[0068] Figure 2 : is a flow chart of a prediction model training method provided in an embodiment of the present application. Figure 2 As shown, the training process of the prediction model includes:

[0069] Collect sample spectrum data, sample sweetness and sample crispness of kumquat samples;

[0070] Performing data analysis based on the sample spectral data to obtain a variety of sample plant characteristic parameters;

[0071] Constructing a training set and a test set based on a plurality of the sample plant characteristic parameters, the sample sweetness and the sample crispness;

[0072] The initial model is trained based on the training set and the test set to obtain the prediction model.

[0073] When collecting sample data, the objects of collection are kumquat samples of different growth periods, different varieties and different planting conditions. The samples are diverse and have strong coverage, so that the trained sweetness and crispness prediction model can predict the sweetness and crispness of the fruit based on data under various planting conditions and data in various growth periods.

[0074] The spectrum data of the samples are collected by using a spectrum collection device, and the collected parts are the leaves, flowers and fruits of the kumquat samples. The sweetness of the sample fruits is measured by using a sugar meter, such as a Brix meter. The crispness of the sample fruits is measured by using a texture analyzer.

[0075] The acquired sample spectral data is preprocessed in advance by means of denoising, normalization and baseline correction to improve the data quality. Then, according to the band screening rules corresponding to the plant part to which the preprocessed sample spectral data belongs, the target sample spectral band for extracting and calculating the characteristic parameters of the sample plant is screened out. The specific bands corresponding to different plant parts are not described here.

[0076] For different target sample spectral bands at different locations, different band features are extracted to obtain the target sample spectral features. The feature types of the target sample spectral features are the same as those of the above spectral features, and will not be described in detail here.

[0077] After the target sample spectral features are obtained, feature conversion is implemented based on the target sample spectral features and the mapping relationship between the target sample spectral features and plant features, and a plurality of sample plant feature parameters are obtained accordingly.

[0078] In some embodiments, the sample plant characteristic parameters may be calculated using a plant characteristic calculation model.

[0079] When constructing a sample data set, it is necessary to first determine the sample plant characteristic parameters that affect the sweetness of the sample, and combine the measured sample sweetness with them, so that one sample sweetness and a group of sample plant characteristic parameters that affect the sweetness of the sample form a sweetness data sample. At the same time, it is also necessary to determine the sample plant characteristic parameters that affect the crispness of the sample, and combine the measured sample crispness with them, so that one sample crispness and a group of sample plant characteristic parameters that affect the crispness of the sample form a crispness data sample. The sample data sets are a sweetness sample data set and a crispness sample data set. Among them, the sweetness sample data set contains sample sweetness and sample plant characteristic parameters related to the sample sweetness, that is, it contains multiple sweetness data samples; the crispness sample data set contains sample crispness and sample plant characteristic parameters related to the sample crispness, that is, it contains multiple crispness data samples.

[0080] In order to ensure that the prediction model can accurately predict the sweetness and crispness of the crisp honey kumquat based on the data of each growth period, the constructed sample data set includes sample sub-datasets corresponding to multiple growth periods of the crisp honey kumquat tree, that is, the sweetness sample data set includes the sweetness sample sub-datasets corresponding to multiple growth periods, and the crispness sample data set includes the crispness sample sub-datasets corresponding to multiple growth periods. In this way, the prediction model obtained by training not only has high prediction accuracy, but also has a wide range of applications. For example, the sample sub-dataset of the flowering period includes the sample plant characteristic parameters of the leaves, the sample plant characteristic parameters of the flowers, and the sweetness and crispness of the fruits finally harvested, that is, the sweetness sample sub-dataset of the flowering period includes the sample plant characteristic parameters of the leaves, the sample plant characteristic parameters of the flowers, and the sweetness of the fruits finally harvested, and the crispness sample sub-dataset of the flowering period includes the sample plant characteristic parameters of the leaves, the sample plant characteristic parameters of the flowers, and the crispness of the fruits finally harvested.

[0081] After obtaining the sample data set, the sample data set is divided according to a set division ratio to obtain a training set and a test set, wherein the set division ratio is usually 4:1, that is, 80% of the data set is usually used as a training set and 20% as a test set.

[0082] In some embodiments, the sweetness sample data set and the crispness sample data set are divided according to a set division ratio, thereby obtaining a sweetness training set and a sweetness test set, as well as a crispness training set and a crispness test set. Accordingly, 80% of the sweetness sample data set is usually used as a sweetness training set, and 20% is used as a sweetness test set, and 80% of the crispness sample data set is used as a crispness training set, and 20% is used as a crispness test set. That is, the data ratio of the sweetness data samples in the sweetness training set and the sweetness test set is equal to the set division ratio, and the data ratio of the crispness data samples in the crispness training set and the crispness test set is equal to the set division ratio.

[0083] In some embodiments, the sample sub-datasets corresponding to each growth period in the sample data set are divided according to a set division ratio to obtain training sets and test sets corresponding to each growth period, thereby achieving training and learning for different growth periods.

[0084] In some embodiments, the sweetness sample data set includes sweetness sample sub-data sets corresponding to multiple growth periods, and the crispness sample data set includes crispness sample sub-data sets corresponding to multiple growth periods. In combination with the growth period, sweetness and crispness, the sample data set is divided according to a set division ratio, that is, the sweetness sample data set and the crispness sample data set are divided respectively, that is, the sweetness sample sub-data set and the crispness sample sub-data set corresponding to each growth period are divided respectively. The sweetness training set obtained by division includes sweetness training subsets for multiple growth periods, the sweetness test set includes sweetness test subsets for multiple growth periods, and the data sample ratio of the sweetness training subset and the sweetness test subset for each growth period is the set division ratio. The crispness training set obtained by division includes crispness training subsets for multiple growth periods, the crispness test set includes crispness test subsets for multiple growth periods, and the data sample ratio of the crispness training subset and the crispness test subset for each growth period is the set division ratio.

[0085] A linear regression model, a support vector machine (SVM) model, a random forest (RF) model, or an artificial neural network (ANN) model is used as the initial model. The initial model is trained using the training set, and the model parameters are adjusted to minimize the prediction error.

[0086] In some embodiments, a sweetness training set and a crispness training set are used to train an initial model that is expected to integrate sweetness prediction function and crispness prediction function. The sweetness training set is used to train the sweetness prediction function of the integrated initial model, and the crispness training set is used to train the crispness prediction function of the integrated initial model.

[0087] In some embodiments, when the prediction model does not refer to an integrated prediction model but refers to two independent models, a sweetness prediction model and a crispness prediction model, the sweetness training set is used to train the initial sweetness prediction model, and the crispness training set is used to train the initial crispness prediction model.

[0088] At the same time, a cross-validation set is divided from the training set, and the cross-validation set is used to tune the hyperparameters and select the best model parameters. Similarly, when dividing the cross-validation set, it is necessary to consider sweetness, crispness and growth period for multi-factor division, obtain the sweetness cross-validation set and crispness cross-validation set corresponding to each growth period, and cross-validate the prediction performance of sweetness and crispness in each growth period to improve the generalization ability and adaptability of the model.

[0089] The test set was used to calculate the mean square error (MSE), the coefficient of determination (R 2 ) or Mean Absolute Percentage Error (MAPE) and other indicators are used to evaluate the performance of the model trained based on the training set, and the prediction accuracy of the integrated prediction model for sweetness and crispness is checked, or the sweetness prediction accuracy of the sweetness prediction model is checked based on the sweetness test set, and the prediction accuracy of the crispness prediction model is checked based on the crispness test set. During the inspection, the prediction performance of each growth period is checked and tested. When the accuracy does not meet expectations, the model is further adjusted and optimized based on the verification results.

[0090] The model whose prediction accuracy met expectations was determined as the prediction model, which was used to predict the sweetness and crispness of Crunchy Honey Kumquat based on plant characteristic parameters at various growth stages.

[0091] Based on the prediction model, the sweetness and crispness of the crispy kumquat can be predicted in real time according to real-time data. It is timely, the prediction results are more scientific, and have more reference value.

[0092] Step 104, performing a nutritional data analysis on the Crisp Honey Kumquat tree based on the predicted sweetness, the predicted crispness, the growth soil data and the reference nutritional information, and generating nutritional control recommendation information.

[0093] The reference nutritional information is the nutritional information corresponding to the Crisp Honey Kumquat tree when the sweetness and crispness of the Crisp Honey Kumquat reach the harvest standard. The nutritional information is the element type and content of each element type of the nutritional elements contained in the Crisp Honey Kumquat tree.

[0094] In some embodiments, the nutritional data of the crisp honey kumquat tree is analyzed based on the predicted sweetness, the predicted crispness, the growing soil data and the reference nutritional information to generate nutritional control recommendation information, including: inputting the predicted sweetness and the predicted crispness into a nutrition and sweetness and crispness relationship model to obtain the predicted nutritional information of the crisp honey kumquat tree output by the nutrition and sweetness and crispness relationship model; comparing the predicted nutritional information with the reference nutritional information to obtain nutritional difference information; determining the nutritional control recommendation information based on the nutritional difference information, the growing soil data and the nutritional utilization data of the crisp honey kumquat tree.

[0095] The nutritional deficit information includes the element type and corresponding content of the nutritional elements that are missing from the Crisp Honey Kumquat Tree. The nutritional utilization data includes data such as the nutritional absorption and metabolic capacity of the Crisp Honey Kumquat Tree.

[0096] The predicted sweetness and predicted crispness obtained by real-time prediction are input into the nutrition and sweetness and crispness relationship model, and the corresponding nutritional information of the Crisp Honey Kumquat Tree is obtained when the predicted sweetness and the predicted crispness are reached. By comparing the nutritional information, nutritional differences can be identified, which helps to determine nutritional problems. Combined with the growth soil data and nutritional utilization data, the introduction of nutritional utilization data improves the accuracy and personalization of nutritional control recommendation information, making it easier to tailor nutritional control recommendation information for the Crisp Honey Kumquat Tree.

[0097] In some embodiments, in order to better determine the nutritional control recommendation information, it is necessary to pre-train the nutrition and sweetness and crispness relationship model. That is, the sample sweetness, sample crispness and sample nutritional information corresponding to each sample sweetness and sample crispness of the kumquat samples are collected in advance, based on which, the model training is performed to obtain the corresponding nutrition and sweetness and crispness relationship model.

[0098] In some embodiments, the nutrient control suggestion information includes adjusting the element type of the nutrient element to be supplemented to the target type, and / or adjusting the water-fertilizer ratio of the nutrient element to be supplemented to a set ratio. The nutrient control suggestion information clearly indicates how to implement nutrient control, thereby improving nutrient control efficiency and optimization efficiency.

[0099] Step 105: sending the nutrition control suggestion information to a fertilization control system.

[0100] In some embodiments, the nutrient control recommendation information is sent to a fertilization control system, which controls the automatic fertilization equipment and irrigation equipment to perform fertilization and irrigation according to the set water-fertilizer ratio. When fertilizing, the type of nutrient elements retrieved by the automatic fertilization equipment is the target type given in the nutrient adjustment recommendation, ensuring that the required nutrients can be accurately delivered according to the actual needs of the crisp honey kumquat tree, providing sufficient nutrient supply for the growth of the crisp honey kumquat tree, and achieving scientific and precise optimization of the sweetness and crispness of the crisp honey kumquat. At the same time, automated fertilization can also improve efficiency.

[0101] In some embodiments, the sweetness and crispness of the crisp honey kumquat are monitored, and when the sweetness and crispness of the crisp honey kumquat reach the harvesting standard, harvesting reminder information is output to prompt harvesting, so that staff can harvest in time.

[0102] In some embodiments, the maturity of the fruit is determined by spectral analysis, and when the fruit is ripe, the sweetness and crispness of the crisp honey kumquat are monitored in real time or at regular intervals, thereby reducing the frequency and cost of manual monitoring and improving monitoring efficiency and accuracy.

[0103] In particular, the priority of sweetness is higher than that of crispness. When the sweetness meets the standard but the crispness does not, if you continue to wait, the sweetness will decrease. In this case, you will not wait for the crispness to increase, and directly output the harvesting prompt information.

[0104] In some embodiments, the sweetness and crispness of the crisp honey kumquats are monitored; when the growth time of the crisp honey kumquats has reached the expected harvest time and the predicted sweetness and / or the predicted crispness do not meet the standard, harvest prompt information for prompting harvesting is output, and the harvesting spectral data, harvesting nutritional information, harvesting sweetness and harvesting crispness of the harvested crisp honey kumquats are obtained; based on the harvesting spectral data, the harvesting sweetness and the harvesting crispness, and the predicted sweetness and the predicted crispness, the prediction model is optimized and trained; based on the harvesting nutritional information, the harvesting sweetness, the harvesting crispness, and the predicted nutritional information obtained by predicting the predicted sweetness and the predicted crispness through the nutrition and sweetness and crispness relationship model, the nutrition and sweetness and crispness relationship model is optimized and trained.

[0105] Among them, the estimated harvesting time is the time when the harvesting operation needs to be performed, and the estimated harvesting time is generally earlier than the end time of the fruit harvesting period, so as to reserve time for the staff to harvest. The harvesting spectral data is the spectral data of the crisp honey kumquat tree collected at the estimated harvesting time. The harvesting nutritional information is the nutritional information of the crisp honey kumquat tree measured in real time at the estimated harvesting time. The harvesting sweetness is the sweetness measured in real time based on a saccharimeter. The harvesting crispness is the crispness measured in real time based on a texture analyzer. The monitored sweetness and crispness are the predicted sweetness and the predicted crispness predicted based on spectral analysis technology and prediction models.

[0106] In some embodiments, when the growth time of the crispy kumquat has reached the expected harvest time, and the predicted sweetness and / or the predicted crispness do not meet the standard, it is necessary to verify whether the prediction accuracy of the prediction model and the nutrition and sweetness and crispness relationship model is abnormal through data comparison, and determine whether the above models need to be optimized and adjusted based on the test results.

[0107] In some embodiments, if the predicted sweetness does not meet the standard, the predicted sweetness is compared with the harvested sweetness to obtain a first comparison difference. If the first comparison difference exceeds the set sweetness error threshold, it means that the sweetness prediction accuracy of the prediction model that integrates the sweetness prediction function and the crispness prediction function is abnormal, or the prediction accuracy of the sweetness prediction model is abnormal. At this time, the harvested spectral data is spectrally analyzed, and a variety of harvested plant characteristic parameters related to sweetness are selected. Based on the harvested sweetness and a variety of harvested plant characteristic parameters related to sweetness, the sweetness prediction function of the integrated prediction model is optimized and adjusted, or the sweetness prediction model is optimized and adjusted.

[0108] In some embodiments, if the predicted crispness does not meet the standard, the predicted crispness is compared with the harvested crispness to obtain a second comparison difference. If the second comparison difference exceeds the set crispness error threshold, it means that the crispness prediction accuracy of the prediction model that integrates the sweetness prediction function and the crispness prediction function is abnormal, or the prediction accuracy of the crispness prediction model is abnormal. At this time, the harvested spectral data is spectrally analyzed, and a variety of harvested plant characteristic parameters related to crispness are selected. Based on the harvested crispness and a variety of harvested plant characteristic parameters related to crispness, the crispness prediction function of the integrated prediction model is optimized and adjusted, or the crispness prediction model is optimized and adjusted.

[0109] In some embodiments, if both the predicted sweetness and the predicted crispness are not up to standard, the predicted sweetness is compared with the harvested sweetness, and the predicted crispness is compared with the harvested crispness, and a first comparison difference and a second comparison difference are obtained, respectively. According to the first comparison difference and the set sweetness error threshold, and the second comparison difference and the set crispness error threshold, it is determined whether there are abnormalities in the sweetness prediction accuracy and the crispness prediction accuracy. If there are abnormalities in the sweetness prediction accuracy, the sweetness prediction function of the integrated prediction model is optimized and adjusted, or the sweetness prediction model is optimized and adjusted; if there are abnormalities in the crispness prediction accuracy, the crispness prediction function of the integrated prediction model is optimized and adjusted, or the crispness prediction model is optimized and adjusted; if there are abnormalities in both the sweetness prediction accuracy and the crispness prediction accuracy, the sweetness prediction function and the crispness prediction function of the integrated prediction model are optimized and adjusted at the same time, or the sweetness prediction model and the crispness prediction model are optimized and adjusted at the same time.

[0110] In some embodiments, when the growth time of the crisp honey kumquat has reached the expected harvest time, and the predicted sweetness and / or predicted crispness do not meet the standard, the predicted sweetness and the predicted crispness are input into the nutrition and sweetness and crispness relationship model, and the corresponding predicted nutritional information is output. The harvested nutritional information is compared with the predicted nutritional information, and the nutritional elements and nutritional element contents contained therein are compared to obtain the nutritional difference value. If the nutritional difference value exceeds the set nutritional error threshold, it means that the model accuracy of the nutrition and sweetness and crispness relationship model is abnormal. At this time, the harvested sweetness and the harvested crispness are used as input data, and the harvested nutritional information is used as output data to adjust the nutrition and sweetness and crispness relationship model.

[0111] By monitoring the sweetness and crispness of the Crisp Honey Kumquat, it is possible to ensure that the fruit is harvested at optimal maturity, thereby maintaining its optimal taste and quality. When it is monitored that the growth time of the Crisp Honey Kumquat exceeds the expected harvest time and the sweetness and / or crispness do not meet the standards, timely output of harvest prompt information can prevent the fruit from losing its commercial value or rotting due to overripeness, thereby reducing economic losses. At the same time, the harvest spectral data, harvest nutritional information, harvest sweetness and harvest crispness are obtained to test the prediction accuracy of the prediction model and the model of the relationship between nutrition and sweetness and crispness. When the prediction accuracy is abnormal, the model is adjusted to improve the accuracy and reliability of the model, and further improve the optimization efficiency and precision of sweetness and crispness.

[0112] This application uses spectral analysis to accurately monitor the sweetness and crispness of the crisp honey kumquat. Through scientific nutritional analysis and intelligent water and fertilizer control, the sweetness and crispness of the crisp honey kumquat can be scientifically and accurately optimized.

[0113] In the embodiment of the present application, the spectral data and growth soil data of the crisp honey kumquat tree are first obtained, and data analysis is performed based on the spectral data, that is, the growth state of the crisp honey kumquat tree is scientifically, immediately and accurately evaluated using the non-destructive detection technology of spectral analysis technology, and a variety of plant characteristic parameters closely related to sweetness and crispness are obtained. Afterwards, the plant characteristic parameters are input into the prediction model to obtain the predicted sweetness and predicted crispness corresponding to the current growth state. Subsequently, the nutritional status of the crisp honey kumquat tree is analyzed using the predicted sweetness, predicted crispness, growth soil data and reference nutritional information, and nutritional problems are accurately identified, and nutritional control recommendation information is tailored for the crisp honey kumquat tree. The generated nutritional control recommendation information is then sent to the fertilization control system, and the nutritional status of the crisp honey kumquat tree is controlled using the fertilization control system to achieve scientific and accurate optimization of the sweetness and crispness of the crisp honey kumquat.

[0114] See also Figure 3 , Figure 3 This is a structural diagram of a sweetness and crispness optimization device for a crispy kumquat provided in an embodiment of the present application. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0115] The sweetness and crispness optimization device 300 of the crispy kumquat comprises: an acquisition module 301 , a spectrum analysis module 302 , a prediction module 303 , a nutrition analysis module 304 , and a sending module 305 .

[0116] An acquisition module 301 is used to acquire spectral data and growth soil data of the Crisp Honey Kumquat tree;

[0117] A spectrum analysis module 302, used to perform data analysis based on the spectrum data to obtain a variety of plant characteristic parameters;

[0118] Prediction module 303, used for inputting a plurality of plant characteristic parameters into a prediction model to obtain predicted sweetness and predicted crispness;

[0119] A nutrition analysis module 304 is used to perform nutrition data analysis on the Crispy Honey Kumquat tree based on the predicted sweetness, the predicted crispness, the growth soil data and the reference nutrition information to generate nutrition control suggestion information;

[0120] The sending module 305 is used to send the nutrition control suggestion information to the fertilization control system.

[0121] In some embodiments, the acquisition module is specifically used to:

[0122] A spectral acquisition device is used to collect data on a specific plant part of the Crisp Honey Kumquat tree to obtain the spectral data, wherein the specific plant part is at least one of leaves, flowers and fruits.

[0123] In some embodiments, the spectral analysis module is specifically used to:

[0124] Filtering a plurality of target spectral bands from the spectral data according to a band filtering rule of the plant part to which the spectral data belongs;

[0125] Based on each of the target spectral bands, extracting target spectral features required for calculating the plant characteristic parameters;

[0126] Based on the mapping relationship between spectral features and plant features, a plurality of plant feature parameters are obtained by converting the target spectral features.

[0127] In some embodiments, the apparatus further comprises a model training module for:

[0128] Collect sample spectrum data, sample sweetness and sample crispness of kumquat samples;

[0129] Performing data analysis based on the sample spectral data to obtain a variety of sample plant characteristic parameters;

[0130] Constructing a training set and a test set based on a plurality of the sample plant characteristic parameters, the sample sweetness and the sample crispness;

[0131] The initial model is trained based on the training set and the test set to obtain the prediction model.

[0132] In some embodiments, the nutrition analysis module is specifically used to:

[0133] Inputting the predicted sweetness and the predicted crispness into a nutrition and sweetness and crispness relationship model to obtain the predicted nutritional information of the Crispy Honey Kumquat tree output by the nutrition and sweetness and crispness relationship model;

[0134] Comparing the predicted nutritional information with the reference nutritional information to obtain nutritional difference information;

[0135] The nutrient control recommendation information is determined based on the nutrient balance information, the growth soil data and the nutrient utilization data of the Crisp Honey Kumquat tree.

[0136] In some embodiments, the nutrient control suggestion information includes adjusting the element type of the nutrient element to be supplemented to a target type, and / or adjusting the water-fertilizer ratio of the nutrient element to be supplemented to a set ratio.

[0137] In some embodiments, the device further comprises a monitoring module for:

[0138] Monitor the sweetness and crispness of the Crisp Honey Kumquat;

[0139] When the growth time of the crisp honey kumquat has reached the expected harvest time and the predicted sweetness and / or the predicted crispness do not meet the standard, output harvest prompt information for prompting harvesting, and obtain harvest spectral data, harvest nutritional information, harvest sweetness and harvest crispness of the harvested crisp honey kumquat;

[0140] Based on the harvested spectral data, the harvested sweetness and the harvested crispness, and the predicted sweetness and the predicted crispness, the prediction model is optimized and trained;

[0141] Based on the harvested nutritional information, the harvested sweetness, the harvested crispness, and the predicted nutritional information obtained by predicting the nutrition and sweetness and crispness relationship model based on the predicted sweetness and the predicted crispness, the nutrition and sweetness and crispness relationship model is optimized and trained.

[0142] The sweetness and crispness optimization device for the crispy kumquat provided in the embodiment of the present application can realize each process of the embodiment of the sweetness and crispness optimization method of the crispy kumquat mentioned above, and can achieve the same technical effect. To avoid repetition, it will not be described here.

[0143] Figure 4 4 is a structural diagram of a terminal provided in an embodiment of the present application. As shown in the figure, the terminal 4 of this embodiment includes: at least one processor 40 ( Figure 4 Only one is shown in the figure), a memory 41, and a computer program 42 stored in the memory 41 and executable on the at least one processor 40, wherein the processor 40 implements the steps of any of the above-mentioned method embodiments when executing the computer program 42.

[0144] The terminal 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 It is only an example of terminal 4 and does not constitute a limitation on terminal 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0145] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0146] The memory 41 may be an internal storage unit of the terminal 4, such as a hard disk or memory of the terminal 4. The memory 41 may also be an external storage device of the terminal 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal 4. Further, the memory 41 may also include both an internal storage unit and an external storage device of the terminal 4. The memory 41 is used to store the computer program and other programs and data required by the terminal. The memory 41 may also be used to temporarily store data that has been output or is to be output.

[0147] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0148] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0149] 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.

[0150] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic. For example, the division of the modules or 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.

[0151] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0152] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0153] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0154] The present application implements all or part of the processes in the above-mentioned embodiment method, and may also be implemented through a computer program product. When the computer program product runs on a terminal, the terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0155] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for optimizing the sweetness and crispness of a crisp honey kumquat, characterized in that: include: Obtain the spectral data and soil data of the Crisp Honey Kumquat tree; Performing data analysis based on the spectral data to obtain a variety of plant characteristic parameters; Inputting a plurality of the plant characteristic parameters into a prediction model to obtain predicted sweetness and predicted crispness; Performing nutrition data analysis on the Crispy Honey Kumquat tree based on the predicted sweetness, the predicted crispness, the growth soil data and reference nutrition information to generate nutrition control suggestion information; The nutrition control suggestion information is sent to a fertilization control system.

2. The method according to claim 1, characterized in that The method of obtaining the spectral data of the crisp honey kumquat tree comprises: A spectral acquisition device is used to collect data on a specific plant part of the Crisp Honey Kumquat tree to obtain the spectral data, wherein the specific plant part is at least one of leaves, flowers and fruits.

3. The method according to claim 1, characterized in that The data analysis is performed based on the spectral data to obtain a variety of plant characteristic parameters, including: Filtering a plurality of target spectral bands from the spectral data according to a band filtering rule of the plant part to which the spectral data belongs; Based on each of the target spectral bands, extracting target spectral features required for calculating the plant characteristic parameters; Based on the mapping relationship between spectral features and plant features, a plurality of plant feature parameters are obtained by converting the target spectral features.

4. The method according to claim 1, characterized in that: The training process of the prediction model includes: Collect sample spectrum data, sample sweetness and sample crispness of kumquat samples; Performing data analysis based on the sample spectral data to obtain a variety of sample plant characteristic parameters; Constructing a training set and a test set based on a plurality of the sample plant characteristic parameters, the sample sweetness and the sample crispness; The initial model is trained based on the training set and the test set to obtain the prediction model.

5. The method according to claim 1, characterized in that The method of performing nutritional data analysis on the Crispy Honey Kumquat Tree based on the predicted sweetness, the predicted crispness, the growth soil data and the reference nutritional information to generate nutritional control suggestion information includes: Inputting the predicted sweetness and the predicted crispness into a nutrition and sweetness and crispness relationship model to obtain the predicted nutritional information of the Crispy Honey Kumquat tree output by the nutrition and sweetness and crispness relationship model; Comparing the predicted nutritional information with the reference nutritional information to obtain nutritional difference information; The nutrient control recommendation information is determined based on the nutrient balance information, the growth soil data and the nutrient utilization data of the Crisp Honey Kumquat tree.

6. The method according to claim 1, characterized in that The nutrition control suggestion information includes adjusting the element type of the nutrient element to be supplemented to a target type, and / or adjusting the water-fertilizer ratio of the nutrient element to be supplemented to a set ratio.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Monitor the sweetness and crispness of the Crisp Honey Kumquat; When the growth time of the crisp honey kumquat has reached the expected harvest time and the predicted sweetness and / or the predicted crispness do not meet the standard, output harvest prompt information for prompting harvesting, and obtain harvest spectral data, harvest nutritional information, harvest sweetness and harvest crispness of the harvested crisp honey kumquat; Based on the harvested spectral data, the harvested sweetness and the harvested crispness, and the predicted sweetness and the predicted crispness, the prediction model is optimized and trained; Based on the harvested nutritional information, the harvested sweetness, the harvested crispness, and the predicted nutritional information obtained by predicting the nutrition and sweetness and crispness relationship model based on the predicted sweetness and the predicted crispness, the nutrition and sweetness and crispness relationship model is optimized and trained.

8. A device for optimizing the sweetness and crispness of crispy kumquat, characterized in that: include: An acquisition module is used to obtain the spectrum data and growth soil data of the Crisp Honey Kumquat tree; A spectral analysis module, used to perform data analysis based on the spectral data to obtain a variety of plant characteristic parameters; A prediction module, used for inputting a plurality of the plant characteristic parameters into a prediction model to obtain predicted sweetness and predicted crispness; A nutrition analysis module, used for performing nutrition data analysis on the Crispy Honey Kumquat tree based on the predicted sweetness, the predicted crispness, the growth soil data and reference nutrition information, and generating nutrition control suggestion information; The sending module is used to send the nutrition control suggestion information to the fertilization control system.

9. A terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images