An intelligent aquaculture traceability method and system based on the Internet of Things

Abstract

The present invention relates to the technical field of aquatic product traceability management, and in particular to an intelligent aquaculture traceability method and system based on the Internet of Things. The method comprises the following steps: obtaining aquaculture area location data; connecting the aquaculture area location data to a sensor network to generate an aquaculture Internet of Things network; performing real-time aquaculture data collection on the aquaculture Internet of Things network to obtain a real-time aquaculture sensor data stream; performing distributed time synchronization on the real-time aquaculture sensor data stream to generate standard aquaculture environment perception data; obtaining aquatic information data; and using the aquaculture area location data to perform real-life aquaculture environment scene mapping on the standard aquaculture environment perception data to generate real-life aquaculture environment scene mapping data. The present invention improves the intelligence and transparency of aquaculture traceability by combining the Internet of Things, blockchain and real-time data synchronization technology.

Description

Technical Field

[0001] The present invention relates to the technical field of aquatic product traceability management, and in particular to an intelligent aquaculture traceability method and system based on the Internet of Things. Background Art

[0002] IoT technology can achieve real-time monitoring of environmental parameters such as water quality, temperature, humidity, and oxygen concentration by deploying various sensors and equipment during the breeding process. These data can timely feedback changes in the breeding environment, help breeders adjust breeding management measures, and ensure the healthy growth of aquatic products. With the combination of big data, cloud computing, and artificial intelligence, the traceability system of aquaculture has gradually shifted from traditional manual records and sampling inspections to digital, automated, and intelligent management models. Initially, aquatic traceability mainly relied on manual records and manual inspections, making it difficult to trace the production process of aquatic products in real time and comprehensively. With the development of IoT technology, smart sensors and remote monitoring equipment make data collection more accurate and efficient. At the same time, combined with blockchain technology, information can be made tamper-proof and transparent, further improving the credibility of the traceability system. At present, the traceability method of intelligent aquaculture based on IoT has gradually formed a complete closed-loop system. Through dynamic monitoring and data analysis of the entire breeding process, it provides accurate traceability information, which not only ensures the safety of aquatic products, but also provides consumers with a higher level of trust. However, traditional aquaculture traceability systems often rely on manual records or periodic sampling, and are unable to monitor and provide feedback on changes in the aquaculture environment in real time. At the same time, there is a gap between aquaculture data collection and behavior analysis, making it difficult to effectively combine environmental data with aquaculture behavior, resulting in low intelligence and transparency in aquaculture traceability. Summary of the invention

[0003] Based on this, it is necessary to provide an intelligent aquaculture traceability method based on the Internet of Things to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a smart aquaculture traceability method based on the Internet of Things is provided, the method comprising the following steps:

[0005] Step S1: Acquire location data of an aquaculture area; perform sensor network connection on the location data of an aquaculture area to generate an aquaculture Internet of Things network; perform real-time aquaculture data collection on the aquaculture Internet of Things network to obtain a real-time aquaculture sensor data stream; perform distributed time synchronization on the real-time aquaculture sensor data stream to generate standard aquaculture environment perception data;

[0006] Step S2: Acquire aquatic information data; use the aquaculture area location data to map the standard aquaculture environment perception data to the real aquaculture environment scene, and generate real aquaculture environment scene mapping data; perform aquaculture behavior pattern recognition on the aquaculture information data through the real aquaculture environment scene mapping data, and generate an aquaculture behavior pattern diagram;

[0007] Step S3: Upload the aquaculture behavior pattern diagram to the blockchain to generate aquaculture traceability upload data; perform multi-node verification and consensus on the aquaculture traceability upload data to generate aquaculture traceability blockchain verification data; perform real-time traceability data update on the aquaculture traceability blockchain verification data to generate real-time aquaculture traceability update data;

[0008] Step S4: Generate a traceability code based on the real-time aquatic traceability update data and the aquaculture behavior pattern diagram to obtain an aquaculture traceability code; perform a scanning request for the aquaculture traceability code, and when a scanning request for the aquaculture traceability code is received, display the real-time aquatic traceability update data and the aquaculture behavior pattern diagram in layers to perform intelligent aquaculture environment traceability operations.

[0009] The present invention constructs an Internet of Things (IoT) network covering the entire breeding area by acquiring accurate aquaculture area location data and connecting through a sensor network. Real-time monitoring and data collection are realized, so that various parameters of the breeding environment (such as water temperature, oxygen concentration, water quality, etc.) can be monitored in real time. This not only improves the accuracy and integrity of the data, but also ensures that various parameters in the breeding process can be fed back in time, which is convenient for timely adjustment of breeding strategies and optimization of breeding management. By using the aquaculture area location data and environmental perception data for scene mapping, this step combines the breeding environment with the actual situation and generates real breeding environment scene data. Combined with these data, the breeding behavior pattern is identified to generate an aquaculture behavior pattern diagram, which helps to discover risks or abnormal behaviors in the breeding process through behavior pattern analysis. This provides a scientific basis for optimizing breeding management, improving the health level of aquatic products, and predicting the growth trend of aquatic products. In this step, the aquaculture behavior pattern diagram is uploaded through blockchain technology to achieve the immutability and transparency of the data. Multi-node verification and consensus mechanism ensure the security and reliability of traceability data and eliminate the risk of data forgery. In addition, real-time updating of traceability data further ensures the timeliness of the data, so that aquatic traceability information always reflects the real breeding process and behavior. It improves consumers' trust in product quality and enhances the transparency of the supply chain. This step realizes the traceability of each batch of aquatic products by generating a unique aquatic traceability code and scanning it for request identification. Scanning the traceability code can display detailed information of the breeding process, such as environmental parameters, breeding behavior, etc. in real time. By displaying the breeding data in layers, consumers or regulators can quickly obtain detailed traceability information, which enhances the transparency and interactivity of the information. This improves the accessibility and convenience of breeding data, provides consumers with a convenient traceability query platform, and also provides regulatory authorities with a more efficient supervision tool. Therefore, the present invention improves the intelligence and transparency of aquaculture traceability by combining the Internet of Things, blockchain and real-time data synchronization technology.

[0010] In this specification, an intelligent aquaculture traceability system based on the Internet of Things is provided, which is used to execute the above-mentioned intelligent aquaculture traceability method based on the Internet of Things. The intelligent aquaculture traceability system based on the Internet of Things includes:

[0011] The data synchronization acquisition module is used to obtain the location data of the aquaculture area; connect the location data of the aquaculture area to the sensor network to generate an aquaculture Internet of Things network; collect real-time aquaculture data on the aquaculture Internet of Things network to obtain real-time aquaculture sensor data stream; perform distributed time synchronization on the real-time aquaculture sensor data stream to generate standard aquaculture environment perception data;

[0012] The scene mapping module is used to obtain aquatic information data; use the aquaculture area location data to map the standard aquaculture environment perception data to the real aquaculture environment scene, and generate real aquaculture environment scene mapping data; use the real aquaculture environment scene mapping data to identify the aquaculture behavior pattern of the aquaculture information data, and generate an aquaculture behavior pattern diagram;

[0013] The traceability module is used to upload the aquaculture behavior pattern diagram to the blockchain to generate aquaculture traceability upload data; perform multi-node verification and consensus on the aquaculture traceability upload data to generate aquaculture traceability blockchain verification data; perform real-time traceability data updates on the aquaculture traceability blockchain verification data to generate real-time aquaculture traceability update data;

[0014] The traceability display module is used to generate traceability codes based on real-time aquatic traceability update data and aquaculture behavior pattern diagrams to obtain aquaculture traceability codes; scan requests for aquaculture traceability codes are identified, and when a scan request for an aquaculture traceability code is received, real-time aquatic traceability update data and aquaculture behavior pattern diagrams are displayed in layers to perform intelligent aquaculture environment traceability operations.

[0015] The beneficial effect of the present invention is that through the establishment of a sensor network and an aquaculture Internet of Things network, the environmental and behavioral data of the aquaculture area are collected in real time. This process not only strengthens the real-time monitoring of the breeding process, but also can respond to environmental changes in a timely manner and provide high-quality environmental perception data. By combining standard aquaculture environmental perception data with aquatic information data, the behavioral patterns in aquaculture can be accurately identified. This intelligent analysis helps breeders to gain an in-depth understanding of aquatic behavior characteristics (such as dynamic behavior, habitat behavior, etc.) and provides data support for the optimization of the aquaculture environment. By uploading the aquaculture behavior pattern diagram and real-time traceability data to the blockchain, the system ensures the immutability and transparency of the traceability data and avoids the risk of information tampering or loss. This move greatly enhances the trust of consumers and ensures that product quality is traceable and verifiable. Through the continuous generation and updating of real-time traceability update data, the platform can reflect each stage of the aquaculture process, so that the traceability process is always kept up to date, ensuring the timeliness and accuracy of breeding information. The system is layered and displayed according to different user needs, so that consumers and regulators can view breeding information of different depths according to their own needs. This approach not only enhances user interactivity, but also improves the comprehensibility of data. Through efficient data collection, intelligent behavior analysis, and precise environmental perception, the entire aquaculture process can be managed more finely. For example, by intelligently identifying the behavior patterns of aquatic products, the breeding strategy can be adjusted in time to reduce resource waste and improve breeding efficiency. Therefore, the present invention improves the intelligence and transparency of aquaculture traceability by combining the Internet of Things, blockchain, and real-time data synchronization technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of the steps of an intelligent aquaculture traceability method based on the Internet of Things;

[0017] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0018] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0019] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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 technicians in this field without creative work are within the scope of protection of the present invention.

[0021] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0022] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0023] To achieve this, please refer to Figures 1 to 3 , an intelligent aquaculture traceability method based on the Internet of Things, the method comprising the following steps:

[0024] Step S1: Acquire location data of an aquaculture area; perform sensor network connection on the location data of an aquaculture area to generate an aquaculture Internet of Things network; perform real-time aquaculture data collection on the aquaculture Internet of Things network to obtain a real-time aquaculture sensor data stream; perform distributed time synchronization on the real-time aquaculture sensor data stream to generate standard aquaculture environment perception data;

[0025] Step S2: Acquire aquatic information data; use the aquaculture area location data to map the standard aquaculture environment perception data to the real aquaculture environment scene, and generate real aquaculture environment scene mapping data; perform aquaculture behavior pattern recognition on the aquaculture information data through the real aquaculture environment scene mapping data, and generate an aquaculture behavior pattern diagram;

[0026] Step S3: Upload the aquaculture behavior pattern diagram to the blockchain to generate aquaculture traceability upload data; perform multi-node verification and consensus on the aquaculture traceability upload data to generate aquaculture traceability blockchain verification data; perform real-time traceability data update on the aquaculture traceability blockchain verification data to generate real-time aquaculture traceability update data;

[0027] Step S4: Generate a traceability code based on the real-time aquatic traceability update data and the aquaculture behavior pattern diagram to obtain an aquaculture traceability code; perform a scanning request for the aquaculture traceability code, and when a scanning request for the aquaculture traceability code is received, display the real-time aquatic traceability update data and the aquaculture behavior pattern diagram in layers to perform intelligent aquaculture environment traceability operations.

[0028] The present invention constructs an Internet of Things (IoT) network covering the entire breeding area by acquiring accurate aquaculture area location data and connecting through a sensor network. Real-time monitoring and data collection are realized, so that various parameters of the breeding environment (such as water temperature, oxygen concentration, water quality, etc.) can be monitored in real time. This not only improves the accuracy and integrity of the data, but also ensures that various parameters in the breeding process can be fed back in time, which is convenient for timely adjustment of breeding strategies and optimization of breeding management. By using the aquaculture area location data and environmental perception data for scene mapping, this step combines the breeding environment with the actual situation and generates real breeding environment scene data. Combined with these data, the breeding behavior pattern is identified to generate an aquaculture behavior pattern diagram, which helps to discover risks or abnormal behaviors in the breeding process through behavior pattern analysis. This provides a scientific basis for optimizing breeding management, improving the health level of aquatic products, and predicting the growth trend of aquatic products. In this step, the aquaculture behavior pattern diagram is uploaded through blockchain technology to achieve the immutability and transparency of the data. Multi-node verification and consensus mechanism ensure the security and reliability of traceability data and eliminate the risk of data forgery. In addition, real-time updating of traceability data further ensures the timeliness of the data, so that aquatic traceability information always reflects the real breeding process and behavior. It improves consumers' trust in product quality and enhances the transparency of the supply chain. This step realizes the traceability of each batch of aquatic products by generating a unique aquatic traceability code and scanning it for request identification. Scanning the traceability code can display detailed information of the breeding process, such as environmental parameters, breeding behavior, etc. in real time. By displaying the breeding data in layers, consumers or regulators can quickly obtain detailed traceability information, which enhances the transparency and interactivity of the information. This improves the accessibility and convenience of breeding data, provides consumers with a convenient traceability query platform, and also provides regulatory authorities with a more efficient supervision tool. Therefore, the present invention improves the intelligence and transparency of aquaculture traceability by combining the Internet of Things, blockchain and real-time data synchronization technology.

[0029] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of an intelligent aquaculture traceability method based on the Internet of Things of the present invention. In this example, the intelligent aquaculture traceability method based on the Internet of Things includes the following steps:

[0030] Step S1: Acquire location data of an aquaculture area; perform sensor network connection on the location data of an aquaculture area to generate an aquaculture Internet of Things network; perform real-time aquaculture data collection on the aquaculture Internet of Things network to obtain a real-time aquaculture sensor data stream; perform distributed time synchronization on the real-time aquaculture sensor data stream to generate standard aquaculture environment perception data;

[0031] In an embodiment of the present invention, the geographical location information of the aquaculture area is collected by remote sensing technology, GPS equipment or drones. A geographic information system (GIS) is used to record the precise coordinates of the aquaculture area, including water boundaries, regional area, topographic features, etc., to form digital map data of the aquaculture area. Various sensors such as water temperature, dissolved oxygen, pH value, turbidity, salinity and other sensors are deployed in the aquaculture area, and the sensors are connected to the central control platform through wireless communication protocols (such as LoRa, NB-IoT, Wi-Fi, etc.). Sensor data is collected in real time through the Internet of Things gateway, and these data streams are transmitted to the data center or cloud platform. The data collection frequency needs to be set according to the aquaculture environment and business needs, which can be once per minute or once per second. The distributed clock synchronization algorithm (such as NTP, PTP or a customized synchronization protocol) is used to synchronize the data of all sensors to ensure that the data collected by different sensors are consistent in time. After synchronization, the data of various sensors are merged to generate a standardized environmental perception data set.

[0032] Step S2: Acquire aquatic information data; use the aquaculture area location data to map the standard aquaculture environment perception data to the real aquaculture environment scene, and generate real aquaculture environment scene mapping data; perform aquaculture behavior pattern recognition on the aquaculture information data through the real aquaculture environment scene mapping data, and generate an aquaculture behavior pattern diagram;

[0033] In an embodiment of the present invention, the growth data of aquatic products in an aquaculture area is obtained by sensors or other data collection means, including but not limited to the number, type, size, weight, health status, etc. of aquatic populations. At the same time, the relevant information data of aquaculture is generated in combination with the feed input amount and the aquaculture management operation records (such as water quality regulation, drug use, etc.) of the farm. Through GIS technology, the geographical location data of the aquaculture area is combined with the standard aquaculture environment perception data (such as water temperature, oxygen concentration, turbidity, etc.) to construct a three-dimensional spatial model of the aquaculture environment. This process includes the following steps: mapping the environmental perception data to the specific location and time of the aquaculture area. According to the area, depth, layout and other information of the aquaculture area, a virtual scene of the aquaculture area is generated through three-dimensional modeling technology (such as using tools such as Unity or Blender). In the virtual scene, real-time environmental data (such as water quality, climate, etc.) is mapped to the three-dimensional scene through dynamic simulation technology to form a real environment model that can reflect the state of the aquaculture area in real time. According to the real aquaculture environment scene mapping data, combined with aquaculture information data, machine learning, deep learning or pattern recognition technology is used to analyze the aquaculture behavior pattern. The specific steps are as follows: Clean and denoise the aquaculture information data, and extract features related to aquaculture behavior, such as aquatic activity patterns, food intake, and clustering behavior. Use machine learning algorithms (such as support vector machines, decision trees, neural networks, etc.) or deep learning algorithms (such as convolutional neural networks, long short-term memory networks, etc.) to perform pattern recognition of aquaculture behavior. Through training, the daily behavior patterns of aquatic products, such as aggregation, foraging, and escape, are identified, and an aquaculture behavior pattern diagram is generated to display the behavior patterns of aquatic products in different time periods and different aquaculture environment conditions, helping aquaculture personnel understand the growth status and health status of aquatic products.

[0034] Step S3: Upload the aquaculture behavior pattern diagram to the blockchain to generate aquaculture traceability upload data; perform multi-node verification and consensus on the aquaculture traceability upload data to generate aquaculture traceability blockchain verification data; perform real-time traceability data update on the aquaculture traceability blockchain verification data to generate real-time aquaculture traceability update data;

[0035] In an embodiment of the present invention, the privacy and security of the data are ensured by encrypting and encapsulating the aquaculture behavior pattern diagram (including the activity data of aquatic populations, environmental status, behavior recognition results, etc.). The encapsulated data may contain multiple key data items, such as aquaculture environment parameters, sampling time, behavior pattern categories, etc. The aquaculture traceability data is uploaded to the blockchain network by utilizing the decentralized and tamper-proof characteristics of blockchain technology. Each set of data will generate a new block, which will be automatically stored by the system through a smart contract to ensure the authenticity and security of the uploaded data. During the data upload process, the relevant information of the behavior pattern diagram needs to be converted into a suitable blockchain readable format (such as JSON or binary format) and interact with the blockchain network through an API interface. In the blockchain network, after the aquaculture data is uploaded, it is verified by multiple nodes. Each node verifies the consistency of the data content to ensure that the data has not been tampered with before being uploaded. The verification process includes timestamp confirmation, data integrity verification, and authenticity verification. The consensus algorithm of blockchain (such as Proof of Work, Proof of Stake, BFT, etc.) is used to confirm the verification results of all nodes. After reaching a consensus, the aquaculture traceability blockchain verification data is generated. The consensus mechanism ensures the high reliability and immutability of the data, preventing malicious attacks and tampering. Once multiple nodes confirm the validity and consistency of the data, the data will be written to the blockchain network to generate the final blockchain verification data. Each verification block will contain the verification results, timestamp, node ID and other information of the data. Combined with real-time data acquisition systems (such as sensor data streams, aquaculture behavior monitoring systems, etc.), aquaculture data is continuously updated. Whenever the data changes (such as changes in water quality, changes in aquaculture behavior, etc.), the system automatically uploads the changed data to the blockchain. In the blockchain network, new aquaculture traceability information is added to the original blockchain data through smart contracts or regular update mechanisms (such as automatic synchronization of on-chain data) to ensure that the data on the blockchain is always kept up to date. Through smart contracts or decentralized applications (DApp), an interface is provided for users to query real-time aquaculture traceability information. Users can verify the production and circulation history of aquatic products at any time based on blockchain verification of aquaculture behavior data. Each data update only generates an incremental data block, reducing network load and ensuring the compatibility of new data with the original data. Each incremental data block records the hash value of the previous block to ensure the integrity and traceability of the traceability chain.

[0036] Step S4: Generate a traceability code based on the real-time aquatic traceability update data and the aquaculture behavior pattern diagram to obtain an aquaculture traceability code; perform a scanning request for the aquaculture traceability code, and when a scanning request for the aquaculture traceability code is received, display the real-time aquatic traceability update data and the aquaculture behavior pattern diagram in layers to perform intelligent aquaculture environment traceability operations.

[0037] In an embodiment of the present invention, a data structure containing multiple dimensional information is formed by integrating the real-time traceability update data and behavior pattern diagram of aquaculture. This data structure includes dynamic data of the aquaculture environment (such as water quality, climate, etc.) and data of aquatic behavior patterns (such as foraging, clustering, disease monitoring, etc.). The integrated data is encrypted using a hash algorithm (such as SHA-256) to generate a unique aquaculture traceability code. The traceability code is a digital fingerprint containing all aquaculture processes, behavior patterns and environmental data, which ensures the uniqueness and non-tamperability of the data. The traceability code should include the following key contents: such as breeding location, breeding waters, breeding time, such as water quality data, climate conditions, feed delivery records, health monitoring data, such as group activity patterns, foraging behavior, reproductive status, etc., and record the time of data collection and traceability code generation. Blockchain smart contracts can be used to package these data and generate traceability codes to ensure the validity and reliability of the traceability codes. The aquaculture traceability code is identified and marked by QR codes, RFID tags, barcodes, etc. When consumers or regulators scan the aquaculture traceability code, the system will receive the corresponding request. After the scanning request is triggered, the system will identify it according to the traceability code. The identification process includes the following steps: The system first checks whether the format of the traceability code is correct, valid, and consistent with the data on the blockchain. Determine whether the scanner has the authority to view the traceability data, such as whether it is a consumer, supply chain manager or regulator. According to the authority of the requester, the system will return the corresponding aquaculture traceability data. For consumers, only the production and transportation process of the product is provided; for regulators, more detailed breeding data and behavior pattern diagrams are provided. Once the scanning request for the traceability code is verified, the system will display the traceability data and breeding behavior pattern diagram in layers so that users can view different data dimensions as needed. The layered display can be divided into the following categories: Basic data layer: Display basic information of aquaculture, such as breeding site, time, breeding waters, etc. Environmental monitoring layer: Display real-time environmental data, such as water quality, dissolved oxygen, temperature, pH value, etc. Breeding behavior pattern layer: Display aquatic behavior pattern diagrams, including clustering status, foraging behavior, disease monitoring, etc. Traceability history layer: displays complete traceability information of aquatic products from breeding to transportation and sales, ensuring that consumers can trace the entire life cycle of aquatic products.

[0038] Preferably, step S1 comprises the following steps:

[0039] Step S11: Acquire location data of aquaculture areas;

[0040] Step S12: performing sensor deployment on the aquaculture area location data to obtain aquaculture sensor deployment data; performing aquaculture facility equipment deployment based on the aquaculture sensor deployment data to obtain aquaculture facility monitoring equipment deployment data;

[0041] Step S13: using the Internet of Things technology to connect the aquaculture sensor deployment data and the aquaculture facility monitoring equipment deployment data to a network, and generate an aquaculture Internet of Things network;

[0042] Step S14: collect real-time aquaculture data on the aquaculture Internet of Things network to obtain a real-time aquaculture sensor data stream; perform distributed time synchronization on the real-time aquaculture sensor data stream to generate a time-series synchronized aquaculture data stream; perform data preprocessing on the time-series synchronized aquaculture data stream to generate standard aquaculture environment perception data.

[0043] In the embodiment of the present invention, the geographical location data of the aquaculture area is obtained by remote sensing technology, GIS (geographic information system), unmanned aerial vehicle (UAV) or satellite imagery. Remote sensing images can extract the precise coordinates of the aquaculture area through high-resolution satellite or unmanned aerial vehicle images. Using Landsat, Sentinel or Gaofen-1 satellite image data, select appropriate images for analysis according to the spatial resolution of the image. Deploy unmanned aerial vehicles for high-precision aerial photography, and combine with the GPS positioning system to ensure the accuracy of the location data. Perform geographic information processing on the collected images or maps, identify water boundaries, water quality characteristics of specific areas, surrounding environment (such as pollution sources, land use, climate) and other information, and draw an accurate location map of the aquaculture area. Combined with the existing aquaculture area management database, ensure the consistency of the newly acquired geographical location data with the existing data to avoid overlap or omission. Environmental monitoring sensors are deployed in the aquaculture area, and the number and type of sensors are optimized according to the size of the water area, the scale of aquaculture, and the environmental characteristics (such as water depth and water flow speed). The deployment plan must ensure that the sensors can fully cover the aquaculture area and obtain accurate environmental data. The deployment personnel select the appropriate sensor type based on the geographical information of the aquaculture area and arrange it in a distributed manner. Sensors need to be installed in key locations such as water surface, sediments, and aquaculture equipment. Connect through wireless sensor networks (WSN) to ensure real-time data transmission. According to the sensor layout, aquaculture facilities and equipment should be arranged reasonably, for example: automatically adjust the feeding amount according to water quality and aquaculture environment data, automatically start or adjust the oxygen supply according to the oxygen concentration in the water body, clean up floating objects on the water surface or bottom sediments, and maintain water quality. Based on the Internet of Things technology, design and deploy a unified data transmission, storage and processing platform. The platform needs to support multiple network protocols, such as Wi-Fi, LoRaWAN, NB-IoT, etc., to ensure seamless communication between sensors, devices and systems. Use the Internet of Things gateway to connect different types of sensors and devices to the network to realize data interaction between devices. The Internet of Things platform needs to have real-time monitoring, data collection and remote management functions for various device states. To ensure compatibility between devices, select communication protocols suitable for aquaculture environments, such as low-power wide area network (LPWAN) protocols (LoRa, NB-IoT) to ensure communication stability in a wide aquaculture area. Sensors collect relevant data such as water quality, weather, and facility status in real time to generate real-time aquaculture sensor data streams. The data stream includes: water quality data, environmental data, equipment working status data, climate data, etc. The data needs to have a high-frequency collection capability (such as once a minute) to ensure that it reflects the dynamic changes in the aquaculture environment. The frequency and accuracy of data collection are adjusted according to the requirements of the breeding species and equipment to ensure real-time and accuracy. In the Internet of Things environment, there will be slight deviations in the collection time of different devices and sensors. Therefore, it is necessary to perform distributed time synchronization on the real-time sensor data stream to ensure that the timestamps of the data are consistent.Use the Network Time Protocol (NTP) or a precise time synchronization protocol (such as PTP) for time synchronization. Each sensor performs timestamp correction on the collected data according to the time synchronization requirements. Use a time series data processing method to merge the data collected by different sensors to form a synchronized time series data stream. Perform data preprocessing on the collected time series synchronization data, including: removing abnormal data caused by sensor errors or external interference, maintaining data accuracy, interpolating missing data caused by equipment failure or sensor disconnection, removing invalid or repeated values, and filling in missing data. Through the above processing, standard aquaculture environment perception data is finally obtained.

[0044] Preferably, performing distributed time synchronization on real-time aquaculture sensor data streams comprises:

[0045] Perform multi-source sensor clock configuration on real-time aquaculture sensor data stream to generate multi-source sensor clocks; perform clock synchronization configuration on multi-source sensor clocks based on PTP protocol to generate synchronization clock configuration data;

[0046] Based on the synchronous clock configuration data, the sensor acquisition timestamp is extracted for the real-time aquaculture sensor data stream to obtain the multi-source sensor acquisition timestamp; the timestamp deviation is calculated for the multi-source sensor acquisition timestamp to obtain the acquisition timestamp deviation data;

[0047] By collecting timestamp deviation data, the transmission delay of real-time aquaculture sensor data stream is corrected to generate sensor acquisition delay correction data; the timestamps of multi-source sensor acquisition timestamps are aligned using sensor acquisition delay correction data to generate sensor timing alignment data;

[0048] Distributed data synchronization verification is performed on the real-time aquaculture sensor data stream according to the sensor timing alignment data to generate a timing synchronized aquaculture data stream, where the distributed synchronization verification includes time difference analysis, timing consistency check and data overlap check.

[0049] In an embodiment of the present invention, in order to ensure the accuracy of time synchronization, a high-precision clock source is selected, such as using a GPS clock, a network time protocol (NTP) or a precision time protocol (PTP) to unify the clocks of all sensors. Based on the device network structure, the clock configuration is transmitted to each sensor through the Internet of Things gateway, and the clock of each sensor is set and calibrated so that it can be synchronized with the main clock source (such as a PTP clock). After the clock configuration of each sensor is completed, multi-source sensor clock data is generated, that is, the difference and calibration information between the internal clock of each sensor and the main clock source. The PTP (Precision Time Protocol) protocol is used for high-precision clock synchronization. The PTP protocol can synchronize clocks in the network, and the accuracy can reach the nanosecond level, which is suitable for time synchronization in distributed sensor networks. The PTP client of each sensor device is configured to communicate with the PTP master clock of the Internet of Things gateway or network switch to ensure that the clocks of all sensors are synchronized with the master clock. The PTP protocol will perform clock compensation according to the network delay, eliminate the clock deviation between different sensors, and ensure that the clock of each sensor is consistent. According to the configuration result of the PTP protocol, synchronous clock configuration data is generated. The data includes information such as the synchronization status of all sensor clocks, clock synchronization deviation, and network delay during synchronization. The synchronized clock data is used to extract the acquisition timestamp of each sensor from the real-time aquaculture sensor data stream. When each sensor collects data, it generates a timestamp for each data record, indicating the data acquisition time. The deviation of each sensor's timestamp is calculated. The deviation refers to the difference between the actual acquisition time and the synchronized clock time. The accuracy of the timestamp will be affected by the inherent error of the sensor clock and the network delay. Calculation method: Deviation = actual acquisition time - synchronized clock time By comparing the timestamp of each sensor with the master clock time, the timestamp deviation data of each sensor is calculated. A transmission delay model is established to calculate the transmission time of the data packet from the sensor to the gateway. Combined with the known network delay data, the data transmission time of each sensor is corrected. After the transmission delay correction, the sensor acquisition delay correction data is generated, that is, the correct time of each sensor's acquisition time after the delay correction. The timestamps of each sensor are aligned using the corrected sensor acquisition delay correction data. According to the time difference when each sensor collects data, the timestamp is adjusted to align them in the global time frame. This alignment will adjust the timestamp of each sensor to synchronize it to a unified moment (such as PTP clock time), ensuring that the timestamps of all sensor data are consistent and forming accurate time series data. Through the timestamp alignment process, sensor timing alignment data is generated, that is, the timestamps of all sensors are uniformly adjusted and synchronized. Compare the time differences between different sensors to verify whether the timing data of each sensor is consistent. Time difference analysis can be achieved by calculating the difference between timestamps.If the time difference of some sensors exceeds the preset threshold, the timestamps of these sensors need to be recalibrated. Check the temporal consistency of sensor data, that is, whether the environmental data collected by each sensor is arranged in the expected order. For example, the data of the water temperature sensor should be consistent with the data of other related sensors in time to avoid time confusion. The timing consistency check can be performed by sliding window algorithm or timing comparison algorithm. Check whether there is repeated collection or missing data in the data stream. By comparing the timestamps of each sensor data stream, verify whether the data is overlapped or missing. If overlapping data or missing data is detected, the redundant data can be supplemented or discarded according to the correction algorithm. After the above verification, the time-synchronized aquaculture data stream is finally generated.

[0050] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0051] Step S21: Acquire aquatic product information data;

[0052] Step S22: constructing a three-dimensional aquaculture environment scene according to the standard aquaculture environment perception data to generate three-dimensional aquaculture environment scene data; using the aquaculture area location data to perform real geographic spatiotemporal mapping on the three-dimensional aquaculture environment scene data to generate real aquaculture environment scene mapping data;

[0053] Step S23: performing sensor data index association on the real aquaculture environment scene mapping data through the aquaculture Internet of Things network to generate a real aquaculture environment associated scene set;

[0054] Step S24: performing aquaculture behavior pattern recognition on the aquaculture information data based on the real aquaculture environment associated scene set to generate an aquaculture behavior pattern diagram.

[0055] In an embodiment of the present invention, real-time aquatic information data is obtained by sensors deployed in an aquaculture area. These data include: such as dissolved oxygen, pH value, ammonia nitrogen, temperature, turbidity, etc., to monitor the basic environmental conditions of the water body. Such as the growth status (weight, size, quantity), survival rate, etc. of aquatic products, to obtain biological information of the aquaculture objects. Such as temperature and humidity, wind speed, air pressure, etc., external weather factors that affect the aquaculture environment. Such as the operating status of equipment such as aerators, feeders, and water pumps, to monitor the operation of aquaculture facilities and equipment. A three-dimensional aquaculture environment model is established using standard aquaculture environment perception data (such as water quality data, aquaculture biological data, and meteorological data). A three-dimensional spatial model is constructed based on spatial information such as the geographical location, depth, and water flow of the water area. Multidimensional environmental data such as water quality and meteorology are converted into corresponding three-dimensional scene features. For example, different levels of water quality (oxygen concentration, temperature change, etc.) can be mapped to different water body levels. Use professional modeling tools (such as Blender, Unity 3D, Unreal Engine, Cesium, etc.) to generate a three-dimensional environmental scene in combination with spatial data collected by sensors. Interactive virtual scenes can be created and visualized through virtual reality (VR) or augmented reality (AR) technology. Various environmental data are integrated with the three-dimensional model so that the environmental data can be updated in real time in the three-dimensional model. For example, water quality data dynamically displays the water quality of the water body through changes in color, transparency, etc., and the density and size of aquatic objects change with the changes in growth data. Based on the environmental data collected by sensors and three-dimensional modeling, three-dimensional aquaculture environment scene data including the aquaculture environment is generated, which can be used for further analysis and simulation. Combined with the geographical location data of the aquaculture area (such as GPS coordinates, geographic information system GIS data, etc.), the three-dimensional aquaculture environment scene is mapped in geographic time and space. The virtual aquaculture area in the three-dimensional model is connected with the aquaculture area in reality. The three-dimensional model is mapped to the actual geographical location using coordinate transformation technology (such as coordinate system transformation, map projection, etc.). The sensor data is matched in time and space based on the timestamp, and the real-time aquatic information obtained is combined with the scene data in the three-dimensional environment model, so that the environmental data at each moment can be reflected in real time in the three-dimensional scene. The three-dimensional environment scene is ensured to be updated synchronously with the real-time data in the aquaculture area (such as water quality, equipment status, etc.) through the Internet of Things network. Spatiotemporal data indexing technology can be used to update the values ​​in the three-dimensional environment scene in real time and ensure that the model is consistent with the changes in the real environment. The mapped three-dimensional aquaculture environment scene data is combined with the actual aquaculture area location data to finally generate the real aquaculture environment scene mapping data. This data is not only three-dimensional visualization data, but also contains real-time environment and aquaculture data, which is used to dynamically simulate the status of the aquaculture area. Using the Internet of Things technology, sensor data is associated with the three-dimensional aquaculture environment scene through data indexing and association.For example, multidimensional data such as water quality, weather, and equipment operating status are bound to the corresponding areas in the three-dimensional environment scene. A multi-source data association model is constructed to integrate and process real-time sensor data through a data stream processing framework (such as Apache Kafka, Apache Flink, etc.) to generate efficient index data. Machine learning algorithms (such as cluster analysis, time series analysis, deep learning, etc.) are used to analyze the set of associated scenes in the real breeding environment to identify behavioral patterns in aquaculture. Different aquatic growth patterns, environmental change patterns, and abnormal behavior patterns in the breeding area are identified. For example, by analyzing environmental changes such as water temperature and dissolved oxygen concentration, the growth cycle and feeding behavior of aquatic organisms are identified. By analyzing sensor data at different time points, periodic behavior patterns are identified, such as feeding patterns, aerator start-stop patterns, etc. By comparing normal patterns, potential abnormal behaviors are identified, such as drastic changes in water quality and abnormal breeding equipment. Through machine learning or pattern recognition algorithms, an aquaculture behavior pattern diagram is generated, which reflects the relationship between different environmental factors and the behavior of aquaculture organisms during aquaculture. It can show the impact of different environmental variables on aquatic behavior, predict future farming behavior, etc.

[0056] Preferably, step S22 includes the following steps:

[0057] Step S221: extracting water and land topography parameters from the standard aquaculture environment perception data to generate land topography data and water topography data of the aquaculture environment;

[0058] Step S222: performing three-dimensional scene modeling on the land topography data of the aquaculture environment and the aquatic topography data of the aquaculture environment to generate three-dimensional aquaculture environment scene data;

[0059] Step S223: converting the geographic coordinate format of the aquaculture area geographic coordinate data through the aquaculture area location data to generate the geographic location coordinate data of the aquaculture area;

[0060] Step S224: performing spatiotemporal mapping analysis on the three-dimensional aquaculture environment scene data and the geographical location coordinate data of the aquaculture area to generate spatiotemporal mapping data of the aquaculture environment scene;

[0061] Step S225: Immersively visualize the real breeding environment scene mapping data to generate real breeding environment scene mapping data.

[0062] In an embodiment of the present invention, the land and water topography of the breeding area is analyzed by using a geographic information system (GIS) tool or a digital elevation model (DEM). The land landform data is processed to extract the terrain features related to aquaculture (such as terrain undulation, drainage system, soil type, etc.). The water landform data is analyzed to extract the hydrogeographic features such as the depth distribution, flow velocity change, and bottom topography of the water area. According to the extracted data, the land landform data of the breeding environment and the water landform data of the breeding environment are generated respectively for subsequent modeling and analysis. Advanced three-dimensional modeling software (such as Blender, AutodeskMaya, SketchUp, etc.) or a special water area modeling tool (such as Aquatic GIS) is used to construct a three-dimensional model. Combined with the land terrain data and the water area landform data, a three-dimensional breeding environment scene is generated by a tool, including: through the elevation data and the terrain features, a rasterized or gridded ground model is established, and relevant soil and vegetation information is added. According to the depth, flow velocity and other data of the water body, a water surface and underwater terrain model is constructed, and the dynamic changes of the water body (such as tides, flow velocity, etc.) are simulated. Optimize the details in the modeling process, especially dynamic factors such as water surface fluctuations, wind and wave effects, and environmental changes. Combine the static features of the landform with the dynamic water flow so that the modeled three-dimensional scene can accurately reflect the actual environment. By integrating different data sources (such as water quality sensor data, aquaculture biological information, etc.), the data is visualized as different three-dimensional layers, which is convenient for multi-dimensional display of aquaculture areas. Based on the above modeling results, three-dimensional aquaculture environment scene data containing multi-dimensional data such as terrain, environment, and dynamic waters is generated to provide a data basis for subsequent spatiotemporal mapping and display. The geographical location data of aquaculture areas are obtained through GPS equipment, remote sensing satellite data, geographic information systems (GIS), etc., usually in the form of latitude and longitude coordinates, UTM coordinates, etc. Use geographic information system (GIS) tools or coordinate conversion algorithms to convert the collected geographical location data of aquaculture areas from the original coordinate system (such as WGS-84, UTM) to a unified format. According to needs, different coordinate systems (such as geographic coordinate system, plane coordinate system) are used for format conversion. The location data of the aquaculture area after the coordinate format conversion is used to generate standardized geographic location coordinate data of the aquaculture area, which will be used for subsequent spatiotemporal mapping analysis. The three-dimensional aquaculture environment scene data is associated with the geographic location coordinate data of the aquaculture area through spatiotemporal data processing tools or algorithms (such as spatial interpolation and Kriging interpolation). The environmental data (such as water quality, temperature, flow rate, etc.) are matched with the geographic location and mapped to the actual geographic coordinates. The data of each time node is spatiotemporally mapped to ensure that the data at different time points can be correctly mapped to the appropriate position of the three-dimensional scene. Through the above analysis, the spatiotemporal mapping data of the aquaculture environment scene is generated, so that the actual environment of the aquaculture area and the three-dimensional scene in the model can reflect the geographical and temporal changes in real time.Using virtual reality (VR) or augmented reality (AR) technology, combined with real-time rendering tools (such as Unity3D, Unreal Engine), the generated aquaculture environment scene spatiotemporal mapping data is immersively visualized. Multi-perspective virtual display platforms (such as panoramic videos, 3D glasses, mobile devices, etc.) can be used to provide an immersive experience. Environmental dynamic elements such as water flow, meteorological changes, water quality fluctuations, etc. are added to the visualization display, so that users can perceive changes in the aquaculture environment in real time. Provide an interactive interface that allows users to freely explore in a three-dimensional scene and view the environmental status of different geographical locations and time nodes. Finally, a visualized real aquaculture environment scene mapping data is generated, which will be used for applications in aquaculture management decision-making, environmental monitoring, problem diagnosis, etc.

[0063] Preferably, step S24 includes the following steps:

[0064] Step S241: dividing aquaculture behavior patterns based on a real aquaculture environment associated scene set, generating aquaculture static behavior division patterns and aquaculture dynamic behavior division patterns;

[0065] Step S242: screening the aquatic product information data for the static positions of aquatic products of the same type according to the aquatic product static behavior classification mode to obtain the aquatic product static position information data of the same type; performing aquatic product static habitat behavior pattern analysis through an underwater camera based on the aquatic product static position information data of the same type to generate aquatic product static behavior pattern analysis data;

[0066] Step S243: screening the aquatic product information data for different types of dynamic positions of aquatic products based on the aquatic product dynamic behavior classification mode to obtain different types of dynamic position information data of aquatic products; analyzing the dynamic movement behavior patterns of aquatic products through underwater video monitoring based on the different types of dynamic position information of aquatic products to generate aquatic product dynamic behavior pattern analysis data;

[0067] Step S244: Perform time series behavior evolution on the aquatic static behavior pattern analysis data and the aquatic dynamic behavior pattern analysis data through a preset long-term and short-term neural network model to generate an aquaculture behavior pattern diagram.

[0068] In an embodiment of the present invention, clustering and classification analysis of aquatic behavior data in aquaculture environments are performed by utilizing a generated set of associated scenes of real aquaculture environments. The behavior data is derived from sensor monitoring data and video surveillance data of aquaculture areas. Different types of aquatic behaviors are divided using data mining algorithms (such as K-means clustering, DBSCAN, support vector machines, etc.). The division criteria can be based on the following features: static behavior: such as aquatic habitat, rest, group gathering, etc. Dynamic behavior: such as aquatic swimming, predation, foraging, reproduction, etc. According to the aquatic static behavior division mode, the static positions of all aquatic products in the aquaculture environment are screened, and aquatic data showing habitat or static behavior is extracted. The data is derived from sensor data (such as temperature, pressure, and flow rate sensors) and real-time location tracking data (such as GPS location data of aquatic products, RFID tag location data, etc.) in aquaculture areas. Underwater cameras are used to conduct video monitoring of the same type of static aquatic products selected to observe their habitat behavior. Combined with video image recognition technology, static behavior patterns such as habitat, rest, and group behavior of aquatic products are analyzed. The image recognition algorithm (such as convolutional neural network CNN) is used to extract features of the habitat position, posture, and movement of aquatic products, and further analyze the habitat pattern of aquatic products. Based on the image data and location data obtained by the underwater camera, combined with the behavior pattern recognition algorithm, the static behavior pattern analysis data of aquatic products is generated, including the static habitat position, habitat time, behavior frequency, etc. of aquatic products. According to the dynamic behavior classification mode of aquatic products, the movement behavior of aquatic products in the breeding area is screened, especially for the dynamic behavior of aquatic products such as swimming and foraging. The screened data includes the movement trajectory, speed, direction, and other information of aquatic products in a specific time and space area. Dynamic data can be obtained through the real-time location tracking system of aquatic products (such as RFID, acoustic positioning system) and motion sensors (such as accelerometers and gyroscopes). The movement trajectory of different types of dynamic aquatic products is monitored and analyzed based on the underwater camera. The movement behavior of aquatic products, such as swimming path, predation behavior, group movement, etc., is analyzed using motion recognition and analysis algorithms (such as optical flow method, background modeling, target tracking algorithm, etc.). Through video surveillance data and motion recognition analysis, aquatic dynamic behavior pattern analysis data is generated, including aquatic movement trajectory, speed, activity time, group interaction and other information. Based on aquatic static behavior pattern analysis data and aquatic dynamic behavior pattern analysis data, a long short-term memory neural network (LSTM) model is constructed to analyze the temporal evolution of aquatic behavior. The LSTM model is trained, and the input includes static behavior data (such as habitat location, habitat time) and dynamic behavior data (such as movement trajectory, speed, etc.). The model learns the long-term dependency and time evolution law of aquatic behavior through the input of time series. Through the trained LSTM model, the evolution of aquatic behavior at future time points is predicted, and the behavior change pattern of aquatic products in different environments is identified.The model output is the evolution trend of aquatic behavior, such as the activity frequency and movement trajectory changes of aquatic products under certain environmental conditions. Based on the output results of the LSTM model, an aquaculture behavior pattern diagram is generated, including the temporal changes of aquatic behavior, the evolution path of behavior, and the aggregation and dispersion trends of group behavior.

[0069] Preferably, the analysis of aquatic dynamic motion behavior patterns based on dynamic position information of different types of aquatic products through underwater video monitoring includes:

[0070] The aquatic activity video stream is collected by underwater video monitoring to obtain the aquatic activity video stream of the heterogeneous aquatic products based on the dynamic position information of the aquatic products; the video frame of the aquatic activity video stream of the heterogeneous aquatic products is segmented to generate the aquatic activity frame image of the heterogeneous aquatic products; the aquatic product object target is tracked and marked in the aquatic activity frame image of the heterogeneous aquatic products to generate the tracking mark data of the aquatic product object;

[0071] Calculate the movement distance of different types of aquatic products on the tracking mark data of different types of aquatic products to obtain the movement distance data of different types of aquatic products; evaluate the intensity of aquatic products activity on the tracking mark data of different types of aquatic products based on the movement distance data of different types of aquatic products to generate the evaluation data of the intensity of aquatic products activity;

[0072] According to the intensity assessment data of heterogeneous aquatic activities, the social interaction behavior patterns of aquatic products are analyzed on the dynamic position information of heterogeneous aquatic products to generate the analysis data of aquatic dynamic behavior patterns.

[0073] In an embodiment of the present invention, by using an underwater camera system, combined with the dynamic position information of different types of aquatic products that have been screened, video stream collection is performed in key areas of aquaculture areas (such as habitats, food source areas, etc.). During the video collection process, it is ensured that the collection device can capture the movement behavior of aquatic products in real time. The underwater camera must have a high frame rate (such as 30 frames per second) and clarity (such as high-definition 1080p or higher) for subsequent accurate tracking and analysis. In order to monitor the dynamic behavior of aquatic products in an all-round way, multiple underwater cameras are used to work together to cover different angles and areas of the aquaculture area to ensure that comprehensive aquatic dynamic video data is obtained. The outputs of all cameras are merged into a unified video stream or video data set, which covers various activities of aquatic products in the aquaculture environment, such as swimming, foraging, etc. The underwater video stream is parsed frame by frame, and the video data of each second is decomposed into multiple independent video frames to form a series of static image data. The video stream is processed using an open source computer vision tool (such as OpenCV) or a custom video processing algorithm to extract each frame of the image. The extracted video frame image is preprocessed to improve the accuracy of target detection. The preprocessing steps include image denoising, brightness equalization, contrast enhancement, etc., to adapt to the particularity of the underwater environment (such as unclear water quality, weak light, etc.). Each frame of the image represents the dynamic state of aquatic products at a time point, and finally generates a large number of frames of aquatic product activity of different types, providing data support for subsequent behavior analysis. The target detection algorithm (such as YOLO, Faster R-CNN, etc.) is used to detect and locate the aquatic product body in each frame of the image, and the type, morphology and position of the aquatic product are identified. For the detected aquatic products, the target tracking algorithm (such as SORT, DeepSORT, etc.) is used to continuously track them to ensure that the aquatic product body can be accurately marked in each frame of the video stream. The trajectory of each aquatic product body is marked to generate tracking mark data of different types of aquatic products, including the coordinates, speed, moving direction and other information of each aquatic product in each frame of the image. The marked data is stored in time series to form a time-series aquatic dynamic behavior data set for subsequent analysis. Based on the spatial position coordinates of each aquatic product between consecutive frames, the coordinate difference of adjacent frames is calculated to obtain the movement distance of the aquatic product within a certain time interval. Use the Euclidean distance formula to calculate the movement distance of the aquatic products between each frame. The formula is as follows: Where d is the movement distance of the aquatic product between two moments, and x1, x2 and y1, y2 are the horizontal and vertical coordinates of the aquatic product body in the continuous frames respectively. Calculate the total movement distance of each aquatic product in each time period, and record the data in the movement distance data of different types of aquatic products to evaluate their behavior intensity. Based on the movement distance data of aquatic products, calculate their activity intensity. Activity intensity can be quantified by the following formula: Where I is the activity intensity, d is the movement distance of the aquatic, and t is the movement time. According to the assessed activity intensity, the aquatic behavior is divided into different intensity levels. For example, the activity intensity can be divided into low, medium, and high levels to further analyze its behavior pattern. The activity intensity data of each aquatic is recorded, including information such as its activity level, movement range, and frequency in the breeding environment, and heterogeneous aquatic activity intensity assessment data is generated. Based on the activity intensity data of aquatic products, the interaction patterns between different aquatic products are analyzed, especially based on the intensity assessment data, the social interaction behaviors of aquatic products (such as group aggregation, collaborative foraging, reproductive interaction, etc.) are identified. Cluster analysis or association rule algorithms are used to identify the interaction patterns in aquatic groups and classify them according to the social behavior of aquatic products. Using the analysis results, aquatic dynamic behavior pattern analysis data is generated, including information such as the pattern of aquatic group interaction behavior, interaction frequency, and group structure. The analysis results are visualized to generate aquatic dynamic behavior pattern diagrams to show the social interaction behavior patterns of different aquatic products in the breeding environment, helping breeding managers understand the behavioral trends of aquatic products in specific environments.

[0074] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0075] Step S31: extracting aquaculture traceability data from the aquaculture behavior pattern diagram to obtain aquaculture traceability data; uploading the aquaculture traceability data to the blockchain to generate aquaculture traceability upload data;

[0076] Step S32: encapsulating the uploaded aquaculture traceability data into data blocks to generate aquaculture traceability data blocks; performing hash linking on the aquaculture traceability data blocks to generate aquaculture traceability encrypted data blocks;

[0077] Step S33: Perform multi-node verification and consensus on the aquaculture traceability encrypted data block through blockchain to generate aquaculture traceability blockchain verification data;

[0078] Step S34: Update the aquaculture traceability blockchain verification data in real time to generate real-time aquaculture traceability update data.

[0079] In an embodiment of the present invention, detailed traceability data extraction of aquaculture behavior is performed through an aquaculture behavior pattern diagram, combined with sensor data, environmental data and aquaculture records in the aquaculture area. The extracted information includes but is not limited to: the growth cycle of each aquatic product, habitat, feed feeding records, disease monitoring data, aquaculture area information, etc. The extracted traceability data should be stored in a standardized format (for example, JSON, CSV, XML, etc.) to facilitate subsequent upload and processing. Based on the extracted data, aquaculture traceability data is generated, including all traceable key node information in the aquaculture process. The aquaculture traceability data is uploaded to the blockchain network using blockchain technology. The blockchain is used to record the timestamps and related information of all aquaculture activities to ensure that the data cannot be tampered with and is traceable. The traceability data is written to the blockchain using a smart contract or API interface. Each traceability data item is verified and recorded through the smart contract mechanism of the blockchain to generate aquaculture traceability upload data, which includes the blockchain transaction hash, timestamp, etc. of the traceability information. A new transaction record is generated on the blockchain to indicate that the traceability data has been uploaded, ensuring the existence and traceability of the data in the blockchain network. The uploaded aquaculture traceability data is encapsulated in data blocks. Each data block contains multiple aquaculture information items and includes necessary metadata, such as the timestamp of the data item, the blockchain transaction hash, the hash value of the previous block, etc. Each encapsulated traceability data block contains multiple transaction records or information items to form a data block. The data block also contains metadata, such as: data block ID, timestamp, hash of the previous data block, etc. The encapsulated data blocks are stored on the chain, and a unique identifier (such as block ID) is generated for each data block for subsequent blockchain verification and query. A hash value is generated for each data block through an encrypted hash algorithm (such as SHA-256) to ensure that each data block is linked to the previous data block to form a blockchain. The hash value is merged with the data block content to form a new aquaculture traceability encrypted data block. Each encrypted data block has an independent hash value and forms a chain structure with the hash value of the previous block. In order to ensure the security and privacy of the data, symmetric or asymmetric encryption technology can also be used to encrypt the data blocks to ensure the confidentiality of the data content during transmission and storage. Multiple nodes in the blockchain network verify the encrypted data blocks of aquaculture traceability. Nodes confirm the validity and legitimacy of data blocks through consensus algorithms (such as PoW, PoS, etc.). The verification process includes checking the hash value, timestamp, data integrity, etc. of the data block to ensure that the data has not been tampered with. After all nodes in the blockchain network reach a consensus, the aquaculture traceability blockchain verification data is generated, which records the consensus results and verification process. The consensus data will be added to the new block to ensure the legitimacy of the entire traceability data chain. The traceability data stored in the blockchain is updated in real time.Based on the dynamic changes in the aquaculture environment and the adjustment of management behaviors, the blockchain system can dynamically receive and update traceability data. New traceability data (such as new farming behaviors, feed usage, health monitoring data, etc.) are uploaded to the blockchain system in real time, and the system automatically updates the existing blockchain based on the new data. The blockchain network will generate a new block after each data update to record the new traceability data. The generated real-time aquaculture traceability update data can be queried through the blockchain browser or API interface.

[0080] Preferably, step S4 comprises the following steps:

[0081] Step S41: constructing a sharing platform based on the real-time aquatic traceability update data and the aquaculture behavior pattern diagram to generate an aquaculture sharing platform; using the aquaculture sharing platform to generate a traceability code for the real-time aquatic traceability update data and the aquaculture behavior pattern diagram to obtain an aquaculture traceability code;

[0082] Step S42: Scan the aquaculture traceability code to identify the scan request. When a scan request for the aquaculture traceability code is received, the real-time aquaculture traceability update data and the aquaculture behavior pattern diagram are displayed in layers to perform intelligent aquaculture environment traceability operations.

[0083] In an embodiment of the present invention, aquaculture traceability update data and aquaculture behavior pattern diagrams are obtained in real time through input sources such as aquaculture sensors, video surveillance, and blockchain traceability data. The platform includes modules such as data storage, display interface, query interface, and intelligent analysis function. Provide services such as data display, real-time query, analysis report, traceability, etc. to ensure the transparency and traceability of aquaculture. Use data stream processing technologies supported by the platform (such as streaming computing and event-driven architecture) to achieve efficient data processing and real-time updates. Integrate aquaculture data from different sources (including sensor data, behavior pattern diagrams, blockchain traceability data, etc.) into the platform to form a unified data model. Design and build database systems, cloud storage, API interfaces and other computing resources to ensure high availability and low latency of data. Develop user interaction interfaces, including PC and mobile Web applications, to facilitate user access and operation. Perform real-time data display, dynamic update, chart analysis and user interaction operations within the platform to generate an aquaculture sharing platform that can be easily accessed and used by all parties such as regulators, consumers, and breeders. The aquaculture traceability code is a unique identifier. It is generated by the platform and contains all traceability information related to aquaculture (such as growth stage, breeding environment, feed usage, health monitoring, etc.), and the data security is guaranteed by encryption. The aquaculture behavior pattern diagram and real-time traceability update data are integrated and summarized through a shared platform. The platform will encode and encrypt each traceability information to ensure the uniqueness and integrity of the data. Based on blockchain technology, smart contracts are used to link the traceability information to the traceability code to ensure that the data cannot be tampered with and is traceable. The platform generates a unique traceability code for each traceability data through algorithms and smart contracts, and stores it in the blockchain or distributed ledger to ensure the integrity of the traceability data throughout the breeding cycle. Using technologies such as QR codes or RFID tags, a unique traceability code is assigned to each aquaculture object (such as aquatic products, breeding equipment, environmental monitoring equipment, etc.). Users or managers request traceability information by scanning QR codes, barcodes, RFID tags, etc., triggering the platform's scanning request. After receiving the scanning request, the system determines the validity of the traceability code. By comparing the traceability code with the data in the blockchain, its legitimacy and validity are verified. If the traceability code is valid, the next step of the display and operation process will be entered; if it is invalid or the data does not match, error processing or feedback will be performed. After receiving the scanning request, the platform will display the real-time aquatic traceability update data and aquaculture behavior pattern diagram in layers according to user needs or device functions. Level 1: Basic information layer: Display basic breeding information, such as aquatic type, breeding area, environmental data, health monitoring, etc. Level 2: Dynamic data layer: Display dynamic behavior data of aquatic products, such as feed use, movement status, environmental changes, etc. Level 3: Traceability history data layer: Display the traceability information in the breeding process, the activity history of each node, data modification records, etc. through blockchain links.Level 4: Behavior pattern analysis layer: Analyze the behavior change trends, health status and key events in the aquaculture process of aquatic products according to the aquaculture behavior pattern diagram. The system intelligently pushes relevant information based on the user's query conditions, such as recent environmental changes, aquaculture behaviors, etc. Based on historical data and real-time monitoring, intelligently analyze potential problems in the aquaculture process, such as abnormal water quality, disease risks, etc., and generate corresponding treatment suggestions. The data will be refreshed in real time according to the traceability update data to ensure that users obtain the latest aquaculture information. When the system performs intelligent traceability operations, it can automatically generate reports according to user needs and output traceability information of aquaculture, including aquatic life cycle, environmental quality, feed records, etc.

[0084] In this specification, an intelligent aquaculture traceability system based on the Internet of Things is provided, which is used to execute the above-mentioned intelligent aquaculture traceability method based on the Internet of Things. The intelligent aquaculture traceability system based on the Internet of Things includes:

[0085] The data synchronization acquisition module is used to obtain the location data of the aquaculture area; connect the location data of the aquaculture area to the sensor network to generate an aquaculture Internet of Things network; collect real-time aquaculture data on the aquaculture Internet of Things network to obtain real-time aquaculture sensor data stream; perform distributed time synchronization on the real-time aquaculture sensor data stream to generate standard aquaculture environment perception data;

[0086] The scene mapping module is used to obtain aquatic information data; use the aquaculture area location data to map the standard aquaculture environment perception data to the real aquaculture environment scene, and generate real aquaculture environment scene mapping data; use the real aquaculture environment scene mapping data to identify the aquaculture behavior pattern of the aquaculture information data, and generate an aquaculture behavior pattern diagram;

[0087] The traceability module is used to upload the aquaculture behavior pattern diagram to the blockchain to generate aquaculture traceability upload data; perform multi-node verification and consensus on the aquaculture traceability upload data to generate aquaculture traceability blockchain verification data; perform real-time traceability data updates on the aquaculture traceability blockchain verification data to generate real-time aquaculture traceability update data;

[0088] The traceability display module is used to generate traceability codes based on real-time aquatic traceability update data and aquaculture behavior pattern diagrams to obtain aquaculture traceability codes; scan requests for aquaculture traceability codes are identified, and when a scan request for an aquaculture traceability code is received, real-time aquatic traceability update data and aquaculture behavior pattern diagrams are displayed in layers to perform intelligent aquaculture environment traceability operations.

[0089] The beneficial effect of the present invention is that through the establishment of a sensor network and an aquaculture Internet of Things network, the environmental and behavioral data of the aquaculture area are collected in real time. This process not only strengthens the real-time monitoring of the breeding process, but also can respond to environmental changes in a timely manner and provide high-quality environmental perception data. By combining standard aquaculture environmental perception data with aquatic information data, the behavioral patterns in aquaculture can be accurately identified. This intelligent analysis helps breeders to gain an in-depth understanding of aquatic behavior characteristics (such as dynamic behavior, habitat behavior, etc.) and provides data support for the optimization of the aquaculture environment. By uploading the aquaculture behavior pattern diagram and real-time traceability data to the blockchain, the system ensures the immutability and transparency of the traceability data and avoids the risk of information tampering or loss. This move greatly enhances the trust of consumers and ensures that product quality is traceable and verifiable. Through the continuous generation and updating of real-time traceability update data, the platform can reflect each stage of the aquaculture process, so that the traceability process is always kept up to date, ensuring the timeliness and accuracy of breeding information. The system is layered and displayed according to different user needs, so that consumers and regulators can view breeding information of different depths according to their own needs. This approach not only enhances user interactivity, but also improves the comprehensibility of data. Through efficient data collection, intelligent behavior analysis, and precise environmental perception, the entire aquaculture process can be managed more finely. For example, by intelligently identifying the behavior patterns of aquatic products, the breeding strategy can be adjusted in time to reduce resource waste and improve breeding efficiency. Therefore, the present invention improves the intelligence and transparency of aquaculture traceability by combining the Internet of Things, blockchain, and real-time data synchronization technology.

[0090] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0091] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent aquaculture traceability method based on the Internet of Things, characterized in that: The following steps are involved: Step S1: Acquire location data of an aquaculture area; connect the location data of the aquaculture area to a sensor network to generate an aquaculture Internet of Things network; collect real-time aquaculture data on the aquaculture Internet of Things network to obtain a real-time aquaculture sensor data stream; Distributed time synchronization of real-time aquaculture sensor data streams to generate standard aquaculture environment perception data; Step S2: Acquire aquatic information data; use the aquaculture area location data to map the standard aquaculture environment perception data to the real aquaculture environment scene, and generate real aquaculture environment scene mapping data; perform aquaculture behavior pattern recognition on the aquaculture information data through the real aquaculture environment scene mapping data, and generate an aquaculture behavior pattern diagram; Step S3: Upload the aquaculture behavior pattern diagram to the blockchain to generate aquaculture traceability upload data; Conduct multi-node verification and consensus on uploaded aquaculture traceability data to generate aquaculture traceability blockchain verification data; Update the aquaculture traceability blockchain verification data in real time to generate real-time aquaculture traceability update data; Step S4: Generate a traceability code based on the real-time aquatic traceability update data and the aquaculture behavior pattern diagram to obtain an aquaculture traceability code; The aquaculture traceability code is scanned and identified. When a scan request for the aquaculture traceability code is received, the real-time aquaculture traceability update data and aquaculture behavior pattern diagram are displayed in layers to perform intelligent aquaculture environment traceability operations.

2. The method for tracing the source of intelligent aquaculture based on the Internet of Things according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire location data of aquaculture areas; Step S12: performing sensor deployment on the aquaculture area location data to obtain aquaculture sensor deployment data; performing aquaculture facility equipment deployment based on the aquaculture sensor deployment data to obtain aquaculture facility monitoring equipment deployment data; Step S13: using the Internet of Things technology to connect the aquaculture sensor deployment data and the aquaculture facility monitoring equipment deployment data to a network, and generate an aquaculture Internet of Things network; Step S14: collect real-time aquaculture data on the aquaculture Internet of Things network to obtain a real-time aquaculture sensor data stream; perform distributed time synchronization on the real-time aquaculture sensor data stream to generate a time-series synchronized aquaculture data stream; perform data preprocessing on the time-series synchronized aquaculture data stream to generate standard aquaculture environment perception data.

3. The intelligent aquaculture traceability method based on the Internet of Things according to claim 2 is characterized in that: Distributed time synchronization of real-time aquaculture sensor data streams includes: Perform multi-source sensor clock configuration on real-time aquaculture sensor data stream to generate multi-source sensor clocks; perform clock synchronization configuration on multi-source sensor clocks based on PTP protocol to generate synchronization clock configuration data; Based on the synchronous clock configuration data, the sensor acquisition timestamp is extracted for the real-time aquaculture sensor data stream to obtain the multi-source sensor acquisition timestamp; the timestamp deviation is calculated for the multi-source sensor acquisition timestamp to obtain the acquisition timestamp deviation data; By collecting timestamp deviation data, the transmission delay of real-time aquaculture sensor data stream is corrected to generate sensor acquisition delay correction data; the timestamps of multi-source sensor acquisition timestamps are aligned using sensor acquisition delay correction data to generate sensor timing alignment data; Distributed data synchronization verification is performed on the real-time aquaculture sensor data stream according to the sensor timing alignment data to generate a timing synchronized aquaculture data stream, where the distributed synchronization verification includes time difference analysis, timing consistency check and data overlap check.

4. The intelligent aquaculture traceability method based on the Internet of Things according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: Acquire aquatic product information data; Step S22: constructing a three-dimensional aquaculture environment scene according to the standard aquaculture environment perception data to generate three-dimensional aquaculture environment scene data; using the aquaculture area location data to perform real geographic spatiotemporal mapping on the three-dimensional aquaculture environment scene data to generate real aquaculture environment scene mapping data; Step S23: performing sensor data index association on the real aquaculture environment scene mapping data through the aquaculture Internet of Things network to generate a real aquaculture environment associated scene set; Step S24: performing aquaculture behavior pattern recognition on the aquaculture information data based on the real aquaculture environment associated scene set to generate an aquaculture behavior pattern diagram.

5. The intelligent aquaculture traceability method based on the Internet of Things according to claim 4 is characterized in that: Step S22 includes the following steps: Step S221: extracting water and land topography parameters from the standard aquaculture environment perception data to generate land topography data and water topography data of the aquaculture environment; Step S222: performing three-dimensional scene modeling on the land topography data of the aquaculture environment and the aquatic topography data of the aquaculture environment to generate three-dimensional aquaculture environment scene data; Step S223: converting the geographic coordinate format of the aquaculture area geographic coordinate data through the aquaculture area location data to generate the geographic location coordinate data of the aquaculture area; Step S224: performing spatiotemporal mapping analysis on the three-dimensional aquaculture environment scene data and the geographical location coordinate data of the aquaculture area to generate spatiotemporal mapping data of the aquaculture environment scene; Step S225: Immersively visualize the real breeding environment scene mapping data to generate real breeding environment scene mapping data.

6. The method for tracing the source of intelligent aquaculture based on the Internet of Things according to claim 4 is characterized in that: Step S24 includes the following steps: Step S241: dividing aquaculture behavior patterns based on a real aquaculture environment associated scene set, generating aquaculture static behavior division patterns and aquaculture dynamic behavior division patterns; Step S242: screening the aquatic product information data for the static positions of aquatic products of the same type according to the aquatic product static behavior classification mode to obtain the aquatic product static position information data of the same type; performing aquatic product static habitat behavior pattern analysis through an underwater camera based on the aquatic product static position information data of the same type to generate aquatic product static behavior pattern analysis data; Step S243: screening the aquatic product information data for different types of dynamic positions of aquatic products based on the aquatic product dynamic behavior classification mode to obtain different types of dynamic position information data of aquatic products; analyzing the dynamic movement behavior patterns of aquatic products through underwater video monitoring based on the different types of dynamic position information of aquatic products to generate aquatic product dynamic behavior pattern analysis data; Step S244: Perform time series behavior evolution on the aquatic static behavior pattern analysis data and the aquatic dynamic behavior pattern analysis data through a preset long-term and short-term neural network model to generate an aquaculture behavior pattern diagram.

7. The method for tracing the source of intelligent aquaculture based on the Internet of Things according to claim 6 is characterized in that: Based on the dynamic position information of different types of aquatic products, the dynamic motion behavior pattern analysis of aquatic products through underwater video monitoring includes: The aquatic activity video stream is collected by underwater video monitoring to obtain the aquatic activity video stream of the heterogeneous aquatic products based on the dynamic position information of the aquatic products; the video frame of the aquatic activity video stream of the heterogeneous aquatic products is segmented to generate the aquatic activity frame image of the heterogeneous aquatic products; the aquatic product object target is tracked and marked in the aquatic activity frame image of the heterogeneous aquatic products to generate the tracking mark data of the aquatic product object; Calculate the movement distance of different types of aquatic products on the tracking mark data of different types of aquatic products to obtain the movement distance data of different types of aquatic products; evaluate the intensity of aquatic products activity on the tracking mark data of different types of aquatic products based on the movement distance data of different types of aquatic products to generate the evaluation data of the intensity of aquatic products activity; According to the intensity assessment data of heterogeneous aquatic activities, the social interaction behavior patterns of aquatic products are analyzed on the dynamic position information of heterogeneous aquatic products to generate the analysis data of aquatic dynamic behavior patterns.

8. The method for tracing the source of intelligent aquaculture based on the Internet of Things according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: extracting aquaculture traceability data from the aquaculture behavior pattern diagram to obtain aquaculture traceability data; uploading the aquaculture traceability data to the blockchain to generate aquaculture traceability upload data; Step S32: encapsulating the uploaded aquaculture traceability data into data blocks to generate aquaculture traceability data blocks; performing hash linking on the aquaculture traceability data blocks to generate aquaculture traceability encrypted data blocks; Step S33: Perform multi-node verification and consensus on the aquaculture traceability encrypted data block through blockchain to generate aquaculture traceability blockchain verification data; Step S34: Update the aquaculture traceability blockchain verification data in real time to generate real-time aquaculture traceability update data.

9. The intelligent aquaculture traceability method based on the Internet of Things according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: constructing a sharing platform based on the real-time aquatic traceability update data and the aquaculture behavior pattern diagram to generate an aquaculture sharing platform; using the aquaculture sharing platform to generate a traceability code for the real-time aquatic traceability update data and the aquaculture behavior pattern diagram to obtain an aquaculture traceability code; Step S42: Scan the aquaculture traceability code to identify the scan request. When a scan request for the aquaculture traceability code is received, the real-time aquaculture traceability update data and the aquaculture behavior pattern diagram are displayed in layers to perform intelligent aquaculture environment traceability operations.

10. An intelligent aquaculture traceability system based on the Internet of Things, characterized in that: Used to execute the intelligent aquaculture traceability method based on the Internet of Things as claimed in claim 1, the intelligent aquaculture traceability system based on the Internet of Things includes: The data synchronization acquisition module is used to obtain the location data of the aquaculture area; connect the location data of the aquaculture area to the sensor network to generate an aquaculture Internet of Things network; collect real-time aquaculture data on the aquaculture Internet of Things network to obtain real-time aquaculture sensor data stream; perform distributed time synchronization on the real-time aquaculture sensor data stream to generate standard aquaculture environment perception data; The scene mapping module is used to obtain aquatic information data; use the aquaculture area location data to map the standard aquaculture environment perception data to the real aquaculture environment scene, and generate real aquaculture environment scene mapping data; use the real aquaculture environment scene mapping data to identify the aquaculture behavior pattern of the aquaculture information data, and generate an aquaculture behavior pattern diagram; The traceability module is used to upload the aquaculture behavior pattern diagram to the blockchain to generate aquaculture traceability upload data; perform multi-node verification and consensus on the aquaculture traceability upload data to generate aquaculture traceability blockchain verification data; perform real-time traceability data updates on the aquaculture traceability blockchain verification data to generate real-time aquaculture traceability update data; The traceability display module is used to generate traceability codes based on real-time aquatic traceability update data and aquaculture behavior pattern diagrams to obtain aquaculture traceability codes; scan requests for aquaculture traceability codes are identified, and when a scan request for an aquaculture traceability code is received, real-time aquatic traceability update data and aquaculture behavior pattern diagrams are displayed in layers to perform intelligent aquaculture environment traceability operations.

Images