Assessment method and system of tea growth model

Abstract

The invention discloses a method and a system for evaluating a tea growth model. The method comprises the following steps: constructing a first growth model according to a data set and a meteorological data set; acquiring pest and disease damage data in the tea leaf detection area, forming a pest and disease damage identification model according to dynamic interaction of multiple pest and disease damage data, and integrally controlling the pest and disease damage identification model and the first growth model. Further, constructing a tea growth model according to the disease and pest recognition model and the first growth model; the tea growth model performs overall evaluation on a tea detection area in a tea garden, defines a corresponding tea growth state according to the tea growth model, each sub-area in the tea detection area and time, and defines a corresponding tea state evaluation diagram according to the tea growth state and the tea detection area; according to the invention, accurate evaluation of the tea leaf detection area by the tea leaf growth model is realized, the accuracy of the tea leaf state evaluation diagram is ensured, and multi-dimensional evaluation of the tea leaf state of the tea leaf state evaluation diagram is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of tea growth models, and in particular to an evaluation method and system for a tea growth model. Background Art

[0002] With the development of science and technology, tea is used in people's lives and serves as one of the crops. Tea grows in tea gardens and is formed through subsequent tea-making processes. In the existing technology, the growth status of tea is evaluated and an overall evaluation is performed based on multiple parameters of tea. However, this overall evaluation does not take into account the impact of the tea testing area, weather, and pests and diseases, and cannot achieve a multi-dimensional evaluation of the tea status. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides an evaluation method and system for a tea growth model, locates a tea detection area in a tea garden, collects multiple tea parameters based on a drone and the tea detection area; outputs a corresponding data set based on data processing of multiple tea parameters; constructs a first growth model based on the data set and a meteorological data set; collects pest and disease data in the tea detection area, forms a pest and disease identification model based on the dynamic interaction of multiple pest and disease data, introduces the pest and disease identification model and the first growth model, and performs overall control on the pest and disease identification model and the first growth model.

[0004] Furthermore, the pest and disease identification model and the first growth model are associated; a tea growth model is constructed based on the pest and disease identification model and the first growth model; the tea growth model performs an overall evaluation on the tea detection area in the tea garden, defines the corresponding tea growth status according to the tea growth model, each sub-area in the tea detection area, and time, and defines the corresponding tea status evaluation map according to the tea growth status and the tea detection area, thereby realizing accurate evaluation of the tea detection area by the tea growth model, ensuring the accuracy of the tea status evaluation map, and realizing multi-dimensional evaluation of the tea status in the tea status evaluation map.

[0005] The embodiment of the present invention provides a tea growth model evaluation method, which is applied to the tea growth model evaluation scenario;

[0006] The tea growth model evaluation method comprises:

[0007] Locate the tea testing area in the tea garden and collect multiple tea parameters based on the drone and the tea testing area;

[0008] Outputting corresponding data sets based on data processing of multiple tea parameters;

[0009] constructing a first growth model based on the data set and the meteorological data set;

[0010] Collect pest and disease data in the tea detection area, and form a pest and disease identification model based on the dynamic interaction of multiple pest and disease data;

[0011] Associating the pest and disease identification model with the first growth model; constructing a tea growth model based on the pest and disease identification model and the first growth model;

[0012] The tea growth model conducts an overall evaluation of the tea detection area in the tea garden, defines the corresponding tea growth status according to the tea growth model, each sub-area in the tea detection area and time, and defines the corresponding tea status evaluation map according to the tea growth status and the tea detection area.

[0013] Optionally, the locating of the tea detection area in the tea garden and collecting a plurality of tea parameters based on the drone and the tea detection area include:

[0014] A three-dimensional diagram of the tea garden is collected, and the tea part and the non-tea part are defined according to the recognition of the three-dimensional diagram;

[0015] Define tea inspection areas in the tea garden based on the location of tea parts and the drone's review images;

[0016] Locate the tea testing area in the tea garden;

[0017] Associate the tea inspection area and the drone in the tea garden, and define the inspection path according to the tea inspection area and the drone in the tea garden;

[0018] Triggering the UAV to dynamically detect the tea detection area along the detection path;

[0019] Based on the dynamic detection of the tea detection area by the drone, multiple tea parameters are collected. The multiple tea parameters are in different dimensions and present the growth parameters of the tea detection area as a whole.

[0020] Optionally, the data processing based on multiple tea parameters to output corresponding data sets includes:

[0021] Freeze multiple tea parameters;

[0022] Define exception parameters based on traversal of multiple tea parameters;

[0023] Defining abnormal events according to various abnormal parameters, corresponding positions and associated matching tables;

[0024] Define the corresponding abnormal level according to abnormal events and abnormal identification models;

[0025] Based on the abnormal events, abnormal levels and tea detection areas, the optimization logic is triggered, and each abnormal parameter is autonomously optimized according to the optimization logic to obtain the optimized tea parameters;

[0026] A corresponding data set is constructed based on the optimized tea parameters, the tea parameters in a non-abnormal state, and the tea detection area, and the corresponding data set is output.

[0027] Optionally, constructing a first growth model according to the data set and the meteorological data set includes:

[0028] Freeze the data set;

[0029] Forming a plurality of data combinations according to the division of the data set;

[0030] Collect meteorological data sets based on meteorological detection in tea detection areas;

[0031] Link multiple data sets and meteorological data sets;

[0032] A first growth model is constructed based on the plurality of data combinations and the meteorological data set.

[0033] Optionally, the collecting of pest and disease data in the tea detection area and forming a pest and disease identification model according to the dynamic interaction of multiple pest and disease data include:

[0034] Define the tea testing area and conduct pest and disease testing in the tea testing area;

[0035] Collect corresponding pest and disease data based on the pest and disease detection in the tea testing area;

[0036] Collect multiple pest and disease data and dynamically interact with the pest and disease data;

[0037] A pest and disease identification model is formed based on the dynamic interaction of multiple pest and disease data and regional calculations of the tea detection area.

[0038] Optionally, associating the pest and disease identification model with the first growth model; constructing the tea growth model according to the pest and disease identification model and the first growth model includes:

[0039] Fixed-frame pest and disease identification model;

[0040] The first growth model is collected, and the pest and disease identification model and the first growth model are associated.

[0041] Optionally, the associating the pest and disease identification model with the first growth model; constructing the tea growth model according to the pest and disease identification model and the first growth model, further includes:

[0042] Conduct multi-dimensional deductions on the pest and disease identification model and the first growth model;

[0043] Collecting a plurality of deduction data based on the deduction of the pest and disease identification model and the first growth model;

[0044] Outputting a corresponding training data set according to the matching of the plurality of deduction data and the corresponding deduction dimensions;

[0045] A tea growth model is constructed based on the training data set and the model matching the tea detection area.

[0046] Optionally, the tea growth model performs an overall evaluation on the tea detection area in the tea garden, defines corresponding tea growth states according to the tea growth model, each sub-area in the tea detection area, and time, and defines corresponding tea state evaluation graphs according to the tea growth states and the tea detection area, including:

[0047] Freeze-frame tea growth model;

[0048] Correlate tea growth models and tea detection areas in tea gardens;

[0049] The tea growth model provides an overall assessment of the tea testing area in the tea garden.

[0050] Optionally, the tea growth model performs an overall evaluation on the tea detection area in the tea garden, defines corresponding tea growth states according to the tea growth model, each sub-area in the tea detection area, and time, and defines corresponding tea state evaluation graphs according to the tea growth states and the tea detection area, further comprising:

[0051] Define multiple growth coefficients according to the tea growth model and the tea detection area;

[0052] The corresponding tea growth states are defined according to a plurality of growth coefficients, each sub-area in the tea detection area, and time;

[0053] The tea growth status and the tea detection area are associated, and a corresponding tea status evaluation diagram is defined according to the tea growth status and the tea detection area.

[0054] In addition, an embodiment of the present invention further provides a tea growth model evaluation system, the tea growth model evaluation system comprising:

[0055] The collection module is used to locate the tea detection area in the tea garden and collect multiple tea parameters based on the drone and the tea detection area;

[0056] A data set module, used for outputting corresponding data sets based on data processing of multiple tea parameters;

[0057] A first growth module, used for constructing a first growth model according to the data set and the meteorological data set;

[0058] The pest and disease module is used to collect pest and disease data in the tea detection area and form a pest and disease identification model based on the dynamic interaction of multiple pest and disease data;

[0059] A tea growth module, used to associate the pest and disease identification model with the first growth model; and to construct a tea growth model according to the pest and disease identification model and the first growth model;

[0060] The evaluation module is used to conduct an overall evaluation of the tea detection area in the tea garden based on the tea growth model, define the corresponding tea growth status according to the tea growth model, each sub-area in the tea detection area and time, and define the corresponding tea status evaluation map according to the tea growth status and the tea detection area.

[0061] In an embodiment of the present invention, through the method in the embodiment of the present invention, the tea detection area in the tea garden is located, and multiple tea parameters are collected based on the drone and the tea detection area; the corresponding data set is output based on the data processing of the multiple tea parameters; the first growth model is constructed according to the data set and the meteorological data set; the pest and disease data in the tea detection area are collected, and the pest and disease identification model is formed according to the dynamic interaction of the multiple pest and disease data, the pest and disease identification model and the first growth model are introduced, and the pest and disease identification model and the first growth model are controlled as a whole.

[0062] Furthermore, the pest and disease identification model and the first growth model are associated; a tea growth model is constructed based on the pest and disease identification model and the first growth model; the tea growth model performs an overall evaluation on the tea detection area in the tea garden, defines the corresponding tea growth status according to the tea growth model, each sub-area in the tea detection area, and time, and defines the corresponding tea status evaluation map according to the tea growth status and the tea detection area, thereby realizing accurate evaluation of the tea detection area by the tea growth model, ensuring the accuracy of the tea status evaluation map, and realizing multi-dimensional evaluation of the tea status in the tea status evaluation map. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0064] Figure 1 is a schematic flow chart of a method for evaluating a tea growth model in an embodiment of the present invention;

[0065] Figure 2 is a schematic flow chart of S11 in the tea growth model evaluation method in the embodiment of the present invention;

[0066] Figure 3 is a schematic flow chart of S12 in the tea growth model evaluation method in an embodiment of the present invention;

[0067] Figure 4 is a schematic flow chart of S13 in the tea growth model evaluation method in an embodiment of the present invention;

[0068] Figure 5 is a schematic flow chart of S14 in the tea growth model evaluation method in an embodiment of the present invention;

[0069] Figure 6 is a schematic flow chart of S15 in the tea growth model evaluation method in an embodiment of the present invention;

[0070] Figure 7 is a schematic flow chart of S16 in the tea growth model evaluation method in an embodiment of the present invention;

[0071] Figure 8 Schematic diagram of the structure of the tea growth model evaluation system in the embodiment of the present invention;

[0072] Fig. 9 The figure is a hardware diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0073] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0074] See also Figures 1 to 9 , a tea growth model evaluation method is applied to the tea growth model evaluation scenario; the tea growth model evaluation method includes:

[0075] Step S11: Locate the tea detection area in the tea garden, and collect multiple tea parameters based on the drone and the tea detection area;

[0076] Step S12: outputting corresponding data sets based on data processing of multiple tea parameters;

[0077] Step S13: outputting corresponding data sets based on data processing of multiple tea parameters;

[0078] Step S14: collecting pest and disease data in the tea detection area, and forming a pest and disease identification model based on the dynamic interaction of multiple pest and disease data;

[0079] Step S15: Associating the pest and disease identification model with the first growth model; constructing a tea growth model according to the pest and disease identification model and the first growth model;

[0080] Step S16: The tea growth model performs an overall assessment of the tea detection area in the tea garden, defines the corresponding tea growth status according to the tea growth model, each sub-area in the tea detection area and time, and defines the corresponding tea status assessment graph according to the tea growth status and the tea detection area.

[0081] In an embodiment of the present invention, through the method in the embodiment of the present invention, the tea detection area in the tea garden is located, and multiple tea parameters are collected based on the drone and the tea detection area; the corresponding data set is output based on the data processing of the multiple tea parameters; the first growth model is constructed according to the data set and the meteorological data set; the pest and disease data in the tea detection area are collected, and the pest and disease identification model is formed according to the dynamic interaction of the multiple pest and disease data, the pest and disease identification model and the first growth model are introduced, and the pest and disease identification model and the first growth model are controlled as a whole.

[0082] Furthermore, the pest and disease identification model and the first growth model are associated; a tea growth model is constructed based on the pest and disease identification model and the first growth model; the tea growth model performs an overall evaluation on the tea detection area in the tea garden, defines the corresponding tea growth status according to the tea growth model, each sub-area in the tea detection area, and time, and defines the corresponding tea status evaluation map according to the tea growth status and the tea detection area, thereby realizing accurate evaluation of the tea detection area by the tea growth model, ensuring the accuracy of the tea status evaluation map, and realizing multi-dimensional evaluation of the tea status in the tea status evaluation map.

[0083] refer to Figure 2 , in step S11, the tea detection area in the tea garden is located, and multiple tea parameters are collected based on the drone and the tea detection area;

[0084] In the specific implementation process of the present invention, the specific steps may be:

[0085] S111: collecting a three-dimensional schematic diagram of the tea garden, and defining a tea part and a non-tea part according to recognition of the three-dimensional schematic diagram;

[0086] S112: defining a tea inspection area in the tea garden based on the location of the tea parts and the review image of the drone;

[0087] S113: Positioning the tea detection area in the tea garden;

[0088] S114: Associating the tea inspection area in the tea garden and the drone, and defining an inspection path according to the tea inspection area in the tea garden and the drone;

[0089] S115: triggering the drone to dynamically detect the tea detection area along the detection path;

[0090] S116: Collect multiple tea parameters according to the dynamic detection of the tea detection area by the drone, where the multiple tea parameters are in different dimensions and present the growth parameters of the tea detection area as a whole.

[0091] In an embodiment of the present application, a three-dimensional schematic diagram of a tea garden is collected, and the tea part and the non-tea part are defined based on the recognition of the three-dimensional schematic diagram, and the tea part and the non-tea part are introduced, and the tea part and the non-tea part are controlled, so that the tea detection area in the tea garden is defined based on the position of the tea part and the review image of the drone, which is compatible with the overall consideration of the position of the tea part and the review image of the drone, realizes multi-dimensional control of the position of the tea part and the review image of the drone, and ensures the accuracy of the tea detection area in the tea garden.

[0092] Furthermore, the tea detection area in the tea garden is located, and at the same time, the tea detection area in the tea garden and the drone are associated, and the detection path is defined according to the tea detection area in the tea garden and the drone, thereby realizing multi-dimensional control of the tea detection area in the tea garden and the drone, thereby triggering dynamic detection of the tea detection area by the drone along the detection path, thereby realizing dynamic detection of the tea detection area by the drone.

[0093] Therefore, multiple tea parameters are collected based on the dynamic detection of the tea detection area by the drone. The multiple tea parameters are in different dimensions and present the growth parameters of the tea detection area as a whole, so as to facilitate the overall control of multiple tea parameters and ensure the evaluation of the growth status of the tea detection area.

[0094] refer to Figure 3 , in step S12, outputting a corresponding data set based on data processing of a plurality of tea parameters;

[0095] In the specific implementation process of the present invention, the specific steps may be:

[0096] S121: freeze multiple tea parameters;

[0097] S122: defining abnormal parameters based on traversal of multiple tea parameters;

[0098] S123: defining an abnormal event according to each abnormal parameter, the corresponding position and the associated matching table;

[0099] S124: defining corresponding abnormality levels according to abnormal events and abnormality recognition models;

[0100] S125: triggering an optimization logic based on the abnormal event, abnormal level and tea detection area, and autonomously optimizing each abnormal parameter according to the optimization logic to obtain optimized tea parameters;

[0101] S126: constructing a corresponding data set based on the optimized tea parameters, the tea parameters in a non-abnormal state, and the tea detection area, and outputting the corresponding data set.

[0102] In the embodiments of the present application, multiple tea parameters are frozen, multiple tea parameters are introduced, and multiple tea parameters are controlled. At the same time, abnormal parameters are defined based on the traversal of multiple tea parameters, abnormal parameters are introduced, and further processing of abnormal parameters is achieved.

[0103] Furthermore, abnormal events are defined according to various abnormal parameters, corresponding positions and associated matching tables, which is compatible with the overall consideration of various abnormal parameters, corresponding positions and associated matching tables, realizes multi-dimensional control of various abnormal parameters, corresponding positions and associated matching tables, and ensures the accuracy of abnormal events.

[0104] Therefore, the corresponding abnormal level is defined according to the abnormal event and the abnormal recognition model; the optimization logic used is triggered based on the abnormal event, abnormal level and tea detection area, and each abnormal parameter is autonomously optimized according to the optimization logic, and the optimized tea parameters are obtained, thereby realizing the autonomous optimization of the abnormal parameters.

[0105] Furthermore, corresponding data sets are constructed based on the optimized tea parameters, tea parameters in a non-abnormal state, and tea detection areas, and the corresponding data sets are output. The optimized tea parameters, tea parameters in a non-abnormal state, and tea detection areas are introduced, and the overall control of the optimized tea parameters, tea parameters in a non-abnormal state, and tea detection areas is achieved.

[0106] refer to Figure 4 , in step S13, constructing a first growth model based on the data set and the meteorological data set;

[0107] In the specific implementation process of the present invention, the specific steps may be:

[0108] S131: freeze the data set;

[0109] S132: forming a plurality of data combinations according to the division of the data set;

[0110] S133: collecting a meteorological data set based on meteorological detection in the tea detection area;

[0111] S134: Associating multiple data sets and meteorological data sets;

[0112] S135: Constructing a first growth model based on the plurality of data combinations and the meteorological data set.

[0113] In an embodiment of the present application, the data set is frozen and controlled. At the same time, multiple data combinations are formed according to the division of the data set, multiple data combinations are introduced, and dynamic interaction between the multiple data combinations is achieved.

[0114] Therefore, meteorological data sets are collected based on meteorological detection in the tea detection area; multiple data combinations and meteorological data sets are associated; and a first growth model is constructed based on multiple data combinations and meteorological data sets, which is compatible with the overall consideration of multiple data combinations and meteorological data sets, realizes multi-dimensional control of multiple data combinations and meteorological data sets, and ensures the accuracy of the first growth model.

[0115] refer to Figure 5 , S14: collecting pest and disease data in the tea detection area, and forming a pest and disease identification model based on the dynamic interaction of multiple pest and disease data;

[0116] In the specific implementation process of the present invention, the specific steps may be:

[0117] S141: freeze the tea testing area and conduct pest and disease detection in the tea testing area;

[0118] S142: Collecting corresponding pest and disease data according to the pest and disease detection in the tea detection area;

[0119] S143: Collect multiple pest and disease data and dynamically interact with the pest and disease data;

[0120] S144: A pest and disease identification model is formed according to the dynamic interaction of multiple pest and disease data and the regional operation of the tea detection area.

[0121] In an embodiment of the present application, a tea inspection area in a tea garden is located, and multiple tea parameters are collected based on a drone and the tea inspection area; a corresponding data set is output based on data processing of the multiple tea parameters; a first growth model is constructed based on the data set and a meteorological data set; pest and disease data in the tea inspection area are collected, and a pest and disease identification model is formed based on the dynamic interaction of multiple pest and disease data, and the pest and disease identification model and the first growth model are introduced, and the pest and disease identification model and the first growth model are controlled as a whole.

[0122] At this time, the tea inspection area is frozen, and pest and disease detection is carried out in the tea inspection area; corresponding pest and disease data are collected based on the pest and disease detection in the tea inspection area, thereby introducing pest and disease data to facilitate further control of the pest and disease data.

[0123] Therefore, multiple pest and disease data are collected, and the pest and disease data are dynamically interacted; a pest and disease identification model is formed based on the dynamic interaction of multiple pest and disease data and the regional operation of the tea detection area, which is compatible with the dynamic interaction of multiple pest and disease data and the regional operation of the tea detection area, and realizes the overall consideration of the dynamic interaction of multiple pest and disease data and the regional operation of the tea detection area, thereby ensuring the accuracy of the pest and disease identification model. At the same time, the pest and disease identification model and the first growth model are introduced to control the pest and disease identification model and the first growth model as a whole.

[0124] refer to Figure 6 , S15: associating the pest and disease identification model with the first growth model; constructing a tea growth model according to the pest and disease identification model and the first growth model;

[0125] In the specific implementation process of the present invention, the specific steps may be:

[0126] S151: Fixed-frame pest and disease identification model;

[0127] S152: collecting the first growth model, and associating the pest identification model with the first growth model;

[0128] S153: Multi-dimensional deduction of pest and disease identification model and the first growth model;

[0129] S154: collecting a plurality of deduction data based on the deduction of the pest and disease identification model and the first growth model;

[0130] S155: Outputting a corresponding training data set according to the matching of the plurality of deduction data and the corresponding deduction dimensions;

[0131] S156: Constructing a tea growth model according to the training data set and the model matched by the tea detection area.

[0132] In an embodiment of the present application, the pest and disease identification model is frozen, and at the same time, the first growth model is collected, and the pest and disease identification model and the first growth model are associated, thereby realizing multiple interactions between the pest and disease identification model and the first growth model.

[0133] At this time, the pest and disease identification model and the first growth model are deduced in multiple dimensions; multiple deduction data are collected based on the deduction of the pest and disease identification model and the first growth model, multiple deduction data are introduced, and further calculation of multiple deduction data is realized.

[0134] Therefore, the corresponding training data set is output according to the matching of multiple deduction data and corresponding deduction dimensions; the tea growth model is constructed according to the training data set and the model matching the tea detection area, thereby achieving the compatibility of the training data set and the model matching the tea detection area and ensuring the accuracy of the tea growth model.

[0135] refer to Figure 7 , S16: the tea growth model performs an overall evaluation on the tea detection area in the tea garden, defines the corresponding tea growth state according to the tea growth model, each sub-area in the tea detection area and time, and defines the corresponding tea state evaluation map according to the tea growth state and the tea detection area;

[0136] In the specific implementation process of the present invention, the specific steps may be:

[0137] S161: freeze-frame tea growth model;

[0138] S162: Correlate tea growth model and tea detection area in tea garden;

[0139] S163: Tea growth model provides an overall assessment of the tea testing area in the tea garden;

[0140] S164: defining a plurality of growth coefficients according to a tea growth model and a tea detection area;

[0141] S165: defining corresponding tea growth states according to the plurality of growth coefficients, each sub-area in the tea detection area, and time;

[0142] S166: Associating the tea growth status and the tea detection area, and defining a corresponding tea status evaluation diagram according to the tea growth status and the tea detection area.

[0143] In the specific implementation process of the present invention, the pest and disease identification model and the first growth model are associated; the tea growth model is constructed according to the pest and disease identification model and the first growth model; the tea growth model performs an overall evaluation on the tea detection area in the tea garden, defines the corresponding tea growth status according to the tea growth model, each sub-area in the tea detection area and time, and defines the corresponding tea state evaluation map according to the tea growth status and the tea detection area, thereby realizing the accurate evaluation of the tea detection area by the tea growth model, ensuring the accuracy of the tea state evaluation map, and realizing the multi-dimensional evaluation of the tea state in the tea state evaluation map.

[0144] At this time, the tea growth model is frozen and introduced. At the same time, the tea growth model and the tea detection area in the tea garden are associated; the tea growth model makes an overall assessment of the tea detection area in the tea garden.

[0145] Furthermore, multiple growth coefficients are defined according to the tea growth model and the tea detection area; the corresponding tea growth states are defined according to the multiple growth coefficients, each sub-area in the tea detection area and time, which is compatible with the overall consideration of multiple growth coefficients, each sub-area in the tea detection area and time, and realizes multi-dimensional control of multiple growth coefficients, each sub-area in the tea detection area and time, thereby ensuring the accuracy of the tea growth state.

[0146] Therefore, the tea growth status and tea detection area are associated, and the corresponding tea status assessment map is defined according to the tea growth status and tea detection area, so that the tea growth model can accurately assess the tea detection area, ensure the accuracy of the tea status assessment map, and realize the multi-dimensional assessment of the tea status of the tea status assessment map.

[0147] In the embodiments of the present application, firstly, by designing a UAV-based hardware and software system, efficient multi-source data collection is achieved; secondly, a tea growth model is constructed, integrating UAV remote sensing data and meteorological data, exploring the relationship between key tea growth parameters and environmental factors, and establishing a tea growth model; finally, a tea yield estimation method is explored, and the established growth model is combined with real-time meteorological data to accurately predict tea yield.

[0148] 1. UAV-based software and hardware systems

[0149] One of the core contents of this project is to build a multi-source data collection and monitoring system based on drone remote sensing technology and high-precision sensors. The high-definition camera, hyperspectral imager, temperature and humidity sensor and other equipment carried by the drone can realize the all-round, multi-angle and high-precision data collection of tea fields. These devices can not only obtain information such as the growth status, pests and diseases of tea, but also detect key indicators such as nutrient content, humidity and pH in the soil in real time. At the same time, high-precision sensors can monitor meteorological data such as temperature, humidity, wind speed, wind direction, etc. in real time, providing data support for the comprehensive analysis of the tea growth environment.

[0150] In terms of hardware design, this project will customize and optimize the functions of drones to meet the special needs of tea planting, so as to ensure that they can complete data collection tasks efficiently and accurately. At the same time, we will develop a mobile application through which users can remotely control drones and collect data. Users can send instructions to the server through their mobile phones to achieve remote control and data collection of drones. Through the establishment of this system, comprehensive and real-time monitoring of the tea growing environment can be achieved, providing a rich data source for subsequent data analysis and decision support.

[0151] 2. Constructing a tea growth model

[0152] The key to building a tea growth model is to deeply understand the complex process of tea growth and systematically transform it into a mathematical model. First, we need to collect various data on tea growth, including different tea varieties, climate and soil characteristics of the growing area, characteristics of the growth, dormancy and picking stages in the growth cycle, and factors that affect tea growth such as temperature, humidity, light, water and nutrition. Secondly, by analyzing and organizing these data, we can find out the laws and key factors in the tea growth process.

[0153] In the modeling process, a variety of methods can be used, such as mathematical equations, statistical models, or machine learning algorithms. For example, data on growth environment factors and influencing factors can be used to build a regression model to predict tea yield and quality. At the same time, considering the characteristics of the tea growth cycle, time series analysis methods can be used to build a model to predict the growth status of tea at different stages. When building a model, special attention should be paid to the interaction between various factors, and the accuracy and reliability of the model should be improved through parameter optimization and model verification.

[0154] Finally, the established tea growth model will be applied to actual production to provide scientific cultivation guidance and decision-making support for tea farmers. Through the prediction and analysis of the model, tea farmers can adjust cultivation measures in time to improve tea yield and quality and achieve sustainable development.

[0155] 3. Explore tea production estimation methods

[0156] We will explore and model the relationship between tea growth status and yield from multiple perspectives. First, we will build a growing season model to consider the impact of seasonal climate changes on tea growth and how to predict the trend of yield changes based on seasonal changes. Second, we will build an environmental factor model, including the quantitative impact of factors such as soil quality, water supply, and light intensity on tea growth, and study how to use these factors to estimate tea yield. In terms of agronomic measures models, we will analyze the impact of different management measures on tea growth and yield, including fertilization, pruning, irrigation, etc., to determine the best management practices. Finally, we will comprehensively consider the above factors and establish a comprehensive model to more accurately predict tea yield and provide scientific basis and management suggestions for agricultural managers. Through the establishment and application of these models, we will be able to better understand the growth of tea and take targeted measures to increase tea yield and promote the sustainable development of the tea industry.

[0157] In an embodiment of the present invention, through the method in the embodiment of the present invention, the tea detection area in the tea garden is located, and multiple tea parameters are collected based on the drone and the tea detection area; the corresponding data set is output based on the data processing of the multiple tea parameters; the first growth model is constructed according to the data set and the meteorological data set; the pest and disease data in the tea detection area are collected, and the pest and disease identification model is formed according to the dynamic interaction of the multiple pest and disease data, the pest and disease identification model and the first growth model are introduced, and the pest and disease identification model and the first growth model are controlled as a whole.

[0158] Furthermore, the pest and disease identification model and the first growth model are associated; a tea growth model is constructed based on the pest and disease identification model and the first growth model; the tea growth model performs an overall evaluation on the tea detection area in the tea garden, defines the corresponding tea growth status according to the tea growth model, each sub-area in the tea detection area, and time, and defines the corresponding tea status evaluation map according to the tea growth status and the tea detection area, thereby realizing accurate evaluation of the tea detection area by the tea growth model, ensuring the accuracy of the tea status evaluation map, and realizing multi-dimensional evaluation of the tea status in the tea status evaluation map.

[0159] See also Figure 8 , Figure 8 It is a schematic diagram of the structural composition of the evaluation system of the tea growth model in the embodiment of the present invention.

[0160] like Figure 8 As shown, a tea growth model evaluation system, the tea growth model evaluation system comprises:

[0161] A collection module 21 is used to locate the tea detection area in the tea garden and collect multiple tea parameters based on the drone and the tea detection area;

[0162] A data set module 22, for outputting a corresponding data set based on data processing of a plurality of tea parameters;

[0163] A first growth module 23, used to construct a first growth model according to the data set and the meteorological data set;

[0164] The pest and disease module 24 is used to collect pest and disease data in the tea detection area and form a pest and disease identification model based on the dynamic interaction of multiple pest and disease data;

[0165] The tea growth module 25 is used to associate the pest and disease identification model with the first growth model; and to construct a tea growth model according to the pest and disease identification model and the first growth model;

[0166] The evaluation module 26 is used to perform an overall evaluation of the tea detection area in the tea garden based on the tea growth model, define the corresponding tea growth status according to the tea growth model, each sub-area in the tea detection area and time, and define the corresponding tea status evaluation map according to the tea growth status and the tea detection area.

[0167] See also Fig. 9 , refer to the following Fig. 9 The electronic device 40 according to this embodiment of the present invention will be described. Fig. 9 The electronic device 40 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0168] like Fig. 9 As shown, the electronic device 40 is in the form of a general computing device. The components of the electronic device 40 may include but are not limited to: at least one processing unit 41, at least one storage unit 42, and a bus 43 connecting different system components (including the storage unit 42 and the processing unit 41).

[0169] The storage unit stores program codes, which can be executed by the processing unit 41, so that the processing unit 41 executes the steps according to various exemplary embodiments of the present invention described in the above “Embodiment Method” section of this specification.

[0170] The storage unit 42 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 421 and / or a cache memory unit 422 , and may further include a read-only memory unit (ROM) 423 .

[0171] The storage unit 42 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0172] Bus 43 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0173] The electronic device 40 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 40, and / or any device that enables the electronic device 40 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 44. Furthermore, the electronic device 40 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 45. Fig. 9 As shown, the network adapter 45 communicates with other modules of the electronic device 40 via the bus 43. It should be understood that although Fig. 9 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 40, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup planning systems.

[0174] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0175] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. In addition, it stores computer program instructions, and when the computer program instructions are executed by a computer, the computer executes the above method.

[0176] In addition, the evaluation method and system of the tea growth model provided in the embodiments of the present invention are introduced in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for evaluating a tea growth model, characterized in that: Evaluation scenarios applied to tea growth models; The tea growth model evaluation method comprises: Locate the tea testing area in the tea garden and collect multiple tea parameters based on the drone and the tea testing area; Outputting corresponding data sets based on data processing of multiple tea parameters; constructing a first growth model based on the data set and the meteorological data set; Collect pest and disease data in the tea detection area, and form a pest and disease identification model based on the dynamic interaction of multiple pest and disease data; Associating the pest and disease identification model with the first growth model; constructing a tea growth model based on the pest and disease identification model and the first growth model; The tea growth model conducts an overall evaluation of the tea detection area in the tea garden, defines the corresponding tea growth status according to the tea growth model, each sub-area in the tea detection area and time, and defines the corresponding tea status evaluation map according to the tea growth status and the tea detection area.

2. The tea growth model evaluation method according to claim 1, characterized in that: The method of locating the tea detection area in the tea garden and collecting multiple tea parameters based on the drone and the tea detection area includes: A three-dimensional diagram of the tea garden is collected, and the tea part and the non-tea part are defined according to the recognition of the three-dimensional diagram; Define tea inspection areas in the tea garden based on the location of tea parts and the drone's review images; Locate the tea testing area in the tea garden; Associate the tea inspection area and the drone in the tea garden, and define the inspection path according to the tea inspection area and the drone in the tea garden; Triggering the UAV to dynamically detect the tea detection area along the detection path; Based on the dynamic detection of the tea detection area by the drone, multiple tea parameters are collected. The multiple tea parameters are in different dimensions and present the growth parameters of the tea detection area as a whole.

3. The tea growth model evaluation method according to claim 1, characterized in that: The data processing based on the plurality of tea parameters to output the corresponding data set includes: Freeze multiple tea parameters; Define exception parameters based on traversal of multiple tea parameters; Defining abnormal events according to various abnormal parameters, corresponding positions and associated matching tables; Define the corresponding abnormal level according to abnormal events and abnormal identification models; Based on the abnormal events, abnormal levels and tea detection areas, the optimization logic is triggered, and each abnormal parameter is autonomously optimized according to the optimization logic to obtain the optimized tea parameters; A corresponding data set is constructed based on the optimized tea parameters, the tea parameters in a non-abnormal state, and the tea detection area, and the corresponding data set is output.

4. The tea growth model evaluation method according to claim 3, characterized in that: The step of constructing a first growth model according to the data set and the meteorological data set includes: Freeze the data set; Forming a plurality of data combinations according to the division of the data set; Collect meteorological data sets based on meteorological detection in tea detection areas; Link multiple data sets and meteorological data sets; A first growth model is constructed based on the plurality of data combinations and the meteorological data set.

5. The tea growth model evaluation method according to claim 4, characterized in that: The method of collecting pest and disease data in the tea detection area and forming a pest and disease identification model according to the dynamic interaction of multiple pest and disease data includes: Define the tea testing area and conduct pest and disease testing in the tea testing area; Collect corresponding pest and disease data based on the pest and disease detection in the tea testing area; Collect multiple pest and disease data and dynamically interact with the pest and disease data; A pest and disease identification model is formed based on the dynamic interaction of multiple pest and disease data and regional calculations of tea detection areas.

6. The tea growth model evaluation method according to claim 5, characterized in that: The associating pest and disease identification model and the first growth model; constructing a tea growth model according to the pest and disease identification model and the first growth model, including: Fixed-frame pest and disease identification model; The first growth model is collected, and the pest and disease identification model and the first growth model are associated.

7. The tea growth model evaluation method according to claim 6, characterized in that: The associating pest and disease identification model and the first growth model; constructing a tea growth model according to the pest and disease identification model and the first growth model, further comprising: Conduct multi-dimensional deductions on the pest and disease identification model and the first growth model; Collecting a plurality of deduction data based on the deduction of the pest and disease identification model and the first growth model; Outputting a corresponding training data set according to the matching of the plurality of deduction data and the corresponding deduction dimensions; A tea growth model is constructed based on the training data set and the model matching the tea detection area.

8. The tea growth model evaluation method according to claim 7, characterized in that: The tea growth model performs an overall evaluation on the tea detection area in the tea garden, defines corresponding tea growth states according to the tea growth model, each sub-area in the tea detection area, and time, and defines corresponding tea state evaluation graphs according to the tea growth states and the tea detection area, including: Freeze-frame tea growth model; Correlate tea growth models and tea detection areas in tea gardens; The tea growth model provides an overall assessment of the tea testing area in the tea garden.

9. The tea growth model evaluation method according to claim 8, characterized in that: The tea growth model performs an overall evaluation on the tea detection area in the tea garden, defines corresponding tea growth states according to the tea growth model, each sub-area in the tea detection area and time, and defines corresponding tea state evaluation graphs according to the tea growth states and the tea detection area, and also includes: Define multiple growth coefficients according to the tea growth model and the tea detection area; The corresponding tea growth states are defined according to a plurality of growth coefficients, each sub-area in the tea detection area, and time; The tea growth status and the tea detection area are associated, and a corresponding tea status evaluation diagram is defined according to the tea growth status and the tea detection area.

10. A tea growth model evaluation system, characterized in that: The tea growth model evaluation system is applied to the tea growth model evaluation method as claimed in any one of claims 1 to 9, and the tea growth model evaluation system comprises: The collection module is used to locate the tea detection area in the tea garden and collect multiple tea parameters based on the drone and the tea detection area; A data set module, used for outputting corresponding data sets based on data processing of multiple tea parameters; A first growth module, used for constructing a first growth model according to the data set and the meteorological data set; The pest and disease module is used to collect pest and disease data in the tea detection area and form a pest and disease identification model based on the dynamic interaction of multiple pest and disease data; A tea growth module, used to associate the pest and disease identification model with the first growth model; and to construct a tea growth model according to the pest and disease identification model and the first growth model; The evaluation module is used to conduct an overall evaluation of the tea detection area in the tea garden based on the tea growth model, define the corresponding tea growth status according to the tea growth model, each sub-area in the tea detection area and time, and define the corresponding tea status evaluation map according to the tea growth status and the tea detection area.

Images