Orchard environment monitoring management system

Abstract

The invention relates to an orchard environment monitoring management system. The system comprises a first acquisition unit used for acquiring soil monitoring data; wherein the soil monitoring data at least comprise soil humidity, soil temperature, soil PH value, soil conductivity and soil tension value; the second acquisition unit is used for acquiring fruit tree growth state information; wherein the fruit tree growth state information comprises growth images of the fruit tree in different growth stages; the third acquisition unit is used for acquiring climate monitoring data; the data processing unit is used for processing the soil monitoring data, the fruit tree growth state information and the climate monitoring data; and the prediction unit is used for predicting the processed soil monitoring data, the fruit tree growth state information and the climate monitoring data through a pre-trained target LSTM network model so as to predict the growth condition of the fruit tree and the orchard environment condition. According to the invention, fruit farmers are helped to make management plans in advance, reasonably arrange manpower and material resources, and realize fine management.

Description

Technical Field

[0001] This application relates to the field of agricultural technologies, and particularly to an orchard environment monitoring and management system. Background Art

[0002] Traditional orchard planting management has long relied on a pure manual model. Fruit farmers shuttle among fruit trees every day and make decisions on the fruit tree planting process based on their accumulated experience and intuition over the years. This manual planting management mode often relies on the experience and intuition of fruit farmers to make decisions, and cannot integrate and scientifically analyze relevant planting data during the orchard planting process. There are subjectivity and uncertainty, resulting in obvious blindness and randomness in decision-making on key planting environments. This may lead to inaccuracy of decisions and instability of effects. Therefore, more scientific and data-driven methods are needed to support decision-making.

[0003] Therefore, it is necessary to provide a new technical solution to improve one or more problems existing in the above solution.

[0004] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of this application, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of this application is to provide an orchard environment monitoring and management system, thereby at least to some extent overcoming one or more problems caused by the limitations and defects of related technologies.

[0006] According to the first aspect of the embodiments of this application, an orchard environment monitoring and management system is provided, and the system includes:

[0007] A first collection unit for collecting soil monitoring data; wherein, the soil monitoring data includes at least soil humidity, soil temperature, soil pH value, soil conductivity, and soil tension value;

[0008] A second collection unit for collecting fruit tree growth status information; wherein, the fruit tree growth status information includes growth images of fruit trees at different growth stages;

[0009] A third collection unit for collecting climate monitoring data; wherein, the climate monitoring data includes at least air humidity, air temperature, wind speed, wind direction, air pressure, rainfall, and sunshine;

[0010] A data processing unit for processing the soil monitoring data, the fruit tree growth status information, and the climate monitoring data;

[0011] A prediction unit for predicting the processed soil monitoring data, the fruit tree growth status information, and the climate monitoring data through a pre-trained target LSTM network model to predict the growth conditions of fruit trees and the orchard environment conditions.

[0012] In an embodiment of the present application, the data processing unit is further configured to perform data processing on sample data; wherein, the sample data includes historical soil monitoring data, historical fruit tree growth status information, and historical climate monitoring data.

[0013] In an embodiment of the present application, the prediction unit includes:

[0014] A training module for inputting the sample data after data processing into an original LSTM network model and performing training to obtain a target LSTM network model; wherein, the target LSTM network model is an improved LSTM network model, and the improved LSTM network model is:

[0015]

[0016] i t =σ(W i X t +U i h t-1 +b i )(3)

[0017] f t =σ(W f X t +U f h t-1 +b f )(4)

[0018] o t =σ(W o X t +U o h t-1 +b o )(5)

[0019] g t =tanh(W g X t +U g h t-1 +b g )(6)

[0020] F t =σ(f t )(7)

[0021]

[0022] Among them, c represents the internal state, h represents the system state, f represents the forgetting gate, i represents the input gate, o represents the output gate, σ represents the sigmoid activation function, and tanh represents the tanh activation function.

[0023] In an embodiment of the present application, it further includes: a storage unit for storing the soil monitoring data, the fruit tree growth status information, and the climate monitoring data.

[0024] In an embodiment of the present application, it further includes:

[0025] A display unit for displaying the growth situation of the fruit trees and the orchard environment situation for fruit farmers to view.

[0026] In an embodiment of the present application, it further includes:

[0027] A knowledge base management unit for managing agricultural knowledge.

[0028] In an embodiment of the present application, the knowledge base management unit includes:

[0029] An input unit for inputting agricultural knowledge;

[0030] An audit unit for auditing the agricultural knowledge.

[0031] In an embodiment of the present application, the knowledge base management unit includes:

[0032] A classification unit for classifying the audited agricultural knowledge according to the knowledge granularity, where the knowledge granularity includes coarse-grained knowledge and fine-grained knowledge; among them, the coarse-grained knowledge at least includes water and fertilizer management strategies, plant protection management strategies, and horticultural management strategies, and the fine-grained knowledge at least includes fruit tree nutrition programs and fruit tree pest control programs.

[0033] In an embodiment of the present application, the knowledge base management unit includes:

[0034] A retrieval unit for obtaining relevant agricultural knowledge from the knowledge base unit according to the retrieval term.

[0035] In an embodiment of the present application, the knowledge base management unit includes:

[0036] An editing module for editing the agricultural knowledge in the knowledge base management unit; among them, the editing methods in the knowledge base management unit include modification, deletion, or addition.

[0037] The technical solution provided by the embodiment of the present application may include the following beneficial effects:

[0038] In one embodiment of the present application, through the above system, the prediction unit uses a pre-trained target LSTM network model to analyze and predict the processed soil monitoring data, fruit tree growth status information, and climate monitoring data, and anticipates in advance the growth situation of fruit trees and the change trend of the orchard environment. This helps fruit farmers formulate management plans in advance, reasonably arrange human and material resources, achieve refined management, greatly reduce management costs, and improve economic benefits. At the same time, long-term monitoring and data analysis also provide a scientific basis for the sustainable development of the orchard, promoting the orchard industry to move towards the direction of intelligence and modernization.

[0039] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. Brief Description of the Drawings

[0040] The drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0041] Figure 1 Schematically shows a block diagram of an orchard environment monitoring and management system in an exemplary embodiment of the present application. Detailed Embodiments

[0042] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the present application will be more complete and comprehensive, and will fully convey the concept of the example embodiments to those skilled in the art. The features, structures, or characteristics described can be combined in any suitable manner in one or more embodiments.

[0043] In addition, the drawings are only schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0044] In this example embodiment, an orchard environment monitoring and management system is provided. Refer to Figure 1As shown in the figure, the system 100 includes: a first acquisition unit 101, a second acquisition unit 102, a third acquisition unit 103, a data processing unit 104, and a prediction unit 105. Among them, the first acquisition unit 101 is used to acquire soil monitoring data; among them, the soil monitoring data at least includes soil humidity, soil temperature, soil pH value, soil conductivity, and soil tension value; the second acquisition unit 102 is used to acquire fruit tree growth status information; among them, the fruit tree growth status information includes growth images of different growth stages of the fruit tree; the third acquisition unit 103 is used to acquire climate monitoring data; among them, the climate monitoring data at least includes air humidity, air temperature, wind speed, wind direction, air pressure, rainfall, and sunshine; the data processing unit 104 performs data processing on the soil monitoring data, fruit tree growth status information, and climate monitoring data; the prediction unit 105 is used to predict the growth situation of the fruit tree and the orchard environment situation by using a pre-trained target LSTM network model for the processed soil monitoring data, fruit tree growth status information, and climate monitoring data.

[0045] It can be understood that the first acquisition unit 101 includes a soil temperature and humidity monitor, a soil tensiometer, a soil pH value monitor, and a soil conductivity meter. The soil temperature and humidity monitor acquires soil humidity and soil temperature. Through the soil temperature and humidity monitor, the changes in soil water content (soil humidity) and temperature (soil temperature) can be grasped in real time, providing a reference for measures such as irrigation and fertilization.

[0046] The soil tension value is acquired through the soil tensiometer, and the soil pH value is acquired through the soil pH value monitor. Among them, the soil pH value, that is, the soil acidity and alkalinity, has an important impact on soil fertility. For example, when the soil pH value exceeds the suitable range for apple growth, with the increase or decrease of the pH value, the growth of apples will be hindered and the development will be delayed.

[0047] Soil conductivity is an index to measure the concentration of soluble ions in the soil. The level of soil conductivity is related to the content of soluble ions in the soil, and soluble ions are one of the nutrient sources necessary for plant growth. Therefore, the level of soil conductivity can reflect the nutrient supply situation in the soil. The soil conductivity is acquired through the soil conductivity meter. The soil tensiometer is a sensor used to measure the soil water tension.

[0048] Specifically, soil temperature and humidity monitors, soil tensiometers, soil pH monitors, and soil conductivity meters are set up in multiple locations in the orchard, and relevant data is collected regularly. For example, in a certain week in summer, the relevant data collected is as follows: the soil humidity is stable at about 60%, the soil temperature is between 28°C and 30°C, the soil pH value is 6.5, the soil conductivity is 1.2 mS / cm, and the soil tension value is 100 kPa. These data reflect the basic physical and chemical properties of the orchard soil and provide a reference for subsequent irrigation and fertilization of fruit trees. Among them, the layout positions of the soil temperature and humidity monitors, soil tensiometers, soil pH monitors, and soil conductivity meters can be specifically set according to the actual situation, and this application does not limit it.

[0049] The second acquisition unit 102 includes a drone. The growth status information of fruit trees is generally collected by the drone. By collecting the growth images of fruit trees at different growth stages through the drone, the growth of crops can be accurately collected, so that fruit farmers can better understand the growth of fruit trees and provide a data basis for agricultural production.

[0050] Specifically, during the flowering period of the fruit tree, the captured growth image shows that the flower opening rate reaches 80%, and the flowers are healthy and brightly colored. During the fruit swelling period, the diameter of the fruit can be measured through image analysis. After measurement, the average fruit diameter reaches 2 cm, and it is judged that the growth of the fruit tree is in the normal stage.

[0051] The third acquisition unit 103 includes an orchard weather station. The orchard weather station is a device used to monitor agricultural meteorological data, mainly monitoring air humidity, air temperature, wind speed, wind direction, air pressure, rainfall, and sunshine, etc.

[0052] Specifically, the orchard weather stations installed in various locations of the orchard collect climate monitoring data in real time. The climate monitoring data for a certain day is as follows: air humidity 50%, air temperature 32°C, wind speed 2 m / s, wind direction southeast, air pressure 101.3 kPa, rainfall 5 mm in the past 24 hours, and sunshine duration 8 hours. Among them, the layout position of the orchard weather station can be specifically set according to the actual situation, and this application does not limit it.

[0053] After the corresponding data is collected by the first acquisition unit 101, the second acquisition unit 102, and the third acquisition unit 103, the data processing unit 104 needs to process the corresponding data so that the processed corresponding data can be input into the pre-trained target LSTM network model. Among them, when the data processing unit 104 processes the corresponding data (that is, soil monitoring data, fruit tree growth status information, and climate monitoring data), it mainly includes methods such as data cleaning and normalization processing. The data cleaning and normalization processing can be understood with reference to the existing technology.

[0054] This application takes the processed soil monitoring data, fruit tree growth status information, and climate monitoring data as inputs and transmits them to a pre-trained target LSTM network model. The target LSTM network model performs forward propagation calculations based on the input data and finally outputs the prediction results of the growth conditions of the fruit trees and the orchard environment, facilitating the provision of scientific guidance and decision-making for fruit farmers.

[0055] In an embodiment of this application, through the above system, on the one hand, by collecting soil monitoring data, fruit tree growth status information, and climate monitoring data, it can help fruit farmers understand the soil, meteorology, and fruit tree growth conditions in the orchard in real time, provide a data basis for scientific planting and refined management, guide the life and production of the orchard, and optimize the growth environment of the fruit trees and improve the yield and quality of the orchard. On the other hand, the prediction unit 105 uses a pre-trained target LSTM network model to analyze and predict the processed soil monitoring data, fruit tree growth status information, and climate monitoring data, and pre-judge the growth conditions of the fruit trees and the change trends of the orchard environment in advance. This helps fruit farmers formulate management plans in advance, reasonably arrange human and material resources, achieve refined management, greatly reduce management costs, and improve economic benefits. At the same time, long-term monitoring and data analysis also provide a scientific basis for the sustainable development of the orchard, promoting the orchard industry to move towards the direction of intelligence and modernization.

[0056] Next, reference will be made to Figure 1 to describe the above system in the exemplary embodiment in more detail.

[0057] In one embodiment, the data processing unit 104 is further configured to perform data processing on sample data; wherein, the sample data includes historical soil monitoring data, historical fruit tree growth status information, and historical climate monitoring data.

[0058] It can be understood that in addition to performing data processing on the collected soil monitoring data, fruit tree growth status information, and climate monitoring data, the data processing unit 104 can also perform data processing on historical soil monitoring data, historical fruit tree growth status information, and historical climate monitoring data. Among them, the historical soil monitoring data also at least includes soil humidity, soil temperature, soil pH value, soil conductivity, and soil tension value, the historical fruit tree growth status information also includes growth images of the fruit trees at different growth stages, and the historical climate monitoring data also at least includes air humidity, air temperature, wind speed, wind direction, air pressure, rainfall, and sunshine.

[0059] In one embodiment, the prediction unit 105 includes:

[0060] A training module, configured to input the sample data after data processing into an original LSTM network model and perform training to obtain a target LSTM network model; wherein, the target LSTM network model is an improved LSTM network model, and the improved LSTM network model is as follows:

[0061]

[0062] i t = σ(W i X t + U i h t-1 + b i )(3)

[0063] f t = σ(W f X t + U f h t-1 + b f )(4)

[0064] o t = σ(W o X t + U o h t-1 + b o )(5)

[0065] g t = tanh(W g X t + U g h t-1 + b g )(6)

[0066] F t = σ(f t )(7)

[0067]

[0068] Wherein, c represents the internal state, h represents the system state, f represents the forget gate, i represents the input gate, o represents the output gate, σ represents the sigmod activation function, and tanh represents the tanh activation function.

[0069] It can be understood that the present application adopts an LSTM network model. The core of the LSTM network model is the cell state, which is represented by a horizontal line passing through the cell. An LSTM network model contains three gates to control the cell state, namely the forget gate, the input gate, and the output gate. For specific understanding, reference can be made to the prior art and will not be elaborated here. However, in the traditional LSTM network model, the forget gate passes through the sigmod activation function, and the output value of the sigmod activation function is 0 to 1. The forget gate determines how much of the information flow from the previous state to the next state will be discarded. If the traditional LSTM network model is used, after passing through multiple traditional LSTM network models, the data flow passing through the forget gate is very likely to be filtered out. The improved LSTM network model mainly modifies the output of the forget gate. After passing through Ft, the output value of the activation function is 0.5 to 1. This setting can effectively reduce information loss. The formula of the improved LSTM network model is as shown in the above formulas (1) to (9). By improving the traditional LSTM network model, the algorithm of the improved LSTM network model converges faster. As the sample data gradually increases, the prediction of the growth situation of fruit trees and the orchard environment will become more and more accurate.

[0070] It should be noted that after the forget gate in the improved LSTM network model passes through the sigmod activation function, it passes through a preset activation function again so that the output value is between 0.5 and 1.

[0071] In one embodiment, it further includes:

[0072] A storage unit for storing the soil monitoring data, the fruit tree growth status information, and the climate monitoring data.

[0073] It can be understood that the present application stores the collected soil monitoring data, fruit tree growth status information, and climate monitoring data in the storage unit. The storage unit is a double data rate synchronous dynamic random access memory, and its data transmission speed is twice the system clock frequency. Due to the increased speed, its transmission performance is more excellent.

[0074] The storage unit can uniformly collect the soil monitoring data, fruit tree growth status information, and climate monitoring data, effectively avoiding the loss or omission of these data, and maintaining the integrity and accuracy of these data for a long time. For example: When recording the annual soil humidity change in the orchard, complete data helps fruit farmers identify the humidity differences in different seasons and provides a basis for subsequent irrigation decisions.

[0075] Fruit farmers or agricultural experts can directly obtain the required data from the storage unit and quickly conduct integrated analysis. Through the comprehensive study and judgment of soil fertility, climate conditions, and the growth trend of fruit trees, a precise farming operation plan can be formulated. For example, when the soil lacks nitrogen elements and the climate is suitable, targeted fertilization operations can be carried out in a timely manner.

[0076] In one embodiment, it further includes:

[0077] A display unit for displaying the growth situation of the fruit trees and the orchard environment situation for the fruit farmers to view.

[0078] It can be understood that after the growth situation of the fruit trees and the orchard situation are predicted, they are displayed through the display unit, which is convenient for the fruit farmers to view, so as to provide scientific guidance and decision-making.

[0079] Furthermore, the system further includes a data statistics module for statistically analyzing the collected soil monitoring data, climate monitoring data, etc.

[0080] For example: Data summary statistics: Calculate statistical indicators such as the average value, maximum value, minimum value, and total of the soil monitoring data. The statistical time period can be flexibly selected, including years, months, days, hours, 10 minutes, or any time period.

[0081] Seasonal analysis: The system can perform seasonal analysis on the soil monitoring data to identify the variation laws of the soil monitoring data in different seasons or time periods.

[0082] After analyzing the soil monitoring data, a statistical report is generated. Among them, generating a statistical report: The report includes the summary of soil monitoring data, trend analysis, seasonal analysis, etc., and is presented in the form of charts, tables, etc., to help farmers better understand and utilize the soil monitoring data.

[0083] Another example: Data summary statistics: Calculate statistical indicators such as the average value, maximum value, minimum value, and total of the fruit tree growth status information. The statistical time period can be flexibly selected, including years, months, days, hours, 10 minutes, or any time period.

[0084] Seasonal analysis: The system can perform seasonal analysis on the fruit tree growth status information to identify the variation laws of the fruit tree growth status information in different seasons or time periods.

[0085] After analyzing the fruit tree growth status information, a statistical report is generated. Among them, generating a statistical report: The report includes the summary of fruit tree growth status information, trend analysis, seasonal analysis, etc., and is presented in the form of charts, tables, etc., to help farmers better understand and utilize the fruit tree growth status information.

[0086] Another example: Data summary statistics: Calculate statistical indicators such as the average value, maximum value, minimum value, and total of the climate monitoring data. The statistical time period can be flexibly selected, including years, months, days, hours, 10 minutes, or any time period.

[0087] Seasonal analysis: The system can perform seasonal analysis on the climate monitoring data to identify the variation laws of the climate monitoring data in different seasons or time periods.

[0088] After analyzing the climate monitoring data, a statistical report is generated. Among them, generating a statistical report: The report includes the summary of climate monitoring data, trend analysis, seasonal analysis, etc., and is presented in the form of charts, tables, etc., to help farmers better understand and utilize the climate monitoring data.

[0089] It should also be noted that the above statistical report can be displayed to farmers through the display unit to help farmers better understand and utilize the soil monitoring data and climate monitoring data.

[0090] In this application, when fruit farmers plant orchards, they are involved in agricultural knowledge. Generally, they need to rely on professional agricultural experts and the knowledge and experience of agricultural science. However, currently, these agricultural knowledge cannot be efficiently managed, making it inconvenient for fruit farmers to quickly understand, thus affecting the growth of fruit trees planted.

[0091] Therefore, the orchard environment monitoring and management system in this application further includes:

[0092] A knowledge base management unit for managing agricultural knowledge.

[0093] It can be understood that agricultural knowledge is numerous and scattered. Through the knowledge base management unit, this knowledge can be collected, sorted, and classified to achieve centralized storage and manage agricultural knowledge, providing a scientific theory for farmers.

[0094] In one embodiment, the knowledge base management unit includes:

[0095] An input unit for inputting agricultural knowledge;

[0096] An audit unit for auditing the agricultural knowledge.

[0097] It can be understood that various agricultural knowledge from different regions, different farmers, or experts is centralized, and various agricultural knowledge is input into the input unit. Then, the manager audits the collected agricultural knowledge through the audit unit to ensure the scientificity, accuracy, and reliability of the knowledge. The auditors can check the source of the knowledge and the authenticity of the content to prevent incorrect or misleading information from entering the knowledge resource library, thereby ensuring that farmers and relevant personnel can obtain correct knowledge. Among them, agricultural knowledge at least includes planting techniques, breeding methods, pest and disease control, etc., to achieve the effective accumulation of agricultural knowledge, facilitate learning and inheritance, and avoid the loss of knowledge.

[0098] The audit unit can evaluate and optimize the integrity, logic, and practicality of agricultural knowledge. For some agricultural knowledge with unclear expressions and incomplete content, it is supplemented and improved to make it more in line with the actual application requirements and enhance the quality of the entire agricultural knowledge system.

[0099] In one embodiment, the knowledge base management unit includes:

[0100] A classification unit for classifying the reviewed agricultural knowledge according to the knowledge granularity, where the knowledge granularity includes coarse-grained knowledge and fine-grained knowledge; wherein the coarse-grained knowledge at least includes water and fertilizer management strategies, plant protection management strategies, and horticultural management strategies, and the fine-grained knowledge at least includes fruit tree nutrition programs and fruit tree pest control programs.

[0101] It can be understood that with the help of the classification unit, whether it is agricultural practitioners, scientific researchers, or learners, they can quickly locate the required knowledge. For example, when a grower faces fruit tree pest problems, they can directly obtain targeted guidance in the "fruit tree pest control program" of the fine-grained knowledge; if a farm manager needs to formulate an overall management strategy, the "plant protection management strategy" and "water and fertilizer management strategy" in the coarse-grained knowledge can provide comprehensive and macroscopic ideas, saving a large amount of time cost for retrieving knowledge.

[0102] Agricultural production has strong professionalism and pertinence, and different scenarios and crops require different management programs. The classification unit enables users to obtain the knowledge that best suits their actual needs, avoiding resource waste and production losses caused by knowledge mismatch. For example: For precise water and fertilizer management in orchards, farmers can formulate scientific fertilization and irrigation plans based on the "fruit tree nutrition program", significantly improving agricultural production efficiency.

[0103] The classification unit provides a clear structure for the update and supplement of agricultural knowledge. When new agricultural technologies or research results emerge, they can be conveniently classified into the corresponding coarse-grained or fine-grained categories. For example, when a new special pest control agent for fruit trees is newly developed, it can be quickly incorporated into the "fruit tree pest control program" section to ensure that agricultural knowledge always maintains timeliness and practicality.

[0104] In one embodiment, the knowledge base management unit includes:

[0105] A retrieval unit for obtaining relevant agricultural knowledge from the knowledge base unit according to the retrieval term.

[0106] It can be understood that through the retrieval unit, new agricultural technology information can be quickly transmitted to practitioners. For example: When farmers face pest control problems, they can obtain the latest control technologies and drug usage instructions through retrieval, take effective measures in a timely manner, reduce crop losses, accelerate the application of new technologies in agricultural production, and promote the process of agricultural modernization.

[0107] In one embodiment, the knowledge base management unit includes:

[0108] An editing module for editing agricultural knowledge in the knowledge base management unit; wherein the editing methods for editing the knowledge base management unit include modification, deletion, or addition.

[0109] It can be understood that the content in the knowledge base can be added, edited, deleted, classified, tagged, and associated, etc., so as to better organize and retrieve knowledge. Manage the knowledge granularity in knowledge base management: Coarse-grained knowledge representation contains higher-level abstractions and summaries, and is suitable for understanding the overall situation and making decisions. For example, water and fertilizer management strategies, plant protection management strategies, horticultural management strategies, etc. all belong to coarse-grained knowledge. Fine-grained knowledge representation is more specific and detailed, and is suitable for solving specific problems and providing operation guidance. For example, fruit tree nutrition programs, fruit tree pest control programs, etc. all belong to fine-grained knowledge. At the same time, the addition of multiple knowledge sources is supported, including technicians adding knowledge content based on practice summaries or relevant experts adding knowledge content, etc.

[0110] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and the practice of the invention disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include known common knowledge or conventional technical means in the technical field not disclosed in the present application.

Claims

1. An orchard environmental monitoring and management system, characterized in that Comprising: A first acquisition unit for acquiring soil monitoring data; wherein, the soil monitoring data at least includes soil humidity, soil temperature, soil pH value, soil conductivity, and soil tension value; A second acquisition unit for acquiring fruit tree growth status information; wherein, the fruit tree growth status information includes growth images of fruit trees at different growth stages; A third acquisition unit for acquiring climate monitoring data; wherein, the climate monitoring data at least includes air humidity, air temperature, wind speed, wind direction, air pressure, rainfall, and sunshine; A data processing unit for processing the soil monitoring data, the fruit tree growth status information, and the climate monitoring data; A prediction unit for predicting the growth situation of fruit trees and the orchard environment situation by using a pre-trained target LSTM network model for the processed soil monitoring data, the fruit tree growth status information, and the climate monitoring data.

2. The orchard environment monitoring and management system according to claim 1, wherein, The data processing unit is further configured to process sample data; wherein, the sample data includes historical soil monitoring data, historical fruit tree growth status information, and historical climate monitoring data.

3. The orchard environment monitoring and management system according to claim 2, characterized in that, The prediction unit includes: A training module for inputting the processed sample data into an original LSTM network model and performing training to obtain a target LSTM network model; wherein, the target LSTM network model is an improved LSTM network model, and the improved LSTM network model is: i t = σ(W i X t + U i h t-1 + b i )(3) f t = σ(W f X t + U f h t-1 + b f )(4) o t = σ(W o X t + U o h t-1 + b o )(5) g t = tanh(W g X t + U g h t-1 + b g )(6) F t = σ(f t )(7) Wherein, c represents the internal state, h represents the system state, f represents the forget gate, i represents the input gate, o represents the output gate, σ represents the sigmod activation function, and tanh represents the tanh activation function.

4. The orchard environment monitoring and management system according to claim 1, characterized in that, Further comprising: A storage unit for storing the soil monitoring data, the fruit tree growth status information, and the climate monitoring data.

5. The orchard environment monitoring and management system according to claim 1, characterized in that Further comprising: A display unit for displaying the growth situation of the fruit trees and the orchard environment situation for fruit farmers to view.

6. The orchard environment monitoring and management system according to claim 1, wherein Further comprising: A knowledge base management unit for managing agricultural knowledge.

7. The orchard environment monitoring and management system according to claim 6, characterized in that, The knowledge base management unit includes: An input unit for inputting agricultural knowledge; An audit unit for auditing the agricultural knowledge.

8. The orchard environment monitoring and management system according to claim 7, characterized in that, The knowledge base management unit includes: A classification unit for classifying the audited agricultural knowledge according to knowledge granularity, wherein the knowledge granularity includes coarse-grained knowledge and fine-grained knowledge; wherein, the coarse-grained knowledge at least includes water and fertilizer management strategies, plant protection management strategies, and horticultural management strategies, and the fine-grained knowledge at least includes fruit tree nutrition programs and fruit tree pest control programs.

9. The orchard environment monitoring and management system according to claim 6, wherein The knowledge base management unit includes: A retrieval unit for obtaining relevant agricultural knowledge from the knowledge base unit according to a retrieval term.

10. The orchard environment monitoring and management system according to claim 6, wherein The knowledge base management unit includes: An editing module for editing the agricultural knowledge in the knowledge base management unit; wherein, the editing methods in the knowledge base management unit include modification, deletion, or addition.

Images