A method and system for orchard supervision based on fruit tree nutrition diagnosis

Acquire orchard data through sensor networks and remote sensing systems, build an analysis model and correct the growth status of fruit trees, calculate the actual nutritional difference value, and determine the orchard regulation strategy. This solves the problem of inaccurate evaluation of fruit trees growth status and improves the dynamic and accurate orchard management of orchard management sex.

CN118761511BActive Publication Date: 2024-11-19SUZHOU LANGHE AGRI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411220484.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-02
Publication Date
2024-11-19
Estimated Expiration
2044-09-02

AI Technical Summary

Technical Problem

In the prior art, the evaluation of fruit tree growth status is not dynamic and precise enough, and it is difficult to reflect fruit tree growth needs in real time, resulting in low orchard management efficiency and lack of orchard supervision and regulation strategies customized based on actual nutritional differences.

Method used

The sensor network and satellite or drone remote sensing system are used to obtain orchard environment and growth data, and the fruit tree growth potential analysis model and environmental analysis model are constructed. Through the correction of temperature, humidity, light, and wind speed errors, the actual nutritional difference value of the fruit tree is calculated and determined based on the difference value. Orchard supervision and control strategies, using three-dimensional simulation digital orchard platform to visualize and update in real time.

Benefits of technology

Accurate assessment and real-time tracking of fruit tree growth status are achieved, timely adjustment of management strategies is made, the accuracy and efficiency of orchard management are improved, and the impact of the external environment on nutritional needs assessment is reduced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118761511B_ABST
    Figure CN118761511B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of online monitoring of fruit trees, and is an orchard supervision method and system based on fruit tree nutrition diagnosis, and the specific method includes: obtaining orchard environmental data and fruit tree growth data; constructing a fruit tree growth analysis model, and dynamically evaluating the growth status of fruit trees; constructing an environmental analysis model according to the orchard environmental data, extracting the actual nutritional difference of fruit trees, and determining the corresponding orchard supervision and control strategy according to the actual nutritional value of fruit trees, and constructing a three-dimensional simulation digital orchard platform, and visualizing the actual nutritional difference of fruit trees and the corresponding orchard supervision and control strategy in real time, and updating them to the three-dimensional simulation digital orchard platform in real time. The present invention solves the problem in the prior art that the evaluation of the growth status of fruit trees may not be dynamic and accurate enough, it is difficult to reflect the growth needs of fruit trees in real time, and there is a lack of an orchard supervision and control strategy customized according to the actual nutritional difference, resulting in low orchard management efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of online monitoring of fruit trees, and relates to an orchard supervision method and system based on fruit tree nutrition diagnosis. Background Art

[0002] In the existing disclosed invention technology, for example, a Chinese patent with publication number CN114128608A discloses an orchard irrigation management method and system, wherein the method comprises: determining sensitive parameters to be corrected in the World Food Research WOFOST model; optimizing the effective photosynthetic leaf area index and photosynthesis module of the WOFOST model by establishing a piecewise equation for the effective photosynthetic leaf area index; correcting the sensitive parameters to be corrected in the optimized WOFOST model to complete the improvement of the WOFOST model; inputting the set basic soil property parameters and meteorological information into the improved WOFOST model to obtain a water stress coefficient; determining the water demand of the fruit tree based on the water stress coefficient, and implementing orchard irrigation management according to the water demand of the fruit tree.

[0003] The above patent is highly dependent on the accuracy and reliability of the WOFOST model. If the parameter settings in the model or the photosynthetic leaf area index segmentation equation are biased, the predicted water stress coefficient may be inaccurate, affecting the effect of irrigation management, and the applicability of the above patent may be limited by factors such as geographical location and climatic conditions. Summary of the invention

[0004] The present invention aims to address the problems in the prior art that the assessment of the growth status of fruit trees may not be dynamic and accurate enough, making it difficult to reflect the growth needs of fruit trees in real time, and lacks an orchard supervision and control strategy customized according to actual nutritional differences, resulting in low orchard management efficiency. An orchard supervision method and system based on fruit tree nutritional diagnosis are proposed.

[0005] In order to achieve the above object, the technical solution of an orchard supervision method based on fruit tree nutrition diagnosis of the present invention comprises the following steps:

[0006] S1: Establish a sensor network and obtain orchard environmental data through the sensor network, and obtain fruit tree growth data through satellite and drone remote sensing systems;

[0007] S2: Construct a fruit tree growth analysis model based on the orchard fruit tree growth data to dynamically evaluate the growth status of the fruit trees;

[0008] S3: Build an environmental analysis model based on the orchard environmental data, correct the evaluation results of the fruit tree growth status through temperature and humidity errors, light errors and wind speed errors, and calculate the actual nutritional difference of the fruit trees;

[0009] S4: extracting the actual nutritional difference of the fruit trees according to S2-S3, and determining the corresponding orchard supervision and control strategy according to the actual nutritional difference of the fruit trees;

[0010] S5: Build a three-dimensional simulated digital orchard platform to visualize the actual nutritional differences of fruit trees and the corresponding orchard supervision and control strategies in real time, and update them to the three-dimensional simulated digital orchard platform in real time.

[0011] Specifically, S1 includes the following specific steps:

[0012] S11: Design the layout of sensors according to the terrain and distribution of fruit trees in the orchard;

[0013] S12: Acquire the ambient temperature data, ambient humidity data, ambient light data and ambient wind speed data of the environment where the fruit tree is located in real time through the temperature sensor, humidity sensor, optical sensor and wind sensor respectively;

[0014] S13: At the same time, fruit tree growth data is obtained through a satellite or UAV remote sensing system, wherein the fruit tree growth data includes: crown height data, branch growth data and leaf growth image data of the fruit tree.

[0015] Specifically, S2 includes the following specific steps:

[0016] S21: extracting the growth data of fruit trees in the orchard and establishing a three-dimensional model of the fruit trees;

[0017] S22: The crown of the fruit tree is evenly divided into N data collection layers according to the crown height data H, wherein the thickness of each data collection layer in the three-dimensional model of the fruit tree is , is an integer;

[0018] S23: extracting the growth data of the branches of the fruit trees, and importing the growth data of the branches of the fruit trees into the nutrition evaluation strategy of the branches of the fruit trees to calculate the nutrition difference of the branches of the fruit trees. The nutrition evaluation strategy of the branches of the fruit trees is as follows:

[0019] ;

[0020] in:

[0021] In the three-dimensional model of the fruit tree, the total number of branches of the fruit tree in the nth data collection layer is X;

[0022] is the nutrient difference between branches and trunks of the fruit tree at the nth data collection layer in the three-dimensional model of the fruit tree;

[0023] is the branch diameter of the x-th fruit tree branch; is the mean diameter of the fruit tree trunk in the nth data collection layer;

[0024] is the length of the branch of the x-th fruit tree; is the mean length of the branches of the fruit trees in the nth data collection layer;

[0025] is the number of branches of the x-th fruit tree trunk; is the mean number of branches of fruit tree trunks in the nth data collection layer;

[0026] These are the coefficients of influence of branch diameter, branch length and number of branches of fruit tree branches on the nutritional difference of branches.

[0027] Specifically, S2 also includes the following specific steps:

[0028] S24: extracting fruit tree leaf growth image data, performing image preprocessing on the fruit tree leaf growth image data, and extracting leaf feature data of the preprocessed fruit tree leaf growth image; the image preprocessing includes: enhancing the contrast of the fruit tree leaf growth image, and graying the fruit tree leaf growth image after the contrast enhancement;

[0029] S25: Construct a leaf area classification and recognition model through the three convolutional layers in the leaf area classification and recognition model The target area is divided for the fruit tree leaf growth image respectively, wherein the threshold processing of the fruit tree leaf growth image in the convolution layer includes:

[0030] Among them, the convolutional layer Used to identify leaf wrinkle areas in fruit tree leaf growth images, convolutional layer The threshold processing formula in is h i ( x i , y i ) ∈ [ H ( U ) min , H ( U ) max ] ;

[0031] Convolutional Layer Used to identify leaf insect damage areas in fruit tree leaf growth images, convolutional layer The threshold processing formula in is h i ( x i , y i ) ∈ [ H ( V ) min , H ( V ) max ] ;

[0032] Convolutional Layer Used to identify healthy leaf areas in fruit tree leaf growth images, convolutional layer The threshold processing formula in is h i ( x i , y i ) ∈ [ H ( V ) max , H ( U ) min ] ;

[0033] The target area division standard is: a threshold interval of the target area is preset, and when the gray value of a certain pixel point in the fruit tree leaf growth image belongs to the threshold interval, the pixel point belongs to the target area;

[0034] The coordinates are The gray value of the pixel;

[0035] They are the minimum grayscale threshold and the maximum grayscale threshold of the leaf wrinkle area respectively; They are the minimum grayscale threshold and the maximum grayscale threshold of the leaf pest area respectively.

[0036] Specifically, S2 also includes the following specific steps:

[0037] S26: Importing the leaf feature data into the fruit tree leaf nutrition assessment strategy to calculate the fruit tree leaf nutrition difference, the fruit tree leaf nutrition assessment strategy is as follows:

[0038] ;

[0039] in, They are leaf color assessment contribution factor, leaf wrinkle assessment contribution factor and leaf insect pest assessment contribution factor;

[0040] In the three-dimensional model of the fruit tree, the total number of leaves on the x-th fruit tree branch is Y;

[0041] is the nutrient difference of fruit tree leaves at the nth data collection layer in the three-dimensional model of fruit trees;

[0042] is the gray value of the yth leaf on the xth branch; is the grayscale mean of all leaves on the x-th branch;

[0043] According to S25, the yth leaf on the xth branch is identified to obtain U1 leaf wrinkle area and V1 leaf insect damage area;

[0044] is the wrinkle degree value of the yth leaf on the xth branch;

[0045] , is the gray value maximum point of the u1th leaf wrinkle area; The closest to all leaf fold areas Gray value of

[0046] is the insect damage degree value of the yth leaf on the xth branch;

[0047] , is the gray value maximum point of the v1th leaf insect-infested area; The closest to all leaf pest areas Gray value of

[0048] S27: Import the nutrient difference value of the fruit tree trunk and the nutrient difference value of the fruit tree leaves into the fruit tree growth status evaluation strategy, and calculate and obtain the fruit tree growth status value Y. The calculation formula of the fruit tree growth status value is: .

[0049] Specifically, S3 includes the following specific steps:

[0050] S31: according to the growth characteristics of the fruit tree species, obtain the standard growth environment data of the target growth of the fruit tree under laboratory conditions;

[0051] S32: Acquire the ambient temperature data, ambient humidity data, ambient light data and ambient wind speed data of the environment where the fruit tree is located in real time through the temperature sensor, humidity sensor, optical sensor and wind sensor respectively;

[0052] S33: Correct the evaluation result of the growth status of the fruit tree by using the temperature and humidity error, the light error and the wind speed error, and calculate the actual nutritional difference of the fruit tree. The calculation strategy of the actual nutritional difference of the fruit tree is as follows:

[0053] Y ′ = Y × [ α 0 + α 1 × w × RH w ′ × R H ′ + α 2 × ( 29 . 15 ∑ n = 1 gz n g z ′ n + 43 . 98 ∑ n = 1 fs n f s ′ n )] ;

[0054] in, is the actual nutritional difference of the fruit tree; All are multiple regression coefficients;

[0055] The ambient temperature data and ambient humidity data of the environment where the fruit trees are located;

[0056] It is the ambient temperature data and ambient humidity data under the standard environment of the fruit tree laboratory;

[0057] The ambient light data and ambient wind speed data of the environment where the fruit trees are located in the nth data collection layer;

[0058] It is the ambient light data and ambient wind speed data of fruit trees in the standard laboratory environment in the nth data collection layer.

[0059] Specifically, S4 includes the following specific steps:

[0060] S41: extracting the actual nutritional difference of fruit trees;

[0061] S42: Dynamically preset the actual nutrient difference threshold of the fruit tree;

[0062] When the actual nutrient difference of the fruit tree is less than or equal to the actual nutrient difference threshold of the fruit tree, the fruit tree is judged to be in a self-healing state and no manual intervention is required;

[0063] When the actual nutrient difference of a fruit tree is greater than the actual nutrient difference threshold of a fruit tree, the fruit tree is judged to be in a state to be repaired, and the corresponding fruit tree irrigation and fertilization strategy needs to be executed through the orchard expert prior knowledge base.

[0064] In addition, the orchard supervision system based on fruit tree nutrition diagnosis of the present invention includes the following modules: data acquisition module, growth analysis module, environment analysis module, supervision strategy execution module, digital orchard platform construction module;

[0065] The data acquisition module is used to establish a sensor network and obtain orchard environmental data through the sensor network, and simultaneously obtain fruit tree growth data through satellite and drone remote sensing systems;

[0066] The growth analysis module constructs a fruit tree growth analysis model based on the orchard fruit tree growth data to dynamically evaluate the growth status of the fruit trees;

[0067] The environmental analysis module constructs an environmental analysis model based on the orchard environmental data, corrects the evaluation results of the fruit tree growth status through temperature and humidity errors, light errors and wind speed errors, and calculates the actual nutritional difference of the fruit trees;

[0068] The supervision strategy execution module is used to extract the actual nutritional difference of the fruit trees and determine the corresponding orchard supervision and control strategy according to the actual nutritional difference of the fruit trees;

[0069] The digital orchard platform construction module is used to construct a three-dimensional simulated digital orchard platform, visualize the actual nutritional differences of fruit trees and the corresponding orchard supervision and control strategies in real time, and update them to the three-dimensional simulated digital orchard platform in real time.

[0070] The digital orchard platform construction module also includes: a nutrient difference update unit, an orchard supervision and control strategy update unit, a water and fertilizer irrigation status display unit, a historical processing record unit and an automatic early warning unit; the nutrient difference update unit is used to monitor and analyze the nutrient status of soil and plants, and update the nutrient difference in real time; the orchard supervision and control strategy update unit is used to monitor the overall condition of the orchard in real time, and update and adjust the management strategy according to the monitoring data; the water and fertilizer irrigation status display unit is used to display the current water and fertilizer irrigation status; the historical processing record unit is used to optimize the orchard control plan according to the historical processing records; the automatic early warning unit is used to monitor abnormal conditions in the orchard in real time.

[0071] A storage medium stores instructions, and when a computer reads the instructions, the computer executes the above-mentioned orchard supervision method based on fruit tree nutrition diagnosis.

[0072] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned orchard supervision method based on fruit tree nutrition diagnosis when executing the computer program.

[0073] Compared with the prior art, the technical effects of the present invention are as follows:

[0074] 1. The present invention combines sensor networks, satellites and drone remote sensing systems, and the solution can comprehensively obtain orchard environmental data and fruit tree growth data, thereby ensuring the comprehensiveness and accuracy of the information, and facilitating more accurate analysis and evaluation of the actual conditions of the fruit trees.

[0075] 2. The present invention can track the growth status of fruit trees in real time and adjust management strategies in time to adapt to environmental changes and the growth needs of fruit trees by dynamically constructing and adjusting the fruit tree growth analysis model and the environmental analysis model.

[0076] 3. The present invention improves the accuracy of fruit tree growth status assessment by correcting temperature, humidity, light and wind speed errors. This refined correction can effectively reduce the impact of the external environment on the fruit tree nutritional demand assessment.

[0077] 4. The present invention utilizes a three-dimensional simulation digital orchard platform to visualize real-time data and management strategies, so that orchard managers can intuitively understand the condition of fruit trees and the effects of regulation, thereby improving the convenience of decision-making and the accuracy of management. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0079] Figure 1 A schematic diagram of a process of an orchard supervision method based on fruit tree nutrition diagnosis of the present invention;

[0080] Figure 2 It is a structural schematic diagram of an orchard supervision system based on fruit tree nutrition diagnosis of the present invention;

[0081] Figure 3 It is a flow chart of the data acquisition method of the present invention;

[0082] Figure 4 It is a structural schematic diagram of the digital orchard platform building module of the present invention. DETAILED DESCRIPTION

[0083] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0084] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0085] Embodiment 1

[0086] like Figure 1 As shown, an orchard supervision method based on fruit tree nutrition diagnosis according to an embodiment of the present invention is as follows: Figure 1 As shown, the specific steps are as follows:

[0087] S1: Establish a sensor network and obtain orchard environmental data through the sensor network, and obtain fruit tree growth data through satellite and drone remote sensing systems;

[0088] like Figure 3 As shown, S1 includes the following steps:

[0089] S11: Design the layout of sensors according to the terrain and distribution of fruit trees in the orchard;

[0090] S12: Acquire the ambient temperature data, ambient humidity data, ambient light data and ambient wind speed data of the environment where the fruit tree is located in real time through the temperature sensor, humidity sensor, optical sensor and wind sensor respectively;

[0091] S13: At the same time, fruit tree growth data is obtained through a satellite or UAV remote sensing system, wherein the fruit tree growth data includes: crown height data, branch growth data and leaf growth image data of the fruit tree.

[0092] S2: Construct a fruit tree growth analysis model based on the orchard fruit tree growth data to dynamically evaluate the growth status of the fruit trees;

[0093] S21: extracting the growth data of fruit trees in the orchard and establishing a three-dimensional model of the fruit trees;

[0094] S22: The crown of the fruit tree is evenly divided into N data collection layers according to the crown height data H, wherein the thickness of each data collection layer in the three-dimensional model of the fruit tree is , is an integer;

[0095] S23: extracting the growth data of the branches of the fruit trees, and importing the growth data of the branches of the fruit trees into the nutrition evaluation strategy of the branches of the fruit trees to calculate the nutrition difference of the branches of the fruit trees. The nutrition evaluation strategy of the branches of the fruit trees is as follows:

[0096] ;

[0097] in:

[0098] In the three-dimensional model of the fruit tree, the total number of branches of the fruit tree in the nth data collection layer is X;

[0099] is the nutrient difference between branches and trunks of the fruit tree at the nth data collection layer in the three-dimensional model of the fruit tree;

[0100] is the branch diameter of the x-th fruit tree branch; is the mean diameter of the fruit tree trunk in the nth data collection layer;

[0101] is the length of the branch of the x-th fruit tree; is the mean length of the branches of the fruit trees in the nth data collection layer;

[0102] is the number of branches of the x-th fruit tree trunk; is the mean number of branches of fruit tree trunks in the nth data collection layer;

[0103] These are the coefficients of influence of branch diameter, branch length and number of branches of fruit tree branches on the nutritional difference of branches.

[0104] S24: extracting fruit tree leaf growth image data, performing image preprocessing on the fruit tree leaf growth image data, and extracting leaf feature data of the preprocessed fruit tree leaf growth image; the image preprocessing includes: enhancing the contrast of the fruit tree leaf growth image, and graying the fruit tree leaf growth image after the contrast enhancement;

[0105] S25: Construct a leaf area classification and recognition model through the three convolutional layers in the leaf area classification and recognition model The target area is divided for the fruit tree leaf growth image respectively, wherein the threshold processing of the fruit tree leaf growth image in the convolution layer includes:

[0106] Among them, the convolutional layer Used to identify leaf wrinkle areas in fruit tree leaf growth images, convolutional layer The threshold processing formula in is h i ( x i , y i ) ∈ [ H ( U ) min , H ( U ) max ] ;

[0107] Convolutional Layer Used to identify leaf insect damage areas in fruit tree leaf growth images, convolutional layer The threshold processing formula in is h i ( x i , y i ) ∈ [ H ( V ) min , H ( V ) max ] ;

[0108] Convolutional Layer Used to identify healthy leaf areas in fruit tree leaf growth images, convolutional layer The threshold processing formula in is h i ( x i , y i ) ∈ [ H ( V ) max , H ( U ) min ] ;

[0109] The target area division standard is: a threshold interval of the target area is preset, and when the gray value of a certain pixel point in the fruit tree leaf growth image belongs to the threshold interval, the pixel point belongs to the target area;

[0110] The coordinates are The gray value of the pixel;

[0111] They are the minimum grayscale threshold and the maximum grayscale threshold of the leaf wrinkle area respectively; They are the minimum grayscale threshold and the maximum grayscale threshold of the leaf pest area respectively.

[0112] S26: Importing the leaf feature data into the fruit tree leaf nutrition assessment strategy to calculate the fruit tree leaf nutrition difference, the fruit tree leaf nutrition assessment strategy is as follows:

[0113] ;

[0114] in, They are leaf color assessment contribution factor, leaf wrinkle assessment contribution factor and leaf insect pest assessment contribution factor;

[0115] In the three-dimensional model of the fruit tree, the total number of leaves on the x-th fruit tree branch is Y;

[0116] is the nutrient difference of fruit tree leaves at the nth data collection layer in the three-dimensional model of fruit trees;

[0117] is the gray value of the yth leaf on the xth branch; is the grayscale mean of all leaves on the x-th branch;

[0118] According to S25, the yth leaf on the xth branch is identified to obtain U1 leaf wrinkle area and V1 leaf insect damage area;

[0119] is the wrinkle degree value of the yth leaf on the xth branch;

[0120] , is the gray value maximum point of the u1th leaf wrinkle area; The closest to all leaf fold areas Gray value of

[0121] is the insect damage degree value of the yth leaf on the xth branch;

[0122] , is the gray value maximum point of the v1th leaf insect-infested area; The closest to all leaf pest areas Gray value of

[0123] S27: Import the nutrient difference value of the fruit tree trunk and the nutrient difference value of the fruit tree leaves into the fruit tree growth status evaluation strategy, and calculate and obtain the fruit tree growth status value Y. The calculation formula of the fruit tree growth status value is: .

[0124] S3: Build an environmental analysis model based on the orchard environmental data, correct the evaluation results of the fruit tree growth status through temperature and humidity errors, light errors and wind speed errors, and calculate the actual nutritional difference of the fruit trees;

[0125] S3 includes the following specific steps:

[0126] S31: according to the growth characteristics of the fruit tree species, obtain the standard growth environment data of the target growth of the fruit tree under laboratory conditions;

[0127] S32: Acquire the ambient temperature data, ambient humidity data, ambient light data and ambient wind speed data of the environment where the fruit tree is located in real time through the temperature sensor, humidity sensor, optical sensor and wind sensor respectively;

[0128] S33: Correct the evaluation result of the growth status of the fruit tree by using the temperature and humidity error, the light error and the wind speed error, and calculate the actual nutritional difference of the fruit tree. The calculation strategy of the actual nutritional difference of the fruit tree is as follows:

[0129] Y ′ = Y × [ α 0 + α 1 × w × RH w ′ × R H ′ + α 2 × ( 29 . 15 ∑ n = 1 gz n g z ′ n + 43 . 98 ∑ n = 1 fs n f s ′ n )] ;

[0130] in, is the actual nutritional difference of the fruit tree; All are multiple regression coefficients;

[0131] The ambient temperature data and ambient humidity data of the environment where the fruit trees are located;

[0132] It is the ambient temperature data and ambient humidity data under the standard environment of the fruit tree laboratory;

[0133] The ambient light data and ambient wind speed data of the environment where the fruit trees are located in the nth data collection layer;

[0134] It is the ambient light data and ambient wind speed data of fruit trees in the standard laboratory environment in the nth data collection layer.

[0135] S4: extracting the actual nutritional difference of the fruit trees according to S2-S3, and determining the corresponding orchard supervision and control strategy according to the actual nutritional difference of the fruit trees;

[0136] S4 includes the following specific steps:

[0137] S41: extracting the actual nutritional difference of fruit trees;

[0138] S42: Dynamically preset the actual nutrient difference threshold of the fruit tree;

[0139] When the actual nutrient difference of the fruit tree is less than or equal to the actual nutrient difference threshold of the fruit tree, the fruit tree is judged to be in a self-healing state and no manual intervention is required;

[0140] When the actual nutrient difference of a fruit tree is greater than the actual nutrient difference threshold of a fruit tree, the fruit tree is judged to be in a state to be repaired, and the corresponding fruit tree irrigation and fertilization strategy needs to be executed through the orchard expert prior knowledge base.

[0141] S5: Build a three-dimensional simulated digital orchard platform to visualize the actual nutritional differences of fruit trees and the corresponding orchard supervision and control strategies in real time, and update them to the three-dimensional simulated digital orchard platform in real time.

[0142] Embodiment 2

[0143] like Figure 2 As shown, an orchard supervision system based on fruit tree nutrition diagnosis according to an embodiment of the present invention is as follows: Figure 2 As shown, it includes the following modules:

[0144] Data acquisition module, growth analysis module, environmental analysis module, supervision strategy execution module, and digital orchard platform construction module;

[0145] The data acquisition module is used to establish a sensor network and obtain orchard environmental data through the sensor network, and simultaneously obtain fruit tree growth data through satellite and drone remote sensing systems;

[0146] The growth analysis module constructs a fruit tree growth analysis model based on the orchard fruit tree growth data to dynamically evaluate the growth status of the fruit trees;

[0147] The environmental analysis module constructs an environmental analysis model based on the orchard environmental data, corrects the evaluation results of the fruit tree growth status through temperature and humidity errors, light errors and wind speed errors, and calculates the actual nutritional difference of the fruit trees;

[0148] The supervision strategy execution module is used to extract the actual nutritional difference of the fruit trees and determine the corresponding orchard supervision and control strategy according to the actual nutritional difference of the fruit trees;

[0149] The digital orchard platform construction module is used to construct a three-dimensional simulated digital orchard platform, visualize the actual nutritional differences of fruit trees and the corresponding orchard supervision and control strategies in real time, and update them to the three-dimensional simulated digital orchard platform in real time.

[0150] like Figure 4 As shown, the digital orchard platform construction module also includes: a nutrient difference update unit, an orchard supervision and control strategy update unit, a water and fertilizer irrigation status display unit, a historical processing record unit and an automatic early warning unit; the nutrient difference update unit is used to monitor and analyze the nutrient status of soil and plants, and update the nutrient difference in real time; the orchard supervision and control strategy update unit is used to monitor the overall condition of the orchard in real time, and update and adjust the management strategy according to the monitoring data; the water and fertilizer irrigation status display unit is used to display the current water and fertilizer irrigation status; the historical processing record unit is used to optimize the orchard control plan according to the historical processing records; the automatic early warning unit is used to monitor abnormal conditions in the orchard in real time.

[0151] Embodiment 3

[0152] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0153] The processor executes the above-mentioned orchard supervision method based on fruit tree nutrition diagnosis by calling the computer program stored in the memory.

[0154] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement an orchard supervision method based on fruit tree nutrition diagnosis provided by the above method embodiment. The electronic device may also include other components for realizing the functions of the device. For example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0155] Embodiment 4

[0156] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0157] When the computer program runs on a computer device, the computer device executes the above-mentioned orchard supervision method based on fruit tree nutrition diagnosis.

[0158] For example, the computer readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0159] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0160] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0161] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0162] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention 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 the present invention.

[0163] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0164] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only one, and 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.

[0165] 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.

[0166] In addition, each functional unit in each embodiment of the present invention 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.

[0167] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0168] In summary, compared with the prior art, the technical effects of the present invention are as follows:

[0169] 1. The present invention combines sensor networks, satellites and drone remote sensing systems, and the solution can comprehensively obtain orchard environmental data and fruit tree growth data, thereby ensuring the comprehensiveness and accuracy of the information, and facilitating more accurate analysis and evaluation of the actual conditions of the fruit trees.

[0170] 2. The present invention can track the growth status of fruit trees in real time and adjust management strategies in time to adapt to environmental changes and the growth needs of fruit trees by dynamically constructing and adjusting the fruit tree growth analysis model and the environmental analysis model.

[0171] 3. The present invention improves the accuracy of fruit tree growth status assessment by correcting temperature, humidity, light and wind speed errors. This refined correction can effectively reduce the impact of the external environment on the fruit tree nutritional demand assessment.

[0172] 4. The present invention utilizes a three-dimensional simulation digital orchard platform to visualize real-time data and management strategies, so that orchard managers can intuitively understand the condition of fruit trees and the effects of regulation, thereby improving the convenience of decision-making and the accuracy of management.

[0173] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. An orchard supervision method based on fruit tree nutrition diagnosis, characterized in that: The method comprises the following specific steps: S1: Establish a sensor network and obtain orchard environmental data through the sensor network, and obtain fruit tree growth data through satellite and drone remote sensing systems; S2: Construct a fruit tree growth analysis model based on the orchard fruit tree growth data to dynamically evaluate the fruit tree growth status value; S3: Build an environmental analysis model based on the orchard environmental data, correct the evaluation results of the fruit tree growth status through temperature and humidity errors, light errors and wind speed errors, and calculate the actual nutritional difference of the fruit trees; S4: extracting the actual nutritional difference of the fruit trees according to S2-S3, and determining the corresponding orchard supervision and control strategy according to the actual nutritional difference of the fruit trees; S5: Build a three-dimensional simulation digital orchard platform to visualize the actual nutritional difference of fruit trees and the corresponding orchard supervision and control strategies in real time, and update them to the three-dimensional simulation digital orchard platform in real time; S2 includes the following specific steps: S21: extracting the growth data of fruit trees in the orchard and establishing a three-dimensional model of the fruit trees; S22: The crown of the fruit tree is evenly divided into N data collection layers according to the crown height data H, wherein the thickness of each data collection layer in the three-dimensional model of the fruit tree is , is an integer; S23: extracting the growth data of the branches of the fruit trees, and importing the growth data of the branches of the fruit trees into the nutrition evaluation strategy of the branches of the fruit trees to calculate the nutrition difference of the branches of the fruit trees. The nutrition evaluation strategy of the branches of the fruit trees is as follows: ; in: In the three-dimensional model of the fruit tree, the total number of branches of the fruit tree in the nth data collection layer is X; is the nutrient difference between branches and trunks of the fruit tree at the nth data collection layer in the three-dimensional model of the fruit tree; is the branch diameter of the x-th fruit tree branch; is the mean diameter of the fruit tree trunk in the nth data collection layer; is the length of the branch of the x-th fruit tree; is the mean length of the branches of the fruit trees in the nth data collection layer; is the number of branches of the x-th fruit tree trunk; is the mean number of branches of fruit tree trunks in the nth data collection layer; They are the coefficients of influence of branch diameter, branch length and number of branches on the branch nutrition difference of fruit tree branches; S2 also includes the following specific steps: S24: extracting fruit tree leaf growth image data, performing image preprocessing on the fruit tree leaf growth image data, and extracting leaf feature data of the preprocessed fruit tree leaf growth image; the image preprocessing includes: enhancing the contrast of the fruit tree leaf growth image, and graying the fruit tree leaf growth image after the contrast enhancement; S25: Construct a leaf area classification and recognition model through the three convolutional layers in the leaf area classification and recognition model The target area is divided for the fruit tree leaf growth image respectively, wherein the threshold processing of the fruit tree leaf growth image in the convolution layer includes: Among them, the convolutional layer Used to identify leaf wrinkle areas in fruit tree leaf growth images, convolutional layer The threshold processing formula in is ; Convolutional Layer Used to identify leaf insect damage areas in fruit tree leaf growth images, convolutional layer The threshold processing formula in is ; Convolutional Layer Used to identify healthy leaf areas in fruit tree leaf growth images, convolutional layer The threshold processing formula in is ; The target area division standard is: a threshold interval of the target area is preset, and when the gray value of a certain pixel point in the fruit tree leaf growth image belongs to the threshold interval, the pixel point belongs to the target area; The coordinates are The gray value of the pixel; They are the minimum grayscale threshold and the maximum grayscale threshold of the leaf wrinkle area respectively; They are the minimum grayscale threshold and the maximum grayscale threshold of the leaf pest area respectively; S2 also includes the following specific steps: S26: Importing the leaf feature data into the fruit tree leaf nutrition assessment strategy to calculate the fruit tree leaf nutrition difference, the fruit tree leaf nutrition assessment strategy is as follows: ; in, They are leaf color assessment contribution factor, leaf wrinkle assessment contribution factor and leaf insect pest assessment contribution factor; In the three-dimensional model of the fruit tree, the total number of leaves on the x-th fruit tree branch is Y; is the nutrient difference of fruit tree leaves at the nth data collection layer in the three-dimensional model of fruit trees; is the gray value of the yth leaf on the xth branch; is the grayscale mean of all leaves on the x-th branch; According to S25, the yth leaf on the xth branch is identified to obtain U1 leaf wrinkle area and V1 leaf insect damage area; is the wrinkle degree value of the yth leaf on the xth branch; , is the gray value maximum point of the u1th leaf wrinkle area; The closest to all leaf fold areas Gray value of is the insect damage degree value of the yth leaf on the xth branch; , is the gray value maximum point of the v1th leaf insect-infested area; The closest to all leaf pest areas Gray value of S27: Import the nutrient difference value of the fruit tree trunk and the nutrient difference value of the fruit tree leaves into the fruit tree growth status evaluation strategy, and calculate and obtain the fruit tree growth status value Y. The calculation formula of the fruit tree growth status value is: ; S3 includes the following specific steps: S31: according to the growth characteristics of the fruit tree species, obtain the standard growth environment data of the target growth of the fruit tree under laboratory conditions; S32: Acquire the ambient temperature data, ambient humidity data, ambient light data and ambient wind speed data of the environment where the fruit tree is located in real time through the temperature sensor, humidity sensor, optical sensor and wind sensor respectively; S33: Correct the evaluation result of the growth status of the fruit tree by using the temperature and humidity error, the light error and the wind speed error, and calculate the actual nutritional difference of the fruit tree. The calculation strategy of the actual nutritional difference of the fruit tree is as follows: ; in, is the actual nutritional difference of the fruit tree; All are multiple regression coefficients; The ambient temperature data and ambient humidity data of the environment where the fruit trees are located; It is the ambient temperature data and ambient humidity data under the standard environment of the fruit tree laboratory; The ambient light data and ambient wind speed data of the environment where the fruit trees are located in the nth data collection layer; It is the ambient light data and ambient wind speed data of fruit trees in the standard laboratory environment in the nth data collection layer.

2. The orchard supervision method based on fruit tree nutrition diagnosis according to claim 1, characterized in that: S1 includes the following specific steps: S11: Design the layout of sensors according to the terrain and distribution of fruit trees in the orchard; S12: Acquire the ambient temperature data, ambient humidity data, ambient light data and ambient wind speed data of the environment where the fruit tree is located in real time through the temperature sensor, humidity sensor, optical sensor and wind sensor respectively; S13: At the same time, fruit tree growth data is obtained through a satellite or UAV remote sensing system, wherein the fruit tree growth data includes: crown height data, branch growth data and leaf growth image data of the fruit tree.

3. The orchard supervision method based on fruit tree nutrition diagnosis according to claim 2 is characterized in that: S4 includes the following specific steps: S41: extracting the actual nutritional difference of fruit trees; S42: Dynamically preset the actual nutrient difference threshold of the fruit tree; When the actual nutrient difference of the fruit tree is less than or equal to the actual nutrient difference threshold of the fruit tree, the fruit tree is judged to be in a self-healing state and no manual intervention is required; When the actual nutrient difference of a fruit tree is greater than the actual nutrient difference threshold of a fruit tree, the fruit tree is judged to be in a state to be repaired, and the corresponding fruit tree irrigation and fertilization strategy needs to be executed through the orchard expert prior knowledge base.

4. An orchard supervision system based on fruit tree nutrition diagnosis, which is used to implement an orchard supervision method based on fruit tree nutrition diagnosis as described in any one of claims 1 to 3, characterized in that: The system includes the following modules: Data acquisition module, growth analysis module, environmental analysis module, supervision strategy execution module, and digital orchard platform construction module; The data acquisition module is used to establish a sensor network and obtain orchard environmental data through the sensor network, and simultaneously obtain fruit tree growth data through satellite and drone remote sensing systems; The growth analysis module constructs a fruit tree growth analysis model based on the orchard fruit tree growth data to dynamically evaluate the growth status of the fruit trees; The environmental analysis module constructs an environmental analysis model based on the orchard environmental data, corrects the evaluation results of the fruit tree growth status through temperature and humidity errors, light errors and wind speed errors, and calculates the actual nutritional difference of the fruit trees; The supervision strategy execution module is used to extract the actual nutritional difference of the fruit trees and determine the corresponding orchard supervision and control strategy according to the actual nutritional difference of the fruit trees; The digital orchard platform construction module is used to construct a three-dimensional simulated digital orchard platform, visualize the actual nutritional differences of fruit trees and the corresponding orchard supervision and control strategies in real time, and update them to the three-dimensional simulated digital orchard platform in real time.

5. The orchard supervision system based on fruit tree nutrition diagnosis according to claim 4 is characterized in that: The digital orchard platform construction module also includes: a nutrient difference update unit, an orchard supervision and control strategy update unit, a water and fertilizer irrigation status display unit, a historical processing record unit and an automatic early warning unit; the nutrient difference update unit is used to monitor and analyze the nutrient status of soil and plants, and update the nutrient difference in real time; the orchard supervision and control strategy update unit is used to monitor the overall condition of the orchard in real time, and update and adjust the management strategy according to the monitoring data; the water and fertilizer irrigation status display unit is used to display the current water and fertilizer irrigation status; the historical processing record unit is used to optimize the orchard control plan according to the historical processing records; the automatic early warning unit is used to monitor abnormal conditions in the orchard in real time.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, an orchard supervision method based on fruit tree nutrition diagnosis as described in any one of claims 1 to 3 is implemented.

7. An electronic device, characterized in that: include: A memory for storing instructions; A processor is used to execute the instructions so that the device performs operations to implement an orchard supervision method based on fruit tree nutrition diagnosis as described in any one of claims 1-3.