Control Method and System for an Automatic Mulberry Tree Harvesting Device

Abstract

The present invention relates to a control method and system for a mulberry tree automatic harvesting device, belonging to the technical field of mulberry tree automatic harvesting. The present invention obtains real-time image data information of mulberry trees through an image acquisition device installed on the mulberry tree automatic harvesting device during relevant recommended harvesting periods, and finally preprocesses the real-time image data information of the mulberry trees to obtain the image features of the mulberry branches of the mulberry trees. According to the image features of the mulberry branches of the mulberry trees, the working frequency and cutting working power of the mulberry tree automatic harvesting device are configured, and the mulberry tree automatic harvesting device is controlled according to the working frequency and cutting working power. By formulating the mulberry tree harvesting period and the working parameters of the mulberry tree automatic harvesting device according to the image features of the mulberry branches of the mulberry trees and the infection probability value when the mulberry branches of the mulberry trees are damaged within a preset time, the present invention can improve the control rationality of the mulberry tree automatic harvesting device and the rationality during the harvesting of mulberry trees.

Description

Technical Field

[0001] The present invention relates to the technical field of mulberry harvesting, and particularly to a control method and system for an automatic mulberry harvesting device. Background Art

[0002] Sericulture production is a traditional agriculture, which is characterized by strong seasonality, high labor intensity, and a large demand for labor in a short period of time. Currently, according to the physiological characteristics of mulberry trees, pruning methods are now adopted in Hezhou, Guangxi Zhuang Autonomous Region for sericulture. Compared with the traditional method of picking mulberry leaves for sericulture, it has higher efficiency and better adaptability to seasons. Especially in summer, when using the pruning method for sericulture, when there are many branches piled together, there are many gaps, which play a role in ventilation and heat dissipation, avoiding the problem that mulberry leaves are prone to heat and deterioration when piled together. The pruning method for sericulture improves labor efficiency and has good season adaptability, which is the development trend of the sericulture industry. After the mulberry trees are harvested, within 45 days, mulberry buds grow from the roots and grow into new mulberry trees, which can then be harvested. However, nowadays, during the mulberry harvesting process, firstly, it is impossible to switch the cutting power, cutting frequency, etc. according to the size of the mulberry branches, resulting in the failure of the automatic mulberry harvesting device to achieve the established goal during the harvesting process, requiring repeated cutting, with low cutting efficiency and high energy consumption. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a control method and system for an automatic mulberry harvesting device.

[0004] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0005] The first aspect of the present invention provides a control method for an automatic mulberry harvesting device, including the following steps:

[0006] Obtain the infection data when the mulberry branches are damaged under various temperature and humidity data of the mulberry trees through big data, and based on the infection data when the mulberry branches are damaged under various temperature and humidity data of the mulberry trees, statistically calculate the infection probability when the mulberry branches are damaged under various temperature and humidity data, and construct a knowledge graph based on the infection probability when the mulberry branches are damaged under various temperature and humidity data;

[0007] Obtain the temperature and humidity data of the current mulberry tree area within a preset time, and obtain the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time according to the temperature and humidity data of the current mulberry tree area within the preset time and the knowledge graph;

[0008] Determine the mulberry harvesting period according to the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time, and generate relevant recommended harvesting periods according to the mulberry harvesting period. Obtain the real-time image data information of the mulberry trees through the image acquisition device installed on the automatic mulberry harvesting device during the relevant recommended harvesting periods;

[0009] By preprocessing the real-time image data information of the mulberry tree, the image features of the mulberry branches are obtained. According to the image features of the mulberry branches of the mulberry tree, the working frequency and cutting power of the automatic mulberry tree harvesting device are configured, and the automatic mulberry tree harvesting device is controlled according to the working frequency and cutting power.

[0010] Further, in this method, the infection data when the mulberry branches are damaged under various temperature and humidity data of the mulberry tree is obtained through big data, and the infection probability when the mulberry branches are damaged under various temperature and humidity data is statistically calculated based on the infection data when the mulberry branches are damaged under various temperature and humidity data of the mulberry tree. Specifically:

[0011] The infection data when the mulberry branches are damaged under various temperature and humidity data of the mulberry tree is obtained through big data, and the number of infections and the number of non-infections when the mulberry branches are damaged under various temperature and humidity data are obtained according to the infection data when the mulberry branches are damaged under various temperature and humidity data of the mulberry tree;

[0012] The total number of statistics is calculated from the number of infections when the mulberry branches are damaged under each temperature and humidity data and the number of non-infections when the mulberry branches are damaged under each temperature and humidity data, and the number of infections when the mulberry branches are damaged under each temperature and humidity data is used as the numerator;

[0013] The total number of statistics is used as the denominator, the infection probability when the mulberry branches are damaged under each temperature and humidity data is statistically calculated, and the infection probability when the mulberry branches are damaged under each temperature and humidity data is output.

[0014] Further, in this method, a knowledge graph is constructed based on the infection probability when the mulberry branches are damaged under each temperature and humidity data, specifically including:

[0015] A knowledge graph is constructed, and several storage spaces are configured for the knowledge graph. The temperature and humidity data and the infection probability when the mulberry branches are damaged are used as nodes, and an undirected heterogeneous graph is constructed based on the nodes;

[0016] The undirected heterogeneous graph is input into the knowledge graph for storage, and node representation is performed on the knowledge graph.

[0017] Further, in this method, the temperature and humidity data within a preset time in the area where the current mulberry tree is located is obtained, and the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time is obtained according to the temperature and humidity data within a preset time in the area where the current mulberry tree is located and the knowledge graph. Specifically including:

[0018] The temperature and humidity data within a preset time in the area where the current mulberry tree is located is obtained, and the temperature and humidity data within a preset time in the area where the current mulberry tree is located is input into the knowledge graph for data matching;

[0019] Obtain the infection probability value when the mulberry branches are damaged within a preset time through data matching, and output the infection probability value when the mulberry branches are damaged within the preset time.

[0020] Further, in this method, formulate the mulberry harvesting period according to the infection probability value when the mulberry branches are damaged within the preset time, and generate relevant recommended harvesting periods according to the mulberry harvesting period, specifically including:

[0021] Set an infection probability threshold, and determine whether the infection probability value when the mulberry branches are damaged within the preset time is greater than the infection probability threshold;

[0022] Obtain the period when the infection probability value is not greater than the infection probability threshold, and use the period when the infection probability value is not greater than the infection probability threshold as the mulberry harvesting period;

[0023] Generate relevant recommended harvesting periods according to the mulberry harvesting period, display the relevant recommended harvesting periods in a preset manner, and control the automatic mulberry harvesting device to harvest during the relevant recommended harvesting periods.

[0024] Further, in this method, preprocess the real-time image data information of the mulberry tree to obtain the mulberry branch image features, specifically including:

[0025] Perform filtering and denoising processing on the real-time image data information of the mulberry tree to obtain preprocessed image data, and introduce a feature pyramid network, and input the preprocessed image data into the feature pyramid network for feature extraction;

[0026] Through feature extraction, obtain the mulberry branch contour feature data, and through contour reconstruction processing on the mulberry branch contour feature data, obtain the mulberry branch image features, and output the mulberry branch image features.

[0027] Further, in this method, configure the working frequency and cutting working power of the automatic mulberry harvesting device according to the mulberry branch image features of the mulberry tree, specifically including:

[0028] Construct a mulberry branch morphological feature model diagram according to the mulberry branch image features of the mulberry tree, and estimate the hardness feature data of the mulberry branches based on the mulberry branch morphological feature model diagram;

[0029] Initialize the working frequency and cutting working power of the automatic mulberry harvesting device based on the hardness feature data of the mulberry branches, and perform cutting simulation based on the working frequency and cutting working power of the automatic mulberry harvesting device;

[0030] Through cutting simulation, obtain the estimated cutting efficiency information of the mulberry tree automatic harvesting device, and determine whether the cutting efficiency is greater than a preset cutting efficiency threshold;

[0031] When the cutting efficiency is greater than the preset cutting efficiency threshold, perform cutting control according to the working frequency and cutting working power of the mulberry tree automatic harvesting device. When the cutting efficiency is not greater than the preset cutting efficiency threshold, increase the working frequency and cutting working power of the mulberry tree automatic harvesting device.

[0032] The second aspect of the present invention provides a control system for a mulberry tree automatic harvesting device, including a memory and a processor. The memory includes a control method program for the mulberry tree automatic harvesting device. When the control method program for the mulberry tree automatic harvesting device is executed by the processor, the steps of any one of the control methods for the mulberry tree automatic harvesting device are realized.

[0033] The third aspect of the present invention provides a computer-readable storage medium, including a control method program for the mulberry tree automatic harvesting device. When the control method program for the mulberry tree automatic harvesting device is executed by a processor, the steps of any one of the control methods for the mulberry tree automatic harvesting device are realized.

[0034] The present invention solves the defects existing in the background technology, and the present invention has the following beneficial effects:

[0035] The present invention obtains the infection data when the mulberry branches are damaged under various temperature and humidity data of the mulberry tree through big data, and statistically calculates the infection probability when the mulberry branches are damaged under various temperature and humidity data based on the infection data when the mulberry branches are damaged under various temperature and humidity data of the mulberry tree. A knowledge graph is constructed based on the infection probability when the mulberry branches are damaged under various temperature and humidity data, and then the temperature and humidity data within a preset time in the area where the current mulberry tree is located are obtained. According to the temperature and humidity data within a preset time in the area where the current mulberry tree is located and the knowledge graph, the infection probability value when the mulberry branches of the mulberry tree are damaged within a preset time is obtained. Thus, a mulberry tree harvesting period is formulated according to the infection probability value when the mulberry branches of the mulberry tree are damaged within a preset time, and a related recommended harvesting period is generated according to the mulberry tree harvesting period. In the related recommended harvesting period, real-time image data information of the mulberry tree is obtained through an image acquisition device installed on the mulberry tree automatic harvesting device. Finally, through preprocessing the real-time image data information of the mulberry tree, the mulberry branch image features of the mulberry tree are obtained. According to the mulberry branch image features of the mulberry tree, the working frequency and cutting working power of the mulberry tree automatic harvesting device are configured, and the mulberry tree automatic harvesting device is controlled according to the working frequency and cutting working power. By formulating the mulberry tree harvesting period and the working parameters of the mulberry tree automatic harvesting device according to the mulberry branch image features of the mulberry tree and the infection probability value when the mulberry branches of the mulberry tree are damaged within a preset time, the present invention can improve the control rationality of the mulberry tree automatic harvesting device and the rationality when the mulberry tree is harvested. Brief Description of the Drawings

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0037] Figure 1 Shows the overall flowchart of the control method of the automated mulberry harvesting device;

[0038] Figure 2 Shows a partial flowchart of the control method of the automated mulberry harvesting device;

[0039] Figure 3 Shows the system block diagram of the control system of the automated mulberry harvesting device. Detailed Description of the Embodiments

[0040] In order to more clearly understand the above-mentioned objects, features, and advantages of the present invention, the present invention will be further described in detail below in conjunction with the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0041] Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0042] As Figure 1 shown, the first aspect of the present invention provides a control method for an automated mulberry harvesting device, including the following steps:

[0043] S102: Obtain the infection data when the mulberry branches are damaged under various temperature and humidity data of the mulberry tree through big data, and based on the infection data when the mulberry branches are damaged under various temperature and humidity data of the mulberry tree, statistically calculate the infection probability when the mulberry branches are damaged under various temperature and humidity data, and construct a knowledge graph based on the infection probability when the mulberry branches are damaged under various temperature and humidity data;

[0044] S104: Obtain the temperature and humidity data of the current mulberry tree area within a preset time, and obtain the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time according to the temperature and humidity data of the current mulberry tree area within the preset time and the knowledge graph;

[0045] S106: Determine the mulberry harvesting period according to the infection probability value when the mulberry branches are damaged within a preset time, generate relevant recommended harvesting periods based on the mulberry harvesting period, and obtain real-time image data information of the mulberry trees through the image acquisition device installed on the mulberry automatic harvesting device during the relevant recommended harvesting periods;

[0046] S108: Preprocess the real-time image data information of the mulberry trees to obtain the image features of the mulberry branches, configure the working frequency and cutting working power of the mulberry automatic harvesting device according to the image features of the mulberry branches, and control the mulberry automatic harvesting device according to the working frequency and cutting working power.

[0047] It should be noted that by determining the mulberry harvesting period and the working parameters of the mulberry automatic harvesting device according to the image features of the mulberry branches and the infection probability value when the mulberry branches are damaged within a preset time, the present invention can improve the control rationality of the mulberry automatic harvesting device and the rationality during mulberry harvesting.

[0048] Furthermore, in this method, obtain the infection data when the mulberry branches are damaged under various temperature and humidity data of the mulberry trees through big data, and based on the infection data when the mulberry branches are damaged under various temperature and humidity data, statistically calculate the infection probability when the mulberry branches are damaged under various temperature and humidity data. Specifically:

[0049] Obtain the infection data when the mulberry branches are damaged under various temperature and humidity data of the mulberry trees through big data, and obtain the number of infected times and the number of non-infected times when the mulberry branches are damaged under various temperature and humidity data according to the infection data when the mulberry branches are damaged under various temperature and humidity data;

[0050] Statistically calculate the total number of statistical times for the number of infected times and the number of non-infected times when the mulberry branches are damaged under various temperature and humidity data, and use the number of infected times when the mulberry branches are damaged under various temperature and humidity data as the numerator;

[0051] Use the total number of statistical times as the denominator, statistically calculate the infection probability when the mulberry branches are damaged under various temperature and humidity data, and output the infection probability when the mulberry branches are damaged under various temperature and humidity data.

[0052] It should be noted that mechanical damage to mulberry branches (such as pruning, insect bites, wind and rain breaks) will form wounds, becoming the invasion channels for fungi, bacteria or viruses. For example: Mulberry blight (bacterial disease): It quickly invades through wounds, causing branch wilt. Mulberry twig blight (fungal disease): Conidia are spread by wind and rain and infect through wounds. Mulberry sclerotium blight: When the temperature is high and the humidity is high, the pathogen is easy to infect through wounds. Secondly, temperature and humidity also affect and accelerate the reproduction of pathogens, increasing the infection risk. Through this method, it is possible to obtain factors that will accelerate the reproduction of pathogens and increase the infection risk, so as to optimize the control of the mulberry automatic harvesting device.

[0053] Furthermore, in this method, a knowledge graph is constructed based on the infection probability when mulberry branches are damaged under various temperature and humidity data, specifically including:

[0054] Construct a knowledge graph, configure several storage spaces for the knowledge graph, use the temperature and humidity data and the infection probability when mulberry branches are damaged as nodes, and construct an undirected heterogeneous graph based on the nodes;

[0055] Input the undirected heterogeneous graph into the knowledge graph for storage, and perform node representation on the knowledge graph.

[0056] Furthermore, in this method, obtain the temperature and humidity data of the area where the current mulberry tree is located within a preset time, and obtain the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time according to the temperature and humidity data of the area where the current mulberry tree is located within the preset time and the knowledge graph, specifically including:

[0057] Obtain the temperature and humidity data of the area where the current mulberry tree is located within a preset time, and input the temperature and humidity data of the area where the current mulberry tree is located within the preset time into the knowledge graph for data matching;

[0058] Through data matching, obtain the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time, and output the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time.

[0059] Furthermore, in this method, formulate the mulberry tree harvesting period according to the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time, and generate relevant recommended harvesting periods according to the mulberry tree harvesting period, specifically including:

[0060] Set an infection probability threshold, and judge whether the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time is greater than the infection probability threshold;

[0061] Obtain the period when the infection probability value is not greater than the infection probability threshold, and use the period when the infection probability value is not greater than the infection probability threshold as the mulberry tree harvesting period;

[0062] Generate relevant recommended harvesting periods according to the mulberry tree harvesting period, display the relevant recommended harvesting periods in a preset manner, and control the automatic mulberry tree harvesting device to harvest during the relevant recommended harvesting periods.

[0063] It should be noted that through this method, relevant recommended harvesting periods can be generated, avoiding the infection of mulberry branches during periodic harvesting and improving the rationality of mulberry branch harvesting.

[0064] Furthermore, in this method, by preprocessing the real-time image data information of the mulberry tree, obtain the mulberry branch image features of the mulberry tree, specifically including:

[0065] By filtering and denoising the real-time image data information of mulberry trees, the preprocessed image data is obtained, and a Feature Pyramid Network is introduced. The preprocessed image data is input into the Feature Pyramid Network for feature extraction;

[0066] Through feature extraction, the contour feature data of the mulberry branches of the mulberry tree is obtained, and through contour reconstruction processing of the contour feature data of the mulberry branches of the mulberry tree, the image features of the mulberry branches of the mulberry tree are obtained, and the image features of the mulberry branches of the mulberry tree are output.

[0067] It should be noted that through this method, the image features of the mulberry branches of the mulberry tree are obtained to identify the size of the mulberry branches, and then the working frequency and cutting power of the mulberry tree harvester are configured according to the size of the mulberry branches.

[0068] As Figure 2 shown, further, in this method, the working frequency and cutting power of the mulberry tree automatic harvesting device are configured according to the image features of the mulberry branches of the mulberry tree, specifically including:

[0069] S202: Construct a morphological feature model diagram of the mulberry branches of the mulberry tree according to the image features of the mulberry branches of the mulberry tree, and estimate the hardness feature data of the mulberry branches of the mulberry tree based on the morphological feature model diagram of the mulberry branches of the mulberry tree;

[0070] S204: Initialize the working frequency and cutting power of the mulberry tree automatic harvesting device based on the hardness feature data of the mulberry branches of the mulberry tree, and perform cutting simulation based on the working frequency and cutting power of the mulberry tree automatic harvesting device;

[0071] S206: Through the cutting simulation, obtain the estimated cutting efficiency information of the mulberry tree automatic harvesting device, and judge whether the cutting efficiency is greater than the preset cutting efficiency threshold;

[0072] S208: When the cutting efficiency is greater than the preset cutting efficiency threshold, perform cutting control according to the working frequency and cutting power of the mulberry tree automatic harvesting device. When the cutting efficiency is not greater than the preset cutting efficiency threshold, increase the working frequency and cutting power of the mulberry tree automatic harvesting device.

[0073] It should be noted that through virtual reality technology and 3D modeling technology, cutting simulation is performed based on the working frequency and cutting power of the mulberry tree automatic harvesting device, which can simulate the estimated cutting efficiency information of the mulberry tree automatic harvesting device, so as to optimize the cutting working parameters of the mulberry tree automatic harvesting device and improve the rationality of cutting.

[0074] In addition, this method further includes the following steps:

[0075] Obtain the historical cutting performance characteristic change data of the cutting blade in the mulberry automated harvesting device through big data, construct a cutting performance characteristic prediction model based on a deep neural network, and input the historical cutting performance characteristic change data of the cutting blade in the mulberry automated harvesting device into the cutting performance characteristic prediction model for training;

[0076] Through training, obtain a trained cutting performance characteristic prediction model, and obtain the cutting performance characteristic change data of the cutting blade in the mulberry automated harvesting device within a preset time;

[0077] Input the cutting performance characteristic change data of the cutting blade in the mulberry automated harvesting device within the preset time into the trained cutting performance characteristic prediction model for prediction. Through prediction, obtain the cutting performance characteristic data of the cutting blade in the mulberry automated harvesting device at the current timestamp;

[0078] Update the estimated cutting efficiency information of the mulberry automated harvesting device according to the cutting performance characteristic data of the cutting blade in the mulberry automated harvesting device at the current timestamp, and re-dynamically adjust the working frequency and cutting working power of the mulberry automated harvesting device.

[0079] It should be noted that the historical cutting performance characteristic change data of the cutting blade in the mulberry automated harvesting device includes cutting efficiency information, cutting amount information per unit time under the same working parameters, etc. Through this method, the estimated cutting efficiency information of the mulberry automated harvesting device can be updated, and the working frequency and cutting working power of the mulberry automated harvesting device can be re-dynamically adjusted to optimize the control of the mulberry automated harvesting device.

[0080] In addition, this method also includes:

[0081] Obtain the transmission biological types related to the disease types generated when the mulberry branches are damaged, construct a transmission biological type recognition model based on a deep neural network, and obtain the image feature data of the transmission biological types related to the disease types generated when the mulberry branches are damaged through big data;

[0082] Input the image feature data of the transmission biological types related to the disease types generated when the mulberry branches are damaged into the transmission biological type recognition model for training, and obtain a trained transmission biological type recognition model;

[0083] Obtain the image data information in the mulberry branch harvesting area through the camera device set on the mulberry automated harvester, and input the image data information in the mulberry branch harvesting area into the trained transmission biological type recognition model for recognition;

[0084] When there is a type of spreading organism related to the disease type generated by mulberry branch damage in the image data information in the mulberry branch harvesting area, a warning is issued for the corresponding mulberry branch harvesting area, and recommended measures for wound treatment are generated.

[0085] It should be noted that the presence of wounds makes it easier for diseases to occur. Common diseases include mulberry blight and mulberry branch blight. These pathogens are usually spread by wind, rain or insects (such as controlling trunk pests like longhorn beetles and mulberry pyralid moths). Wounds increase the chance of infection. Through this method, growers can be reminded to take treatment measures during harvesting, reducing the occurrence of diseases.

[0086] The second aspect of the present invention provides a control system 4 for a mulberry tree automatic harvesting device, including a memory 41 and a processor 42. The memory 41 includes a control method program for the mulberry tree automatic harvesting device. When the control method program for the mulberry tree automatic harvesting device is executed by the processor 42, the following steps are implemented:

[0087] Obtain the infection data when mulberry branches are damaged under various temperature and humidity data of mulberry trees through big data, and based on the infection data when mulberry branches are damaged under various temperature and humidity data of mulberry trees, statistically calculate the infection probability when mulberry branches are damaged under various temperature and humidity data. Construct a knowledge graph based on the infection probability when mulberry branches are damaged under various temperature and humidity data;

[0088] Obtain the temperature and humidity data within a preset time in the area where the current mulberry tree is located, and obtain the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time according to the temperature and humidity data within the preset time in the area where the current mulberry tree is located and the knowledge graph;

[0089] Determine the mulberry tree harvesting period according to the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time, and generate relevant recommended harvesting periods according to the mulberry tree harvesting period. Obtain the real-time image data information of the mulberry tree through the image acquisition device installed on the mulberry tree automatic harvesting device during the relevant recommended harvesting periods;

[0090] Through preprocessing the real-time image data information of the mulberry tree, obtain the mulberry branch image features of the mulberry tree, configure the working frequency and cutting working power for the mulberry tree automatic harvesting device according to the mulberry branch image features of the mulberry tree, and control the mulberry tree automatic harvesting device according to the working frequency and cutting working power.

[0091] It should be noted that by determining the mulberry tree harvesting period and the working parameters of the mulberry tree automatic harvesting device according to the mulberry branch image features of the mulberry tree and the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time, the present invention can improve the control rationality of the mulberry tree automatic harvesting device and the rationality during the harvesting of mulberry trees.

[0092] Further, in this system, infection data of mulberry branches when damaged under various temperature and humidity data is obtained through big data, and the infection probability of mulberry branches when damaged under various temperature and humidity data is statistically calculated based on the infection data. Specifically:

[0093] Infection data of mulberry branches when damaged under various temperature and humidity data is obtained through big data, and the number of infections and the number of non-infections of mulberry branches when damaged under various temperature and humidity data are obtained according to the infection data of mulberry branches when damaged under various temperature and humidity data;

[0094] The total number of statistical times is calculated from the number of infections of mulberry branches when damaged under various temperature and humidity data and the number of non-infections of mulberry branches when damaged under various temperature and humidity data, and the number of infections of mulberry branches when damaged under various temperature and humidity data is used as the numerator;

[0095] The total number of statistical times is used as the denominator, the infection probability of mulberry branches when damaged under various temperature and humidity data is calculated, and the infection probability of mulberry branches when damaged under various temperature and humidity data is output.

[0096] It should be noted that mechanical damage to mulberry branches (such as pruning, insect bites, wind and rain breakage) will form wounds, becoming an invasion channel for fungi, bacteria or viruses. For example: Mulberry blight (bacterial disease): It quickly invades through wounds, causing branch wilt. Mulberry twig blight (fungal disease): Conidia are spread by wind and rain and infect from wounds. Mulberry southern blight: When the temperature is high and the humidity is high, the pathogen is easy to infect from wounds. Secondly, temperature and humidity also affect and accelerate the reproduction of pathogens, increasing the infection risk. Through this method, it is possible to obtain factors that will accelerate the reproduction of pathogens and increase the infection risk, so as to optimize the control of the mulberry automated harvesting device.

[0097] Further, in this system, a knowledge graph is constructed based on the infection probability of mulberry branches when damaged under various temperature and humidity data, specifically including:

[0098] A knowledge graph is constructed, and several storage spaces are configured for the knowledge graph. The temperature and humidity data and the infection probability of mulberry branches when damaged are used as nodes, and an undirected heterogeneous graph is constructed based on the nodes;

[0099] The undirected heterogeneous graph is input into the knowledge graph for storage, and node representation is performed on the knowledge graph.

[0100] Further, in this system, the temperature and humidity data of the current mulberry tree location within a preset time is obtained, and the infection probability value of mulberry branches when damaged within the preset time is obtained according to the temperature and humidity data of the current mulberry tree location within the preset time and the knowledge graph. Specifically including:

[0101] Obtain the temperature and humidity data of the area where the current mulberry tree is located within a preset time, and input the temperature and humidity data of the area where the current mulberry tree is located within a preset time into the knowledge graph for data matching;

[0102] Through data matching, obtain the infection probability value when the mulberry branches of the mulberry tree are damaged within a preset time, and output the infection probability value when the mulberry branches of the mulberry tree are damaged within a preset time.

[0103] Furthermore, in this system, according to the infection probability value when the mulberry branches of the mulberry tree are damaged within a preset time, formulate the mulberry tree harvesting period, and generate relevant recommended harvesting periods according to the mulberry tree harvesting period, specifically including:

[0104] Set an infection probability threshold, and determine whether the infection probability value when the mulberry branches of the mulberry tree are damaged within a preset time is greater than the infection probability threshold;

[0105] Obtain the period when the infection probability value is not greater than the infection probability threshold, and use the period when the infection probability value is not greater than the infection probability threshold as the mulberry tree harvesting period;

[0106] Generate relevant recommended harvesting periods according to the mulberry tree harvesting period, display the relevant recommended harvesting periods in a preset manner, and control the automatic mulberry tree harvesting device to harvest during the relevant recommended harvesting periods.

[0107] It should be noted that through this method, relevant recommended harvesting periods can be generated, avoiding the infection of mulberry branches during periodic harvesting and improving the rationality of mulberry branch harvesting.

[0108] Furthermore, in this system, by preprocessing the real-time image data information of the mulberry tree, obtain the mulberry branch image features of the mulberry tree, specifically including:

[0109] Through filtering and denoising processing of the real-time image data information of the mulberry tree, obtain the preprocessed image data, and introduce a feature pyramid network, and input the preprocessed image data into the feature pyramid network for feature extraction;

[0110] Through feature extraction, obtain the mulberry branch contour feature data of the mulberry tree, and through contour reconstruction processing of the mulberry branch contour feature data of the mulberry tree, obtain the mulberry branch image features of the mulberry tree, and output the mulberry branch image features of the mulberry tree.

[0111] It should be noted that through this method, the mulberry branch image features of the mulberry tree are obtained to identify the size of the mulberry branches, and then the working frequency and cutting power of the mulberry tree harvester are configured according to the size of the mulberry branches.

[0112] Furthermore, in this system, configure the working frequency and cutting power of the automatic mulberry tree harvesting device according to the mulberry branch image features of the mulberry tree, specifically including:

[0113] Construct a morphological feature model diagram of the mulberry branches based on the image features of the mulberry branches of the mulberry tree, and estimate the hardness feature data of the mulberry branches of the mulberry tree based on the morphological feature model diagram of the mulberry branches of the mulberry tree;

[0114] Initialize the working frequency and cutting power of the automatic mulberry harvesting device based on the hardness feature data of the mulberry branches of the mulberry tree, and perform cutting simulation based on the working frequency and cutting power of the automatic mulberry harvesting device;

[0115] Through the cutting simulation, obtain the estimated cutting efficiency information of the automatic mulberry harvesting device, and determine whether the cutting efficiency is greater than the preset cutting efficiency threshold;

[0116] When the cutting efficiency is greater than the preset cutting efficiency threshold, perform cutting control according to the working frequency and cutting power of the automatic mulberry harvesting device. When the cutting efficiency is not greater than the preset cutting efficiency threshold, increase the working frequency and cutting power of the automatic mulberry harvesting device.

[0117] It should be noted that by using virtual reality technology and 3D modeling technology to perform cutting simulation based on the working frequency and cutting power of the automatic mulberry harvesting device, the estimated cutting efficiency information of the automatic mulberry harvesting device can be simulated, so as to optimize the cutting working parameters of the automatic mulberry harvesting device and improve the rationality of cutting.

[0118] The third aspect of the present invention provides a computer-readable storage medium, including a control method program for the automatic mulberry harvesting device. When the control method program for the automatic mulberry harvesting device is executed by a processor, the steps of the control method for the automatic mulberry harvesting device in any one of the above are implemented.

[0119] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces. The indirect coupling or communication connection of the devices or units can be electrical, mechanical, or other forms.

[0120] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] In addition, each functional unit in the embodiments of the present invention may all be integrated into one processing unit, or each unit may be separately taken as one unit, 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 a combination of hardware and software functional units.

[0122] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium includes: removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks and other various media that can store program codes.

[0123] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention essentially or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the various embodiments of the present invention. And the foregoing storage medium includes: removable storage devices, ROM, RAM, magnetic disks, or optical disks and other various media that can store program codes.

[0124] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A control method for an automatic mulberry harvesting device, characterized in that, Including the following steps: Obtain the infection data of mulberry branches when damaged under various temperature and humidity data through big data, and based on the infection data of mulberry branches when damaged under various temperature and humidity data, statistically calculate the infection probability of mulberry branches when damaged under various temperature and humidity data. Construct a knowledge graph based on the infection probability of mulberry branches when damaged under various temperature and humidity data; Obtain the temperature and humidity data of the current mulberry tree area within a preset time, and obtain the infection probability value of mulberry branches when damaged within the preset time according to the temperature and humidity data of the current mulberry tree area within the preset time and the knowledge graph; Formulate the mulberry harvesting period according to the infection probability value of mulberry branches when damaged within the preset time, generate relevant recommended harvesting periods according to the mulberry harvesting period, and obtain the real-time image data information of the mulberry tree through the image acquisition device installed on the mulberry tree automatic harvesting device during the relevant recommended harvesting periods; Preprocess the real-time image data information of the mulberry tree to obtain the mulberry branch image features of the mulberry tree, configure the working frequency and cutting working power of the mulberry tree automatic harvesting device according to the mulberry branch image features of the mulberry tree, and control the mulberry tree automatic harvesting device according to the working frequency and cutting working power; Formulate the mulberry harvesting period according to the infection probability value of mulberry branches when damaged within the preset time, and generate relevant recommended harvesting periods according to the mulberry harvesting period, specifically including: Set an infection probability threshold, and determine whether the infection probability value of mulberry branches when damaged within the preset time is greater than the infection probability threshold; Obtain the time period when the infection probability value is not greater than the infection probability threshold, and use the time period when the infection probability value is not greater than the infection probability threshold as the mulberry harvesting period; Generate relevant recommended harvesting periods according to the mulberry harvesting period, display the relevant recommended harvesting periods in a preset manner, and control the mulberry tree automatic harvesting device to harvest during the relevant recommended harvesting periods.

2. The control method of an automated mulberry harvesting device according to claim 1, characterized in that, Obtain the infection data of mulberry branches when damaged under various temperature and humidity data through big data, and based on the infection data of mulberry branches when damaged under various temperature and humidity data, statistically calculate the infection probability of mulberry branches when damaged under various temperature and humidity data, specifically: Obtain the infection data of mulberry branches when damaged under various temperature and humidity data through big data, and obtain the number of infections and the number of non-infections of mulberry branches when damaged under various temperature and humidity data according to the infection data of mulberry branches when damaged under various temperature and humidity data; Statistically calculate the total number of statistics for the number of infections of mulberry branches when damaged under each temperature and humidity data and the number of non-infections of mulberry branches when damaged under each temperature and humidity data, and use the number of infections of mulberry branches when damaged under each temperature and humidity data as the numerator; Use the total number of statistics as the denominator, statistically calculate the infection probability of mulberry branches when damaged under various temperature and humidity data, and output the infection probability of mulberry branches when damaged under various temperature and humidity data.

3. The control method of an automated mulberry harvesting device according to claim 1, characterized in that, Construct a knowledge graph based on the infection probability of mulberry branches when damaged under various temperature and humidity data, specifically including: Construct a knowledge graph, configure several storage spaces for the knowledge graph, use temperature and humidity data and the infection probability when mulberry branches are damaged as nodes, and construct an undirected heterogeneous graph based on the nodes; Input the undirected heterogeneous graph into the knowledge graph for storage, and perform node representation on the knowledge graph.

4. The control method of an automated mulberry harvesting device according to claim 1, characterized in that, Obtain the temperature and humidity data of the area where the current mulberry tree is located within a preset time, and obtain the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time according to the temperature and humidity data of the area where the current mulberry tree is located within the preset time and the knowledge graph. Specifically, it includes: Obtain the temperature and humidity data of the area where the current mulberry tree is located within a preset time, and input the temperature and humidity data of the area where the current mulberry tree is located within the preset time into the knowledge graph for data matching; Through data matching, obtain the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time, and output the infection probability value when the mulberry branches of the mulberry tree are damaged within the preset time.

5. The control method of an automated mulberry harvesting device according to claim 1, characterized in that, Through preprocessing the real-time image data information of the mulberry tree, obtain the mulberry branch image features of the mulberry tree. Specifically, it includes: Through filtering and denoising the real-time image data information of the mulberry tree, obtain the preprocessed image data, introduce a feature pyramid network, and input the preprocessed image data into the feature pyramid network for feature extraction; Through feature extraction, obtain the mulberry branch contour feature data of the mulberry tree, and through contour reconstruction processing of the mulberry branch contour feature data of the mulberry tree, obtain the mulberry branch image features of the mulberry tree, and output the mulberry branch image features of the mulberry tree.

6. The control method of an automatic mulberry harvesting device according to claim 1, characterized in that, Configure the working frequency and cutting working power for the mulberry tree automatic harvesting device according to the mulberry branch image features of the mulberry tree. Specifically, it includes: Construct a mulberry branch morphological feature model diagram of the mulberry tree according to the mulberry branch image features of the mulberry tree, and estimate the hardness feature data of the mulberry branches of the mulberry tree based on the mulberry branch morphological feature model diagram of the mulberry tree; Initialize the working frequency and cutting working power of the mulberry tree automatic harvesting device based on the hardness feature data of the mulberry branches of the mulberry tree, and perform cutting simulation based on the working frequency and cutting working power of the mulberry tree automatic harvesting device; Through cutting simulation, obtain the estimated cutting efficiency information of the mulberry tree automatic harvesting device, and determine whether the cutting efficiency is greater than a preset cutting efficiency threshold; When the cutting efficiency is greater than the preset cutting efficiency threshold, perform cutting control according to the working frequency and cutting working power of the mulberry tree automatic harvesting device. When the cutting efficiency is not greater than the preset cutting efficiency threshold, increase the working frequency and cutting working power of the mulberry tree automatic harvesting device.

7. A control system for an automated mulberry harvesting device, characterized in that, It includes a memory and a processor. The memory includes a control method program for the mulberry tree automatic harvesting device. When the control method program for the mulberry tree automatic harvesting device is executed by the processor, the steps of the control method for the mulberry tree automatic harvesting device according to any one of claims 1-6 are implemented.

8. A computer-readable storage medium, characterized in that, A control method program for a mulberry tree automatic harvesting device, when the control method program of the mulberry tree automatic harvesting device is executed by a processor, implements the steps of the control method of the mulberry tree automatic harvesting device according to any one of claims 1-6.

Images