Rice-fish symbiosis multifunctional water quality monitoring and analyzing device and use method

Abstract

The invention discloses a rice-fish symbiosis multifunctional water quality monitoring and analyzing device and a use method. The device comprises the following core modules: a data acquisition module, which is responsible for acquiring water quality data from front-end monitoring equipment in real time; the data processing module is used for deeply processing the collected water quality data and image information; the data analysis module is used for introducing a prediction model based on machine learning and accurately predicting a future water quality change trend in combination with historical water quality data and real-time monitoring data; the intelligent decision support module is responsible for automatically identifying potential risks in water quality and generating targeted intelligent decision suggestions according to the potential risks; according to the method, image recognition and spectral analysis technologies are introduced, a high-definition camera, a precise underwater spectrometer and other equipment are utilized, and a deep learning algorithm and a spectral database are combined, so that precise recognition and classification of suspended solids, algae and other biocenosis in water are realized, and more comprehensive and multi-dimensional information is provided for water quality evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality monitoring, and in particular to a rice-fish symbiosis multifunctional water quality monitoring and analysis device and a use method thereof. Background Art

[0002] The rice-fish symbiosis system, as an innovative ecological integrated breeding model, combines rice cultivation with the breeding of aquatic organisms such as fish, snails, and shrimps, achieving efficient and environmentally friendly agricultural production. The system makes full use of the biodiversity and spatial resources in the rice field ecosystem. Through the activities of aquatic organisms such as fish, it promotes the turning of rice field soil and the decomposition of organic matter. At the same time, fish and other organisms can also prey on pests and weeds in rice fields, reducing dependence on chemical pesticides and herbicides. In addition, the excrement of aquatic organisms provides rich nutrients for rice, promoting the growth of rice and increasing its yield. The stable operation of the rice-fish symbiosis system is inseparable from the effective monitoring and management of water quality. The quality of water is directly related to the survival of aquatic organisms and the balance of the rice field ecosystem.

[0003] Existing water quality monitoring technologies usually only focus on limited water quality parameters, such as temperature, pH value, dissolved oxygen, etc. Although these parameters are important, they are not enough to fully reflect the overall condition of water quality. With the promotion and in-depth research of rice-fish symbiosis system, the demand for water quality monitoring is becoming increasingly diversified, and more comprehensive water quality parameter monitoring is needed to ensure the stable operation of the system and the quality and safety of agricultural products. Therefore, a multifunctional water quality monitoring and analysis device for rice-fish symbiosis and its use method are proposed, aiming to achieve comprehensive, accurate and real-time monitoring of water quality parameters in rice-fish symbiosis system, and provide scientific basis and technical support for agricultural production. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art, that the prior art may only be able to monitor limited water quality parameters, such as temperature, pH value, etc., but cannot fully reflect the water quality conditions. With the development of rice-fish symbiosis systems, the demand for water quality monitoring is becoming increasingly diversified, and more comprehensive parameter monitoring is needed to ensure the stable operation of the system. A multifunctional water quality monitoring and analysis device for rice-fish symbiosis and a method of use are proposed.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A rice-fish symbiosis multifunctional water quality monitoring and analysis device, comprising:

[0007] Data acquisition module: responsible for collecting water quality data in real time from front-end monitoring equipment (such as temperature sensors, pH sensors, dissolved oxygen sensors, etc.), and obtaining water quality image information through image recognition and spectral analysis technology;

[0008] Data processing module: responsible for in-depth processing of water quality data and image information, including data filtering (noise removal), denoising (improving data purity), data fusion (integrating different sensor data into comprehensive information) and analysis (extracting valuable information from data);

[0009] Data analysis module: introduces a prediction model to predict future water quality changes based on historical data and provide forward-looking guidance for water quality management;

[0010] Intelligent decision support module: responsible for building knowledge graphs and decision support, identifying potential problems in water quality, such as excessive pollution and nutrient imbalance, and generating intelligent decision suggestions based on this, including adjusting aquaculture density, optimizing fertilization plans, and placing ecological restoration agents;

[0011] Information sharing and collaboration module: As the core of the system, the information sharing and collaboration module is responsible for summarizing and integrating the data, reports and decision-making suggestions generated by each module and providing them to all authorized users for access;

[0012] The data acquisition module transmits the water quality data and image information collected in real time to the data processing module, and the data processing module transmits the processed data to the data analysis module and the intelligent decision support module. The data analysis module transmits the analysis results (such as water quality assessment report, prediction model output, etc.) to the intelligent decision support module, and the intelligent decision support module transmits the generated decision recommendations to the user terminal.

[0013] The above technical solution further includes:

[0014] Furthermore, the data acquisition module includes a front-end monitoring device and a data transmission unit. The front-end monitoring device includes a temperature sensor, a pH sensor, a dissolved oxygen sensor, an ammonia nitrogen sensor, a nitrate sensor, etc., as well as image recognition and spectral analysis equipment such as a camera and an underwater spectrometer, which are responsible for real-time collection of various physical and chemical parameters of water quality, as well as water quality image information. The front-end monitoring device transmits the collected raw data to the data transmission unit. The data transmission unit adopts high-speed communication technologies such as 5G and the Internet of Things (IoT), and is responsible for real-time transmission of various physical and chemical parameters of water quality, as well as water quality image information collected by the front-end monitoring device to the data processing module.

[0015] Furthermore, an edge computing unit is deployed near the front-end monitoring equipment, which is responsible for preliminary data processing, including data filtering, denoising, compression, etc., to reduce the amount of data transmission and improve the system response speed. The edge computing unit compresses the pre-processed data to reduce the transmission bandwidth requirement. The data transmission unit predicts the data transmission demand in the future based on historical data through a machine learning model. Based on the prediction results, the data transmission unit dynamically adjusts the data transmission plan, such as increasing the cache before the peak period and transmitting a large amount of data during the off-peak period. The data transmission unit uses an adaptive routing algorithm to select the optimal path to transmit data according to the network topology and real-time conditions.

[0016] Furthermore, the data processing module includes a data receiving unit, a data preprocessing unit, a data fusion unit and a data analysis unit. The data receiving unit is responsible for receiving the water quality data and image information transmitted by the data transmission unit. The data preprocessing unit performs preliminary data processing, including data filtering (noise removal) and denoising (improving data purity). The data preprocessing unit receives the data from the data receiving unit and outputs it to the data fusion unit after processing. The data fusion unit integrates data from different sensors (such as temperature, pH value, dissolved oxygen, ammonia nitrogen, nitrate, etc.) to form comprehensive water quality information. The data fusion unit receives the preprocessed data, performs fusion processing, and then passes the comprehensive data to the data analysis unit. The data analysis unit extracts valuable information from the comprehensive data. The data analysis unit receives the fused data, performs analysis processing, and passes the result to the data analysis module.

[0017] Furthermore, the data analysis unit uses the trained image recognition model to identify suspended matter, algae and other biological communities in the water quality, and at the same time, uses the reference data in the spectral library for comparison to identify specific components and pollutants in the water body. The specific steps are:

[0018] Feature extraction: Use the trained convolutional neural network model to extract features from image information. These features may include color, texture, shape, etc., which can describe the characteristics of different objects in the image.

[0019] Classification and recognition: The extracted features are compared with the known features in the model, and the suspended matter, algae and other biological communities in the water are identified through the softmax classifier. This step will output the category and location information of each identified object;

[0020] Spectral comparison: compare the spectral data with the reference data in the spectral library, which contains the spectral characteristics of various known components and pollutants. Specific components and pollutants in the water can be identified through comparison;

[0021] Quantitative analysis: Quantitative analysis of spectral data to calculate the concentration or content of various components and pollutants in water bodies;

[0022] Data integration: Integrate the result data of image recognition and spectral analysis to form a comprehensive data set.

[0023] Furthermore, the data analysis module includes a feature extraction unit, a prediction model unit and a model optimization unit. The feature extraction unit is responsible for receiving the processing results provided by the data analysis unit and performing feature extraction. The feature extraction unit passes the extracted features to the prediction model unit to train the prediction model and predict future water quality changes. The prediction model unit predicts future water quality changes based on historical data using the prediction model. The model optimization unit receives the prediction results and real-time data to optimize the prediction model in real time. The prediction model unit outputs the prediction results to the intelligent decision support module.

[0024] Furthermore, the intelligent decision support module includes a data interface component, a knowledge graph construction unit, a decision support unit, an intelligent recommendation unit, an NLP unit and a user interface. The data interface component is responsible for receiving the data analysis results from the data processing and analysis module and the processed data from the data processing module. The knowledge graph construction unit constructs a water quality knowledge graph based on the received data. The knowledge graph construction unit interacts with the data interface component to obtain the required data. The knowledge graph construction unit transmits the constructed knowledge graph to the decision support unit. The decision support unit simulates, evaluates and predicts based on the knowledge graph. The decision support unit receives the knowledge graph transmitted by the knowledge graph construction unit and generates decision suggestions. The support unit interacts with the intelligent recommendation unit and the NLP unit to provide the information required for decision support. The intelligent recommendation unit provides personalized water quality management suggestions and plans based on the monitoring results and user needs. The intelligent recommendation unit interacts with the decision support unit to obtain decision support information. At the same time, the intelligent recommendation unit interacts with the user interface to deliver the recommendation results. The NLP unit is responsible for converting the monitoring data and decision suggestions into natural language text. The NLP unit receives the decision suggestions from the decision support unit, performs text conversion, and delivers the generated report or interpretation instructions to the user interface. The user interface serves as a bridge between the system and the user, receives the report or interpretation instructions generated by the NLP unit, displays them to the user, and receives user input requests.

[0025] Furthermore, the knowledge graph construction unit constructs the water quality knowledge graph based on the received data in the following specific steps:

[0026] Data collection: Collect water quality related data from the data interface component.

[0027] Entity recognition: Use CRF to perform entity recognition on text data related to water quality, identify key entities such as water area names and pollutant names, and evaluate the recognition results to ensure that the accuracy meets the requirements;

[0028] Relationship extraction: Define relationship templates according to actual needs, such as "pollutant-concentration", "water area-pollution status", etc., use template-based or deep learning methods to extract the relationship between entities from the text, and verify the extracted relationship to ensure the accuracy and rationality of the relationship;

[0029] Knowledge fusion: Use entity alignment algorithms to merge the same or similar entities from different data sources, handle conflicting information in the data fusion process, and ensure the consistency and accuracy of the knowledge graph;

[0030] Knowledge graph construction: Use standard representation methods such as RDF and OWL to convert entities and relationships into nodes and edges in the knowledge graph, and store the constructed knowledge graph in the graph database for subsequent query and reasoning.

[0031] Furthermore, the information sharing and collaboration module includes a cloud platform data storage and management unit, a data sharing platform unit, a collaborative work system unit, a multi-terminal access support unit, a data export and report generation unit, and an optimization and intelligent analysis unit. The cloud platform data storage and management unit is responsible for the storage, management and security of water quality monitoring data. The data sharing platform unit builds a data sharing platform based on the cloud platform to support data access by multiple users, multiple departments, and multiple regions. The collaborative work system unit provides task allocation, progress tracking, and message notification, and supports multi-user online collaboration. The collaborative work system unit interacts with the data sharing platform unit to obtain data as the basis for collaboration. At the same time, the collaborative work system unit feeds back the collaboration results to the data sharing platform unit. The multi-terminal access support unit supports users to access the data sharing platform and the collaborative work system through different terminals (PC, mobile phone, tablet, etc.). The data export and report generation unit provides data export and report generation functions to meet the needs of users for further analysis. The optimization and intelligent analysis unit: optimizes the information sharing process and collaboration mechanism.

[0032] A method for using a rice-fish symbiosis multifunctional water quality monitoring and analysis device, the specific steps of using the device include:

[0033] System deployment: According to the actual situation of the rice-fish symbiosis system, select appropriate monitoring points to deploy front-end monitoring equipment, install edge computing units, and connect them with the front-end monitoring equipment to ensure the real-time and stability of data transmission. Configure the communication network to ensure smooth data transmission between the front-end monitoring equipment and the cloud platform;

[0034] Data collection: Start the front-end monitoring equipment to collect water quality data (such as temperature, pH value, dissolved oxygen content, etc.) and image information (such as water color, suspended matter distribution, etc.) in real time. The edge computing unit performs preliminary processing and analysis on the collected data and transmits it to the cloud platform;

[0035] Data processing: The data processing module receives data and image information from the data acquisition module and performs in-depth processing, including data filtering, denoising, data fusion and analysis, to identify suspended matter, algae and other biological communities in the water, and at the same time, identify specific components and pollutants in the water;

[0036] Data analysis: The data analysis module introduces an AI prediction model to predict future water quality changes based on historical water quality data and current real-time data. The prediction results include water quality change trends, potential pollution risks, etc., providing forward-looking guidance for water quality management;

[0037] Information review and decision-making: The intelligent decision support module builds a knowledge graph based on the output results of the data analysis module, identifies potential problems in water quality (such as excessive pollution, nutrient imbalance, etc.), and generates intelligent decision-making suggestions based on this, providing personalized water quality management suggestions and plans, including adjusting breeding density, optimizing fertilization plans, and placing ecological restoration agents.

[0038] The present invention has the following beneficial effects:

[0039] 1. In the present invention, image recognition and spectral analysis technology are introduced to identify suspended matter, algae and other biological communities in water quality through high-definition cameras, underwater spectrometers and other equipment, providing more dimensional information for water quality assessment.

[0040] 2. In the present invention, high-speed communication technologies such as 5G and the Internet of Things are used to realize real-time transmission of monitoring data to the cloud or processing center. An adaptive routing algorithm is used to select the optimal path to transmit data according to the network topology and real-time conditions. Edge computing technology is developed, and edge computing units are deployed near the front-end monitoring equipment to reduce the amount of data transmission and improve the system response speed.

[0041] 3. In the present invention, by constructing a knowledge graph and a decision support system, intelligent decision support is provided for water quality management, and an intelligent recommendation system is introduced to provide personalized water quality management suggestions and solutions based on monitoring results and user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a system block diagram of a rice-fish symbiosis multifunctional water quality monitoring and analysis device and a method of use proposed by the present invention;

[0043] Figure 2A flow chart of the analysis of the data analysis unit in the present invention for identifying suspended matter, algae, other biological communities in water quality, and specific components and pollutants in the water body. DETAILED DESCRIPTION

[0044] 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.

[0045] See also Figure 1-Figure 2 As shown, the present invention is a rice-fish symbiosis multifunctional water quality monitoring and analysis device, comprising:

[0046] Data acquisition module: responsible for collecting water quality data in real time from front-end monitoring equipment (such as temperature sensors, pH sensors, dissolved oxygen sensors, etc.), and obtaining water quality image information through image recognition and spectral analysis technology;

[0047] Data processing module: responsible for in-depth processing of water quality data and image information, including data filtering (noise removal), denoising (improving data purity), data fusion (integrating different sensor data into comprehensive information) and analysis (extracting valuable information from data);

[0048] Data analysis module: Introducing AI prediction models to predict future water quality changes based on historical data and provide forward-looking guidance for water quality management;

[0049] Intelligent decision support module: responsible for building knowledge graphs and decision support, identifying potential problems in water quality, such as excessive pollution, nutrient imbalance, eutrophication, etc., and generating intelligent decision suggestions based on this. Intelligent decision suggestions include adjusting aquaculture density, optimizing fertilization plans, placing ecological restoration agents, optimizing the input of symbiotic aquatic products, etc.;

[0050] Information sharing and collaboration module: As the core of the system, the information sharing and collaboration module is responsible for summarizing and integrating the data, reports and decision-making suggestions generated by each module and providing them to all authorized users for access;

[0051] The data acquisition module transmits the real-time collected water quality data and image information to the data processing module. The data processing module transmits the processed data to the data analysis module and the intelligent decision support module. The data analysis module transmits the analysis results (such as water quality assessment report, prediction model output, etc.) to the intelligent decision support module. The intelligent decision support module transmits the generated decision recommendations to the user terminal.

[0052] The working principle of the rice-fish symbiosis multifunctional water quality monitoring and analysis device and the use method thereof proposed by the present invention is that the data acquisition module:

[0053] Temperature sensors, pH sensors, dissolved oxygen sensors and other front-end monitoring equipment collect water quality data in real time, and image recognition and spectral analysis technology obtain water quality image information;

[0054] The data processing module performs preliminary processing on the collected water quality data and image information, such as data filtering to remove noise, improve data purity, perform data fusion, integrate different sensor data to form comprehensive information, analyze data, identify suspended matter, algae and other biological communities in water quality, identify specific components and pollutants in water bodies, and extract valuable information;

[0055] The data analysis module uses historical data through predictive models to predict future water quality changes and generate water quality assessment reports and predictive model outputs. The intelligent decision support module builds a knowledge graph and decision support system to identify potential problems in water quality, such as excessive pollution and nutrient imbalance, and generates intelligent decision-making recommendations based on the analysis results, such as adjusting breeding density, optimizing fertilization plans, and introducing ecological restoration agents.

[0056] The information sharing and collaboration module aggregates and integrates the data, reports and decision-making recommendations generated by each module, and provides them to all authorized users for access, thus achieving information sharing and collaboration.

[0057] In one embodiment, for the above-mentioned data acquisition module, the data acquisition module includes a front-end monitoring device and a data transmission unit. The front-end monitoring device includes a temperature sensor, a pH sensor, a dissolved oxygen sensor, an ammonia nitrogen sensor, a nitrate sensor, etc., as well as image recognition and spectral analysis equipment such as a camera and an underwater spectrometer, which are responsible for real-time collection of various physical and chemical parameters of water quality, as well as water quality image information. The front-end monitoring device transmits the collected original data to the data transmission unit. The data transmission unit adopts high-speed communication technologies such as 5G and the Internet of Things (IoT), and is responsible for real-time transmission of various physical and chemical parameters of water quality, as well as water quality image information collected by the front-end monitoring device to the data processing module.

[0058] In one embodiment, for the above-mentioned front-end monitoring device, an edge computing unit is deployed near the front-end monitoring device to be responsible for preliminary data processing, including data filtering, denoising, compression, etc., to reduce the amount of data transmission and improve the system response speed. The edge computing unit compresses the pre-processed data to reduce the transmission bandwidth requirement. The data transmission unit predicts the data transmission demand in the future based on historical data through a machine learning model. Based on the prediction results, the data transmission unit dynamically adjusts the data transmission plan, such as increasing the cache before the peak period and transmitting a large amount of data during the off-peak period. The data transmission unit uses an adaptive routing algorithm to select the optimal path to transmit data according to the network topology and real-time conditions.

[0059] In one embodiment, for the above-mentioned data processing module, the data processing module includes a data receiving unit, a data preprocessing unit, a data fusion unit and a data analysis unit. The data receiving unit is responsible for receiving the water quality data and image information transmitted by the data transmission unit. The data preprocessing unit performs preliminary data processing, including data filtering (noise removal) and denoising (improving data purity). The data preprocessing unit receives the data from the data receiving unit and outputs it to the data fusion unit after processing. The data fusion unit integrates the data from different sensors (such as temperature, pH value, dissolved oxygen, ammonia nitrogen, nitrate, etc.) to form comprehensive water quality information. The data fusion unit receives the preprocessed data, performs fusion processing, and then passes the comprehensive data to the data analysis unit. The data analysis unit extracts valuable information from the comprehensive data. The data analysis unit receives the fused data, performs analysis processing, and passes the result to the data analysis module.

[0060] In one embodiment, for the above-mentioned data analysis unit, the data analysis unit uses the trained image recognition model to identify suspended matter, algae and other biological communities in the water quality, and at the same time, uses the reference data in the spectral library for comparison to identify specific components and pollutants in the water body. The specific steps are:

[0061] Feature extraction: Use the trained convolutional neural network model to extract features from image information. These features may include color, texture, shape, etc., which can describe the characteristics of different objects in the image.

[0062] Classification and recognition: The extracted features are compared with the known features in the model, and the suspended matter, algae and other biological communities in the water are identified through the softmax classifier. This step will output the category and location information of each identified object;

[0063] Spectral comparison: compare the spectral data with the reference data in the spectral library, which contains the spectral characteristics of various known components and pollutants. Specific components and pollutants in the water can be identified through comparison;

[0064] Quantitative analysis: Quantitative analysis of spectral data to calculate the concentration or content of various components and pollutants in water bodies;

[0065] Data integration: Integrate the result data of image recognition and spectral analysis to form a comprehensive data set.

[0066] In one embodiment, for the above-mentioned data analysis module, the data analysis module includes a feature extraction unit, a prediction model unit and a model optimization unit. The feature extraction unit is responsible for receiving the processing results provided by the data analysis unit and performing feature extraction. The feature extraction unit passes the extracted features to the prediction model unit to train the prediction model and predict future water quality changes. The prediction model unit predicts future water quality changes based on historical data using the prediction model. The model optimization unit receives the prediction results and real-time data to optimize the prediction model in real time. The prediction model unit outputs the prediction results to the intelligent decision support module.

[0067] In one embodiment, for the above-mentioned intelligent decision support module, the intelligent decision support module includes a data interface component, a knowledge graph construction unit, a decision support unit, an intelligent recommendation unit, an NLP unit and a user interface. The data interface component is responsible for receiving the data analysis results from the data processing and analysis module and the processed data of the data processing module. The knowledge graph construction unit constructs a water quality knowledge graph based on the received data. The knowledge graph construction unit interacts with the data interface component to obtain the required data. The knowledge graph construction unit transmits the constructed knowledge graph to the decision support unit. The decision support unit simulates, evaluates and predicts based on the knowledge graph. The decision support unit receives the knowledge graph transmitted by the knowledge graph construction unit and generates a decision. The decision support unit interacts with the intelligent recommendation unit and the NLP unit to provide the information required for decision support. The intelligent recommendation unit provides personalized water quality management suggestions and plans based on the monitoring results and user needs. The intelligent recommendation unit interacts with the decision support unit to obtain decision support information. At the same time, the intelligent recommendation unit interacts with the user interface to deliver the recommendation results. The NLP unit is responsible for converting monitoring data and decision suggestions into natural language text. The NLP unit receives the decision suggestions from the decision support unit, performs text conversion, and passes the generated report or interpretation instructions to the user interface. The user interface serves as a bridge between the system and the user, receives the report or interpretation instructions generated by the NLP unit, displays them to the user, and at the same time, receives user input requests.

[0068] In one embodiment, for the above-mentioned knowledge graph construction unit, the specific steps of the knowledge graph construction unit to construct a water quality knowledge graph based on the received data are as follows:

[0069] Data collection: Collect water quality related data from the data interface component.

[0070] Entity recognition: Use CRF to perform entity recognition on text data related to water quality, identify key entities such as water area names and pollutant names, and evaluate the recognition results to ensure that the accuracy meets the requirements;

[0071] Relationship extraction: Define relationship templates according to actual needs, such as "pollutant-concentration", "water area-pollution status", etc., use template-based or deep learning methods to extract the relationship between entities from the text, and verify the extracted relationship to ensure the accuracy and rationality of the relationship;

[0072] Knowledge fusion: Use entity alignment algorithms to merge the same or similar entities from different data sources, handle conflicting information in the data fusion process, and ensure the consistency and accuracy of the knowledge graph;

[0073] Knowledge graph construction: Use standard representation methods such as RDF and OWL to convert entities and relationships into nodes and edges in the knowledge graph, and store the constructed knowledge graph in the graph database for subsequent query and reasoning.

[0074] In one embodiment, for the above-mentioned information sharing and collaboration module, the information sharing and collaboration module includes a cloud platform data storage and management unit, a data sharing platform unit, a collaborative work system unit, a multi-terminal access support unit, a data export and report generation unit, and an optimization and intelligent analysis unit. The cloud platform data storage and management unit is responsible for the storage, management and security of water quality monitoring data. The data sharing platform unit builds a data sharing platform based on the cloud platform to support data access by multiple users, multiple departments, and multiple regions. The collaborative work system unit provides task allocation, progress tracking, and message notification, and supports multi-user online collaboration. The collaborative work system unit interacts with the data sharing platform unit to obtain data as the basis for collaboration. At the same time, the collaborative work system unit feeds back the collaboration results to the data sharing platform unit. The multi-terminal access support unit supports users to access the data sharing platform and the collaborative work system through different terminals (PC, mobile phone, tablet, etc.). The data export and report generation unit provides data export and report generation functions to meet the needs of users for further analysis. The optimization and intelligent analysis unit: optimizes the information sharing process and collaboration mechanism.

[0075] A method for using a rice-fish symbiosis multifunctional water quality monitoring and analysis device, the specific steps of using the device include:

[0076] System deployment: According to the actual situation of the rice-fish symbiosis system, select appropriate monitoring points to deploy front-end monitoring equipment, install edge computing units, and connect them with the front-end monitoring equipment to ensure the real-time and stability of data transmission. Configure the communication network to ensure smooth data transmission between the front-end monitoring equipment and the cloud platform;

[0077] Data collection: Start the front-end monitoring equipment to collect water quality data (such as temperature, pH value, dissolved oxygen content, etc.) and image information (such as water color, suspended matter distribution, etc.) in real time. The edge computing unit performs preliminary processing and analysis on the collected data and transmits it to the cloud platform;

[0078] Data processing: The data processing module receives data and image information from the data acquisition module and performs in-depth processing, including data filtering, denoising, data fusion and analysis, to identify suspended matter, algae and other biological communities in the water, and at the same time, identify specific components and pollutants in the water;

[0079] Data analysis: The data analysis module introduces an AI prediction model to predict future water quality changes based on historical water quality data and current real-time data. The prediction results include water quality change trends, potential pollution risks, etc., providing forward-looking guidance for water quality management;

[0080] Information review and decision-making: The intelligent decision support module builds a knowledge graph based on the output results of the data analysis module, identifies potential problems in water quality (such as excessive pollution, nutrient imbalance, etc.), and generates intelligent decision-making suggestions based on this, providing personalized water quality management suggestions and plans, including adjusting breeding density, optimizing fertilization plans, and placing ecological restoration agents.

[0081] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A multifunctional water quality monitoring and analysis device for rice-fish symbiosis, characterized in that: include: Data acquisition module: responsible for collecting water quality data from front-end monitoring equipment in real time, and extracting suspended matter, algae distribution and water quality parameter information from water quality images with the help of image recognition and spectral analysis technology; Data processing module: processes the collected water quality data and image information, covering data filtering, denoising, data fusion and analytical processing steps; Data analysis module: introduces a prediction model based on machine learning, combines historical water quality data and real-time monitoring data to predict future water quality trends; Intelligent decision support module: responsible for building a water quality knowledge graph, providing decision support in combination with the expert system, automatically identifying potential risks in water quality, and generating targeted intelligent decision-making suggestions accordingly; Information sharing and collaboration module: responsible for summarizing and integrating the data, reports and decision-making suggestions generated by each module, and providing them to all authorized users for access, so as to achieve information sharing and collaborative work; The data acquisition module transmits the real-time collected water quality data and image information to the data processing module, the data processing module transmits the processed data to the data analysis module and the intelligent decision support module, the data analysis module transmits the analysis results to the intelligent decision support module, and the intelligent decision support module transmits the generated decision recommendations to the user terminal.

2. The rice-fish symbiosis multifunctional water quality monitoring and analysis device according to claim 1, characterized in that: The data acquisition module further includes a front-end monitoring device and a data transmission unit connected thereto, wherein the front-end monitoring device is responsible for real-time collection of various physical and chemical parameters of water quality, as well as water quality image information, and the front-end monitoring device transmits the collected original data to the data transmission unit, and the data transmission unit is responsible for real-time transmission of the various physical and chemical parameters of water quality, as well as water quality image information, collected by the front-end monitoring device to the data processing module.

3. The rice-fish symbiosis multifunctional water quality monitoring and analysis device according to claim 2, characterized in that: An edge computing unit is deployed near the front-end monitoring equipment, which is responsible for performing preliminary data processing tasks, aiming to reduce the amount of data transmission and speed up the system response speed. The edge computing unit compresses the preprocessed data. The data transmission unit predicts the data transmission demand in the future based on historical data through a machine learning model. Based on the prediction results, the data transmission unit dynamically adjusts the data transmission plan. The data transmission unit uses an adaptive routing algorithm to select the optimal path to transmit data according to the network topology and real-time conditions, thereby ensuring efficient and reliable data transmission.

4. The rice-fish symbiosis multifunctional water quality monitoring and analysis device according to claim 2, characterized in that: The data processing module includes four sub-units: a data receiving unit, a data preprocessing unit, a data fusion unit and a data analysis unit. The data receiving unit is responsible for receiving the water quality data and image information transmitted by the data transmission unit. The data preprocessing unit performs preliminary data processing, including data filtering and denoising. The data preprocessing unit receives the data from the data receiving unit and outputs it to the data fusion unit after processing. The data fusion unit integrates the data from different sensors to form comprehensive water quality information. The data fusion unit receives the preprocessed data, performs fusion processing, and then passes the comprehensive data to the data analysis unit. The data analysis unit extracts valuable information from the comprehensive data. The data analysis unit receives the fused data, performs analysis processing, and passes the result to the data analysis module.

5. The rice-fish symbiosis multifunctional water quality monitoring and analysis device according to claim 4, characterized in that: The data analysis unit uses the trained image recognition model to identify suspended matter, algae and other biological communities in the water quality. At the same time, it uses the reference data in the spectral library for comparison to identify specific components and pollutants in the water body. The specific implementation steps are as follows: Feature extraction: Use the trained convolutional neural network-based model to extract features from image information; Classification and identification: Compare the extracted features with the known features in the model, and identify suspended matter, algae and other biological communities in the water through the softmax classifier; Spectral comparison: compare the spectral data with the reference data in the spectral library to identify specific components and pollutants in the water; Quantitative analysis: Quantitative analysis of spectral data to calculate the concentration or content of various components and pollutants in water bodies; Data integration: Integrate the result data of image recognition and spectral analysis to form a comprehensive data set.

6. The rice-fish symbiosis multifunctional water quality monitoring and analysis device according to claim 4, characterized in that: The data analysis module includes a feature extraction unit, a prediction model unit and a model optimization unit. The feature extraction unit is responsible for receiving the processing results provided by the data analysis unit and performing feature extraction. The feature extraction unit passes the extracted features to the prediction model unit to train the prediction model and predict future water quality changes. The prediction model unit predicts future water quality changes based on historical data using the prediction model. The model optimization unit receives the prediction results and real-time data to optimize the prediction model in real time. The prediction model unit outputs the prediction results to the intelligent decision support module.

7. The rice-fish symbiosis multifunctional water quality monitoring and analysis device according to claim 5, characterized in that: The intelligent decision support module includes a data interface component, a knowledge graph construction unit, a decision support unit, an intelligent recommendation unit, an NLP unit and a user interface. The data interface component is responsible for receiving the data analysis results from the data processing and analysis module and the processed data from the data processing module. The knowledge graph construction unit constructs a water quality knowledge graph based on the received data. The knowledge graph construction unit interacts with the data interface component to obtain the required data. The knowledge graph construction unit passes the constructed knowledge graph to the decision support unit. The decision support unit simulates, evaluates and predicts based on the knowledge graph. The decision support unit receives the knowledge graph transmitted by the knowledge graph construction unit and generates decision suggestions. The decision support unit interacts with the intelligent recommendation unit and the NLP unit to provide the information required for decision support. The intelligent recommendation unit provides personalized water quality management suggestions and plans based on monitoring results and user needs. The intelligent recommendation unit interacts with the decision support unit to obtain decision support information. At the same time, the intelligent recommendation unit interacts with the user interface to deliver the recommendation results. The NLP unit is responsible for converting monitoring data and decision suggestions into natural language text. The NLP unit receives the decision suggestions of the decision support unit, performs text conversion, and delivers the generated report or interpretation instructions to the user interface. The user interface receives the report or interpretation instructions generated by the NLP unit, displays them to the user, and receives user input requests.

8. The rice-fish symbiosis multifunctional water quality monitoring and analysis device according to claim 7, characterized in that: The specific steps of the knowledge graph construction unit for constructing a water quality knowledge graph based on the received data are as follows: Data collection: Collect water quality related data from the data interface component; Entity recognition: Use CRF to perform entity recognition on text data related to water quality and evaluate the recognition results; Relationship extraction: define relationship templates according to actual needs, extract relationships between entities from text, and verify the extracted relationships; Knowledge fusion: Use entity alignment algorithms to merge the same or similar entities from different data sources and handle conflicting information during data fusion; Knowledge graph construction: Use standard representation methods to convert entities and relationships into nodes and edges in the knowledge graph, and store the constructed knowledge graph in the graph database.

9. The rice-fish symbiosis multifunctional water quality monitoring and analysis device according to claim 6, characterized in that: The information sharing and collaboration module includes a cloud platform data storage and management unit, a data sharing platform unit, a collaborative work system unit, a multi-terminal access support unit, a data export and report generation unit, and an optimization and intelligent analysis unit. The cloud platform data storage and management unit is responsible for the storage, management and security of water quality monitoring data. The data sharing platform unit builds a data sharing platform based on the cloud platform to support data access by multiple users, multiple departments, and multiple regions. The collaborative work system unit provides task allocation, progress tracking, and message notification, and supports multi-user online collaboration. The collaborative work system unit interacts with the data sharing platform unit to obtain data as the basis for collaboration. At the same time, the collaborative work system unit feeds back the collaboration results to the data sharing platform unit. The multi-terminal access support unit supports users to access the data sharing platform and the collaborative work system through different terminals. The data export and report generation unit provides data export and report generation functions. The optimization and intelligent analysis unit optimizes the information sharing process and collaboration mechanism.

10. The method for using the rice-fish symbiosis multifunctional water quality monitoring and analysis device according to claim 1, characterized in that: The specific steps used include: Data collection: Start the front-end monitoring equipment and start collecting water quality data and image information in real time; Data processing: The data processing module receives data and image information from the data acquisition module and performs in-depth processing, including data filtering, denoising, data fusion and analysis, to identify suspended matter, algae and other biological communities in the water, and at the same time, identify specific components and pollutants in the water; Data analysis: The data analysis module introduces a prediction model to predict future water quality changes based on historical water quality data and current real-time data; Information review and decision-making: The intelligent decision support module builds a knowledge graph based on the output results of the data analysis module, generates intelligent decision-making suggestions, and provides personalized water quality management suggestions and solutions.

Images